926 files changed, 34974 insertions, 25352 deletions

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 6977f8248df7..f37b1c56f7c4 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -431,10 +431,10 @@ config VSOCKMON
 config MHI_NET
 	tristate "MHI network driver"
 	depends on MHI_BUS
-	select WWAN
 	help
 	  This is the network driver for MHI bus.  It can be used with
-	  QCOM based WWAN modems (like SDX55).  Say Y or M.
+	  QCOM based WWAN modems for IP or QMAP/rmnet protocol (like SDX55).
+	  Say Y or M.
 
 endif # NET_CORE
 
@@ -483,6 +483,8 @@ config NET_SB1000
 
 source "drivers/net/phy/Kconfig"
 
+source "drivers/net/mctp/Kconfig"
+
 source "drivers/net/mdio/Kconfig"
 
 source "drivers/net/pcs/Kconfig"
@@ -549,8 +551,8 @@ config VMXNET3
 	tristate "VMware VMXNET3 ethernet driver"
 	depends on PCI && INET
 	depends on !(PAGE_SIZE_64KB || ARM64_64K_PAGES || \
-		     IA64_PAGE_SIZE_64KB || MICROBLAZE_64K_PAGES || \
-		     PARISC_PAGE_SIZE_64KB || PPC_64K_PAGES)
+		     IA64_PAGE_SIZE_64KB || PARISC_PAGE_SIZE_64KB || \
+		     PPC_64K_PAGES)
 	help
 	  This driver supports VMware's vmxnet3 virtual ethernet NIC.
 	  To compile this driver as a module, choose M here: the
@@ -604,4 +606,11 @@ config NET_FAILOVER
 	  a VM with direct attached VF by failing over to the paravirtual
 	  datapath when the VF is unplugged.
 
+config NETDEV_LEGACY_INIT
+	bool
+	depends on ISA
+	help
+	  Drivers that call netdev_boot_setup_check() should select this
+	  symbol, everything else no longer needs it.
+
 endif # NETDEVICES
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 7ffd2d03efaf..739838623cf6 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -18,7 +18,8 @@ obj-$(CONFIG_MACVLAN) += macvlan.o
 obj-$(CONFIG_MACVTAP) += macvtap.o
 obj-$(CONFIG_MII) += mii.o
 obj-$(CONFIG_MDIO) += mdio.o
-obj-$(CONFIG_NET) += Space.o loopback.o
+obj-$(CONFIG_NET) += loopback.o
+obj-$(CONFIG_NETDEV_LEGACY_INIT) += Space.o
 obj-$(CONFIG_NETCONSOLE) += netconsole.o
 obj-y += phy/
 obj-y += mdio/
@@ -36,7 +37,7 @@ obj-$(CONFIG_GTP) += gtp.o
 obj-$(CONFIG_NLMON) += nlmon.o
 obj-$(CONFIG_NET_VRF) += vrf.o
 obj-$(CONFIG_VSOCKMON) += vsockmon.o
-obj-$(CONFIG_MHI_NET) += mhi/
+obj-$(CONFIG_MHI_NET) += mhi_net.o
 
 #
 # Networking Drivers
@@ -69,6 +70,7 @@ obj-$(CONFIG_WAN) += wan/
 obj-$(CONFIG_WLAN) += wireless/
 obj-$(CONFIG_IEEE802154) += ieee802154/
 obj-$(CONFIG_WWAN) += wwan/
+obj-$(CONFIG_MCTP) += mctp/
 
 obj-$(CONFIG_VMXNET3) += vmxnet3/
 obj-$(CONFIG_XEN_NETDEV_FRONTEND) += xen-netfront.o
diff --git a/drivers/net/Space.c b/drivers/net/Space.c
index df79e7370bcc..49e67c9fb5a4 100644
--- a/drivers/net/Space.c
+++ b/drivers/net/Space.c
@@ -30,6 +30,148 @@
 #include <linux/netlink.h>
 #include <net/Space.h>
 
+/*
+ * This structure holds boot-time configured netdevice settings. They
+ * are then used in the device probing.
+ */
+struct netdev_boot_setup {
+	char name[IFNAMSIZ];
+	struct ifmap map;
+};
+#define NETDEV_BOOT_SETUP_MAX 8
+
+
+/******************************************************************************
+ *
+ *		      Device Boot-time Settings Routines
+ *
+ ******************************************************************************/
+
+/* Boot time configuration table */
+static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX];
+
+/**
+ *	netdev_boot_setup_add	- add new setup entry
+ *	@name: name of the device
+ *	@map: configured settings for the device
+ *
+ *	Adds new setup entry to the dev_boot_setup list.  The function
+ *	returns 0 on error and 1 on success.  This is a generic routine to
+ *	all netdevices.
+ */
+static int netdev_boot_setup_add(char *name, struct ifmap *map)
+{
+	struct netdev_boot_setup *s;
+	int i;
+
+	s = dev_boot_setup;
+	for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
+		if (s[i].name[0] == '\0' || s[i].name[0] == ' ') {
+			memset(s[i].name, 0, sizeof(s[i].name));
+			strlcpy(s[i].name, name, IFNAMSIZ);
+			memcpy(&s[i].map, map, sizeof(s[i].map));
+			break;
+		}
+	}
+
+	return i >= NETDEV_BOOT_SETUP_MAX ? 0 : 1;
+}
+
+/**
+ * netdev_boot_setup_check	- check boot time settings
+ * @dev: the netdevice
+ *
+ * Check boot time settings for the device.
+ * The found settings are set for the device to be used
+ * later in the device probing.
+ * Returns 0 if no settings found, 1 if they are.
+ */
+int netdev_boot_setup_check(struct net_device *dev)
+{
+	struct netdev_boot_setup *s = dev_boot_setup;
+	int i;
+
+	for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
+		if (s[i].name[0] != '\0' && s[i].name[0] != ' ' &&
+		    !strcmp(dev->name, s[i].name)) {
+			dev->irq = s[i].map.irq;
+			dev->base_addr = s[i].map.base_addr;
+			dev->mem_start = s[i].map.mem_start;
+			dev->mem_end = s[i].map.mem_end;
+			return 1;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL(netdev_boot_setup_check);
+
+/**
+ * netdev_boot_base	- get address from boot time settings
+ * @prefix: prefix for network device
+ * @unit: id for network device
+ *
+ * Check boot time settings for the base address of device.
+ * The found settings are set for the device to be used
+ * later in the device probing.
+ * Returns 0 if no settings found.
+ */
+static unsigned long netdev_boot_base(const char *prefix, int unit)
+{
+	const struct netdev_boot_setup *s = dev_boot_setup;
+	char name[IFNAMSIZ];
+	int i;
+
+	sprintf(name, "%s%d", prefix, unit);
+
+	/*
+	 * If device already registered then return base of 1
+	 * to indicate not to probe for this interface
+	 */
+	if (__dev_get_by_name(&init_net, name))
+		return 1;
+
+	for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++)
+		if (!strcmp(name, s[i].name))
+			return s[i].map.base_addr;
+	return 0;
+}
+
+/*
+ * Saves at boot time configured settings for any netdevice.
+ */
+static int __init netdev_boot_setup(char *str)
+{
+	int ints[5];
+	struct ifmap map;
+
+	str = get_options(str, ARRAY_SIZE(ints), ints);
+	if (!str || !*str)
+		return 0;
+
+	/* Save settings */
+	memset(&map, 0, sizeof(map));
+	if (ints[0] > 0)
+		map.irq = ints[1];
+	if (ints[0] > 1)
+		map.base_addr = ints[2];
+	if (ints[0] > 2)
+		map.mem_start = ints[3];
+	if (ints[0] > 3)
+		map.mem_end = ints[4];
+
+	/* Add new entry to the list */
+	return netdev_boot_setup_add(str, &map);
+}
+
+__setup("netdev=", netdev_boot_setup);
+
+static int __init ether_boot_setup(char *str)
+{
+	return netdev_boot_setup(str);
+}
+__setup("ether=", ether_boot_setup);
+
+
 /* A unified ethernet device probe.  This is the easiest way to have every
  * ethernet adaptor have the name "eth[0123...]".
  */
@@ -77,39 +219,15 @@ static struct devprobe2 isa_probes[] __initdata = {
 #ifdef CONFIG_SMC9194
 	{smc_init, 0},
 #endif
-#ifdef CONFIG_CS89x0
-#ifndef CONFIG_CS89x0_PLATFORM
+#ifdef CONFIG_CS89x0_ISA
 	{cs89x0_probe, 0},
 #endif
-#endif
-#if defined(CONFIG_MVME16x_NET) || defined(CONFIG_BVME6000_NET)	/* Intel */
-	{i82596_probe, 0},					/* I82596 */
-#endif
 #ifdef CONFIG_NI65
 	{ni65_probe, 0},
 #endif
 	{NULL, 0},
 };
 
-static struct devprobe2 m68k_probes[] __initdata = {
-#ifdef CONFIG_ATARILANCE	/* Lance-based Atari ethernet boards */
-	{atarilance_probe, 0},
-#endif
-#ifdef CONFIG_SUN3LANCE         /* sun3 onboard Lance chip */
-	{sun3lance_probe, 0},
-#endif
-#ifdef CONFIG_SUN3_82586        /* sun3 onboard Intel 82586 chip */
-	{sun3_82586_probe, 0},
-#endif
-#ifdef CONFIG_APNE		/* A1200 PCMCIA NE2000 */
-	{apne_probe, 0},
-#endif
-#ifdef CONFIG_MVME147_NET	/* MVME147 internal Ethernet */
-	{mvme147lance_probe, 0},
-#endif
-	{NULL, 0},
-};
-
 /* Unified ethernet device probe, segmented per architecture and
  * per bus interface. This drives the legacy devices only for now.
  */
@@ -121,8 +239,7 @@ static void __init ethif_probe2(int unit)
 	if (base_addr == 1)
 		return;
 
-	(void)(probe_list2(unit, m68k_probes, base_addr == 0) &&
-		probe_list2(unit, isa_probes, base_addr == 0));
+	probe_list2(unit, isa_probes, base_addr == 0);
 }
 
 /*  Statically configured drivers -- order matters here. */
@@ -130,10 +247,6 @@ static int __init net_olddevs_init(void)
 {
 	int num;
 
-#ifdef CONFIG_SBNI
-	for (num = 0; num < 8; ++num)
-		sbni_probe(num);
-#endif
 	for (num = 0; num < 8; ++num)
 		ethif_probe2(num);
 
@@ -142,9 +255,6 @@ static int __init net_olddevs_init(void)
 	cops_probe(1);
 	cops_probe(2);
 #endif
-#ifdef CONFIG_LTPC
-	ltpc_probe();
-#endif
 
 	return 0;
 }
diff --git a/drivers/net/appletalk/Kconfig b/drivers/net/appletalk/Kconfig
index 43918398f0d3..90b9f1d6eda9 100644
--- a/drivers/net/appletalk/Kconfig
+++ b/drivers/net/appletalk/Kconfig
@@ -52,7 +52,9 @@ config LTPC
 
 config COPS
 	tristate "COPS LocalTalk PC support"
-	depends on DEV_APPLETALK && (ISA || EISA)
+	depends on DEV_APPLETALK && ISA
+	depends on NETDEVICES
+	select NETDEV_LEGACY_INIT
 	help
 	  This allows you to use COPS AppleTalk cards to connect to LocalTalk
 	  networks. You also need version 1.3.3 or later of the netatalk
diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c
index 51cf5eca9c7f..5566daefbff4 100644
--- a/drivers/net/appletalk/ipddp.c
+++ b/drivers/net/appletalk/ipddp.c
@@ -54,11 +54,12 @@ static netdev_tx_t ipddp_xmit(struct sk_buff *skb,
 static int ipddp_create(struct ipddp_route *new_rt);
 static int ipddp_delete(struct ipddp_route *rt);
 static struct ipddp_route* __ipddp_find_route(struct ipddp_route *rt);
-static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
+static int ipddp_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+				void __user *data, int cmd);
 
 static const struct net_device_ops ipddp_netdev_ops = {
 	.ndo_start_xmit		= ipddp_xmit,
-	.ndo_do_ioctl   	= ipddp_ioctl,
+	.ndo_siocdevprivate	= ipddp_siocdevprivate,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
@@ -268,15 +269,18 @@ static struct ipddp_route* __ipddp_find_route(struct ipddp_route *rt)
         return NULL;
 }
 
-static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int ipddp_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+				void __user *data, int cmd)
 {
-        struct ipddp_route __user *rt = ifr->ifr_data;
         struct ipddp_route rcp, rcp2, *rp;
 
+	if (in_compat_syscall())
+		return -EOPNOTSUPP;
+
         if(!capable(CAP_NET_ADMIN))
                 return -EPERM;
 
-	if(copy_from_user(&rcp, rt, sizeof(rcp)))
+	if (copy_from_user(&rcp, data, sizeof(rcp)))
 		return -EFAULT;
 
         switch(cmd)
@@ -296,7 +300,7 @@ static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			spin_unlock_bh(&ipddp_route_lock);
 
 			if (rp) {
-				if (copy_to_user(rt, &rcp2,
+				if (copy_to_user(data, &rcp2,
 						 sizeof(struct ipddp_route)))
 					return -EFAULT;
 				return 0;
diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c
index 69c270885ff0..1f8925e75b3f 100644
--- a/drivers/net/appletalk/ltpc.c
+++ b/drivers/net/appletalk/ltpc.c
@@ -1015,7 +1015,7 @@ static const struct net_device_ops ltpc_netdev = {
 	.ndo_set_rx_mode	= set_multicast_list,
 };
 
-struct net_device * __init ltpc_probe(void)
+static struct net_device * __init ltpc_probe(void)
 {
 	struct net_device *dev;
 	int err = -ENOMEM;
@@ -1221,12 +1221,10 @@ static int __init ltpc_setup(char *str)
 }
 
 __setup("ltpc=", ltpc_setup);
-#endif /* MODULE */
+#endif
 
 static struct net_device *dev_ltpc;
 
-#ifdef MODULE
-
 MODULE_LICENSE("GPL");
 module_param(debug, int, 0);
 module_param_hw(io, int, ioport, 0);
@@ -1244,7 +1242,6 @@ static int __init ltpc_module_init(void)
 	return PTR_ERR_OR_ZERO(dev_ltpc);
 }
 module_init(ltpc_module_init);
-#endif
 
 static void __exit ltpc_cleanup(void)
 {
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 6908822d9773..a4a202b9a0a2 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -96,7 +96,7 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker);
 static void ad_mux_machine(struct port *port, bool *update_slave_arr);
 static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port);
 static void ad_tx_machine(struct port *port);
-static void ad_periodic_machine(struct port *port);
+static void ad_periodic_machine(struct port *port, struct bond_params bond_params);
 static void ad_port_selection_logic(struct port *port, bool *update_slave_arr);
 static void ad_agg_selection_logic(struct aggregator *aggregator,
 				   bool *update_slave_arr);
@@ -1294,10 +1294,11 @@ static void ad_tx_machine(struct port *port)
 /**
  * ad_periodic_machine - handle a port's periodic state machine
  * @port: the port we're looking at
+ * @bond_params: bond parameters we will use
  *
  * Turn ntt flag on priodically to perform periodic transmission of lacpdu's.
  */
-static void ad_periodic_machine(struct port *port)
+static void ad_periodic_machine(struct port *port, struct bond_params bond_params)
 {
 	periodic_states_t last_state;
 
@@ -1306,8 +1307,8 @@ static void ad_periodic_machine(struct port *port)
 
 	/* check if port was reinitialized */
 	if (((port->sm_vars & AD_PORT_BEGIN) || !(port->sm_vars & AD_PORT_LACP_ENABLED) || !port->is_enabled) ||
-	    (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY))
-	   ) {
+	    (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY)) ||
+	    !bond_params.lacp_active) {
 		port->sm_periodic_state = AD_NO_PERIODIC;
 	}
 	/* check if state machine should change state */
@@ -2341,7 +2342,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 		}
 
 		ad_rx_machine(NULL, port);
-		ad_periodic_machine(port);
+		ad_periodic_machine(port, bond->params);
 		ad_port_selection_logic(port, &update_slave_arr);
 		ad_mux_machine(port, &update_slave_arr);
 		ad_tx_machine(port);
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 22e5632089ac..7d3752cbf761 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -17,7 +17,6 @@
 #include <linux/if_bonding.h>
 #include <linux/if_vlan.h>
 #include <linux/in.h>
-#include <net/ipx.h>
 #include <net/arp.h>
 #include <net/ipv6.h>
 #include <asm/byteorder.h>
@@ -1351,8 +1350,6 @@ struct slave *bond_xmit_tlb_slave_get(struct bonding *bond,
 	if (!is_multicast_ether_addr(eth_data->h_dest)) {
 		switch (skb->protocol) {
 		case htons(ETH_P_IP):
-		case htons(ETH_P_IPX):
-		    /* In case of IPX, it will falback to L2 hash */
 		case htons(ETH_P_IPV6):
 			hash_index = bond_xmit_hash(bond, skb);
 			if (bond->params.tlb_dynamic_lb) {
@@ -1454,35 +1451,6 @@ struct slave *bond_xmit_alb_slave_get(struct bonding *bond,
 		hash_size = sizeof(ip6hdr->daddr);
 		break;
 	}
-	case ETH_P_IPX: {
-		const struct ipxhdr *ipxhdr;
-
-		if (pskb_network_may_pull(skb, sizeof(*ipxhdr))) {
-			do_tx_balance = false;
-			break;
-		}
-		ipxhdr = (struct ipxhdr *)skb_network_header(skb);
-
-		if (ipxhdr->ipx_checksum != IPX_NO_CHECKSUM) {
-			/* something is wrong with this packet */
-			do_tx_balance = false;
-			break;
-		}
-
-		if (ipxhdr->ipx_type != IPX_TYPE_NCP) {
-			/* The only protocol worth balancing in
-			 * this family since it has an "ARP" like
-			 * mechanism
-			 */
-			do_tx_balance = false;
-			break;
-		}
-
-		eth_data = eth_hdr(skb);
-		hash_start = (char *)eth_data->h_dest;
-		hash_size = ETH_ALEN;
-		break;
-	}
 	case ETH_P_ARP:
 		do_tx_balance = false;
 		if (bond_info->rlb_enabled)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 31730efa7538..b0966e733926 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -317,6 +317,25 @@ bool bond_sk_check(struct bonding *bond)
 	}
 }
 
+static bool bond_xdp_check(struct bonding *bond)
+{
+	switch (BOND_MODE(bond)) {
+	case BOND_MODE_ROUNDROBIN:
+	case BOND_MODE_ACTIVEBACKUP:
+		return true;
+	case BOND_MODE_8023AD:
+	case BOND_MODE_XOR:
+		/* vlan+srcmac is not supported with XDP as in most cases the 802.1q
+		 * payload is not in the packet due to hardware offload.
+		 */
+		if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC)
+			return true;
+		fallthrough;
+	default:
+		return false;
+	}
+}
+
 /*---------------------------------- VLAN -----------------------------------*/
 
 /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid,
@@ -732,7 +751,7 @@ static int bond_check_dev_link(struct bonding *bond,
 			BMSR_LSTATUS : 0;
 
 	/* Ethtool can't be used, fallback to MII ioctls. */
-	ioctl = slave_ops->ndo_do_ioctl;
+	ioctl = slave_ops->ndo_eth_ioctl;
 	if (ioctl) {
 		/* TODO: set pointer to correct ioctl on a per team member
 		 *       bases to make this more efficient. that is, once
@@ -756,7 +775,7 @@ static int bond_check_dev_link(struct bonding *bond,
 		}
 	}
 
-	/* If reporting, report that either there's no dev->do_ioctl,
+	/* If reporting, report that either there's no ndo_eth_ioctl,
 	 * or both SIOCGMIIREG and get_link failed (meaning that we
 	 * cannot report link status).  If not reporting, pretend
 	 * we're ok.
@@ -1712,6 +1731,20 @@ void bond_lower_state_changed(struct slave *slave)
 	netdev_lower_state_changed(slave->dev, &info);
 }
 
+#define BOND_NL_ERR(bond_dev, extack, errmsg) do {		\
+	if (extack)						\
+		NL_SET_ERR_MSG(extack, errmsg);			\
+	else							\
+		netdev_err(bond_dev, "Error: %s\n", errmsg);	\
+} while (0)
+
+#define SLAVE_NL_ERR(bond_dev, slave_dev, extack, errmsg) do {		\
+	if (extack)							\
+		NL_SET_ERR_MSG(extack, errmsg);				\
+	else								\
+		slave_err(bond_dev, slave_dev, "Error: %s\n", errmsg);	\
+} while (0)
+
 /* enslave device <slave> to bond device <master> */
 int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		 struct netlink_ext_ack *extack)
@@ -1725,29 +1758,26 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 
 	if (slave_dev->flags & IFF_MASTER &&
 	    !netif_is_bond_master(slave_dev)) {
-		NL_SET_ERR_MSG(extack, "Device with IFF_MASTER cannot be enslaved");
-		netdev_err(bond_dev,
-			   "Error: Device with IFF_MASTER cannot be enslaved\n");
+		BOND_NL_ERR(bond_dev, extack,
+			    "Device type (master device) cannot be enslaved");
 		return -EPERM;
 	}
 
 	if (!bond->params.use_carrier &&
 	    slave_dev->ethtool_ops->get_link == NULL &&
-	    slave_ops->ndo_do_ioctl == NULL) {
+	    slave_ops->ndo_eth_ioctl == NULL) {
 		slave_warn(bond_dev, slave_dev, "no link monitoring support\n");
 	}
 
 	/* already in-use? */
 	if (netdev_is_rx_handler_busy(slave_dev)) {
-		NL_SET_ERR_MSG(extack, "Device is in use and cannot be enslaved");
-		slave_err(bond_dev, slave_dev,
-			  "Error: Device is in use and cannot be enslaved\n");
+		SLAVE_NL_ERR(bond_dev, slave_dev, extack,
+			     "Device is in use and cannot be enslaved");
 		return -EBUSY;
 	}
 
 	if (bond_dev == slave_dev) {
-		NL_SET_ERR_MSG(extack, "Cannot enslave bond to itself.");
-		netdev_err(bond_dev, "cannot enslave bond to itself.\n");
+		BOND_NL_ERR(bond_dev, extack, "Cannot enslave bond to itself.");
 		return -EPERM;
 	}
 
@@ -1756,8 +1786,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) {
 		slave_dbg(bond_dev, slave_dev, "is NETIF_F_VLAN_CHALLENGED\n");
 		if (vlan_uses_dev(bond_dev)) {
-			NL_SET_ERR_MSG(extack, "Can not enslave VLAN challenged device to VLAN enabled bond");
-			slave_err(bond_dev, slave_dev, "Error: cannot enslave VLAN challenged slave on VLAN enabled bond\n");
+			SLAVE_NL_ERR(bond_dev, slave_dev, extack,
+				     "Can not enslave VLAN challenged device to VLAN enabled bond");
 			return -EPERM;
 		} else {
 			slave_warn(bond_dev, slave_dev, "enslaved VLAN challenged slave. Adding VLANs will be blocked as long as it is part of bond.\n");
@@ -1775,8 +1805,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	 * enslaving it; the old ifenslave will not.
 	 */
 	if (slave_dev->flags & IFF_UP) {
-		NL_SET_ERR_MSG(extack, "Device can not be enslaved while up");
-		slave_err(bond_dev, slave_dev, "slave is up - this may be due to an out of date ifenslave\n");
+		SLAVE_NL_ERR(bond_dev, slave_dev, extack,
+			     "Device can not be enslaved while up");
 		return -EPERM;
 	}
 
@@ -1815,17 +1845,15 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 						 bond_dev);
 		}
 	} else if (bond_dev->type != slave_dev->type) {
-		NL_SET_ERR_MSG(extack, "Device type is different from other slaves");
-		slave_err(bond_dev, slave_dev, "ether type (%d) is different from other slaves (%d), can not enslave it\n",
-			  slave_dev->type, bond_dev->type);
+		SLAVE_NL_ERR(bond_dev, slave_dev, extack,
+			     "Device type is different from other slaves");
 		return -EINVAL;
 	}
 
 	if (slave_dev->type == ARPHRD_INFINIBAND &&
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
-		NL_SET_ERR_MSG(extack, "Only active-backup mode is supported for infiniband slaves");
-		slave_warn(bond_dev, slave_dev, "Type (%d) supports only active-backup mode\n",
-			   slave_dev->type);
+		SLAVE_NL_ERR(bond_dev, slave_dev, extack,
+			     "Only active-backup mode is supported for infiniband slaves");
 		res = -EOPNOTSUPP;
 		goto err_undo_flags;
 	}
@@ -1839,8 +1867,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 				bond->params.fail_over_mac = BOND_FOM_ACTIVE;
 				slave_warn(bond_dev, slave_dev, "Setting fail_over_mac to active for active-backup mode\n");
 			} else {
-				NL_SET_ERR_MSG(extack, "Slave device does not support setting the MAC address, but fail_over_mac is not set to active");
-				slave_err(bond_dev, slave_dev, "The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active\n");
+				SLAVE_NL_ERR(bond_dev, slave_dev, extack,
+					     "Slave device does not support setting the MAC address, but fail_over_mac is not set to active");
 				res = -EOPNOTSUPP;
 				goto err_undo_flags;
 			}
@@ -2133,6 +2161,39 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		bond_update_slave_arr(bond, NULL);
 
 
+	if (!slave_dev->netdev_ops->ndo_bpf ||
+	    !slave_dev->netdev_ops->ndo_xdp_xmit) {
+		if (bond->xdp_prog) {
+			SLAVE_NL_ERR(bond_dev, slave_dev, extack,
+				     "Slave does not support XDP");
+			res = -EOPNOTSUPP;
+			goto err_sysfs_del;
+		}
+	} else {
+		struct netdev_bpf xdp = {
+			.command = XDP_SETUP_PROG,
+			.flags   = 0,
+			.prog    = bond->xdp_prog,
+			.extack  = extack,
+		};
+
+		if (dev_xdp_prog_count(slave_dev) > 0) {
+			SLAVE_NL_ERR(bond_dev, slave_dev, extack,
+				     "Slave has XDP program loaded, please unload before enslaving");
+			res = -EOPNOTSUPP;
+			goto err_sysfs_del;
+		}
+
+		res = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+		if (res < 0) {
+			/* ndo_bpf() sets extack error message */
+			slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res);
+			goto err_sysfs_del;
+		}
+		if (bond->xdp_prog)
+			bpf_prog_inc(bond->xdp_prog);
+	}
+
 	slave_info(bond_dev, slave_dev, "Enslaving as %s interface with %s link\n",
 		   bond_is_active_slave(new_slave) ? "an active" : "a backup",
 		   new_slave->link != BOND_LINK_DOWN ? "an up" : "a down");
@@ -2252,7 +2313,17 @@ static int __bond_release_one(struct net_device *bond_dev,
 	/* recompute stats just before removing the slave */
 	bond_get_stats(bond->dev, &bond->bond_stats);
 
-	bond_upper_dev_unlink(bond, slave);
+	if (bond->xdp_prog) {
+		struct netdev_bpf xdp = {
+			.command = XDP_SETUP_PROG,
+			.flags   = 0,
+			.prog	 = NULL,
+			.extack  = NULL,
+		};
+		if (slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp))
+			slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n");
+	}
+
 	/* unregister rx_handler early so bond_handle_frame wouldn't be called
 	 * for this slave anymore.
 	 */
@@ -2261,6 +2332,8 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (BOND_MODE(bond) == BOND_MODE_8023AD)
 		bond_3ad_unbind_slave(slave);
 
+	bond_upper_dev_unlink(bond, slave);
+
 	if (bond_mode_can_use_xmit_hash(bond))
 		bond_update_slave_arr(bond, slave);
 
@@ -3613,90 +3686,112 @@ static struct notifier_block bond_netdev_notifier = {
 
 /*---------------------------- Hashing Policies -----------------------------*/
 
+/* Helper to access data in a packet, with or without a backing skb.
+ * If skb is given the data is linearized if necessary via pskb_may_pull.
+ */
+static inline const void *bond_pull_data(struct sk_buff *skb,
+					 const void *data, int hlen, int n)
+{
+	if (likely(n <= hlen))
+		return data;
+	else if (skb && likely(pskb_may_pull(skb, n)))
+		return skb->head;
+
+	return NULL;
+}
+
 /* L2 hash helper */
-static inline u32 bond_eth_hash(struct sk_buff *skb)
+static inline u32 bond_eth_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen)
 {
-	struct ethhdr *ep, hdr_tmp;
+	struct ethhdr *ep;
 
-	ep = skb_header_pointer(skb, 0, sizeof(hdr_tmp), &hdr_tmp);
-	if (ep)
-		return ep->h_dest[5] ^ ep->h_source[5] ^ ep->h_proto;
-	return 0;
+	data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr));
+	if (!data)
+		return 0;
+
+	ep = (struct ethhdr *)(data + mhoff);
+	return ep->h_dest[5] ^ ep->h_source[5] ^ be16_to_cpu(ep->h_proto);
 }
 
-static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk,
-			 int *noff, int *proto, bool l34)
+static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, const void *data,
+			 int hlen, __be16 l2_proto, int *nhoff, int *ip_proto, bool l34)
 {
 	const struct ipv6hdr *iph6;
 	const struct iphdr *iph;
 
-	if (skb->protocol == htons(ETH_P_IP)) {
-		if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph))))
+	if (l2_proto == htons(ETH_P_IP)) {
+		data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph));
+		if (!data)
 			return false;
-		iph = (const struct iphdr *)(skb->data + *noff);
+
+		iph = (const struct iphdr *)(data + *nhoff);
 		iph_to_flow_copy_v4addrs(fk, iph);
-		*noff += iph->ihl << 2;
+		*nhoff += iph->ihl << 2;
 		if (!ip_is_fragment(iph))
-			*proto = iph->protocol;
-	} else if (skb->protocol == htons(ETH_P_IPV6)) {
-		if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph6))))
+			*ip_proto = iph->protocol;
+	} else if (l2_proto == htons(ETH_P_IPV6)) {
+		data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph6));
+		if (!data)
 			return false;
-		iph6 = (const struct ipv6hdr *)(skb->data + *noff);
+
+		iph6 = (const struct ipv6hdr *)(data + *nhoff);
 		iph_to_flow_copy_v6addrs(fk, iph6);
-		*noff += sizeof(*iph6);
-		*proto = iph6->nexthdr;
+		*nhoff += sizeof(*iph6);
+		*ip_proto = iph6->nexthdr;
 	} else {
 		return false;
 	}
 
-	if (l34 && *proto >= 0)
-		fk->ports.ports = skb_flow_get_ports(skb, *noff, *proto);
+	if (l34 && *ip_proto >= 0)
+		fk->ports.ports = __skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen);
 
 	return true;
 }
 
-static u32 bond_vlan_srcmac_hash(struct sk_buff *skb)
+static u32 bond_vlan_srcmac_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen)
 {
-	struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
 	u32 srcmac_vendor = 0, srcmac_dev = 0;
-	u16 vlan;
+	struct ethhdr *mac_hdr;
+	u16 vlan = 0;
 	int i;
 
+	data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr));
+	if (!data)
+		return 0;
+	mac_hdr = (struct ethhdr *)(data + mhoff);
+
 	for (i = 0; i < 3; i++)
 		srcmac_vendor = (srcmac_vendor << 8) | mac_hdr->h_source[i];
 
 	for (i = 3; i < ETH_ALEN; i++)
 		srcmac_dev = (srcmac_dev << 8) | mac_hdr->h_source[i];
 
-	if (!skb_vlan_tag_present(skb))
-		return srcmac_vendor ^ srcmac_dev;
-
-	vlan = skb_vlan_tag_get(skb);
+	if (skb && skb_vlan_tag_present(skb))
+		vlan = skb_vlan_tag_get(skb);
 
 	return vlan ^ srcmac_vendor ^ srcmac_dev;
 }
 
 /* Extract the appropriate headers based on bond's xmit policy */
-static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
-			      struct flow_keys *fk)
+static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const void *data,
+			      __be16 l2_proto, int nhoff, int hlen, struct flow_keys *fk)
 {
 	bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34;
-	int noff, proto = -1;
+	int ip_proto = -1;
 
 	switch (bond->params.xmit_policy) {
 	case BOND_XMIT_POLICY_ENCAP23:
 	case BOND_XMIT_POLICY_ENCAP34:
 		memset(fk, 0, sizeof(*fk));
 		return __skb_flow_dissect(NULL, skb, &flow_keys_bonding,
-					  fk, NULL, 0, 0, 0, 0);
+					  fk, data, l2_proto, nhoff, hlen, 0);
 	default:
 		break;
 	}
 
 	fk->ports.ports = 0;
 	memset(&fk->icmp, 0, sizeof(fk->icmp));
-	noff = skb_network_offset(skb);
-	if (!bond_flow_ip(skb, fk, &noff, &proto, l34))
+	if (!bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34))
 		return false;
 
 	/* ICMP error packets contains at least 8 bytes of the header
@@ -3704,22 +3799,20 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
 	 * to correlate ICMP error packets within the same flow which
 	 * generated the error.
 	 */
-	if (proto == IPPROTO_ICMP || proto == IPPROTO_ICMPV6) {
-		skb_flow_get_icmp_tci(skb, &fk->icmp, skb->data,
-				      skb_transport_offset(skb),
-				      skb_headlen(skb));
-		if (proto == IPPROTO_ICMP) {
+	if (ip_proto == IPPROTO_ICMP || ip_proto == IPPROTO_ICMPV6) {
+		skb_flow_get_icmp_tci(skb, &fk->icmp, data, nhoff, hlen);
+		if (ip_proto == IPPROTO_ICMP) {
 			if (!icmp_is_err(fk->icmp.type))
 				return true;
 
-			noff += sizeof(struct icmphdr);
-		} else if (proto == IPPROTO_ICMPV6) {
+			nhoff += sizeof(struct icmphdr);
+		} else if (ip_proto == IPPROTO_ICMPV6) {
 			if (!icmpv6_is_err(fk->icmp.type))
 				return true;
 
-			noff += sizeof(struct icmp6hdr);
+			nhoff += sizeof(struct icmp6hdr);
 		}
-		return bond_flow_ip(skb, fk, &noff, &proto, l34);
+		return bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34);
 	}
 
 	return true;
@@ -3735,33 +3828,26 @@ static u32 bond_ip_hash(u32 hash, struct flow_keys *flow)
 	return hash >> 1;
 }
 
-/**
- * bond_xmit_hash - generate a hash value based on the xmit policy
- * @bond: bonding device
- * @skb: buffer to use for headers
- *
- * This function will extract the necessary headers from the skb buffer and use
- * them to generate a hash based on the xmit_policy set in the bonding device
+/* Generate hash based on xmit policy. If @skb is given it is used to linearize
+ * the data as required, but this function can be used without it if the data is
+ * known to be linear (e.g. with xdp_buff).
  */
-u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
+static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, const void *data,
+			    __be16 l2_proto, int mhoff, int nhoff, int hlen)
 {
 	struct flow_keys flow;
 	u32 hash;
 
-	if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 &&
-	    skb->l4_hash)
-		return skb->hash;
-
 	if (bond->params.xmit_policy == BOND_XMIT_POLICY_VLAN_SRCMAC)
-		return bond_vlan_srcmac_hash(skb);
+		return bond_vlan_srcmac_hash(skb, data, mhoff, hlen);
 
 	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 ||
-	    !bond_flow_dissect(bond, skb, &flow))
-		return bond_eth_hash(skb);
+	    !bond_flow_dissect(bond, skb, data, l2_proto, nhoff, hlen, &flow))
+		return bond_eth_hash(skb, data, mhoff, hlen);
 
 	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 ||
 	    bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) {
-		hash = bond_eth_hash(skb);
+		hash = bond_eth_hash(skb, data, mhoff, hlen);
 	} else {
 		if (flow.icmp.id)
 			memcpy(&hash, &flow.icmp, sizeof(hash));
@@ -3772,6 +3858,45 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 	return bond_ip_hash(hash, &flow);
 }
 
+/**
+ * bond_xmit_hash - generate a hash value based on the xmit policy
+ * @bond: bonding device
+ * @skb: buffer to use for headers
+ *
+ * This function will extract the necessary headers from the skb buffer and use
+ * them to generate a hash based on the xmit_policy set in the bonding device
+ */
+u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
+{
+	if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 &&
+	    skb->l4_hash)
+		return skb->hash;
+
+	return __bond_xmit_hash(bond, skb, skb->head, skb->protocol,
+				skb->mac_header, skb->network_header,
+				skb_headlen(skb));
+}
+
+/**
+ * bond_xmit_hash_xdp - generate a hash value based on the xmit policy
+ * @bond: bonding device
+ * @xdp: buffer to use for headers
+ *
+ * The XDP variant of bond_xmit_hash.
+ */
+static u32 bond_xmit_hash_xdp(struct bonding *bond, struct xdp_buff *xdp)
+{
+	struct ethhdr *eth;
+
+	if (xdp->data + sizeof(struct ethhdr) > xdp->data_end)
+		return 0;
+
+	eth = (struct ethhdr *)xdp->data;
+
+	return __bond_xmit_hash(bond, NULL, xdp->data, eth->h_proto, 0,
+				sizeof(struct ethhdr), xdp->data_end - xdp->data);
+}
+
 /*-------------------------- Device entry points ----------------------------*/
 
 void bond_work_init_all(struct bonding *bond)
@@ -3962,20 +4087,13 @@ static void bond_get_stats(struct net_device *bond_dev,
 	rcu_read_unlock();
 }
 
-static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
+static int bond_eth_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct net_device *slave_dev = NULL;
-	struct ifbond k_binfo;
-	struct ifbond __user *u_binfo = NULL;
-	struct ifslave k_sinfo;
-	struct ifslave __user *u_sinfo = NULL;
 	struct mii_ioctl_data *mii = NULL;
-	struct bond_opt_value newval;
-	struct net *net;
-	int res = 0;
+	int res;
 
-	netdev_dbg(bond_dev, "bond_ioctl: cmd=%d\n", cmd);
+	netdev_dbg(bond_dev, "bond_eth_ioctl: cmd=%d\n", cmd);
 
 	switch (cmd) {
 	case SIOCGMIIPHY:
@@ -4000,7 +4118,28 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 		}
 
 		return 0;
-	case BOND_INFO_QUERY_OLD:
+	default:
+		res = -EOPNOTSUPP;
+	}
+
+	return res;
+}
+
+static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+	struct net_device *slave_dev = NULL;
+	struct ifbond k_binfo;
+	struct ifbond __user *u_binfo = NULL;
+	struct ifslave k_sinfo;
+	struct ifslave __user *u_sinfo = NULL;
+	struct bond_opt_value newval;
+	struct net *net;
+	int res = 0;
+
+	netdev_dbg(bond_dev, "bond_ioctl: cmd=%d\n", cmd);
+
+	switch (cmd) {
 	case SIOCBONDINFOQUERY:
 		u_binfo = (struct ifbond __user *)ifr->ifr_data;
 
@@ -4012,7 +4151,6 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 			return -EFAULT;
 
 		return 0;
-	case BOND_SLAVE_INFO_QUERY_OLD:
 	case SIOCBONDSLAVEINFOQUERY:
 		u_sinfo = (struct ifslave __user *)ifr->ifr_data;
 
@@ -4042,19 +4180,15 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 		return -ENODEV;
 
 	switch (cmd) {
-	case BOND_ENSLAVE_OLD:
 	case SIOCBONDENSLAVE:
 		res = bond_enslave(bond_dev, slave_dev, NULL);
 		break;
-	case BOND_RELEASE_OLD:
 	case SIOCBONDRELEASE:
 		res = bond_release(bond_dev, slave_dev);
 		break;
-	case BOND_SETHWADDR_OLD:
 	case SIOCBONDSETHWADDR:
 		res = bond_set_dev_addr(bond_dev, slave_dev);
 		break;
-	case BOND_CHANGE_ACTIVE_OLD:
 	case SIOCBONDCHANGEACTIVE:
 		bond_opt_initstr(&newval, slave_dev->name);
 		res = __bond_opt_set_notify(bond, BOND_OPT_ACTIVE_SLAVE,
@@ -4067,6 +4201,29 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 	return res;
 }
 
+static int bond_siocdevprivate(struct net_device *bond_dev, struct ifreq *ifr,
+			       void __user *data, int cmd)
+{
+	struct ifreq ifrdata = { .ifr_data = data };
+
+	switch (cmd) {
+	case BOND_INFO_QUERY_OLD:
+		return bond_do_ioctl(bond_dev, &ifrdata, SIOCBONDINFOQUERY);
+	case BOND_SLAVE_INFO_QUERY_OLD:
+		return bond_do_ioctl(bond_dev, &ifrdata, SIOCBONDSLAVEINFOQUERY);
+	case BOND_ENSLAVE_OLD:
+		return bond_do_ioctl(bond_dev, ifr, SIOCBONDENSLAVE);
+	case BOND_RELEASE_OLD:
+		return bond_do_ioctl(bond_dev, ifr, SIOCBONDRELEASE);
+	case BOND_SETHWADDR_OLD:
+		return bond_do_ioctl(bond_dev, ifr, SIOCBONDSETHWADDR);
+	case BOND_CHANGE_ACTIVE_OLD:
+		return bond_do_ioctl(bond_dev, ifr, SIOCBONDCHANGEACTIVE);
+	}
+
+	return -EOPNOTSUPP;
+}
+
 static void bond_change_rx_flags(struct net_device *bond_dev, int change)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
@@ -4388,6 +4545,47 @@ non_igmp:
 	return NULL;
 }
 
+static struct slave *bond_xdp_xmit_roundrobin_slave_get(struct bonding *bond,
+							struct xdp_buff *xdp)
+{
+	struct slave *slave;
+	int slave_cnt;
+	u32 slave_id;
+	const struct ethhdr *eth;
+	void *data = xdp->data;
+
+	if (data + sizeof(struct ethhdr) > xdp->data_end)
+		goto non_igmp;
+
+	eth = (struct ethhdr *)data;
+	data += sizeof(struct ethhdr);
+
+	/* See comment on IGMP in bond_xmit_roundrobin_slave_get() */
+	if (eth->h_proto == htons(ETH_P_IP)) {
+		const struct iphdr *iph;
+
+		if (data + sizeof(struct iphdr) > xdp->data_end)
+			goto non_igmp;
+
+		iph = (struct iphdr *)data;
+
+		if (iph->protocol == IPPROTO_IGMP) {
+			slave = rcu_dereference(bond->curr_active_slave);
+			if (slave)
+				return slave;
+			return bond_get_slave_by_id(bond, 0);
+		}
+	}
+
+non_igmp:
+	slave_cnt = READ_ONCE(bond->slave_cnt);
+	if (likely(slave_cnt)) {
+		slave_id = bond_rr_gen_slave_id(bond) % slave_cnt;
+		return bond_get_slave_by_id(bond, slave_id);
+	}
+	return NULL;
+}
+
 static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
 					struct net_device *bond_dev)
 {
@@ -4401,8 +4599,7 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
 	return bond_tx_drop(bond_dev, skb);
 }
 
-static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond,
-						      struct sk_buff *skb)
+static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond)
 {
 	return rcu_dereference(bond->curr_active_slave);
 }
@@ -4416,7 +4613,7 @@ static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb,
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave;
 
-	slave = bond_xmit_activebackup_slave_get(bond, skb);
+	slave = bond_xmit_activebackup_slave_get(bond);
 	if (slave)
 		return bond_dev_queue_xmit(bond, skb, slave->dev);
 
@@ -4604,6 +4801,22 @@ static struct slave *bond_xmit_3ad_xor_slave_get(struct bonding *bond,
 	return slave;
 }
 
+static struct slave *bond_xdp_xmit_3ad_xor_slave_get(struct bonding *bond,
+						     struct xdp_buff *xdp)
+{
+	struct bond_up_slave *slaves;
+	unsigned int count;
+	u32 hash;
+
+	hash = bond_xmit_hash_xdp(bond, xdp);
+	slaves = rcu_dereference(bond->usable_slaves);
+	count = slaves ? READ_ONCE(slaves->count) : 0;
+	if (unlikely(!count))
+		return NULL;
+
+	return slaves->arr[hash % count];
+}
+
 /* Use this Xmit function for 3AD as well as XOR modes. The current
  * usable slave array is formed in the control path. The xmit function
  * just calculates hash and sends the packet out.
@@ -4714,7 +4927,7 @@ static struct net_device *bond_xmit_get_slave(struct net_device *master_dev,
 		slave = bond_xmit_roundrobin_slave_get(bond, skb);
 		break;
 	case BOND_MODE_ACTIVEBACKUP:
-		slave = bond_xmit_activebackup_slave_get(bond, skb);
+		slave = bond_xmit_activebackup_slave_get(bond);
 		break;
 	case BOND_MODE_8023AD:
 	case BOND_MODE_XOR:
@@ -4888,6 +5101,172 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
+static struct net_device *
+bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+	struct slave *slave;
+
+	/* Caller needs to hold rcu_read_lock() */
+
+	switch (BOND_MODE(bond)) {
+	case BOND_MODE_ROUNDROBIN:
+		slave = bond_xdp_xmit_roundrobin_slave_get(bond, xdp);
+		break;
+
+	case BOND_MODE_ACTIVEBACKUP:
+		slave = bond_xmit_activebackup_slave_get(bond);
+		break;
+
+	case BOND_MODE_8023AD:
+	case BOND_MODE_XOR:
+		slave = bond_xdp_xmit_3ad_xor_slave_get(bond, xdp);
+		break;
+
+	default:
+		/* Should never happen. Mode guarded by bond_xdp_check() */
+		netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n", BOND_MODE(bond));
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	if (slave)
+		return slave->dev;
+
+	return NULL;
+}
+
+static int bond_xdp_xmit(struct net_device *bond_dev,
+			 int n, struct xdp_frame **frames, u32 flags)
+{
+	int nxmit, err = -ENXIO;
+
+	rcu_read_lock();
+
+	for (nxmit = 0; nxmit < n; nxmit++) {
+		struct xdp_frame *frame = frames[nxmit];
+		struct xdp_frame *frames1[] = {frame};
+		struct net_device *slave_dev;
+		struct xdp_buff xdp;
+
+		xdp_convert_frame_to_buff(frame, &xdp);
+
+		slave_dev = bond_xdp_get_xmit_slave(bond_dev, &xdp);
+		if (!slave_dev) {
+			err = -ENXIO;
+			break;
+		}
+
+		err = slave_dev->netdev_ops->ndo_xdp_xmit(slave_dev, 1, frames1, flags);
+		if (err < 1)
+			break;
+	}
+
+	rcu_read_unlock();
+
+	/* If error happened on the first frame then we can pass the error up, otherwise
+	 * report the number of frames that were xmitted.
+	 */
+	if (err < 0)
+		return (nxmit == 0 ? err : nxmit);
+
+	return nxmit;
+}
+
+static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog,
+			struct netlink_ext_ack *extack)
+{
+	struct bonding *bond = netdev_priv(dev);
+	struct list_head *iter;
+	struct slave *slave, *rollback_slave;
+	struct bpf_prog *old_prog;
+	struct netdev_bpf xdp = {
+		.command = XDP_SETUP_PROG,
+		.flags   = 0,
+		.prog    = prog,
+		.extack  = extack,
+	};
+	int err;
+
+	ASSERT_RTNL();
+
+	if (!bond_xdp_check(bond))
+		return -EOPNOTSUPP;
+
+	old_prog = bond->xdp_prog;
+	bond->xdp_prog = prog;
+
+	bond_for_each_slave(bond, slave, iter) {
+		struct net_device *slave_dev = slave->dev;
+
+		if (!slave_dev->netdev_ops->ndo_bpf ||
+		    !slave_dev->netdev_ops->ndo_xdp_xmit) {
+			SLAVE_NL_ERR(dev, slave_dev, extack,
+				     "Slave device does not support XDP");
+			err = -EOPNOTSUPP;
+			goto err;
+		}
+
+		if (dev_xdp_prog_count(slave_dev) > 0) {
+			SLAVE_NL_ERR(dev, slave_dev, extack,
+				     "Slave has XDP program loaded, please unload before enslaving");
+			err = -EOPNOTSUPP;
+			goto err;
+		}
+
+		err = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+		if (err < 0) {
+			/* ndo_bpf() sets extack error message */
+			slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err);
+			goto err;
+		}
+		if (prog)
+			bpf_prog_inc(prog);
+	}
+
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	if (prog)
+		static_branch_inc(&bpf_master_redirect_enabled_key);
+	else
+		static_branch_dec(&bpf_master_redirect_enabled_key);
+
+	return 0;
+
+err:
+	/* unwind the program changes */
+	bond->xdp_prog = old_prog;
+	xdp.prog = old_prog;
+	xdp.extack = NULL; /* do not overwrite original error */
+
+	bond_for_each_slave(bond, rollback_slave, iter) {
+		struct net_device *slave_dev = rollback_slave->dev;
+		int err_unwind;
+
+		if (slave == rollback_slave)
+			break;
+
+		err_unwind = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+		if (err_unwind < 0)
+			slave_err(dev, slave_dev,
+				  "Error %d when unwinding XDP program change\n", err_unwind);
+		else if (xdp.prog)
+			bpf_prog_inc(xdp.prog);
+	}
+	return err;
+}
+
+static int bond_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return bond_xdp_set(dev, xdp->prog, xdp->extack);
+	default:
+		return -EINVAL;
+	}
+}
+
 static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed)
 {
 	if (speed == 0 || speed == SPEED_UNKNOWN)
@@ -4955,7 +5334,9 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_start_xmit		= bond_start_xmit,
 	.ndo_select_queue	= bond_select_queue,
 	.ndo_get_stats64	= bond_get_stats,
-	.ndo_do_ioctl		= bond_do_ioctl,
+	.ndo_eth_ioctl		= bond_eth_ioctl,
+	.ndo_siocbond		= bond_do_ioctl,
+	.ndo_siocdevprivate	= bond_siocdevprivate,
 	.ndo_change_rx_flags	= bond_change_rx_flags,
 	.ndo_set_rx_mode	= bond_set_rx_mode,
 	.ndo_change_mtu		= bond_change_mtu,
@@ -4974,6 +5355,9 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_features_check	= passthru_features_check,
 	.ndo_get_xmit_slave	= bond_xmit_get_slave,
 	.ndo_sk_get_lower_dev	= bond_sk_get_lower_dev,
+	.ndo_bpf		= bond_xdp,
+	.ndo_xdp_xmit           = bond_xdp_xmit,
+	.ndo_xdp_get_xmit_slave = bond_xdp_get_xmit_slave,
 };
 
 static const struct device_type bond_type = {
@@ -5443,6 +5827,7 @@ static int bond_check_params(struct bond_params *params)
 	params->downdelay = downdelay;
 	params->peer_notif_delay = 0;
 	params->use_carrier = use_carrier;
+	params->lacp_active = 1;
 	params->lacp_fast = lacp_fast;
 	params->primary[0] = 0;
 	params->primary_reselect = primary_reselect_value;
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 0561ece1ba45..5d54e11d18fa 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -100,6 +100,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_MIN_LINKS]		= { .type = NLA_U32 },
 	[IFLA_BOND_LP_INTERVAL]		= { .type = NLA_U32 },
 	[IFLA_BOND_PACKETS_PER_SLAVE]	= { .type = NLA_U32 },
+	[IFLA_BOND_AD_LACP_ACTIVE]	= { .type = NLA_U8 },
 	[IFLA_BOND_AD_LACP_RATE]	= { .type = NLA_U8 },
 	[IFLA_BOND_AD_SELECT]		= { .type = NLA_U8 },
 	[IFLA_BOND_AD_INFO]		= { .type = NLA_NESTED },
@@ -387,6 +388,16 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[],
 		if (err)
 			return err;
 	}
+
+	if (data[IFLA_BOND_AD_LACP_ACTIVE]) {
+		int lacp_active = nla_get_u8(data[IFLA_BOND_AD_LACP_ACTIVE]);
+
+		bond_opt_initval(&newval, lacp_active);
+		err = __bond_opt_set(bond, BOND_OPT_LACP_ACTIVE, &newval);
+		if (err)
+			return err;
+	}
+
 	if (data[IFLA_BOND_AD_LACP_RATE]) {
 		int lacp_rate =
 			nla_get_u8(data[IFLA_BOND_AD_LACP_RATE]);
@@ -490,6 +501,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_MIN_LINKS */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_LP_INTERVAL */
 		nla_total_size(sizeof(u32)) +  /* IFLA_BOND_PACKETS_PER_SLAVE */
+		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_AD_LACP_ACTIVE */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_AD_LACP_RATE */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_AD_SELECT */
 		nla_total_size(sizeof(struct nlattr)) + /* IFLA_BOND_AD_INFO */
@@ -622,6 +634,10 @@ static int bond_fill_info(struct sk_buff *skb,
 			packets_per_slave))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_BOND_AD_LACP_ACTIVE,
+		       bond->params.lacp_active))
+		goto nla_put_failure;
+
 	if (nla_put_u8(skb, IFLA_BOND_AD_LACP_RATE,
 		       bond->params.lacp_fast))
 		goto nla_put_failure;
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 0cf25de6f46d..a8fde3bc458f 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -58,6 +58,8 @@ static int bond_option_lp_interval_set(struct bonding *bond,
 				       const struct bond_opt_value *newval);
 static int bond_option_pps_set(struct bonding *bond,
 			       const struct bond_opt_value *newval);
+static int bond_option_lacp_active_set(struct bonding *bond,
+				       const struct bond_opt_value *newval);
 static int bond_option_lacp_rate_set(struct bonding *bond,
 				     const struct bond_opt_value *newval);
 static int bond_option_ad_select_set(struct bonding *bond,
@@ -135,6 +137,12 @@ static const struct bond_opt_value bond_intmax_tbl[] = {
 	{ NULL,      -1,      0}
 };
 
+static const struct bond_opt_value bond_lacp_active[] = {
+	{ "off", 0,  0},
+	{ "on",  1,  BOND_VALFLAG_DEFAULT},
+	{ NULL,  -1, 0}
+};
+
 static const struct bond_opt_value bond_lacp_rate_tbl[] = {
 	{ "slow", AD_LACP_SLOW, 0},
 	{ "fast", AD_LACP_FAST, 0},
@@ -283,6 +291,15 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 		.values = bond_intmax_tbl,
 		.set = bond_option_updelay_set
 	},
+	[BOND_OPT_LACP_ACTIVE] = {
+		.id = BOND_OPT_LACP_ACTIVE,
+		.name = "lacp_active",
+		.desc = "Send LACPDU frames with configured lacp rate or acts as speak when spoken to",
+		.flags = BOND_OPTFLAG_IFDOWN,
+		.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
+		.values = bond_lacp_active,
+		.set = bond_option_lacp_active_set
+	},
 	[BOND_OPT_LACP_RATE] = {
 		.id = BOND_OPT_LACP_RATE,
 		.name = "lacp_rate",
@@ -1333,6 +1350,16 @@ static int bond_option_pps_set(struct bonding *bond,
 	return 0;
 }
 
+static int bond_option_lacp_active_set(struct bonding *bond,
+				       const struct bond_opt_value *newval)
+{
+	netdev_dbg(bond->dev, "Setting LACP active to %s (%llu)\n",
+		   newval->string, newval->value);
+	bond->params.lacp_active = newval->value;
+
+	return 0;
+}
+
 static int bond_option_lacp_rate_set(struct bonding *bond,
 				     const struct bond_opt_value *newval)
 {
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index 0fb1da361bb1..f3e3bfd72556 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -133,6 +133,8 @@ static void bond_info_show_master(struct seq_file *seq)
 		struct ad_info ad_info;
 
 		seq_puts(seq, "\n802.3ad info\n");
+		seq_printf(seq, "LACP active: %s\n",
+			   (bond->params.lacp_active) ? "on" : "off");
 		seq_printf(seq, "LACP rate: %s\n",
 			   (bond->params.lacp_fast) ? "fast" : "slow");
 		seq_printf(seq, "Min links: %d\n", bond->params.min_links);
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 5f9e9a240226..b9e9842fed94 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -339,10 +339,24 @@ static ssize_t bonding_show_peer_notif_delay(struct device *d,
 static DEVICE_ATTR(peer_notif_delay, 0644,
 		   bonding_show_peer_notif_delay, bonding_sysfs_store_option);
 
-/* Show the LACP interval. */
-static ssize_t bonding_show_lacp(struct device *d,
-				 struct device_attribute *attr,
-				 char *buf)
+/* Show the LACP activity and interval. */
+static ssize_t bonding_show_lacp_active(struct device *d,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct bonding *bond = to_bond(d);
+	const struct bond_opt_value *val;
+
+	val = bond_opt_get_val(BOND_OPT_LACP_ACTIVE, bond->params.lacp_active);
+
+	return sprintf(buf, "%s %d\n", val->string, bond->params.lacp_active);
+}
+static DEVICE_ATTR(lacp_active, 0644,
+		   bonding_show_lacp_active, bonding_sysfs_store_option);
+
+static ssize_t bonding_show_lacp_rate(struct device *d,
+				      struct device_attribute *attr,
+				      char *buf)
 {
 	struct bonding *bond = to_bond(d);
 	const struct bond_opt_value *val;
@@ -352,7 +366,7 @@ static ssize_t bonding_show_lacp(struct device *d,
 	return sprintf(buf, "%s %d\n", val->string, bond->params.lacp_fast);
 }
 static DEVICE_ATTR(lacp_rate, 0644,
-		   bonding_show_lacp, bonding_sysfs_store_option);
+		   bonding_show_lacp_rate, bonding_sysfs_store_option);
 
 static ssize_t bonding_show_min_links(struct device *d,
 				      struct device_attribute *attr,
@@ -738,6 +752,7 @@ static struct attribute *per_bond_attrs[] = {
 	&dev_attr_downdelay.attr,
 	&dev_attr_updelay.attr,
 	&dev_attr_peer_notif_delay.attr,
+	&dev_attr_lacp_active.attr,
 	&dev_attr_lacp_rate.attr,
 	&dev_attr_ad_select.attr,
 	&dev_attr_xmit_hash_policy.attr,
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index e355d3974977..fff259247d52 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -97,7 +97,8 @@ config CAN_AT91
 
 config CAN_FLEXCAN
 	tristate "Support for Freescale FLEXCAN based chips"
-	depends on OF && HAS_IOMEM
+	depends on OF || COLDFIRE || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Say Y here if you want to support for Freescale FlexCAN.
 
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index 04d0bb3ffe89..b06af90a9964 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -43,14 +43,14 @@ enum at91_reg {
 };
 
 /* Mailbox registers (0 <= i <= 15) */
-#define AT91_MMR(i)		(enum at91_reg)(0x200 + ((i) * 0x20))
-#define AT91_MAM(i)		(enum at91_reg)(0x204 + ((i) * 0x20))
-#define AT91_MID(i)		(enum at91_reg)(0x208 + ((i) * 0x20))
-#define AT91_MFID(i)		(enum at91_reg)(0x20C + ((i) * 0x20))
-#define AT91_MSR(i)		(enum at91_reg)(0x210 + ((i) * 0x20))
-#define AT91_MDL(i)		(enum at91_reg)(0x214 + ((i) * 0x20))
-#define AT91_MDH(i)		(enum at91_reg)(0x218 + ((i) * 0x20))
-#define AT91_MCR(i)		(enum at91_reg)(0x21C + ((i) * 0x20))
+#define AT91_MMR(i)		((enum at91_reg)(0x200 + ((i) * 0x20)))
+#define AT91_MAM(i)		((enum at91_reg)(0x204 + ((i) * 0x20)))
+#define AT91_MID(i)		((enum at91_reg)(0x208 + ((i) * 0x20)))
+#define AT91_MFID(i)		((enum at91_reg)(0x20C + ((i) * 0x20)))
+#define AT91_MSR(i)		((enum at91_reg)(0x210 + ((i) * 0x20)))
+#define AT91_MDL(i)		((enum at91_reg)(0x214 + ((i) * 0x20)))
+#define AT91_MDH(i)		((enum at91_reg)(0x218 + ((i) * 0x20)))
+#define AT91_MCR(i)		((enum at91_reg)(0x21C + ((i) * 0x20)))
 
 /* Register bits */
 #define AT91_MR_CANEN		BIT(0)
@@ -87,19 +87,19 @@ enum at91_mb_mode {
 };
 
 /* Interrupt mask bits */
-#define AT91_IRQ_ERRA		(1 << 16)
-#define AT91_IRQ_WARN		(1 << 17)
-#define AT91_IRQ_ERRP		(1 << 18)
-#define AT91_IRQ_BOFF		(1 << 19)
-#define AT91_IRQ_SLEEP		(1 << 20)
-#define AT91_IRQ_WAKEUP		(1 << 21)
-#define AT91_IRQ_TOVF		(1 << 22)
-#define AT91_IRQ_TSTP		(1 << 23)
-#define AT91_IRQ_CERR		(1 << 24)
-#define AT91_IRQ_SERR		(1 << 25)
-#define AT91_IRQ_AERR		(1 << 26)
-#define AT91_IRQ_FERR		(1 << 27)
-#define AT91_IRQ_BERR		(1 << 28)
+#define AT91_IRQ_ERRA		BIT(16)
+#define AT91_IRQ_WARN		BIT(17)
+#define AT91_IRQ_ERRP		BIT(18)
+#define AT91_IRQ_BOFF		BIT(19)
+#define AT91_IRQ_SLEEP		BIT(20)
+#define AT91_IRQ_WAKEUP		BIT(21)
+#define AT91_IRQ_TOVF		BIT(22)
+#define AT91_IRQ_TSTP		BIT(23)
+#define AT91_IRQ_CERR		BIT(24)
+#define AT91_IRQ_SERR		BIT(25)
+#define AT91_IRQ_AERR		BIT(26)
+#define AT91_IRQ_FERR		BIT(27)
+#define AT91_IRQ_BERR		BIT(28)
 
 #define AT91_IRQ_ERR_ALL	(0x1fff0000)
 #define AT91_IRQ_ERR_FRAME	(AT91_IRQ_CERR | AT91_IRQ_SERR | \
@@ -163,7 +163,7 @@ static const struct can_bittiming_const at91_bittiming_const = {
 	.tseg2_min	= 2,
 	.tseg2_max	= 8,
 	.sjw_max	= 4,
-	.brp_min 	= 2,
+	.brp_min	= 2,
 	.brp_max	= 128,
 	.brp_inc	= 1,
 };
@@ -281,19 +281,20 @@ static inline u32 at91_read(const struct at91_priv *priv, enum at91_reg reg)
 }
 
 static inline void at91_write(const struct at91_priv *priv, enum at91_reg reg,
-		u32 value)
+			      u32 value)
 {
 	writel_relaxed(value, priv->reg_base + reg);
 }
 
 static inline void set_mb_mode_prio(const struct at91_priv *priv,
-		unsigned int mb, enum at91_mb_mode mode, int prio)
+				    unsigned int mb, enum at91_mb_mode mode,
+				    int prio)
 {
 	at91_write(priv, AT91_MMR(mb), (mode << 24) | (prio << 16));
 }
 
 static inline void set_mb_mode(const struct at91_priv *priv, unsigned int mb,
-		enum at91_mb_mode mode)
+			       enum at91_mb_mode mode)
 {
 	set_mb_mode_prio(priv, mb, mode, 0);
 }
@@ -316,8 +317,7 @@ static void at91_setup_mailboxes(struct net_device *dev)
 	unsigned int i;
 	u32 reg_mid;
 
-	/*
-	 * Due to a chip bug (errata 50.2.6.3 & 50.3.5.3) the first
+	/* Due to a chip bug (errata 50.2.6.3 & 50.3.5.3) the first
 	 * mailbox is disabled. The next 11 mailboxes are used as a
 	 * reception FIFO. The last mailbox is configured with
 	 * overwrite option. The overwrite flag indicates a FIFO
@@ -368,7 +368,7 @@ static int at91_set_bittiming(struct net_device *dev)
 }
 
 static int at91_get_berr_counter(const struct net_device *dev,
-		struct can_berr_counter *bec)
+				 struct can_berr_counter *bec)
 {
 	const struct at91_priv *priv = netdev_priv(dev);
 	u32 reg_ecr = at91_read(priv, AT91_ECR);
@@ -423,8 +423,7 @@ static void at91_chip_stop(struct net_device *dev, enum can_state state)
 	priv->can.state = state;
 }
 
-/*
- * theory of operation:
+/* theory of operation:
  *
  * According to the datasheet priority 0 is the highest priority, 15
  * is the lowest. If two mailboxes have the same priority level the
@@ -486,8 +485,7 @@ static netdev_tx_t at91_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* _NOTE_: subtract AT91_MB_TX_FIRST offset from mb! */
 	can_put_echo_skb(skb, dev, mb - get_mb_tx_first(priv), 0);
 
-	/*
-	 * we have to stop the queue and deliver all messages in case
+	/* we have to stop the queue and deliver all messages in case
 	 * of a prio+mb counter wrap around. This is the case if
 	 * tx_next buffer prio and mailbox equals 0.
 	 *
@@ -515,6 +513,7 @@ static netdev_tx_t at91_start_xmit(struct sk_buff *skb, struct net_device *dev)
 static inline void at91_activate_rx_low(const struct at91_priv *priv)
 {
 	u32 mask = get_mb_rx_low_mask(priv);
+
 	at91_write(priv, AT91_TCR, mask);
 }
 
@@ -526,9 +525,10 @@ static inline void at91_activate_rx_low(const struct at91_priv *priv)
  * Reenables given mailbox for reception of new CAN messages
  */
 static inline void at91_activate_rx_mb(const struct at91_priv *priv,
-		unsigned int mb)
+				       unsigned int mb)
 {
 	u32 mask = 1 << mb;
+
 	at91_write(priv, AT91_TCR, mask);
 }
 
@@ -568,7 +568,7 @@ static void at91_rx_overflow_err(struct net_device *dev)
  * given can frame. "mb" and "cf" must be valid.
  */
 static void at91_read_mb(struct net_device *dev, unsigned int mb,
-		struct can_frame *cf)
+			 struct can_frame *cf)
 {
 	const struct at91_priv *priv = netdev_priv(dev);
 	u32 reg_msr, reg_mid;
@@ -582,9 +582,9 @@ static void at91_read_mb(struct net_device *dev, unsigned int mb,
 	reg_msr = at91_read(priv, AT91_MSR(mb));
 	cf->len = can_cc_dlc2len((reg_msr >> 16) & 0xf);
 
-	if (reg_msr & AT91_MSR_MRTR)
+	if (reg_msr & AT91_MSR_MRTR) {
 		cf->can_id |= CAN_RTR_FLAG;
-	else {
+	} else {
 		*(u32 *)(cf->data + 0) = at91_read(priv, AT91_MDL(mb));
 		*(u32 *)(cf->data + 4) = at91_read(priv, AT91_MDH(mb));
 	}
@@ -685,7 +685,7 @@ static int at91_poll_rx(struct net_device *dev, int quota)
 	if (priv->rx_next > get_mb_rx_low_last(priv) &&
 	    reg_sr & get_mb_rx_low_mask(priv))
 		netdev_info(dev,
-			"order of incoming frames cannot be guaranteed\n");
+			    "order of incoming frames cannot be guaranteed\n");
 
  again:
 	for (mb = find_next_bit(addr, get_mb_tx_first(priv), priv->rx_next);
@@ -718,7 +718,7 @@ static int at91_poll_rx(struct net_device *dev, int quota)
 }
 
 static void at91_poll_err_frame(struct net_device *dev,
-		struct can_frame *cf, u32 reg_sr)
+				struct can_frame *cf, u32 reg_sr)
 {
 	struct at91_priv *priv = netdev_priv(dev);
 
@@ -796,8 +796,7 @@ static int at91_poll(struct napi_struct *napi, int quota)
 	if (reg_sr & get_irq_mb_rx(priv))
 		work_done += at91_poll_rx(dev, quota - work_done);
 
-	/*
-	 * The error bits are clear on read,
+	/* The error bits are clear on read,
 	 * so use saved value from irq handler.
 	 */
 	reg_sr |= priv->reg_sr;
@@ -807,6 +806,7 @@ static int at91_poll(struct napi_struct *napi, int quota)
 	if (work_done < quota) {
 		/* enable IRQs for frame errors and all mailboxes >= rx_next */
 		u32 reg_ier = AT91_IRQ_ERR_FRAME;
+
 		reg_ier |= get_irq_mb_rx(priv) & ~AT91_MB_MASK(priv->rx_next);
 
 		napi_complete_done(napi, work_done);
@@ -816,8 +816,7 @@ static int at91_poll(struct napi_struct *napi, int quota)
 	return work_done;
 }
 
-/*
- * theory of operation:
+/* theory of operation:
  *
  * priv->tx_echo holds the number of the oldest can_frame put for
  * transmission into the hardware, but not yet ACKed by the CAN tx
@@ -846,8 +845,7 @@ static void at91_irq_tx(struct net_device *dev, u32 reg_sr)
 		/* Disable irq for this TX mailbox */
 		at91_write(priv, AT91_IDR, 1 << mb);
 
-		/*
-		 * only echo if mailbox signals us a transfer
+		/* only echo if mailbox signals us a transfer
 		 * complete (MSR_MRDY). Otherwise it's a tansfer
 		 * abort. "can_bus_off()" takes care about the skbs
 		 * parked in the echo queue.
@@ -862,8 +860,7 @@ static void at91_irq_tx(struct net_device *dev, u32 reg_sr)
 		}
 	}
 
-	/*
-	 * restart queue if we don't have a wrap around but restart if
+	/* restart queue if we don't have a wrap around but restart if
 	 * we get a TX int for the last can frame directly before a
 	 * wrap around.
 	 */
@@ -873,7 +870,7 @@ static void at91_irq_tx(struct net_device *dev, u32 reg_sr)
 }
 
 static void at91_irq_err_state(struct net_device *dev,
-		struct can_frame *cf, enum can_state new_state)
+			       struct can_frame *cf, enum can_state new_state)
 {
 	struct at91_priv *priv = netdev_priv(dev);
 	u32 reg_idr = 0, reg_ier = 0;
@@ -883,8 +880,7 @@ static void at91_irq_err_state(struct net_device *dev,
 
 	switch (priv->can.state) {
 	case CAN_STATE_ERROR_ACTIVE:
-		/*
-		 * from: ERROR_ACTIVE
+		/* from: ERROR_ACTIVE
 		 * to  : ERROR_WARNING, ERROR_PASSIVE, BUS_OFF
 		 * =>  : there was a warning int
 		 */
@@ -900,8 +896,7 @@ static void at91_irq_err_state(struct net_device *dev,
 		}
 		fallthrough;
 	case CAN_STATE_ERROR_WARNING:
-		/*
-		 * from: ERROR_ACTIVE, ERROR_WARNING
+		/* from: ERROR_ACTIVE, ERROR_WARNING
 		 * to  : ERROR_PASSIVE, BUS_OFF
 		 * =>  : error passive int
 		 */
@@ -917,8 +912,7 @@ static void at91_irq_err_state(struct net_device *dev,
 		}
 		break;
 	case CAN_STATE_BUS_OFF:
-		/*
-		 * from: BUS_OFF
+		/* from: BUS_OFF
 		 * to  : ERROR_ACTIVE, ERROR_WARNING, ERROR_PASSIVE
 		 */
 		if (new_state <= CAN_STATE_ERROR_PASSIVE) {
@@ -935,12 +929,10 @@ static void at91_irq_err_state(struct net_device *dev,
 		break;
 	}
 
-
 	/* process state changes depending on the new state */
 	switch (new_state) {
 	case CAN_STATE_ERROR_ACTIVE:
-		/*
-		 * actually we want to enable AT91_IRQ_WARN here, but
+		/* actually we want to enable AT91_IRQ_WARN here, but
 		 * it screws up the system under certain
 		 * circumstances. so just enable AT91_IRQ_ERRP, thus
 		 * the "fallthrough"
@@ -983,7 +975,7 @@ static void at91_irq_err_state(struct net_device *dev,
 }
 
 static int at91_get_state_by_bec(const struct net_device *dev,
-		enum can_state *state)
+				 enum can_state *state)
 {
 	struct can_berr_counter bec;
 	int err;
@@ -1004,7 +996,6 @@ static int at91_get_state_by_bec(const struct net_device *dev,
 	return 0;
 }
 
-
 static void at91_irq_err(struct net_device *dev)
 {
 	struct at91_priv *priv = netdev_priv(dev);
@@ -1018,15 +1009,15 @@ static void at91_irq_err(struct net_device *dev)
 		reg_sr = at91_read(priv, AT91_SR);
 
 		/* we need to look at the unmasked reg_sr */
-		if (unlikely(reg_sr & AT91_IRQ_BOFF))
+		if (unlikely(reg_sr & AT91_IRQ_BOFF)) {
 			new_state = CAN_STATE_BUS_OFF;
-		else if (unlikely(reg_sr & AT91_IRQ_ERRP))
+		} else if (unlikely(reg_sr & AT91_IRQ_ERRP)) {
 			new_state = CAN_STATE_ERROR_PASSIVE;
-		else if (unlikely(reg_sr & AT91_IRQ_WARN))
+		} else if (unlikely(reg_sr & AT91_IRQ_WARN)) {
 			new_state = CAN_STATE_ERROR_WARNING;
-		else if (likely(reg_sr & AT91_IRQ_ERRA))
+		} else if (likely(reg_sr & AT91_IRQ_ERRA)) {
 			new_state = CAN_STATE_ERROR_ACTIVE;
-		else {
+		} else {
 			netdev_err(dev, "BUG! hardware in undefined state\n");
 			return;
 		}
@@ -1053,8 +1044,7 @@ static void at91_irq_err(struct net_device *dev)
 	priv->can.state = new_state;
 }
 
-/*
- * interrupt handler
+/* interrupt handler
  */
 static irqreturn_t at91_irq(int irq, void *dev_id)
 {
@@ -1075,8 +1065,7 @@ static irqreturn_t at91_irq(int irq, void *dev_id)
 
 	/* Receive or error interrupt? -> napi */
 	if (reg_sr & (get_irq_mb_rx(priv) | AT91_IRQ_ERR_FRAME)) {
-		/*
-		 * The error bits are clear on read,
+		/* The error bits are clear on read,
 		 * save for later use.
 		 */
 		priv->reg_sr = reg_sr;
@@ -1133,8 +1122,7 @@ static int at91_open(struct net_device *dev)
 	return err;
 }
 
-/*
- * stop CAN bus activity
+/* stop CAN bus activity
  */
 static int at91_close(struct net_device *dev)
 {
@@ -1176,8 +1164,8 @@ static const struct net_device_ops at91_netdev_ops = {
 	.ndo_change_mtu = can_change_mtu,
 };
 
-static ssize_t at91_sysfs_show_mb0_id(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t mb0_id_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
 {
 	struct at91_priv *priv = netdev_priv(to_net_dev(dev));
 
@@ -1187,8 +1175,9 @@ static ssize_t at91_sysfs_show_mb0_id(struct device *dev,
 		return snprintf(buf, PAGE_SIZE, "0x%03x\n", priv->mb0_id);
 }
 
-static ssize_t at91_sysfs_set_mb0_id(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t mb0_id_store(struct device *dev,
+			    struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	struct net_device *ndev = to_net_dev(dev);
 	struct at91_priv *priv = netdev_priv(ndev);
@@ -1222,7 +1211,7 @@ static ssize_t at91_sysfs_set_mb0_id(struct device *dev,
 	return ret;
 }
 
-static DEVICE_ATTR(mb0_id, 0644, at91_sysfs_show_mb0_id, at91_sysfs_set_mb0_id);
+static DEVICE_ATTR_RW(mb0_id);
 
 static struct attribute *at91_sysfs_attrs[] = {
 	&dev_attr_mb0_id.attr,
diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h
index 4247ff80a29c..08b6efa7a1a7 100644
--- a/drivers/net/can/c_can/c_can.h
+++ b/drivers/net/can/c_can/c_can.h
@@ -176,6 +176,13 @@ struct c_can_raminit {
 	bool needs_pulse;
 };
 
+/* c_can tx ring structure */
+struct c_can_tx_ring {
+	unsigned int head;
+	unsigned int tail;
+	unsigned int obj_num;
+};
+
 /* c_can private data structure */
 struct c_can_priv {
 	struct can_priv can;	/* must be the first member */
@@ -190,17 +197,16 @@ struct c_can_priv {
 	unsigned int msg_obj_tx_first;
 	unsigned int msg_obj_tx_last;
 	u32 msg_obj_rx_mask;
-	atomic_t tx_active;
 	atomic_t sie_pending;
 	unsigned long tx_dir;
 	int last_status;
+	struct c_can_tx_ring tx;
 	u16 (*read_reg)(const struct c_can_priv *priv, enum reg index);
 	void (*write_reg)(const struct c_can_priv *priv, enum reg index, u16 val);
 	u32 (*read_reg32)(const struct c_can_priv *priv, enum reg index);
 	void (*write_reg32)(const struct c_can_priv *priv, enum reg index, u32 val);
 	void __iomem *base;
 	const u16 *regs;
-	void *priv;		/* for board-specific data */
 	enum c_can_dev_id type;
 	struct c_can_raminit raminit_sys;	/* RAMINIT via syscon regmap */
 	void (*raminit)(const struct c_can_priv *priv, bool enable);
@@ -220,4 +226,19 @@ int c_can_power_down(struct net_device *dev);
 
 void c_can_set_ethtool_ops(struct net_device *dev);
 
+static inline u8 c_can_get_tx_head(const struct c_can_tx_ring *ring)
+{
+	return ring->head & (ring->obj_num - 1);
+}
+
+static inline u8 c_can_get_tx_tail(const struct c_can_tx_ring *ring)
+{
+	return ring->tail & (ring->obj_num - 1);
+}
+
+static inline u8 c_can_get_tx_free(const struct c_can_tx_ring *ring)
+{
+	return ring->obj_num - (ring->head - ring->tail);
+}
+
 #endif /* C_CAN_H */
diff --git a/drivers/net/can/c_can/c_can_main.c b/drivers/net/can/c_can/c_can_main.c
index 7588f70ca0fe..52671d1ea17d 100644
--- a/drivers/net/can/c_can/c_can_main.c
+++ b/drivers/net/can/c_can/c_can_main.c
@@ -160,8 +160,8 @@
 
 #define IF_MCONT_TX		(IF_MCONT_TXIE | IF_MCONT_EOB)
 
-/* Use IF1 for RX and IF2 for TX */
-#define IF_RX			0
+/* Use IF1 in NAPI path and IF2 in TX path */
+#define IF_NAPI			0
 #define IF_TX			1
 
 /* minimum timeout for checking BUSY status */
@@ -427,24 +427,51 @@ static void c_can_setup_receive_object(struct net_device *dev, int iface,
 	c_can_object_put(dev, iface, obj, IF_COMM_RCV_SETUP);
 }
 
+static bool c_can_tx_busy(const struct c_can_priv *priv,
+			  const struct c_can_tx_ring *tx_ring)
+{
+	if (c_can_get_tx_free(tx_ring) > 0)
+		return false;
+
+	netif_stop_queue(priv->dev);
+
+	/* Memory barrier before checking tx_free (head and tail) */
+	smp_mb();
+
+	if (c_can_get_tx_free(tx_ring) == 0) {
+		netdev_dbg(priv->dev,
+			   "Stopping tx-queue (tx_head=0x%08x, tx_tail=0x%08x, len=%d).\n",
+			   tx_ring->head, tx_ring->tail,
+			   tx_ring->head - tx_ring->tail);
+		return true;
+	}
+
+	netif_start_queue(priv->dev);
+	return false;
+}
+
 static netdev_tx_t c_can_start_xmit(struct sk_buff *skb,
 				    struct net_device *dev)
 {
 	struct can_frame *frame = (struct can_frame *)skb->data;
 	struct c_can_priv *priv = netdev_priv(dev);
-	u32 idx, obj;
+	struct c_can_tx_ring *tx_ring = &priv->tx;
+	u32 idx, obj, cmd = IF_COMM_TX;
 
 	if (can_dropped_invalid_skb(dev, skb))
 		return NETDEV_TX_OK;
-	/* This is not a FIFO. C/D_CAN sends out the buffers
-	 * prioritized. The lowest buffer number wins.
-	 */
-	idx = fls(atomic_read(&priv->tx_active));
-	obj = idx + priv->msg_obj_tx_first;
 
-	/* If this is the last buffer, stop the xmit queue */
-	if (idx == priv->msg_obj_tx_num - 1)
+	if (c_can_tx_busy(priv, tx_ring))
+		return NETDEV_TX_BUSY;
+
+	idx = c_can_get_tx_head(tx_ring);
+	tx_ring->head++;
+	if (c_can_get_tx_free(tx_ring) == 0)
 		netif_stop_queue(dev);
+
+	if (idx < c_can_get_tx_tail(tx_ring))
+		cmd &= ~IF_COMM_TXRQST; /* Cache the message */
+
 	/* Store the message in the interface so we can call
 	 * can_put_echo_skb(). We must do this before we enable
 	 * transmit as we might race against do_tx().
@@ -452,11 +479,8 @@ static netdev_tx_t c_can_start_xmit(struct sk_buff *skb,
 	c_can_setup_tx_object(dev, IF_TX, frame, idx);
 	priv->dlc[idx] = frame->len;
 	can_put_echo_skb(skb, dev, idx, 0);
-
-	/* Update the active bits */
-	atomic_add(BIT(idx), &priv->tx_active);
-	/* Start transmission */
-	c_can_object_put(dev, IF_TX, obj, IF_COMM_TX);
+	obj = idx + priv->msg_obj_tx_first;
+	c_can_object_put(dev, IF_TX, obj, cmd);
 
 	return NETDEV_TX_OK;
 }
@@ -529,13 +553,13 @@ static void c_can_configure_msg_objects(struct net_device *dev)
 
 	/* first invalidate all message objects */
 	for (i = priv->msg_obj_rx_first; i <= priv->msg_obj_num; i++)
-		c_can_inval_msg_object(dev, IF_RX, i);
+		c_can_inval_msg_object(dev, IF_NAPI, i);
 
 	/* setup receive message objects */
 	for (i = priv->msg_obj_rx_first; i < priv->msg_obj_rx_last; i++)
-		c_can_setup_receive_object(dev, IF_RX, i, 0, 0, IF_MCONT_RCV);
+		c_can_setup_receive_object(dev, IF_NAPI, i, 0, 0, IF_MCONT_RCV);
 
-	c_can_setup_receive_object(dev, IF_RX, priv->msg_obj_rx_last, 0, 0,
+	c_can_setup_receive_object(dev, IF_NAPI, priv->msg_obj_rx_last, 0, 0,
 				   IF_MCONT_RCV_EOB);
 }
 
@@ -567,6 +591,7 @@ static int c_can_software_reset(struct net_device *dev)
 static int c_can_chip_config(struct net_device *dev)
 {
 	struct c_can_priv *priv = netdev_priv(dev);
+	struct c_can_tx_ring *tx_ring = &priv->tx;
 	int err;
 
 	err = c_can_software_reset(dev);
@@ -598,7 +623,8 @@ static int c_can_chip_config(struct net_device *dev)
 	priv->write_reg(priv, C_CAN_STS_REG, LEC_UNUSED);
 
 	/* Clear all internal status */
-	atomic_set(&priv->tx_active, 0);
+	tx_ring->head = 0;
+	tx_ring->tail = 0;
 	priv->tx_dir = 0;
 
 	/* set bittiming params */
@@ -696,40 +722,57 @@ static int c_can_get_berr_counter(const struct net_device *dev,
 static void c_can_do_tx(struct net_device *dev)
 {
 	struct c_can_priv *priv = netdev_priv(dev);
+	struct c_can_tx_ring *tx_ring = &priv->tx;
 	struct net_device_stats *stats = &dev->stats;
-	u32 idx, obj, pkts = 0, bytes = 0, pend, clr;
+	u32 idx, obj, pkts = 0, bytes = 0, pend;
+	u8 tail;
 
 	if (priv->msg_obj_tx_last > 32)
 		pend = priv->read_reg32(priv, C_CAN_INTPND3_REG);
 	else
 		pend = priv->read_reg(priv, C_CAN_INTPND2_REG);
-	clr = pend;
 
 	while ((idx = ffs(pend))) {
 		idx--;
 		pend &= ~BIT(idx);
 		obj = idx + priv->msg_obj_tx_first;
 
-		/* We use IF_RX interface instead of IF_TX because we
+		/* We use IF_NAPI interface instead of IF_TX because we
 		 * are called from c_can_poll(), which runs inside
-		 * NAPI. We are not trasmitting.
+		 * NAPI. We are not transmitting.
 		 */
-		c_can_inval_tx_object(dev, IF_RX, obj);
+		c_can_inval_tx_object(dev, IF_NAPI, obj);
 		can_get_echo_skb(dev, idx, NULL);
 		bytes += priv->dlc[idx];
 		pkts++;
 	}
 
-	/* Clear the bits in the tx_active mask */
-	atomic_sub(clr, &priv->tx_active);
+	if (!pkts)
+		return;
 
-	if (clr & BIT(priv->msg_obj_tx_num - 1))
-		netif_wake_queue(dev);
+	tx_ring->tail += pkts;
+	if (c_can_get_tx_free(tx_ring)) {
+		/* Make sure that anybody stopping the queue after
+		 * this sees the new tx_ring->tail.
+		 */
+		smp_mb();
+		netif_wake_queue(priv->dev);
+	}
 
-	if (pkts) {
-		stats->tx_bytes += bytes;
-		stats->tx_packets += pkts;
-		can_led_event(dev, CAN_LED_EVENT_TX);
+	stats->tx_bytes += bytes;
+	stats->tx_packets += pkts;
+	can_led_event(dev, CAN_LED_EVENT_TX);
+
+	tail = c_can_get_tx_tail(tx_ring);
+
+	if (tail == 0) {
+		u8 head = c_can_get_tx_head(tx_ring);
+
+		/* Start transmission for all cached messages */
+		for (idx = tail; idx < head; idx++) {
+			obj = idx + priv->msg_obj_tx_first;
+			c_can_object_put(dev, IF_NAPI, obj, IF_COMM_TXRQST);
+		}
 	}
 }
 
@@ -766,14 +809,14 @@ static u32 c_can_adjust_pending(u32 pend, u32 rx_mask)
 static inline void c_can_rx_object_get(struct net_device *dev,
 				       struct c_can_priv *priv, u32 obj)
 {
-	c_can_object_get(dev, IF_RX, obj, priv->comm_rcv_high);
+	c_can_object_get(dev, IF_NAPI, obj, priv->comm_rcv_high);
 }
 
 static inline void c_can_rx_finalize(struct net_device *dev,
 				     struct c_can_priv *priv, u32 obj)
 {
 	if (priv->type != BOSCH_D_CAN)
-		c_can_object_get(dev, IF_RX, obj, IF_COMM_CLR_NEWDAT);
+		c_can_object_get(dev, IF_NAPI, obj, IF_COMM_CLR_NEWDAT);
 }
 
 static int c_can_read_objects(struct net_device *dev, struct c_can_priv *priv,
@@ -785,10 +828,12 @@ static int c_can_read_objects(struct net_device *dev, struct c_can_priv *priv,
 		pend &= ~BIT(obj - 1);
 
 		c_can_rx_object_get(dev, priv, obj);
-		ctrl = priv->read_reg(priv, C_CAN_IFACE(MSGCTRL_REG, IF_RX));
+		ctrl = priv->read_reg(priv, C_CAN_IFACE(MSGCTRL_REG, IF_NAPI));
 
 		if (ctrl & IF_MCONT_MSGLST) {
-			int n = c_can_handle_lost_msg_obj(dev, IF_RX, obj, ctrl);
+			int n;
+
+			n = c_can_handle_lost_msg_obj(dev, IF_NAPI, obj, ctrl);
 
 			pkts += n;
 			quota -= n;
@@ -803,7 +848,7 @@ static int c_can_read_objects(struct net_device *dev, struct c_can_priv *priv,
 			continue;
 
 		/* read the data from the message object */
-		c_can_read_msg_object(dev, IF_RX, ctrl);
+		c_can_read_msg_object(dev, IF_NAPI, ctrl);
 
 		c_can_rx_finalize(dev, priv, obj);
 
@@ -1205,6 +1250,10 @@ struct net_device *alloc_c_can_dev(int msg_obj_num)
 	priv->msg_obj_tx_last =
 		priv->msg_obj_tx_first + priv->msg_obj_tx_num - 1;
 
+	priv->tx.head = 0;
+	priv->tx.tail = 0;
+	priv->tx.obj_num = msg_obj_tx_num;
+
 	netif_napi_add(dev, &priv->napi, c_can_poll, priv->msg_obj_rx_num);
 
 	priv->dev = dev;
diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index 36950363682f..86e95e9d6533 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -385,7 +385,6 @@ static int c_can_plat_probe(struct platform_device *pdev)
 	priv->base = addr;
 	priv->device = &pdev->dev;
 	priv->can.clock.freq = clk_get_rate(clk);
-	priv->priv = clk;
 	priv->type = drvdata->id;
 
 	platform_set_drvdata(pdev, dev);
diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c
index 311d8564d611..e3d840b81357 100644
--- a/drivers/net/can/dev/dev.c
+++ b/drivers/net/can/dev/dev.c
@@ -15,6 +15,7 @@
 #include <linux/can/dev.h>
 #include <linux/can/skb.h>
 #include <linux/can/led.h>
+#include <linux/gpio/consumer.h>
 #include <linux/of.h>
 
 #define MOD_DESC "CAN device driver interface"
@@ -400,10 +401,69 @@ void close_candev(struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(close_candev);
 
+static int can_set_termination(struct net_device *ndev, u16 term)
+{
+	struct can_priv *priv = netdev_priv(ndev);
+	int set;
+
+	if (term == priv->termination_gpio_ohms[CAN_TERMINATION_GPIO_ENABLED])
+		set = 1;
+	else
+		set = 0;
+
+	gpiod_set_value(priv->termination_gpio, set);
+
+	return 0;
+}
+
+static int can_get_termination(struct net_device *ndev)
+{
+	struct can_priv *priv = netdev_priv(ndev);
+	struct device *dev = ndev->dev.parent;
+	struct gpio_desc *gpio;
+	u32 term;
+	int ret;
+
+	/* Disabling termination by default is the safe choice: Else if many
+	 * bus participants enable it, no communication is possible at all.
+	 */
+	gpio = devm_gpiod_get_optional(dev, "termination", GPIOD_OUT_LOW);
+	if (IS_ERR(gpio))
+		return dev_err_probe(dev, PTR_ERR(gpio),
+				     "Cannot get termination-gpios\n");
+
+	if (!gpio)
+		return 0;
+
+	ret = device_property_read_u32(dev, "termination-ohms", &term);
+	if (ret) {
+		netdev_err(ndev, "Cannot get termination-ohms: %pe\n",
+			   ERR_PTR(ret));
+		return ret;
+	}
+
+	if (term > U16_MAX) {
+		netdev_err(ndev, "Invalid termination-ohms value (%u > %u)\n",
+			   term, U16_MAX);
+		return -EINVAL;
+	}
+
+	priv->termination_const_cnt = ARRAY_SIZE(priv->termination_gpio_ohms);
+	priv->termination_const = priv->termination_gpio_ohms;
+	priv->termination_gpio = gpio;
+	priv->termination_gpio_ohms[CAN_TERMINATION_GPIO_DISABLED] =
+		CAN_TERMINATION_DISABLED;
+	priv->termination_gpio_ohms[CAN_TERMINATION_GPIO_ENABLED] = term;
+	priv->do_set_termination = can_set_termination;
+
+	return 0;
+}
+
 /* Register the CAN network device */
 int register_candev(struct net_device *dev)
 {
 	struct can_priv *priv = netdev_priv(dev);
+	int err;
 
 	/* Ensure termination_const, termination_const_cnt and
 	 * do_set_termination consistency. All must be either set or
@@ -419,6 +479,12 @@ int register_candev(struct net_device *dev)
 	if (!priv->data_bitrate_const != !priv->data_bitrate_const_cnt)
 		return -EINVAL;
 
+	if (!priv->termination_const) {
+		err = can_get_termination(dev);
+		if (err)
+			return err;
+	}
+
 	dev->rtnl_link_ops = &can_link_ops;
 	netif_carrier_off(dev);
 
diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index e38c2566aff4..80425636049d 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -47,7 +47,7 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[],
 	}
 
 	if (data[IFLA_CAN_DATA_BITTIMING]) {
-		if (!is_can_fd || !data[IFLA_CAN_BITTIMING])
+		if (!is_can_fd)
 			return -EOPNOTSUPP;
 	}
 
@@ -116,7 +116,7 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 		maskedflags = cm->flags & cm->mask;
 
 		/* check whether provided bits are allowed to be passed */
-		if (cm->mask & ~(priv->ctrlmode_supported | ctrlstatic))
+		if (maskedflags & ~(priv->ctrlmode_supported | ctrlstatic))
 			return -EOPNOTSUPP;
 
 		/* do not check for static fd-non-iso if 'fd' is disabled */
@@ -132,10 +132,13 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 		priv->ctrlmode |= maskedflags;
 
 		/* CAN_CTRLMODE_FD can only be set when driver supports FD */
-		if (priv->ctrlmode & CAN_CTRLMODE_FD)
+		if (priv->ctrlmode & CAN_CTRLMODE_FD) {
 			dev->mtu = CANFD_MTU;
-		else
+		} else {
 			dev->mtu = CAN_MTU;
+			memset(&priv->data_bittiming, 0,
+			       sizeof(priv->data_bittiming));
+		}
 	}
 
 	if (data[IFLA_CAN_RESTART_MS]) {
diff --git a/drivers/net/can/dev/rx-offload.c b/drivers/net/can/dev/rx-offload.c
index ab2c1543786c..37b0cc65237b 100644
--- a/drivers/net/can/dev/rx-offload.c
+++ b/drivers/net/can/dev/rx-offload.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2014      Protonic Holland,
  *                         David Jander
- * Copyright (C) 2014-2017 Pengutronix,
+ * Copyright (C) 2014-2021 Pengutronix,
  *                         Marc Kleine-Budde <kernel@pengutronix.de>
  */
 
@@ -174,10 +174,8 @@ can_rx_offload_offload_one(struct can_rx_offload *offload, unsigned int n)
 int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload,
 					 u64 pending)
 {
-	struct sk_buff_head skb_queue;
 	unsigned int i;
-
-	__skb_queue_head_init(&skb_queue);
+	int received = 0;
 
 	for (i = offload->mb_first;
 	     can_rx_offload_le(offload, i, offload->mb_last);
@@ -191,26 +189,12 @@ int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload,
 		if (IS_ERR_OR_NULL(skb))
 			continue;
 
-		__skb_queue_add_sort(&skb_queue, skb, can_rx_offload_compare);
-	}
-
-	if (!skb_queue_empty(&skb_queue)) {
-		unsigned long flags;
-		u32 queue_len;
-
-		spin_lock_irqsave(&offload->skb_queue.lock, flags);
-		skb_queue_splice_tail(&skb_queue, &offload->skb_queue);
-		spin_unlock_irqrestore(&offload->skb_queue.lock, flags);
-
-		queue_len = skb_queue_len(&offload->skb_queue);
-		if (queue_len > offload->skb_queue_len_max / 8)
-			netdev_dbg(offload->dev, "%s: queue_len=%d\n",
-				   __func__, queue_len);
-
-		can_rx_offload_schedule(offload);
+		__skb_queue_add_sort(&offload->skb_irq_queue, skb,
+				     can_rx_offload_compare);
+		received++;
 	}
 
-	return skb_queue_len(&skb_queue);
+	return received;
 }
 EXPORT_SYMBOL_GPL(can_rx_offload_irq_offload_timestamp);
 
@@ -226,13 +210,10 @@ int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload)
 		if (!skb)
 			break;
 
-		skb_queue_tail(&offload->skb_queue, skb);
+		__skb_queue_tail(&offload->skb_irq_queue, skb);
 		received++;
 	}
 
-	if (received)
-		can_rx_offload_schedule(offload);
-
 	return received;
 }
 EXPORT_SYMBOL_GPL(can_rx_offload_irq_offload_fifo);
@@ -241,7 +222,6 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload,
 				struct sk_buff *skb, u32 timestamp)
 {
 	struct can_rx_offload_cb *cb;
-	unsigned long flags;
 
 	if (skb_queue_len(&offload->skb_queue) >
 	    offload->skb_queue_len_max) {
@@ -252,11 +232,8 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload,
 	cb = can_rx_offload_get_cb(skb);
 	cb->timestamp = timestamp;
 
-	spin_lock_irqsave(&offload->skb_queue.lock, flags);
-	__skb_queue_add_sort(&offload->skb_queue, skb, can_rx_offload_compare);
-	spin_unlock_irqrestore(&offload->skb_queue.lock, flags);
-
-	can_rx_offload_schedule(offload);
+	__skb_queue_add_sort(&offload->skb_irq_queue, skb,
+			     can_rx_offload_compare);
 
 	return 0;
 }
@@ -295,13 +272,56 @@ int can_rx_offload_queue_tail(struct can_rx_offload *offload,
 		return -ENOBUFS;
 	}
 
-	skb_queue_tail(&offload->skb_queue, skb);
-	can_rx_offload_schedule(offload);
+	__skb_queue_tail(&offload->skb_irq_queue, skb);
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(can_rx_offload_queue_tail);
 
+void can_rx_offload_irq_finish(struct can_rx_offload *offload)
+{
+	unsigned long flags;
+	int queue_len;
+
+	if (skb_queue_empty_lockless(&offload->skb_irq_queue))
+		return;
+
+	spin_lock_irqsave(&offload->skb_queue.lock, flags);
+	skb_queue_splice_tail_init(&offload->skb_irq_queue, &offload->skb_queue);
+	spin_unlock_irqrestore(&offload->skb_queue.lock, flags);
+
+	queue_len = skb_queue_len(&offload->skb_queue);
+	if (queue_len > offload->skb_queue_len_max / 8)
+		netdev_dbg(offload->dev, "%s: queue_len=%d\n",
+			   __func__, queue_len);
+
+	napi_schedule(&offload->napi);
+}
+EXPORT_SYMBOL_GPL(can_rx_offload_irq_finish);
+
+void can_rx_offload_threaded_irq_finish(struct can_rx_offload *offload)
+{
+	unsigned long flags;
+	int queue_len;
+
+	if (skb_queue_empty_lockless(&offload->skb_irq_queue))
+		return;
+
+	spin_lock_irqsave(&offload->skb_queue.lock, flags);
+	skb_queue_splice_tail_init(&offload->skb_irq_queue, &offload->skb_queue);
+	spin_unlock_irqrestore(&offload->skb_queue.lock, flags);
+
+	queue_len = skb_queue_len(&offload->skb_queue);
+	if (queue_len > offload->skb_queue_len_max / 8)
+		netdev_dbg(offload->dev, "%s: queue_len=%d\n",
+			   __func__, queue_len);
+
+	local_bh_disable();
+	napi_schedule(&offload->napi);
+	local_bh_enable();
+}
+EXPORT_SYMBOL_GPL(can_rx_offload_threaded_irq_finish);
+
 static int can_rx_offload_init_queue(struct net_device *dev,
 				     struct can_rx_offload *offload,
 				     unsigned int weight)
@@ -312,6 +332,7 @@ static int can_rx_offload_init_queue(struct net_device *dev,
 	offload->skb_queue_len_max = 2 << fls(weight);
 	offload->skb_queue_len_max *= 4;
 	skb_queue_head_init(&offload->skb_queue);
+	__skb_queue_head_init(&offload->skb_irq_queue);
 
 	netif_napi_add(dev, &offload->napi, can_rx_offload_napi_poll, weight);
 
@@ -373,5 +394,6 @@ void can_rx_offload_del(struct can_rx_offload *offload)
 {
 	netif_napi_del(&offload->napi);
 	skb_queue_purge(&offload->skb_queue);
+	__skb_queue_purge(&offload->skb_irq_queue);
 }
 EXPORT_SYMBOL_GPL(can_rx_offload_del);
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 57f3635ad8d7..7734229aa078 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -28,6 +28,7 @@
 #include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
+#include <linux/can/platform/flexcan.h>
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
@@ -208,18 +209,19 @@
 /* FLEXCAN hardware feature flags
  *
  * Below is some version info we got:
- *    SOC   Version   IP-Version  Glitch- [TR]WRN_INT IRQ Err Memory err RTR rece-   FD Mode
+ *    SOC   Version   IP-Version  Glitch- [TR]WRN_INT IRQ Err Memory err RTR rece-   FD Mode     MB
  *                                Filter? connected?  Passive detection  ption in MB Supported?
- *   MX25  FlexCAN2  03.00.00.00     no        no        no       no        no           no
- *   MX28  FlexCAN2  03.00.04.00    yes       yes        no       no        no           no
- *   MX35  FlexCAN2  03.00.00.00     no        no        no       no        no           no
- *   MX53  FlexCAN2  03.00.00.00    yes        no        no       no        no           no
- *   MX6s  FlexCAN3  10.00.12.00    yes       yes        no       no       yes           no
- *   MX8QM FlexCAN3  03.00.23.00    yes       yes        no       no       yes          yes
- *   MX8MP FlexCAN3  03.00.17.01    yes       yes        no      yes       yes          yes
- *   VF610 FlexCAN3  ?               no       yes        no      yes       yes?          no
- * LS1021A FlexCAN2  03.00.04.00     no       yes        no       no       yes           no
- * LX2160A FlexCAN3  03.00.23.00     no       yes        no      yes       yes          yes
+ * MCF5441X FlexCAN2  ?               no       yes        no       no       yes           no     16
+ *    MX25  FlexCAN2  03.00.00.00     no        no        no       no        no           no     64
+ *    MX28  FlexCAN2  03.00.04.00    yes       yes        no       no        no           no     64
+ *    MX35  FlexCAN2  03.00.00.00     no        no        no       no        no           no     64
+ *    MX53  FlexCAN2  03.00.00.00    yes        no        no       no        no           no     64
+ *    MX6s  FlexCAN3  10.00.12.00    yes       yes        no       no       yes           no     64
+ *    MX8QM FlexCAN3  03.00.23.00    yes       yes        no       no       yes          yes     64
+ *    MX8MP FlexCAN3  03.00.17.01    yes       yes        no      yes       yes          yes     64
+ *    VF610 FlexCAN3  ?               no       yes        no      yes       yes?          no     64
+ *  LS1021A FlexCAN2  03.00.04.00     no       yes        no       no       yes           no     64
+ *  LX2160A FlexCAN3  03.00.23.00     no       yes        no      yes       yes          yes     64
  *
  * Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected.
  */
@@ -246,6 +248,10 @@
 #define FLEXCAN_QUIRK_SUPPORT_ECC BIT(10)
 /* Setup stop mode with SCU firmware to support wakeup */
 #define FLEXCAN_QUIRK_SETUP_STOP_MODE_SCFW BIT(11)
+/* Setup 3 separate interrupts, main, boff and err */
+#define FLEXCAN_QUIRK_NR_IRQ_3 BIT(12)
+/* Setup 16 mailboxes */
+#define FLEXCAN_QUIRK_NR_MB_16 BIT(13)
 
 /* Structure of the message buffer */
 struct flexcan_mb {
@@ -363,6 +369,9 @@ struct flexcan_priv {
 	struct regulator *reg_xceiver;
 	struct flexcan_stop_mode stm;
 
+	int irq_boff;
+	int irq_err;
+
 	/* IPC handle when setup stop mode by System Controller firmware(scfw) */
 	struct imx_sc_ipc *sc_ipc_handle;
 
@@ -371,6 +380,11 @@ struct flexcan_priv {
 	void (*write)(u32 val, void __iomem *addr);
 };
 
+static const struct flexcan_devtype_data fsl_mcf5441x_devtype_data = {
+	.quirks = FLEXCAN_QUIRK_BROKEN_PERR_STATE |
+		FLEXCAN_QUIRK_NR_IRQ_3 | FLEXCAN_QUIRK_NR_MB_16,
+};
+
 static const struct flexcan_devtype_data fsl_p1010_devtype_data = {
 	.quirks = FLEXCAN_QUIRK_BROKEN_WERR_STATE |
 		FLEXCAN_QUIRK_BROKEN_PERR_STATE |
@@ -635,15 +649,19 @@ static inline void flexcan_error_irq_disable(const struct flexcan_priv *priv)
 
 static int flexcan_clks_enable(const struct flexcan_priv *priv)
 {
-	int err;
+	int err = 0;
 
-	err = clk_prepare_enable(priv->clk_ipg);
-	if (err)
-		return err;
+	if (priv->clk_ipg) {
+		err = clk_prepare_enable(priv->clk_ipg);
+		if (err)
+			return err;
+	}
 
-	err = clk_prepare_enable(priv->clk_per);
-	if (err)
-		clk_disable_unprepare(priv->clk_ipg);
+	if (priv->clk_per) {
+		err = clk_prepare_enable(priv->clk_per);
+		if (err)
+			clk_disable_unprepare(priv->clk_ipg);
+	}
 
 	return err;
 }
@@ -1198,6 +1216,9 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id)
 		}
 	}
 
+	if (handled)
+		can_rx_offload_irq_finish(&priv->offload);
+
 	return handled;
 }
 
@@ -1401,8 +1422,12 @@ static int flexcan_rx_offload_setup(struct net_device *dev)
 		priv->mb_size = sizeof(struct flexcan_mb) + CANFD_MAX_DLEN;
 	else
 		priv->mb_size = sizeof(struct flexcan_mb) + CAN_MAX_DLEN;
-	priv->mb_count = (sizeof(priv->regs->mb[0]) / priv->mb_size) +
-			 (sizeof(priv->regs->mb[1]) / priv->mb_size);
+
+	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_NR_MB_16)
+		priv->mb_count = 16;
+	else
+		priv->mb_count = (sizeof(priv->regs->mb[0]) / priv->mb_size) +
+				 (sizeof(priv->regs->mb[1]) / priv->mb_size);
 
 	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP)
 		priv->tx_mb_reserved =
@@ -1774,6 +1799,18 @@ static int flexcan_open(struct net_device *dev)
 	if (err)
 		goto out_can_rx_offload_disable;
 
+	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_NR_IRQ_3) {
+		err = request_irq(priv->irq_boff,
+				  flexcan_irq, IRQF_SHARED, dev->name, dev);
+		if (err)
+			goto out_free_irq;
+
+		err = request_irq(priv->irq_err,
+				  flexcan_irq, IRQF_SHARED, dev->name, dev);
+		if (err)
+			goto out_free_irq_boff;
+	}
+
 	flexcan_chip_interrupts_enable(dev);
 
 	can_led_event(dev, CAN_LED_EVENT_OPEN);
@@ -1782,6 +1819,10 @@ static int flexcan_open(struct net_device *dev)
 
 	return 0;
 
+ out_free_irq_boff:
+	free_irq(priv->irq_boff, dev);
+ out_free_irq:
+	free_irq(dev->irq, dev);
  out_can_rx_offload_disable:
 	can_rx_offload_disable(&priv->offload);
 	flexcan_chip_stop(dev);
@@ -1803,6 +1844,12 @@ static int flexcan_close(struct net_device *dev)
 
 	netif_stop_queue(dev);
 	flexcan_chip_interrupts_disable(dev);
+
+	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_NR_IRQ_3) {
+		free_irq(priv->irq_err, dev);
+		free_irq(priv->irq_boff, dev);
+	}
+
 	free_irq(dev->irq, dev);
 	can_rx_offload_disable(&priv->offload);
 	flexcan_chip_stop_disable_on_error(dev);
@@ -2039,14 +2086,26 @@ static const struct of_device_id flexcan_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, flexcan_of_match);
 
+static const struct platform_device_id flexcan_id_table[] = {
+	{
+		.name = "flexcan-mcf5441x",
+		.driver_data = (kernel_ulong_t)&fsl_mcf5441x_devtype_data,
+	}, {
+		/* sentinel */
+	},
+};
+MODULE_DEVICE_TABLE(platform, flexcan_id_table);
+
 static int flexcan_probe(struct platform_device *pdev)
 {
+	const struct of_device_id *of_id;
 	const struct flexcan_devtype_data *devtype_data;
 	struct net_device *dev;
 	struct flexcan_priv *priv;
 	struct regulator *reg_xceiver;
 	struct clk *clk_ipg = NULL, *clk_per = NULL;
 	struct flexcan_regs __iomem *regs;
+	struct flexcan_platform_data *pdata;
 	int err, irq;
 	u8 clk_src = 1;
 	u32 clock_freq = 0;
@@ -2064,6 +2123,12 @@ static int flexcan_probe(struct platform_device *pdev)
 				     "clock-frequency", &clock_freq);
 		of_property_read_u8(pdev->dev.of_node,
 				    "fsl,clk-source", &clk_src);
+	} else {
+		pdata = dev_get_platdata(&pdev->dev);
+		if (pdata) {
+			clock_freq = pdata->clock_frequency;
+			clk_src = pdata->clk_src;
+		}
 	}
 
 	if (!clock_freq) {
@@ -2089,7 +2154,14 @@ static int flexcan_probe(struct platform_device *pdev)
 	if (IS_ERR(regs))
 		return PTR_ERR(regs);
 
-	devtype_data = of_device_get_match_data(&pdev->dev);
+	of_id = of_match_device(flexcan_of_match, &pdev->dev);
+	if (of_id)
+		devtype_data = of_id->data;
+	else if (platform_get_device_id(pdev)->driver_data)
+		devtype_data = (struct flexcan_devtype_data *)
+			platform_get_device_id(pdev)->driver_data;
+	else
+		return -ENODEV;
 
 	if ((devtype_data->quirks & FLEXCAN_QUIRK_SUPPORT_FD) &&
 	    !(devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP)) {
@@ -2133,6 +2205,19 @@ static int flexcan_probe(struct platform_device *pdev)
 	priv->devtype_data = devtype_data;
 	priv->reg_xceiver = reg_xceiver;
 
+	if (devtype_data->quirks & FLEXCAN_QUIRK_NR_IRQ_3) {
+		priv->irq_boff = platform_get_irq(pdev, 1);
+		if (priv->irq_boff <= 0) {
+			err = -ENODEV;
+			goto failed_platform_get_irq;
+		}
+		priv->irq_err = platform_get_irq(pdev, 2);
+		if (priv->irq_err <= 0) {
+			err = -ENODEV;
+			goto failed_platform_get_irq;
+		}
+	}
+
 	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_SUPPORT_FD) {
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD |
 			CAN_CTRLMODE_FD_NON_ISO;
@@ -2170,6 +2255,7 @@ static int flexcan_probe(struct platform_device *pdev)
  failed_register:
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+ failed_platform_get_irq:
 	free_candev(dev);
 	return err;
 }
@@ -2322,6 +2408,7 @@ static struct platform_driver flexcan_driver = {
 	},
 	.probe = flexcan_probe,
 	.remove = flexcan_remove,
+	.id_table = flexcan_id_table,
 };
 
 module_platform_driver(flexcan_driver);
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index 2a6c918186c0..c68ad56628bd 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -1815,9 +1815,9 @@ static int ican3_get_berr_counter(const struct net_device *ndev,
  * Sysfs Attributes
  */
 
-static ssize_t ican3_sysfs_show_term(struct device *dev,
-				     struct device_attribute *attr,
-				     char *buf)
+static ssize_t termination_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
 {
 	struct ican3_dev *mod = netdev_priv(to_net_dev(dev));
 	int ret;
@@ -1834,9 +1834,9 @@ static ssize_t ican3_sysfs_show_term(struct device *dev,
 	return snprintf(buf, PAGE_SIZE, "%u\n", mod->termination_enabled);
 }
 
-static ssize_t ican3_sysfs_set_term(struct device *dev,
-				    struct device_attribute *attr,
-				    const char *buf, size_t count)
+static ssize_t termination_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct ican3_dev *mod = netdev_priv(to_net_dev(dev));
 	unsigned long enable;
@@ -1852,18 +1852,17 @@ static ssize_t ican3_sysfs_set_term(struct device *dev,
 	return count;
 }
 
-static ssize_t ican3_sysfs_show_fwinfo(struct device *dev,
-				       struct device_attribute *attr,
-				       char *buf)
+static ssize_t fwinfo_show(struct device *dev,
+			   struct device_attribute *attr,
+			   char *buf)
 {
 	struct ican3_dev *mod = netdev_priv(to_net_dev(dev));
 
 	return scnprintf(buf, PAGE_SIZE, "%s\n", mod->fwinfo);
 }
 
-static DEVICE_ATTR(termination, 0644, ican3_sysfs_show_term,
-		   ican3_sysfs_set_term);
-static DEVICE_ATTR(fwinfo, 0444, ican3_sysfs_show_fwinfo, NULL);
+static DEVICE_ATTR_RW(termination);
+static DEVICE_ATTR_RO(fwinfo);
 
 static struct attribute *ican3_sysfs_attrs[] = {
 	&dev_attr_termination.attr,
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 43bca315a66c..2470c47b2e31 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -21,6 +21,7 @@
 #include <linux/iopoll.h>
 #include <linux/can/dev.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/phy/phy.h>
 
 #include "m_can.h"
 
@@ -278,7 +279,7 @@ enum m_can_reg {
 /* Message RAM Elements */
 #define M_CAN_FIFO_ID		0x0
 #define M_CAN_FIFO_DLC		0x4
-#define M_CAN_FIFO_DATA(n)	(0x8 + ((n) << 2))
+#define M_CAN_FIFO_DATA		0x8
 
 /* Rx Buffer Element */
 /* R0 */
@@ -308,6 +309,15 @@ enum m_can_reg {
 #define TX_EVENT_MM_MASK	GENMASK(31, 24)
 #define TX_EVENT_TXTS_MASK	GENMASK(15, 0)
 
+/* The ID and DLC registers are adjacent in M_CAN FIFO memory,
+ * and we can save a (potentially slow) bus round trip by combining
+ * reads and writes to them.
+ */
+struct id_and_dlc {
+	u32 id;
+	u32 dlc;
+};
+
 static inline u32 m_can_read(struct m_can_classdev *cdev, enum m_can_reg reg)
 {
 	return cdev->ops->read_reg(cdev, reg);
@@ -319,36 +329,39 @@ static inline void m_can_write(struct m_can_classdev *cdev, enum m_can_reg reg,
 	cdev->ops->write_reg(cdev, reg, val);
 }
 
-static u32 m_can_fifo_read(struct m_can_classdev *cdev,
-			   u32 fgi, unsigned int offset)
+static int
+m_can_fifo_read(struct m_can_classdev *cdev,
+		u32 fgi, unsigned int offset, void *val, size_t val_count)
 {
 	u32 addr_offset = cdev->mcfg[MRAM_RXF0].off + fgi * RXF0_ELEMENT_SIZE +
 		offset;
 
-	return cdev->ops->read_fifo(cdev, addr_offset);
+	return cdev->ops->read_fifo(cdev, addr_offset, val, val_count);
 }
 
-static void m_can_fifo_write(struct m_can_classdev *cdev,
-			     u32 fpi, unsigned int offset, u32 val)
+static int
+m_can_fifo_write(struct m_can_classdev *cdev,
+		 u32 fpi, unsigned int offset, const void *val, size_t val_count)
 {
 	u32 addr_offset = cdev->mcfg[MRAM_TXB].off + fpi * TXB_ELEMENT_SIZE +
 		offset;
 
-	cdev->ops->write_fifo(cdev, addr_offset, val);
+	return cdev->ops->write_fifo(cdev, addr_offset, val, val_count);
 }
 
-static inline void m_can_fifo_write_no_off(struct m_can_classdev *cdev,
-					   u32 fpi, u32 val)
+static inline int m_can_fifo_write_no_off(struct m_can_classdev *cdev,
+					  u32 fpi, u32 val)
 {
-	cdev->ops->write_fifo(cdev, fpi, val);
+	return cdev->ops->write_fifo(cdev, fpi, &val, 1);
 }
 
-static u32 m_can_txe_fifo_read(struct m_can_classdev *cdev, u32 fgi, u32 offset)
+static int
+m_can_txe_fifo_read(struct m_can_classdev *cdev, u32 fgi, u32 offset, u32 *val)
 {
 	u32 addr_offset = cdev->mcfg[MRAM_TXE].off + fgi * TXE_ELEMENT_SIZE +
 		offset;
 
-	return cdev->ops->read_fifo(cdev, addr_offset);
+	return cdev->ops->read_fifo(cdev, addr_offset, val, 1);
 }
 
 static inline bool m_can_tx_fifo_full(struct m_can_classdev *cdev)
@@ -436,7 +449,7 @@ static void m_can_clean(struct net_device *net)
  * napi. For non-peripherals, RX is done in napi already, so push
  * directly. timestamp is used to ensure good skb ordering in
  * rx-offload and is ignored for non-peripherals.
-*/
+ */
 static void m_can_receive_skb(struct m_can_classdev *cdev,
 			      struct sk_buff *skb,
 			      u32 timestamp)
@@ -454,54 +467,57 @@ static void m_can_receive_skb(struct m_can_classdev *cdev,
 	}
 }
 
-static void m_can_read_fifo(struct net_device *dev, u32 rxfs)
+static int m_can_read_fifo(struct net_device *dev, u32 rxfs)
 {
 	struct net_device_stats *stats = &dev->stats;
 	struct m_can_classdev *cdev = netdev_priv(dev);
 	struct canfd_frame *cf;
 	struct sk_buff *skb;
-	u32 id, fgi, dlc;
+	struct id_and_dlc fifo_header;
+	u32 fgi;
 	u32 timestamp = 0;
-	int i;
+	int err;
 
 	/* calculate the fifo get index for where to read data */
 	fgi = FIELD_GET(RXFS_FGI_MASK, rxfs);
-	dlc = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_DLC);
-	if (dlc & RX_BUF_FDF)
+	err = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_ID, &fifo_header, 2);
+	if (err)
+		goto out_fail;
+
+	if (fifo_header.dlc & RX_BUF_FDF)
 		skb = alloc_canfd_skb(dev, &cf);
 	else
 		skb = alloc_can_skb(dev, (struct can_frame **)&cf);
 	if (!skb) {
 		stats->rx_dropped++;
-		return;
+		return 0;
 	}
 
-	if (dlc & RX_BUF_FDF)
-		cf->len = can_fd_dlc2len((dlc >> 16) & 0x0F);
+	if (fifo_header.dlc & RX_BUF_FDF)
+		cf->len = can_fd_dlc2len((fifo_header.dlc >> 16) & 0x0F);
 	else
-		cf->len = can_cc_dlc2len((dlc >> 16) & 0x0F);
+		cf->len = can_cc_dlc2len((fifo_header.dlc >> 16) & 0x0F);
 
-	id = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_ID);
-	if (id & RX_BUF_XTD)
-		cf->can_id = (id & CAN_EFF_MASK) | CAN_EFF_FLAG;
+	if (fifo_header.id & RX_BUF_XTD)
+		cf->can_id = (fifo_header.id & CAN_EFF_MASK) | CAN_EFF_FLAG;
 	else
-		cf->can_id = (id >> 18) & CAN_SFF_MASK;
+		cf->can_id = (fifo_header.id >> 18) & CAN_SFF_MASK;
 
-	if (id & RX_BUF_ESI) {
+	if (fifo_header.id & RX_BUF_ESI) {
 		cf->flags |= CANFD_ESI;
 		netdev_dbg(dev, "ESI Error\n");
 	}
 
-	if (!(dlc & RX_BUF_FDF) && (id & RX_BUF_RTR)) {
+	if (!(fifo_header.dlc & RX_BUF_FDF) && (fifo_header.id & RX_BUF_RTR)) {
 		cf->can_id |= CAN_RTR_FLAG;
 	} else {
-		if (dlc & RX_BUF_BRS)
+		if (fifo_header.dlc & RX_BUF_BRS)
 			cf->flags |= CANFD_BRS;
 
-		for (i = 0; i < cf->len; i += 4)
-			*(u32 *)(cf->data + i) =
-				m_can_fifo_read(cdev, fgi,
-						M_CAN_FIFO_DATA(i / 4));
+		err = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_DATA,
+				      cf->data, DIV_ROUND_UP(cf->len, 4));
+		if (err)
+			goto out_fail;
 	}
 
 	/* acknowledge rx fifo 0 */
@@ -510,9 +526,15 @@ static void m_can_read_fifo(struct net_device *dev, u32 rxfs)
 	stats->rx_packets++;
 	stats->rx_bytes += cf->len;
 
-	timestamp = FIELD_GET(RX_BUF_RXTS_MASK, dlc);
+	timestamp = FIELD_GET(RX_BUF_RXTS_MASK, fifo_header.dlc);
 
 	m_can_receive_skb(cdev, skb, timestamp);
+
+	return 0;
+
+out_fail:
+	netdev_err(dev, "FIFO read returned %d\n", err);
+	return err;
 }
 
 static int m_can_do_rx_poll(struct net_device *dev, int quota)
@@ -520,6 +542,7 @@ static int m_can_do_rx_poll(struct net_device *dev, int quota)
 	struct m_can_classdev *cdev = netdev_priv(dev);
 	u32 pkts = 0;
 	u32 rxfs;
+	int err;
 
 	rxfs = m_can_read(cdev, M_CAN_RXF0S);
 	if (!(rxfs & RXFS_FFL_MASK)) {
@@ -528,7 +551,9 @@ static int m_can_do_rx_poll(struct net_device *dev, int quota)
 	}
 
 	while ((rxfs & RXFS_FFL_MASK) && (quota > 0)) {
-		m_can_read_fifo(dev, rxfs);
+		err = m_can_read_fifo(dev, rxfs);
+		if (err)
+			return err;
 
 		quota--;
 		pkts++;
@@ -874,6 +899,7 @@ static int m_can_handle_bus_errors(struct net_device *dev, u32 irqstatus,
 static int m_can_rx_handler(struct net_device *dev, int quota)
 {
 	struct m_can_classdev *cdev = netdev_priv(dev);
+	int rx_work_or_err;
 	int work_done = 0;
 	u32 irqstatus, psr;
 
@@ -910,8 +936,13 @@ static int m_can_rx_handler(struct net_device *dev, int quota)
 	if (irqstatus & IR_ERR_BUS_30X)
 		work_done += m_can_handle_bus_errors(dev, irqstatus, psr);
 
-	if (irqstatus & IR_RF0N)
-		work_done += m_can_do_rx_poll(dev, (quota - work_done));
+	if (irqstatus & IR_RF0N) {
+		rx_work_or_err = m_can_do_rx_poll(dev, (quota - work_done));
+		if (rx_work_or_err < 0)
+			return rx_work_or_err;
+
+		work_done += rx_work_or_err;
+	}
 end:
 	return work_done;
 }
@@ -919,12 +950,17 @@ end:
 static int m_can_rx_peripheral(struct net_device *dev)
 {
 	struct m_can_classdev *cdev = netdev_priv(dev);
+	int work_done;
 
-	m_can_rx_handler(dev, M_CAN_NAPI_WEIGHT);
+	work_done = m_can_rx_handler(dev, M_CAN_NAPI_WEIGHT);
 
-	m_can_enable_all_interrupts(cdev);
+	/* Don't re-enable interrupts if the driver had a fatal error
+	 * (e.g., FIFO read failure).
+	 */
+	if (work_done >= 0)
+		m_can_enable_all_interrupts(cdev);
 
-	return 0;
+	return work_done;
 }
 
 static int m_can_poll(struct napi_struct *napi, int quota)
@@ -934,7 +970,11 @@ static int m_can_poll(struct napi_struct *napi, int quota)
 	int work_done;
 
 	work_done = m_can_rx_handler(dev, quota);
-	if (work_done < quota) {
+
+	/* Don't re-enable interrupts if the driver had a fatal error
+	 * (e.g., FIFO read failure).
+	 */
+	if (work_done >= 0 && work_done < quota) {
 		napi_complete_done(napi, work_done);
 		m_can_enable_all_interrupts(cdev);
 	}
@@ -945,7 +985,7 @@ static int m_can_poll(struct napi_struct *napi, int quota)
 /* Echo tx skb and update net stats. Peripherals use rx-offload for
  * echo. timestamp is used for peripherals to ensure correct ordering
  * by rx-offload, and is ignored for non-peripherals.
-*/
+ */
 static void m_can_tx_update_stats(struct m_can_classdev *cdev,
 				  unsigned int msg_mark,
 				  u32 timestamp)
@@ -965,7 +1005,7 @@ static void m_can_tx_update_stats(struct m_can_classdev *cdev,
 	stats->tx_packets++;
 }
 
-static void m_can_echo_tx_event(struct net_device *dev)
+static int m_can_echo_tx_event(struct net_device *dev)
 {
 	u32 txe_count = 0;
 	u32 m_can_txefs;
@@ -984,12 +1024,18 @@ static void m_can_echo_tx_event(struct net_device *dev)
 	/* Get and process all sent elements */
 	for (i = 0; i < txe_count; i++) {
 		u32 txe, timestamp = 0;
+		int err;
 
 		/* retrieve get index */
 		fgi = FIELD_GET(TXEFS_EFGI_MASK, m_can_read(cdev, M_CAN_TXEFS));
 
 		/* get message marker, timestamp */
-		txe = m_can_txe_fifo_read(cdev, fgi, 4);
+		err = m_can_txe_fifo_read(cdev, fgi, 4, &txe);
+		if (err) {
+			netdev_err(dev, "TXE FIFO read returned %d\n", err);
+			return err;
+		}
+
 		msg_mark = FIELD_GET(TX_EVENT_MM_MASK, txe);
 		timestamp = FIELD_GET(TX_EVENT_TXTS_MASK, txe);
 
@@ -1000,6 +1046,8 @@ static void m_can_echo_tx_event(struct net_device *dev)
 		/* update stats */
 		m_can_tx_update_stats(cdev, msg_mark, timestamp);
 	}
+
+	return 0;
 }
 
 static irqreturn_t m_can_isr(int irq, void *dev_id)
@@ -1031,8 +1079,8 @@ static irqreturn_t m_can_isr(int irq, void *dev_id)
 		m_can_disable_all_interrupts(cdev);
 		if (!cdev->is_peripheral)
 			napi_schedule(&cdev->napi);
-		else
-			m_can_rx_peripheral(dev);
+		else if (m_can_rx_peripheral(dev) < 0)
+			goto out_fail;
 	}
 
 	if (cdev->version == 30) {
@@ -1050,7 +1098,9 @@ static irqreturn_t m_can_isr(int irq, void *dev_id)
 	} else  {
 		if (ir & IR_TEFN) {
 			/* New TX FIFO Element arrived */
-			m_can_echo_tx_event(dev);
+			if (m_can_echo_tx_event(dev) != 0)
+				goto out_fail;
+
 			can_led_event(dev, CAN_LED_EVENT_TX);
 			if (netif_queue_stopped(dev) &&
 			    !m_can_tx_fifo_full(cdev))
@@ -1058,6 +1108,13 @@ static irqreturn_t m_can_isr(int irq, void *dev_id)
 		}
 	}
 
+	if (cdev->is_peripheral)
+		can_rx_offload_threaded_irq_finish(&cdev->offload);
+
+	return IRQ_HANDLED;
+
+out_fail:
+	m_can_disable_all_interrupts(cdev);
 	return IRQ_HANDLED;
 }
 
@@ -1302,7 +1359,8 @@ static void m_can_chip_config(struct net_device *dev)
 	m_can_set_bittiming(dev);
 
 	/* enable internal timestamp generation, with a prescalar of 16. The
-	 * prescalar is applied to the nominal bit timing */
+	 * prescalar is applied to the nominal bit timing
+	 */
 	m_can_write(cdev, M_CAN_TSCC, FIELD_PREP(TSCC_TCP_MASK, 0xf));
 
 	m_can_config_endisable(cdev, false);
@@ -1436,32 +1494,20 @@ static int m_can_dev_setup(struct m_can_classdev *cdev)
 	case 30:
 		/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.x */
 		can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO);
-		cdev->can.bittiming_const = cdev->bit_timing ?
-			cdev->bit_timing : &m_can_bittiming_const_30X;
-
-		cdev->can.data_bittiming_const = cdev->data_timing ?
-			cdev->data_timing :
-			&m_can_data_bittiming_const_30X;
+		cdev->can.bittiming_const = &m_can_bittiming_const_30X;
+		cdev->can.data_bittiming_const = &m_can_data_bittiming_const_30X;
 		break;
 	case 31:
 		/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */
 		can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO);
-		cdev->can.bittiming_const = cdev->bit_timing ?
-			cdev->bit_timing : &m_can_bittiming_const_31X;
-
-		cdev->can.data_bittiming_const = cdev->data_timing ?
-			cdev->data_timing :
-			&m_can_data_bittiming_const_31X;
+		cdev->can.bittiming_const = &m_can_bittiming_const_31X;
+		cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X;
 		break;
 	case 32:
 	case 33:
 		/* Support both MCAN version v3.2.x and v3.3.0 */
-		cdev->can.bittiming_const = cdev->bit_timing ?
-			cdev->bit_timing : &m_can_bittiming_const_31X;
-
-		cdev->can.data_bittiming_const = cdev->data_timing ?
-			cdev->data_timing :
-			&m_can_data_bittiming_const_31X;
+		cdev->can.bittiming_const = &m_can_bittiming_const_31X;
+		cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X;
 
 		cdev->can.ctrlmode_supported |=
 			(m_can_niso_supported(cdev) ?
@@ -1518,6 +1564,8 @@ static int m_can_close(struct net_device *dev)
 	close_candev(dev);
 	can_led_event(dev, CAN_LED_EVENT_STOP);
 
+	phy_power_off(cdev->transceiver);
+
 	return 0;
 }
 
@@ -1540,8 +1588,9 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev)
 	struct canfd_frame *cf = (struct canfd_frame *)cdev->tx_skb->data;
 	struct net_device *dev = cdev->net;
 	struct sk_buff *skb = cdev->tx_skb;
-	u32 id, cccr, fdflags;
-	int i;
+	struct id_and_dlc fifo_header;
+	u32 cccr, fdflags;
+	int err;
 	int putidx;
 
 	cdev->tx_skb = NULL;
@@ -1549,27 +1598,29 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev)
 	/* Generate ID field for TX buffer Element */
 	/* Common to all supported M_CAN versions */
 	if (cf->can_id & CAN_EFF_FLAG) {
-		id = cf->can_id & CAN_EFF_MASK;
-		id |= TX_BUF_XTD;
+		fifo_header.id = cf->can_id & CAN_EFF_MASK;
+		fifo_header.id |= TX_BUF_XTD;
 	} else {
-		id = ((cf->can_id & CAN_SFF_MASK) << 18);
+		fifo_header.id = ((cf->can_id & CAN_SFF_MASK) << 18);
 	}
 
 	if (cf->can_id & CAN_RTR_FLAG)
-		id |= TX_BUF_RTR;
+		fifo_header.id |= TX_BUF_RTR;
 
 	if (cdev->version == 30) {
 		netif_stop_queue(dev);
 
-		/* message ram configuration */
-		m_can_fifo_write(cdev, 0, M_CAN_FIFO_ID, id);
-		m_can_fifo_write(cdev, 0, M_CAN_FIFO_DLC,
-				 can_fd_len2dlc(cf->len) << 16);
+		fifo_header.dlc = can_fd_len2dlc(cf->len) << 16;
+
+		/* Write the frame ID, DLC, and payload to the FIFO element. */
+		err = m_can_fifo_write(cdev, 0, M_CAN_FIFO_ID, &fifo_header, 2);
+		if (err)
+			goto out_fail;
 
-		for (i = 0; i < cf->len; i += 4)
-			m_can_fifo_write(cdev, 0,
-					 M_CAN_FIFO_DATA(i / 4),
-					 *(u32 *)(cf->data + i));
+		err = m_can_fifo_write(cdev, 0, M_CAN_FIFO_DATA,
+				       cf->data, DIV_ROUND_UP(cf->len, 4));
+		if (err)
+			goto out_fail;
 
 		can_put_echo_skb(skb, dev, 0, 0);
 
@@ -1613,8 +1664,11 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev)
 		/* get put index for frame */
 		putidx = FIELD_GET(TXFQS_TFQPI_MASK,
 				   m_can_read(cdev, M_CAN_TXFQS));
-		/* Write ID Field to FIFO Element */
-		m_can_fifo_write(cdev, putidx, M_CAN_FIFO_ID, id);
+
+		/* Construct DLC Field, with CAN-FD configuration.
+		 * Use the put index of the fifo as the message marker,
+		 * used in the TX interrupt for sending the correct echo frame.
+		 */
 
 		/* get CAN FD configuration of frame */
 		fdflags = 0;
@@ -1624,20 +1678,17 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev)
 				fdflags |= TX_BUF_BRS;
 		}
 
-		/* Construct DLC Field. Also contains CAN-FD configuration
-		 * use put index of fifo as message marker
-		 * it is used in TX interrupt for
-		 * sending the correct echo frame
-		 */
-		m_can_fifo_write(cdev, putidx, M_CAN_FIFO_DLC,
-				 FIELD_PREP(TX_BUF_MM_MASK, putidx) |
-				 FIELD_PREP(TX_BUF_DLC_MASK,
-					    can_fd_len2dlc(cf->len)) |
-				 fdflags | TX_BUF_EFC);
+		fifo_header.dlc = FIELD_PREP(TX_BUF_MM_MASK, putidx) |
+			FIELD_PREP(TX_BUF_DLC_MASK, can_fd_len2dlc(cf->len)) |
+			fdflags | TX_BUF_EFC;
+		err = m_can_fifo_write(cdev, putidx, M_CAN_FIFO_ID, &fifo_header, 2);
+		if (err)
+			goto out_fail;
 
-		for (i = 0; i < cf->len; i += 4)
-			m_can_fifo_write(cdev, putidx, M_CAN_FIFO_DATA(i / 4),
-					 *(u32 *)(cf->data + i));
+		err = m_can_fifo_write(cdev, putidx, M_CAN_FIFO_DATA,
+				       cf->data, DIV_ROUND_UP(cf->len, 4));
+		if (err)
+			goto out_fail;
 
 		/* Push loopback echo.
 		 * Will be looped back on TX interrupt based on message marker
@@ -1654,6 +1705,11 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev)
 	}
 
 	return NETDEV_TX_OK;
+
+out_fail:
+	netdev_err(dev, "FIFO write returned %d\n", err);
+	m_can_disable_all_interrupts(cdev);
+	return NETDEV_TX_BUSY;
 }
 
 static void m_can_tx_work_queue(struct work_struct *ws)
@@ -1703,10 +1759,14 @@ static int m_can_open(struct net_device *dev)
 	struct m_can_classdev *cdev = netdev_priv(dev);
 	int err;
 
-	err = m_can_clk_start(cdev);
+	err = phy_power_on(cdev->transceiver);
 	if (err)
 		return err;
 
+	err = m_can_clk_start(cdev);
+	if (err)
+		goto out_phy_power_off;
+
 	/* open the can device */
 	err = open_candev(dev);
 	if (err) {
@@ -1763,6 +1823,8 @@ out_wq_fail:
 	close_candev(dev);
 exit_disable_clks:
 	m_can_clk_stop(cdev);
+out_phy_power_off:
+	phy_power_off(cdev->transceiver);
 	return err;
 }
 
@@ -1819,9 +1881,10 @@ static void m_can_of_parse_mram(struct m_can_classdev *cdev,
 		cdev->mcfg[MRAM_TXB].off, cdev->mcfg[MRAM_TXB].num);
 }
 
-void m_can_init_ram(struct m_can_classdev *cdev)
+int m_can_init_ram(struct m_can_classdev *cdev)
 {
 	int end, i, start;
+	int err = 0;
 
 	/* initialize the entire Message RAM in use to avoid possible
 	 * ECC/parity checksum errors when reading an uninitialized buffer
@@ -1830,8 +1893,13 @@ void m_can_init_ram(struct m_can_classdev *cdev)
 	end = cdev->mcfg[MRAM_TXB].off +
 		cdev->mcfg[MRAM_TXB].num * TXB_ELEMENT_SIZE;
 
-	for (i = start; i < end; i += 4)
-		m_can_fifo_write_no_off(cdev, i, 0x0);
+	for (i = start; i < end; i += 4) {
+		err = m_can_fifo_write_no_off(cdev, i, 0x0);
+		if (err)
+			break;
+	}
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(m_can_init_ram);
 
diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h
index ace071c3e58c..d18b515e6ccc 100644
--- a/drivers/net/can/m_can/m_can.h
+++ b/drivers/net/can/m_can/m_can.h
@@ -28,6 +28,7 @@
 #include <linux/iopoll.h>
 #include <linux/can/dev.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/phy/phy.h>
 
 /* m_can lec values */
 enum m_can_lec_type {
@@ -64,9 +65,9 @@ struct m_can_ops {
 	int (*clear_interrupts)(struct m_can_classdev *cdev);
 	u32 (*read_reg)(struct m_can_classdev *cdev, int reg);
 	int (*write_reg)(struct m_can_classdev *cdev, int reg, int val);
-	u32 (*read_fifo)(struct m_can_classdev *cdev, int addr_offset);
+	int (*read_fifo)(struct m_can_classdev *cdev, int addr_offset, void *val, size_t val_count);
 	int (*write_fifo)(struct m_can_classdev *cdev, int addr_offset,
-			  int val);
+			  const void *val, size_t val_count);
 	int (*init)(struct m_can_classdev *cdev);
 };
 
@@ -82,9 +83,7 @@ struct m_can_classdev {
 	struct workqueue_struct *tx_wq;
 	struct work_struct tx_work;
 	struct sk_buff *tx_skb;
-
-	struct can_bittiming_const *bit_timing;
-	struct can_bittiming_const *data_timing;
+	struct phy *transceiver;
 
 	struct m_can_ops *ops;
 
@@ -102,7 +101,7 @@ void m_can_class_free_dev(struct net_device *net);
 int m_can_class_register(struct m_can_classdev *cdev);
 void m_can_class_unregister(struct m_can_classdev *cdev);
 int m_can_class_get_clocks(struct m_can_classdev *cdev);
-void m_can_init_ram(struct m_can_classdev *priv);
+int m_can_init_ram(struct m_can_classdev *priv);
 
 int m_can_class_suspend(struct device *dev);
 int m_can_class_resume(struct device *dev);
diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c
index 128808605c3f..89cc3d41e952 100644
--- a/drivers/net/can/m_can/m_can_pci.c
+++ b/drivers/net/can/m_can/m_can_pci.c
@@ -39,11 +39,13 @@ static u32 iomap_read_reg(struct m_can_classdev *cdev, int reg)
 	return readl(priv->base + reg);
 }
 
-static u32 iomap_read_fifo(struct m_can_classdev *cdev, int offset)
+static int iomap_read_fifo(struct m_can_classdev *cdev, int offset, void *val, size_t val_count)
 {
 	struct m_can_pci_priv *priv = cdev_to_priv(cdev);
 
-	return readl(priv->base + offset);
+	ioread32_rep(priv->base + offset, val, val_count);
+
+	return 0;
 }
 
 static int iomap_write_reg(struct m_can_classdev *cdev, int reg, int val)
@@ -55,11 +57,12 @@ static int iomap_write_reg(struct m_can_classdev *cdev, int reg, int val)
 	return 0;
 }
 
-static int iomap_write_fifo(struct m_can_classdev *cdev, int offset, int val)
+static int iomap_write_fifo(struct m_can_classdev *cdev, int offset,
+			    const void *val, size_t val_count)
 {
 	struct m_can_pci_priv *priv = cdev_to_priv(cdev);
 
-	writel(val, priv->base + offset);
+	iowrite32_rep(priv->base + offset, val, val_count);
 
 	return 0;
 }
diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c
index 599de0e08cd7..308d4f2fff00 100644
--- a/drivers/net/can/m_can/m_can_platform.c
+++ b/drivers/net/can/m_can/m_can_platform.c
@@ -6,6 +6,7 @@
 // Copyright (C) 2018-19 Texas Instruments Incorporated - http://www.ti.com/
 
 #include <linux/platform_device.h>
+#include <linux/phy/phy.h>
 
 #include "m_can.h"
 
@@ -28,11 +29,13 @@ static u32 iomap_read_reg(struct m_can_classdev *cdev, int reg)
 	return readl(priv->base + reg);
 }
 
-static u32 iomap_read_fifo(struct m_can_classdev *cdev, int offset)
+static int iomap_read_fifo(struct m_can_classdev *cdev, int offset, void *val, size_t val_count)
 {
 	struct m_can_plat_priv *priv = cdev_to_priv(cdev);
 
-	return readl(priv->mram_base + offset);
+	ioread32_rep(priv->mram_base + offset, val, val_count);
+
+	return 0;
 }
 
 static int iomap_write_reg(struct m_can_classdev *cdev, int reg, int val)
@@ -44,11 +47,12 @@ static int iomap_write_reg(struct m_can_classdev *cdev, int reg, int val)
 	return 0;
 }
 
-static int iomap_write_fifo(struct m_can_classdev *cdev, int offset, int val)
+static int iomap_write_fifo(struct m_can_classdev *cdev, int offset,
+			    const void *val, size_t val_count)
 {
 	struct m_can_plat_priv *priv = cdev_to_priv(cdev);
 
-	writel(val, priv->mram_base + offset);
+	iowrite32_rep(priv->base + offset, val, val_count);
 
 	return 0;
 }
@@ -67,6 +71,7 @@ static int m_can_plat_probe(struct platform_device *pdev)
 	struct resource *res;
 	void __iomem *addr;
 	void __iomem *mram_addr;
+	struct phy *transceiver;
 	int irq, ret = 0;
 
 	mcan_class = m_can_class_allocate_dev(&pdev->dev,
@@ -80,8 +85,7 @@ static int m_can_plat_probe(struct platform_device *pdev)
 	if (ret)
 		goto probe_fail;
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "m_can");
-	addr = devm_ioremap_resource(&pdev->dev, res);
+	addr = devm_platform_ioremap_resource_byname(pdev, "m_can");
 	irq = platform_get_irq_byname(pdev, "int0");
 	if (IS_ERR(addr) || irq < 0) {
 		ret = -EINVAL;
@@ -101,6 +105,16 @@ static int m_can_plat_probe(struct platform_device *pdev)
 		goto probe_fail;
 	}
 
+	transceiver = devm_phy_optional_get(&pdev->dev, NULL);
+	if (IS_ERR(transceiver)) {
+		ret = PTR_ERR(transceiver);
+		dev_err_probe(&pdev->dev, ret, "failed to get phy\n");
+		goto probe_fail;
+	}
+
+	if (transceiver)
+		mcan_class->can.bitrate_max = transceiver->attrs.max_link_rate;
+
 	priv->base = addr;
 	priv->mram_base = mram_addr;
 
@@ -108,6 +122,7 @@ static int m_can_plat_probe(struct platform_device *pdev)
 	mcan_class->pm_clock_support = 1;
 	mcan_class->can.clock.freq = clk_get_rate(mcan_class->cclk);
 	mcan_class->dev = &pdev->dev;
+	mcan_class->transceiver = transceiver;
 
 	mcan_class->ops = &m_can_plat_ops;
 
@@ -115,7 +130,9 @@ static int m_can_plat_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, mcan_class);
 
-	m_can_init_ram(mcan_class);
+	ret = m_can_init_ram(mcan_class);
+	if (ret)
+		goto probe_fail;
 
 	pm_runtime_enable(mcan_class->dev);
 	ret = m_can_class_register(mcan_class);
diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c
index 4147cecfbbd6..04687b15b250 100644
--- a/drivers/net/can/m_can/tcan4x5x-core.c
+++ b/drivers/net/can/m_can/tcan4x5x-core.c
@@ -105,7 +105,6 @@
 static inline struct tcan4x5x_priv *cdev_to_priv(struct m_can_classdev *cdev)
 {
 	return container_of(cdev, struct tcan4x5x_priv, cdev);
-
 }
 
 static void tcan4x5x_check_wake(struct tcan4x5x_priv *priv)
@@ -154,14 +153,12 @@ static u32 tcan4x5x_read_reg(struct m_can_classdev *cdev, int reg)
 	return val;
 }
 
-static u32 tcan4x5x_read_fifo(struct m_can_classdev *cdev, int addr_offset)
+static int tcan4x5x_read_fifo(struct m_can_classdev *cdev, int addr_offset,
+			      void *val, size_t val_count)
 {
 	struct tcan4x5x_priv *priv = cdev_to_priv(cdev);
-	u32 val;
-
-	regmap_read(priv->regmap, TCAN4X5X_MRAM_START + addr_offset, &val);
 
-	return val;
+	return regmap_bulk_read(priv->regmap, TCAN4X5X_MRAM_START + addr_offset, val, val_count);
 }
 
 static int tcan4x5x_write_reg(struct m_can_classdev *cdev, int reg, int val)
@@ -172,11 +169,11 @@ static int tcan4x5x_write_reg(struct m_can_classdev *cdev, int reg, int val)
 }
 
 static int tcan4x5x_write_fifo(struct m_can_classdev *cdev,
-			       int addr_offset, int val)
+			       int addr_offset, const void *val, size_t val_count)
 {
 	struct tcan4x5x_priv *priv = cdev_to_priv(cdev);
 
-	return regmap_write(priv->regmap, TCAN4X5X_MRAM_START + addr_offset, val);
+	return regmap_bulk_write(priv->regmap, TCAN4X5X_MRAM_START + addr_offset, val, val_count);
 }
 
 static int tcan4x5x_power_enable(struct regulator *reg, int enable)
@@ -238,7 +235,9 @@ static int tcan4x5x_init(struct m_can_classdev *cdev)
 		return ret;
 
 	/* Zero out the MCAN buffers */
-	m_can_init_ram(cdev);
+	ret = m_can_init_ram(cdev);
+	if (ret)
+		return ret;
 
 	ret = regmap_update_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG,
 				 TCAN4X5X_MODE_SEL_MASK, TCAN4X5X_MODE_NORMAL);
diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c
index e254e04ae257..35892c1efef0 100644
--- a/drivers/net/can/mscan/mpc5xxx_can.c
+++ b/drivers/net/can/mscan/mpc5xxx_can.c
@@ -279,7 +279,6 @@ static u32 mpc512x_can_get_clock(struct platform_device *ofdev,
 static const struct of_device_id mpc5xxx_can_table[];
 static int mpc5xxx_can_probe(struct platform_device *ofdev)
 {
-	const struct of_device_id *match;
 	const struct mpc5xxx_can_data *data;
 	struct device_node *np = ofdev->dev.of_node;
 	struct net_device *dev;
@@ -289,10 +288,9 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)
 	int irq, mscan_clksrc = 0;
 	int err = -ENOMEM;
 
-	match = of_match_device(mpc5xxx_can_table, &ofdev->dev);
-	if (!match)
+	data = of_device_get_match_data(&ofdev->dev);
+	if (!data)
 		return -EINVAL;
-	data = match->data;
 
 	base = of_iomap(np, 0);
 	if (!base) {
@@ -319,7 +317,6 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)
 
 	clock_name = of_get_property(np, "fsl,mscan-clock-source", NULL);
 
-	BUG_ON(!data);
 	priv->type = data->type;
 	priv->can.clock.freq = data->get_clock(ofdev, clock_name,
 					       &mscan_clksrc);
diff --git a/drivers/net/can/rcar/Kconfig b/drivers/net/can/rcar/Kconfig
index 29cabc20109e..56320a7f828b 100644
--- a/drivers/net/can/rcar/Kconfig
+++ b/drivers/net/can/rcar/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 config CAN_RCAR
 	tristate "Renesas R-Car and RZ/G CAN controller"
-	depends on ARCH_RENESAS || ARM
+	depends on ARCH_RENESAS || ARM || COMPILE_TEST
 	help
 	  Say Y here if you want to use CAN controller found on Renesas R-Car
 	  or RZ/G SoCs.
@@ -11,7 +11,7 @@ config CAN_RCAR
 
 config CAN_RCAR_CANFD
 	tristate "Renesas R-Car CAN FD controller"
-	depends on ARCH_RENESAS || ARM
+	depends on ARCH_RENESAS || ARM || COMPILE_TEST
 	help
 	  Say Y here if you want to use CAN FD controller found on
 	  Renesas R-Car SoCs. The driver puts the controller in CAN FD only
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index 311e6ca3bdc4..c47988d3674e 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -37,9 +37,15 @@
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <linux/iopoll.h>
+#include <linux/reset.h>
 
 #define RCANFD_DRV_NAME			"rcar_canfd"
 
+enum rcanfd_chip_id {
+	RENESAS_RCAR_GEN3 = 0,
+	RENESAS_RZG2L,
+};
+
 /* Global register bits */
 
 /* RSCFDnCFDGRMCFG */
@@ -513,6 +519,9 @@ struct rcar_canfd_global {
 	enum rcar_canfd_fcanclk fcan;	/* CANFD or Ext clock */
 	unsigned long channels_mask;	/* Enabled channels mask */
 	bool fdmode;			/* CAN FD or Classical CAN only mode */
+	struct reset_control *rstc1;
+	struct reset_control *rstc2;
+	enum rcanfd_chip_id chip_id;
 };
 
 /* CAN FD mode nominal rate constants */
@@ -1070,38 +1079,70 @@ static void rcar_canfd_tx_done(struct net_device *ndev)
 	can_led_event(ndev, CAN_LED_EVENT_TX);
 }
 
+static void rcar_canfd_handle_global_err(struct rcar_canfd_global *gpriv, u32 ch)
+{
+	struct rcar_canfd_channel *priv = gpriv->ch[ch];
+	struct net_device *ndev = priv->ndev;
+	u32 gerfl;
+
+	/* Handle global error interrupts */
+	gerfl = rcar_canfd_read(priv->base, RCANFD_GERFL);
+	if (unlikely(RCANFD_GERFL_ERR(gpriv, gerfl)))
+		rcar_canfd_global_error(ndev);
+}
+
+static irqreturn_t rcar_canfd_global_err_interrupt(int irq, void *dev_id)
+{
+	struct rcar_canfd_global *gpriv = dev_id;
+	u32 ch;
+
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS)
+		rcar_canfd_handle_global_err(gpriv, ch);
+
+	return IRQ_HANDLED;
+}
+
+static void rcar_canfd_handle_global_receive(struct rcar_canfd_global *gpriv, u32 ch)
+{
+	struct rcar_canfd_channel *priv = gpriv->ch[ch];
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+	u32 sts;
+
+	/* Handle Rx interrupts */
+	sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(ridx));
+	if (likely(sts & RCANFD_RFSTS_RFIF)) {
+		if (napi_schedule_prep(&priv->napi)) {
+			/* Disable Rx FIFO interrupts */
+			rcar_canfd_clear_bit(priv->base,
+					     RCANFD_RFCC(ridx),
+					     RCANFD_RFCC_RFIE);
+			__napi_schedule(&priv->napi);
+		}
+	}
+}
+
+static irqreturn_t rcar_canfd_global_receive_fifo_interrupt(int irq, void *dev_id)
+{
+	struct rcar_canfd_global *gpriv = dev_id;
+	u32 ch;
+
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS)
+		rcar_canfd_handle_global_receive(gpriv, ch);
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t rcar_canfd_global_interrupt(int irq, void *dev_id)
 {
 	struct rcar_canfd_global *gpriv = dev_id;
-	struct net_device *ndev;
-	struct rcar_canfd_channel *priv;
-	u32 sts, gerfl;
-	u32 ch, ridx;
+	u32 ch;
 
 	/* Global error interrupts still indicate a condition specific
 	 * to a channel. RxFIFO interrupt is a global interrupt.
 	 */
 	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
-		priv = gpriv->ch[ch];
-		ndev = priv->ndev;
-		ridx = ch + RCANFD_RFFIFO_IDX;
-
-		/* Global error interrupts */
-		gerfl = rcar_canfd_read(priv->base, RCANFD_GERFL);
-		if (unlikely(RCANFD_GERFL_ERR(gpriv, gerfl)))
-			rcar_canfd_global_error(ndev);
-
-		/* Handle Rx interrupts */
-		sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(ridx));
-		if (likely(sts & RCANFD_RFSTS_RFIF)) {
-			if (napi_schedule_prep(&priv->napi)) {
-				/* Disable Rx FIFO interrupts */
-				rcar_canfd_clear_bit(priv->base,
-						     RCANFD_RFCC(ridx),
-						     RCANFD_RFCC_RFIE);
-				__napi_schedule(&priv->napi);
-			}
-		}
+		rcar_canfd_handle_global_err(gpriv, ch);
+		rcar_canfd_handle_global_receive(gpriv, ch);
 	}
 	return IRQ_HANDLED;
 }
@@ -1139,38 +1180,73 @@ static void rcar_canfd_state_change(struct net_device *ndev,
 	}
 }
 
-static irqreturn_t rcar_canfd_channel_interrupt(int irq, void *dev_id)
+static void rcar_canfd_handle_channel_tx(struct rcar_canfd_global *gpriv, u32 ch)
+{
+	struct rcar_canfd_channel *priv = gpriv->ch[ch];
+	struct net_device *ndev = priv->ndev;
+	u32 sts;
+
+	/* Handle Tx interrupts */
+	sts = rcar_canfd_read(priv->base,
+			      RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX));
+	if (likely(sts & RCANFD_CFSTS_CFTXIF))
+		rcar_canfd_tx_done(ndev);
+}
+
+static irqreturn_t rcar_canfd_channel_tx_interrupt(int irq, void *dev_id)
 {
 	struct rcar_canfd_global *gpriv = dev_id;
-	struct net_device *ndev;
-	struct rcar_canfd_channel *priv;
-	u32 sts, ch, cerfl;
+	u32 ch;
+
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS)
+		rcar_canfd_handle_channel_tx(gpriv, ch);
+
+	return IRQ_HANDLED;
+}
+
+static void rcar_canfd_handle_channel_err(struct rcar_canfd_global *gpriv, u32 ch)
+{
+	struct rcar_canfd_channel *priv = gpriv->ch[ch];
+	struct net_device *ndev = priv->ndev;
 	u16 txerr, rxerr;
+	u32 sts, cerfl;
+
+	/* Handle channel error interrupts */
+	cerfl = rcar_canfd_read(priv->base, RCANFD_CERFL(ch));
+	sts = rcar_canfd_read(priv->base, RCANFD_CSTS(ch));
+	txerr = RCANFD_CSTS_TECCNT(sts);
+	rxerr = RCANFD_CSTS_RECCNT(sts);
+	if (unlikely(RCANFD_CERFL_ERR(cerfl)))
+		rcar_canfd_error(ndev, cerfl, txerr, rxerr);
+
+	/* Handle state change to lower states */
+	if (unlikely(priv->can.state != CAN_STATE_ERROR_ACTIVE &&
+		     priv->can.state != CAN_STATE_BUS_OFF))
+		rcar_canfd_state_change(ndev, txerr, rxerr);
+}
+
+static irqreturn_t rcar_canfd_channel_err_interrupt(int irq, void *dev_id)
+{
+	struct rcar_canfd_global *gpriv = dev_id;
+	u32 ch;
+
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS)
+		rcar_canfd_handle_channel_err(gpriv, ch);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t rcar_canfd_channel_interrupt(int irq, void *dev_id)
+{
+	struct rcar_canfd_global *gpriv = dev_id;
+	u32 ch;
 
 	/* Common FIFO is a per channel resource */
 	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
-		priv = gpriv->ch[ch];
-		ndev = priv->ndev;
-
-		/* Channel error interrupts */
-		cerfl = rcar_canfd_read(priv->base, RCANFD_CERFL(ch));
-		sts = rcar_canfd_read(priv->base, RCANFD_CSTS(ch));
-		txerr = RCANFD_CSTS_TECCNT(sts);
-		rxerr = RCANFD_CSTS_RECCNT(sts);
-		if (unlikely(RCANFD_CERFL_ERR(cerfl)))
-			rcar_canfd_error(ndev, cerfl, txerr, rxerr);
-
-		/* Handle state change to lower states */
-		if (unlikely((priv->can.state != CAN_STATE_ERROR_ACTIVE) &&
-			     (priv->can.state != CAN_STATE_BUS_OFF)))
-			rcar_canfd_state_change(ndev, txerr, rxerr);
-
-		/* Handle Tx interrupts */
-		sts = rcar_canfd_read(priv->base,
-				      RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX));
-		if (likely(sts & RCANFD_CFSTS_CFTXIF))
-			rcar_canfd_tx_done(ndev);
+		rcar_canfd_handle_channel_err(gpriv, ch);
+		rcar_canfd_handle_channel_tx(gpriv, ch);
 	}
+
 	return IRQ_HANDLED;
 }
 
@@ -1577,6 +1653,53 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
 	priv->can.clock.freq = fcan_freq;
 	dev_info(&pdev->dev, "can_clk rate is %u\n", priv->can.clock.freq);
 
+	if (gpriv->chip_id == RENESAS_RZG2L) {
+		char *irq_name;
+		int err_irq;
+		int tx_irq;
+
+		err_irq = platform_get_irq_byname(pdev, ch == 0 ? "ch0_err" : "ch1_err");
+		if (err_irq < 0) {
+			err = err_irq;
+			goto fail;
+		}
+
+		tx_irq = platform_get_irq_byname(pdev, ch == 0 ? "ch0_trx" : "ch1_trx");
+		if (tx_irq < 0) {
+			err = tx_irq;
+			goto fail;
+		}
+
+		irq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+					  "canfd.ch%d_err", ch);
+		if (!irq_name) {
+			err = -ENOMEM;
+			goto fail;
+		}
+		err = devm_request_irq(&pdev->dev, err_irq,
+				       rcar_canfd_channel_err_interrupt, 0,
+				       irq_name, gpriv);
+		if (err) {
+			dev_err(&pdev->dev, "devm_request_irq CH Err(%d) failed, error %d\n",
+				err_irq, err);
+			goto fail;
+		}
+		irq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+					  "canfd.ch%d_trx", ch);
+		if (!irq_name) {
+			err = -ENOMEM;
+			goto fail;
+		}
+		err = devm_request_irq(&pdev->dev, tx_irq,
+				       rcar_canfd_channel_tx_interrupt, 0,
+				       irq_name, gpriv);
+		if (err) {
+			dev_err(&pdev->dev, "devm_request_irq Tx (%d) failed, error %d\n",
+				tx_irq, err);
+			goto fail;
+		}
+	}
+
 	if (gpriv->fdmode) {
 		priv->can.bittiming_const = &rcar_canfd_nom_bittiming_const;
 		priv->can.data_bittiming_const =
@@ -1636,7 +1759,11 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 	struct device_node *of_child;
 	unsigned long channels_mask = 0;
 	int err, ch_irq, g_irq;
+	int g_err_irq, g_recc_irq;
 	bool fdmode = true;			/* CAN FD only mode - default */
+	enum rcanfd_chip_id chip_id;
+
+	chip_id = (uintptr_t)of_device_get_match_data(&pdev->dev);
 
 	if (of_property_read_bool(pdev->dev.of_node, "renesas,no-can-fd"))
 		fdmode = false;			/* Classical CAN only mode */
@@ -1649,16 +1776,30 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 	if (of_child && of_device_is_available(of_child))
 		channels_mask |= BIT(1);	/* Channel 1 */
 
-	ch_irq = platform_get_irq(pdev, 0);
-	if (ch_irq < 0) {
-		err = ch_irq;
-		goto fail_dev;
-	}
+	if (chip_id == RENESAS_RCAR_GEN3) {
+		ch_irq = platform_get_irq_byname_optional(pdev, "ch_int");
+		if (ch_irq < 0) {
+			/* For backward compatibility get irq by index */
+			ch_irq = platform_get_irq(pdev, 0);
+			if (ch_irq < 0)
+				return ch_irq;
+		}
 
-	g_irq = platform_get_irq(pdev, 1);
-	if (g_irq < 0) {
-		err = g_irq;
-		goto fail_dev;
+		g_irq = platform_get_irq_byname_optional(pdev, "g_int");
+		if (g_irq < 0) {
+			/* For backward compatibility get irq by index */
+			g_irq = platform_get_irq(pdev, 1);
+			if (g_irq < 0)
+				return g_irq;
+		}
+	} else {
+		g_err_irq = platform_get_irq_byname(pdev, "g_err");
+		if (g_err_irq < 0)
+			return g_err_irq;
+
+		g_recc_irq = platform_get_irq_byname(pdev, "g_recc");
+		if (g_recc_irq < 0)
+			return g_recc_irq;
 	}
 
 	/* Global controller context */
@@ -1670,6 +1811,19 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 	gpriv->pdev = pdev;
 	gpriv->channels_mask = channels_mask;
 	gpriv->fdmode = fdmode;
+	gpriv->chip_id = chip_id;
+
+	if (gpriv->chip_id == RENESAS_RZG2L) {
+		gpriv->rstc1 = devm_reset_control_get_exclusive(&pdev->dev, "rstp_n");
+		if (IS_ERR(gpriv->rstc1))
+			return dev_err_probe(&pdev->dev, PTR_ERR(gpriv->rstc1),
+					     "failed to get rstp_n\n");
+
+		gpriv->rstc2 = devm_reset_control_get_exclusive(&pdev->dev, "rstc_n");
+		if (IS_ERR(gpriv->rstc2))
+			return dev_err_probe(&pdev->dev, PTR_ERR(gpriv->rstc2),
+					     "failed to get rstc_n\n");
+	}
 
 	/* Peripheral clock */
 	gpriv->clkp = devm_clk_get(&pdev->dev, "fck");
@@ -1699,7 +1853,7 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 	}
 	fcan_freq = clk_get_rate(gpriv->can_clk);
 
-	if (gpriv->fcan == RCANFD_CANFDCLK)
+	if (gpriv->fcan == RCANFD_CANFDCLK && gpriv->chip_id == RENESAS_RCAR_GEN3)
 		/* CANFD clock is further divided by (1/2) within the IP */
 		fcan_freq /= 2;
 
@@ -1711,20 +1865,51 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 	gpriv->base = addr;
 
 	/* Request IRQ that's common for both channels */
-	err = devm_request_irq(&pdev->dev, ch_irq,
-			       rcar_canfd_channel_interrupt, 0,
-			       "canfd.chn", gpriv);
-	if (err) {
-		dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n",
-			ch_irq, err);
-		goto fail_dev;
+	if (gpriv->chip_id == RENESAS_RCAR_GEN3) {
+		err = devm_request_irq(&pdev->dev, ch_irq,
+				       rcar_canfd_channel_interrupt, 0,
+				       "canfd.ch_int", gpriv);
+		if (err) {
+			dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n",
+				ch_irq, err);
+			goto fail_dev;
+		}
+
+		err = devm_request_irq(&pdev->dev, g_irq,
+				       rcar_canfd_global_interrupt, 0,
+				       "canfd.g_int", gpriv);
+		if (err) {
+			dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n",
+				g_irq, err);
+			goto fail_dev;
+		}
+	} else {
+		err = devm_request_irq(&pdev->dev, g_recc_irq,
+				       rcar_canfd_global_receive_fifo_interrupt, 0,
+				       "canfd.g_recc", gpriv);
+
+		if (err) {
+			dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n",
+				g_recc_irq, err);
+			goto fail_dev;
+		}
+
+		err = devm_request_irq(&pdev->dev, g_err_irq,
+				       rcar_canfd_global_err_interrupt, 0,
+				       "canfd.g_err", gpriv);
+		if (err) {
+			dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n",
+				g_err_irq, err);
+			goto fail_dev;
+		}
 	}
-	err = devm_request_irq(&pdev->dev, g_irq,
-			       rcar_canfd_global_interrupt, 0,
-			       "canfd.gbl", gpriv);
+
+	err = reset_control_reset(gpriv->rstc1);
+	if (err)
+		goto fail_dev;
+	err = reset_control_reset(gpriv->rstc2);
 	if (err) {
-		dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n",
-			g_irq, err);
+		reset_control_assert(gpriv->rstc1);
 		goto fail_dev;
 	}
 
@@ -1733,7 +1918,7 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 	if (err) {
 		dev_err(&pdev->dev,
 			"failed to enable peripheral clock, error %d\n", err);
-		goto fail_dev;
+		goto fail_reset;
 	}
 
 	err = rcar_canfd_reset_controller(gpriv);
@@ -1790,6 +1975,9 @@ fail_mode:
 	rcar_canfd_disable_global_interrupts(gpriv);
 fail_clk:
 	clk_disable_unprepare(gpriv->clkp);
+fail_reset:
+	reset_control_assert(gpriv->rstc1);
+	reset_control_assert(gpriv->rstc2);
 fail_dev:
 	return err;
 }
@@ -1810,6 +1998,9 @@ static int rcar_canfd_remove(struct platform_device *pdev)
 	/* Enter global sleep mode */
 	rcar_canfd_set_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GSLPR);
 	clk_disable_unprepare(gpriv->clkp);
+	reset_control_assert(gpriv->rstc1);
+	reset_control_assert(gpriv->rstc2);
+
 	return 0;
 }
 
@@ -1827,7 +2018,8 @@ static SIMPLE_DEV_PM_OPS(rcar_canfd_pm_ops, rcar_canfd_suspend,
 			 rcar_canfd_resume);
 
 static const struct of_device_id rcar_canfd_of_table[] = {
-	{ .compatible = "renesas,rcar-gen3-canfd" },
+	{ .compatible = "renesas,rcar-gen3-canfd", .data = (void *)RENESAS_RCAR_GEN3 },
+	{ .compatible = "renesas,rzg2l-canfd", .data = (void *)RENESAS_RZG2L },
 	{ }
 };
 
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index 84eac8cb8686..6db90dc4bc9d 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -28,6 +28,10 @@ MODULE_LICENSE("GPL v2");
 
 #define DRV_NAME  "peak_pci"
 
+/* FPGA cards FW version registers */
+#define PEAK_VER_REG1		0x40
+#define PEAK_VER_REG2		0x44
+
 struct peak_pciec_card;
 struct peak_pci_chan {
 	void __iomem *cfg_base;		/* Common for all channels */
@@ -41,9 +45,7 @@ struct peak_pci_chan {
 #define PEAK_PCI_CDR		(CDR_CBP | CDR_CLKOUT_MASK)
 #define PEAK_PCI_OCR		OCR_TX0_PUSHPULL
 
-/*
- * Important PITA registers
- */
+/* Important PITA registers */
 #define PITA_ICR		0x00	/* Interrupt control register */
 #define PITA_GPIOICR		0x18	/* GPIO interface control register */
 #define PITA_MISC		0x1C	/* Miscellaneous register */
@@ -70,27 +72,47 @@ static const u16 peak_pci_icr_masks[PEAK_PCI_CHAN_MAX] = {
 };
 
 static const struct pci_device_id peak_pci_tbl[] = {
-	{PEAK_PCI_VENDOR_ID, PEAK_PCI_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,},
-	{PEAK_PCI_VENDOR_ID, PEAK_PCIE_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,},
-	{PEAK_PCI_VENDOR_ID, PEAK_MPCI_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,},
-	{PEAK_PCI_VENDOR_ID, PEAK_MPCIE_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,},
-	{PEAK_PCI_VENDOR_ID, PEAK_PC_104P_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,},
-	{PEAK_PCI_VENDOR_ID, PEAK_PCI_104E_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,},
-	{PEAK_PCI_VENDOR_ID, PEAK_CPCI_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,},
-	{PEAK_PCI_VENDOR_ID, PEAK_PCIE_OEM_ID, PCI_ANY_ID, PCI_ANY_ID,},
+	{
+		PEAK_PCI_VENDOR_ID, PEAK_PCI_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,
+		.driver_data = (kernel_ulong_t)"PCAN-PCI",
+	}, {
+		PEAK_PCI_VENDOR_ID, PEAK_PCIE_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,
+		.driver_data = (kernel_ulong_t)"PCAN-PCI Express",
+	}, {
+		PEAK_PCI_VENDOR_ID, PEAK_MPCI_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,
+		.driver_data = (kernel_ulong_t)"PCAN-miniPCI",
+	}, {
+		PEAK_PCI_VENDOR_ID, PEAK_MPCIE_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,
+		.driver_data = (kernel_ulong_t)"PCAN-miniPCIe",
+	}, {
+		PEAK_PCI_VENDOR_ID, PEAK_PC_104P_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,
+		.driver_data = (kernel_ulong_t)"PCAN-PC/104-Plus Quad",
+	}, {
+		PEAK_PCI_VENDOR_ID, PEAK_PCI_104E_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,
+		.driver_data = (kernel_ulong_t)"PCAN-PCI/104-Express",
+	}, {
+		PEAK_PCI_VENDOR_ID, PEAK_CPCI_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,
+		.driver_data = (kernel_ulong_t)"PCAN-cPCI",
+	}, {
+		PEAK_PCI_VENDOR_ID, PEAK_PCIE_OEM_ID, PCI_ANY_ID, PCI_ANY_ID,
+		.driver_data = (kernel_ulong_t)"PCAN-Chip PCIe",
+	},
 #ifdef CONFIG_CAN_PEAK_PCIEC
-	{PEAK_PCI_VENDOR_ID, PEAK_PCIEC_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,},
-	{PEAK_PCI_VENDOR_ID, PEAK_PCIEC34_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,},
+	{
+		PEAK_PCI_VENDOR_ID, PEAK_PCIEC_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,
+		.driver_data = (kernel_ulong_t)"PCAN-ExpressCard",
+	}, {
+		PEAK_PCI_VENDOR_ID, PEAK_PCIEC34_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,
+		.driver_data = (kernel_ulong_t)"PCAN-ExpressCard 34",
+	},
 #endif
-	{0,}
+	{ /* sentinel */ }
 };
 
 MODULE_DEVICE_TABLE(pci, peak_pci_tbl);
 
 #ifdef CONFIG_CAN_PEAK_PCIEC
-/*
- * PCAN-ExpressCard needs I2C bit-banging configuration option.
- */
+/* PCAN-ExpressCard needs I2C bit-banging configuration option. */
 
 /* GPIOICR byte access offsets */
 #define PITA_GPOUT		0x18	/* GPx output value */
@@ -156,12 +178,14 @@ static void peak_pci_write_reg(const struct sja1000_priv *priv,
 static inline void pita_set_scl_highz(struct peak_pciec_card *card)
 {
 	u8 gp_outen = readb(card->cfg_base + PITA_GPOEN) & ~PITA_GPIN_SCL;
+
 	writeb(gp_outen, card->cfg_base + PITA_GPOEN);
 }
 
 static inline void pita_set_sda_highz(struct peak_pciec_card *card)
 {
 	u8 gp_outen = readb(card->cfg_base + PITA_GPOEN) & ~PITA_GPIN_SDA;
+
 	writeb(gp_outen, card->cfg_base + PITA_GPOEN);
 }
 
@@ -230,9 +254,7 @@ static int pita_getscl(void *data)
 	return (readb(card->cfg_base + PITA_GPIN) & PITA_GPIN_SCL) ? 1 : 0;
 }
 
-/*
- * write commands to the LED chip though the I2C-bus of the PCAN-PCIeC
- */
+/* write commands to the LED chip though the I2C-bus of the PCAN-PCIeC */
 static int peak_pciec_write_pca9553(struct peak_pciec_card *card,
 				    u8 offset, u8 data)
 {
@@ -248,7 +270,7 @@ static int peak_pciec_write_pca9553(struct peak_pciec_card *card,
 	int ret;
 
 	/* cache led mask */
-	if ((offset == 5) && (data == card->led_cache))
+	if (offset == 5 && data == card->led_cache)
 		return 0;
 
 	ret = i2c_transfer(&card->led_chip, &msg, 1);
@@ -261,9 +283,7 @@ static int peak_pciec_write_pca9553(struct peak_pciec_card *card,
 	return 0;
 }
 
-/*
- * delayed work callback used to control the LEDs
- */
+/* delayed work callback used to control the LEDs */
 static void peak_pciec_led_work(struct work_struct *work)
 {
 	struct peak_pciec_card *card =
@@ -309,9 +329,7 @@ static void peak_pciec_led_work(struct work_struct *work)
 		schedule_delayed_work(&card->led_work, HZ);
 }
 
-/*
- * set LEDs blinking state
- */
+/* set LEDs blinking state */
 static void peak_pciec_set_leds(struct peak_pciec_card *card, u8 led_mask, u8 s)
 {
 	u8 new_led = card->led_cache;
@@ -328,25 +346,19 @@ static void peak_pciec_set_leds(struct peak_pciec_card *card, u8 led_mask, u8 s)
 	peak_pciec_write_pca9553(card, 5, new_led);
 }
 
-/*
- * start one second delayed work to control LEDs
- */
+/* start one second delayed work to control LEDs */
 static void peak_pciec_start_led_work(struct peak_pciec_card *card)
 {
 	schedule_delayed_work(&card->led_work, HZ);
 }
 
-/*
- * stop LEDs delayed work
- */
+/* stop LEDs delayed work */
 static void peak_pciec_stop_led_work(struct peak_pciec_card *card)
 {
 	cancel_delayed_work_sync(&card->led_work);
 }
 
-/*
- * initialize the PCA9553 4-bit I2C-bus LED chip
- */
+/* initialize the PCA9553 4-bit I2C-bus LED chip */
 static int peak_pciec_init_leds(struct peak_pciec_card *card)
 {
 	int err;
@@ -375,17 +387,14 @@ static int peak_pciec_init_leds(struct peak_pciec_card *card)
 	return peak_pciec_write_pca9553(card, 5, PCA9553_LS0_INIT);
 }
 
-/*
- * restore LEDs state to off peak_pciec_leds_exit
- */
+/* restore LEDs state to off peak_pciec_leds_exit */
 static void peak_pciec_leds_exit(struct peak_pciec_card *card)
 {
 	/* switch LEDs to off */
 	peak_pciec_write_pca9553(card, 5, PCA9553_LED_OFF_ALL);
 }
 
-/*
- * normal write sja1000 register method overloaded to catch when controller
+/* normal write sja1000 register method overloaded to catch when controller
  * is started or stopped, to control leds
  */
 static void peak_pciec_write_reg(const struct sja1000_priv *priv,
@@ -443,7 +452,7 @@ static int peak_pciec_probe(struct pci_dev *pdev, struct net_device *dev)
 	/* channel is the first one: do the init part */
 	} else {
 		/* create the bit banging I2C adapter structure */
-		card = kzalloc(sizeof(struct peak_pciec_card), GFP_KERNEL);
+		card = kzalloc(sizeof(*card), GFP_KERNEL);
 		if (!card)
 			return -ENOMEM;
 
@@ -506,9 +515,7 @@ static void peak_pciec_remove(struct peak_pciec_card *card)
 
 #else /* CONFIG_CAN_PEAK_PCIEC */
 
-/*
- * Placebo functions when PCAN-ExpressCard support is not selected
- */
+/* Placebo functions when PCAN-ExpressCard support is not selected */
 static inline int peak_pciec_probe(struct pci_dev *pdev, struct net_device *dev)
 {
 	return -ENODEV;
@@ -549,6 +556,7 @@ static int peak_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	void __iomem *cfg_base, *reg_base;
 	u16 sub_sys_id, icr;
 	int i, err, channels;
+	char fw_str[14] = "";
 
 	err = pci_enable_device(pdev);
 	if (err)
@@ -602,6 +610,21 @@ static int peak_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Leave parport mux mode */
 	writeb(0x04, cfg_base + PITA_MISC + 3);
 
+	/* FPGA equipped card if not 0 */
+	if (readl(cfg_base + PEAK_VER_REG1)) {
+		/* FPGA card: display version of the running firmware */
+		u32 fw_ver = readl(cfg_base + PEAK_VER_REG2);
+
+		snprintf(fw_str, sizeof(fw_str), " FW v%u.%u.%u",
+			 (fw_ver >> 12) & 0xf,
+			 (fw_ver >> 8) & 0xf,
+			 (fw_ver >> 4) & 0xf);
+	}
+
+	/* Display commercial name (and, eventually, FW version) of the card */
+	dev_info(&pdev->dev, "%ux CAN %s%s\n",
+		 channels, (const char *)ent->driver_data, fw_str);
+
 	icr = readw(cfg_base + PITA_ICR + 2);
 
 	for (i = 0; i < channels; i++) {
@@ -642,8 +665,7 @@ static int peak_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		chan->prev_dev = pci_get_drvdata(pdev);
 		pci_set_drvdata(pdev, dev);
 
-		/*
-		 * PCAN-ExpressCard needs some additional i2c init.
+		/* PCAN-ExpressCard needs some additional i2c init.
 		 * This must be done *before* register_sja1000dev() but
 		 * *after* devices linkage
 		 */
@@ -709,7 +731,8 @@ failure_disable_pci:
 
 	/* pci_xxx_config_word() return positive PCIBIOS_xxx error codes while
 	 * the probe() function must return a negative errno in case of failure
-	 * (err is unchanged if negative) */
+	 * (err is unchanged if negative)
+	 */
 	return pcibios_err_to_errno(err);
 }
 
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 9ae48072b6c6..673861ab665a 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -15,10 +15,10 @@
 #include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/device.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 
 #include <asm/unaligned.h>
 
@@ -1456,7 +1456,7 @@ mcp251xfd_rx_ring_update(const struct mcp251xfd_priv *priv,
 }
 
 static void
-mcp251xfd_hw_rx_obj_to_skb(struct mcp251xfd_priv *priv,
+mcp251xfd_hw_rx_obj_to_skb(const struct mcp251xfd_priv *priv,
 			   const struct mcp251xfd_hw_rx_obj_canfd *hw_rx_obj,
 			   struct sk_buff *skb)
 {
@@ -2195,8 +2195,10 @@ static irqreturn_t mcp251xfd_irq(int irq, void *dev_id)
 			FIELD_GET(MCP251XFD_REG_INT_IE_MASK,
 				  priv->regs_status.intf);
 
-		if (!(intf_pending))
+		if (!(intf_pending)) {
+			can_rx_offload_threaded_irq_finish(&priv->offload);
 			return handled;
+		}
 
 		/* Some interrupts must be ACKed in the
 		 * MCP251XFD_REG_INT register.
@@ -2296,6 +2298,8 @@ static irqreturn_t mcp251xfd_irq(int irq, void *dev_id)
 	} while (1);
 
  out_fail:
+	can_rx_offload_threaded_irq_finish(&priv->offload);
+
 	netdev_err(priv->ndev, "IRQ handler returned %d (intf=0x%08x).\n",
 		   err, priv->regs_status.intf);
 	mcp251xfd_dump(priv);
@@ -2524,8 +2528,8 @@ static int mcp251xfd_open(struct net_device *ndev)
 	can_rx_offload_enable(&priv->offload);
 
 	err = request_threaded_irq(spi->irq, NULL, mcp251xfd_irq,
-				   IRQF_ONESHOT, dev_name(&spi->dev),
-				   priv);
+				   IRQF_SHARED | IRQF_ONESHOT,
+				   dev_name(&spi->dev), priv);
 	if (err)
 		goto out_can_rx_offload_disable;
 
@@ -2857,7 +2861,7 @@ static int mcp251xfd_probe(struct spi_device *spi)
 	struct gpio_desc *rx_int;
 	struct regulator *reg_vdd, *reg_xceiver;
 	struct clk *clk;
-	u32 freq;
+	u32 freq = 0;
 	int err;
 
 	if (!spi->irq)
@@ -2884,11 +2888,19 @@ static int mcp251xfd_probe(struct spi_device *spi)
 		return dev_err_probe(&spi->dev, PTR_ERR(reg_xceiver),
 				     "Failed to get Transceiver regulator!\n");
 
-	clk = devm_clk_get(&spi->dev, NULL);
+	clk = devm_clk_get_optional(&spi->dev, NULL);
 	if (IS_ERR(clk))
 		return dev_err_probe(&spi->dev, PTR_ERR(clk),
 				     "Failed to get Oscillator (clock)!\n");
-	freq = clk_get_rate(clk);
+	if (clk) {
+		freq = clk_get_rate(clk);
+	} else {
+		err = device_property_read_u32(&spi->dev, "clock-frequency",
+					       &freq);
+		if (err)
+			return dev_err_probe(&spi->dev, err,
+					     "Failed to get clock-frequency!\n");
+	}
 
 	/* Sanity check */
 	if (freq < MCP251XFD_SYSCLOCK_HZ_MIN ||
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
index ed3169274d24..712e09186987 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
@@ -13,7 +13,7 @@
 
 static u64 mcp251xfd_timestamp_read(const struct cyclecounter *cc)
 {
-	struct mcp251xfd_priv *priv;
+	const struct mcp251xfd_priv *priv;
 	u32 timestamp = 0;
 	int err;
 
@@ -39,7 +39,7 @@ static void mcp251xfd_timestamp_work(struct work_struct *work)
 			      MCP251XFD_TIMESTAMP_WORK_DELAY_SEC * HZ);
 }
 
-void mcp251xfd_skb_set_timestamp(struct mcp251xfd_priv *priv,
+void mcp251xfd_skb_set_timestamp(const struct mcp251xfd_priv *priv,
 				 struct sk_buff *skb, u32 timestamp)
 {
 	struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
index 1002f3902ad2..0f322dabaf65 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
@@ -853,7 +853,7 @@ int mcp251xfd_regmap_init(struct mcp251xfd_priv *priv);
 u16 mcp251xfd_crc16_compute2(const void *cmd, size_t cmd_size,
 			     const void *data, size_t data_size);
 u16 mcp251xfd_crc16_compute(const void *data, size_t data_size);
-void mcp251xfd_skb_set_timestamp(struct mcp251xfd_priv *priv,
+void mcp251xfd_skb_set_timestamp(const struct mcp251xfd_priv *priv,
 				 struct sk_buff *skb, u32 timestamp);
 void mcp251xfd_timestamp_init(struct mcp251xfd_priv *priv);
 void mcp251xfd_timestamp_stop(struct mcp251xfd_priv *priv);
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 73245d8836a9..353062ead98f 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -786,6 +786,8 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 		int_status = hecc_read(priv, HECC_CANGIF0);
 	}
 
+	can_rx_offload_irq_finish(&priv->offload);
+
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index 95ae740fc311..c6068a251fbe 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -476,7 +476,7 @@ static void esd_usb2_write_bulk_callback(struct urb *urb)
 	netif_trans_update(netdev);
 }
 
-static ssize_t show_firmware(struct device *d,
+static ssize_t firmware_show(struct device *d,
 			     struct device_attribute *attr, char *buf)
 {
 	struct usb_interface *intf = to_usb_interface(d);
@@ -487,9 +487,9 @@ static ssize_t show_firmware(struct device *d,
 		       (dev->version >> 8) & 0xf,
 		       dev->version & 0xff);
 }
-static DEVICE_ATTR(firmware, 0444, show_firmware, NULL);
+static DEVICE_ATTR_RO(firmware);
 
-static ssize_t show_hardware(struct device *d,
+static ssize_t hardware_show(struct device *d,
 			     struct device_attribute *attr, char *buf)
 {
 	struct usb_interface *intf = to_usb_interface(d);
@@ -500,9 +500,9 @@ static ssize_t show_hardware(struct device *d,
 		       (dev->version >> 24) & 0xf,
 		       (dev->version >> 16) & 0xff);
 }
-static DEVICE_ATTR(hardware, 0444, show_hardware, NULL);
+static DEVICE_ATTR_RO(hardware);
 
-static ssize_t show_nets(struct device *d,
+static ssize_t nets_show(struct device *d,
 			 struct device_attribute *attr, char *buf)
 {
 	struct usb_interface *intf = to_usb_interface(d);
@@ -510,7 +510,7 @@ static ssize_t show_nets(struct device *d,
 
 	return sprintf(buf, "%d", dev->net_count);
 }
-static DEVICE_ATTR(nets, 0444, show_nets, NULL);
+static DEVICE_ATTR_RO(nets);
 
 static int esd_usb2_send_msg(struct esd_usb2 *dev, struct esd_usb2_msg *msg)
 {
diff --git a/drivers/net/can/usb/etas_es58x/es581_4.c b/drivers/net/can/usb/etas_es58x/es581_4.c
index 1985f772fc3c..14e360c9f2c9 100644
--- a/drivers/net/can/usb/etas_es58x/es581_4.c
+++ b/drivers/net/can/usb/etas_es58x/es581_4.c
@@ -355,7 +355,7 @@ static int es581_4_tx_can_msg(struct es58x_priv *priv,
 		return -EMSGSIZE;
 
 	if (priv->tx_can_msg_cnt == 0) {
-		msg_len = 1; /* struct es581_4_bulk_tx_can_msg:num_can_msg */
+		msg_len = sizeof(es581_4_urb_cmd->bulk_tx_can_msg.num_can_msg);
 		es581_4_fill_urb_header(urb_cmd, ES581_4_CAN_COMMAND_TYPE,
 					ES581_4_CMD_ID_TX_MSG,
 					priv->channel_idx, msg_len);
@@ -371,8 +371,7 @@ static int es581_4_tx_can_msg(struct es58x_priv *priv,
 		return ret;
 
 	/* Fill message contents. */
-	tx_can_msg = (struct es581_4_tx_can_msg *)
-	    &es581_4_urb_cmd->bulk_tx_can_msg.tx_can_msg_buf[msg_len - 1];
+	tx_can_msg = (typeof(tx_can_msg))&es581_4_urb_cmd->raw_msg[msg_len];
 	put_unaligned_le32(es58x_get_raw_can_id(cf), &tx_can_msg->can_id);
 	put_unaligned_le32(priv->tx_head, &tx_can_msg->packet_idx);
 	put_unaligned_le16((u16)es58x_get_flags(skb), &tx_can_msg->flags);
diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c
index 8e9102482c52..96a13c770e4a 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_core.c
+++ b/drivers/net/can/usb/etas_es58x/es58x_core.c
@@ -19,7 +19,7 @@
 #include "es58x_core.h"
 
 #define DRV_VERSION "1.00"
-MODULE_AUTHOR("Mailhol Vincent <mailhol.vincent@wanadoo.fr>");
+MODULE_AUTHOR("Vincent Mailhol <mailhol.vincent@wanadoo.fr>");
 MODULE_AUTHOR("Arunachalam Santhanam <arunachalam.santhanam@in.bosch.com>");
 MODULE_DESCRIPTION("Socket CAN driver for ETAS ES58X USB adapters");
 MODULE_VERSION(DRV_VERSION);
@@ -70,7 +70,7 @@ MODULE_DEVICE_TABLE(usb, es58x_id_table);
  * bytes (the start of frame) are skipped and the CRC calculation
  * starts on the third byte.
  */
-#define ES58X_CRC_CALC_OFFSET 2
+#define ES58X_CRC_CALC_OFFSET sizeof_field(union es58x_urb_cmd, sof)
 
 /**
  * es58x_calculate_crc() - Compute the crc16 of a given URB.
@@ -2108,6 +2108,25 @@ static int es58x_init_netdev(struct es58x_device *es58x_dev, int channel_idx)
 }
 
 /**
+ * es58x_free_netdevs() - Release all network resources of the device.
+ * @es58x_dev: ES58X device.
+ */
+static void es58x_free_netdevs(struct es58x_device *es58x_dev)
+{
+	int i;
+
+	for (i = 0; i < es58x_dev->num_can_ch; i++) {
+		struct net_device *netdev = es58x_dev->netdev[i];
+
+		if (!netdev)
+			continue;
+		unregister_candev(netdev);
+		es58x_dev->netdev[i] = NULL;
+		free_candev(netdev);
+	}
+}
+
+/**
  * es58x_get_product_info() - Get the product information and print them.
  * @es58x_dev: ES58X device.
  *
@@ -2152,14 +2171,13 @@ static int es58x_get_product_info(struct es58x_device *es58x_dev)
 /**
  * es58x_init_es58x_dev() - Initialize the ES58X device.
  * @intf: USB interface.
- * @p_es58x_dev: pointer to the address of the ES58X device.
  * @driver_info: Quirks of the device.
  *
- * Return: zero on success, errno when any error occurs.
+ * Return: pointer to an ES58X device on success, error pointer when
+ *	any error occurs.
  */
-static int es58x_init_es58x_dev(struct usb_interface *intf,
-				struct es58x_device **p_es58x_dev,
-				kernel_ulong_t driver_info)
+static struct es58x_device *es58x_init_es58x_dev(struct usb_interface *intf,
+						 kernel_ulong_t driver_info)
 {
 	struct device *dev = &intf->dev;
 	struct es58x_device *es58x_dev;
@@ -2176,7 +2194,7 @@ static int es58x_init_es58x_dev(struct usb_interface *intf,
 	ret = usb_find_common_endpoints(intf->cur_altsetting, &ep_in, &ep_out,
 					NULL, NULL);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	if (driver_info & ES58X_FD_FAMILY) {
 		param = &es58x_fd_param;
@@ -2186,9 +2204,10 @@ static int es58x_init_es58x_dev(struct usb_interface *intf,
 		ops = &es581_4_ops;
 	}
 
-	es58x_dev = kzalloc(es58x_sizeof_es58x_device(param), GFP_KERNEL);
+	es58x_dev = devm_kzalloc(dev, es58x_sizeof_es58x_device(param),
+				 GFP_KERNEL);
 	if (!es58x_dev)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	es58x_dev->param = param;
 	es58x_dev->ops = ops;
@@ -2213,9 +2232,7 @@ static int es58x_init_es58x_dev(struct usb_interface *intf,
 					     ep_out->bEndpointAddress);
 	es58x_dev->rx_max_packet_size = le16_to_cpu(ep_in->wMaxPacketSize);
 
-	*p_es58x_dev = es58x_dev;
-
-	return 0;
+	return es58x_dev;
 }
 
 /**
@@ -2232,30 +2249,21 @@ static int es58x_probe(struct usb_interface *intf,
 	struct es58x_device *es58x_dev;
 	int ch_idx, ret;
 
-	ret = es58x_init_es58x_dev(intf, &es58x_dev, id->driver_info);
-	if (ret)
-		return ret;
+	es58x_dev = es58x_init_es58x_dev(intf, id->driver_info);
+	if (IS_ERR(es58x_dev))
+		return PTR_ERR(es58x_dev);
 
 	ret = es58x_get_product_info(es58x_dev);
 	if (ret)
-		goto cleanup_es58x_dev;
+		return ret;
 
 	for (ch_idx = 0; ch_idx < es58x_dev->num_can_ch; ch_idx++) {
 		ret = es58x_init_netdev(es58x_dev, ch_idx);
-		if (ret)
-			goto cleanup_candev;
-	}
-
-	return ret;
-
- cleanup_candev:
-	for (ch_idx = 0; ch_idx < es58x_dev->num_can_ch; ch_idx++)
-		if (es58x_dev->netdev[ch_idx]) {
-			unregister_candev(es58x_dev->netdev[ch_idx]);
-			free_candev(es58x_dev->netdev[ch_idx]);
+		if (ret) {
+			es58x_free_netdevs(es58x_dev);
+			return ret;
 		}
- cleanup_es58x_dev:
-	kfree(es58x_dev);
+	}
 
 	return ret;
 }
@@ -2270,24 +2278,12 @@ static int es58x_probe(struct usb_interface *intf,
 static void es58x_disconnect(struct usb_interface *intf)
 {
 	struct es58x_device *es58x_dev = usb_get_intfdata(intf);
-	struct net_device *netdev;
-	int i;
 
 	dev_info(&intf->dev, "Disconnecting %s %s\n",
 		 es58x_dev->udev->manufacturer, es58x_dev->udev->product);
 
-	for (i = 0; i < es58x_dev->num_can_ch; i++) {
-		netdev = es58x_dev->netdev[i];
-		if (!netdev)
-			continue;
-		unregister_candev(netdev);
-		es58x_dev->netdev[i] = NULL;
-		free_candev(netdev);
-	}
-
+	es58x_free_netdevs(es58x_dev);
 	es58x_free_urbs(es58x_dev);
-
-	kfree(es58x_dev);
 	usb_set_intfdata(intf, NULL);
 }
 
diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.h b/drivers/net/can/usb/etas_es58x/es58x_core.h
index fcf219e727bf..826a15871573 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_core.h
+++ b/drivers/net/can/usb/etas_es58x/es58x_core.h
@@ -287,7 +287,7 @@ struct es58x_priv {
  * @rx_urb_cmd_max_len: Maximum length of a RX URB command.
  * @fifo_mask: Bit mask to quickly convert the tx_tail and tx_head
  *	field of the struct es58x_priv into echo_skb
- *	indexes. Properties: @fifo_mask = echos_skb_max - 1 where
+ *	indexes. Properties: @fifo_mask = echo_skb_max - 1 where
  *	echo_skb_max must be a power of two. Also, echo_skb_max must
  *	not exceed the maximum size of the device internal TX FIFO
  *	length. This parameter is used to control the network queue
diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.c b/drivers/net/can/usb/etas_es58x/es58x_fd.c
index 1a2779d383a4..af042aa55f59 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_fd.c
+++ b/drivers/net/can/usb/etas_es58x/es58x_fd.c
@@ -357,8 +357,7 @@ static int es58x_fd_tx_can_msg(struct es58x_priv *priv,
 		return ret;
 
 	/* Fill message contents. */
-	tx_can_msg = (struct es58x_fd_tx_can_msg *)
-	    &es58x_fd_urb_cmd->tx_can_msg_buf[msg_len];
+	tx_can_msg = (typeof(tx_can_msg))&es58x_fd_urb_cmd->raw_msg[msg_len];
 	tx_can_msg->packet_idx = (u8)priv->tx_head;
 	put_unaligned_le32(es58x_get_raw_can_id(cf), &tx_can_msg->can_id);
 	tx_can_msg->flags = (u8)es58x_get_flags(skb);
@@ -463,9 +462,9 @@ static int es58x_fd_get_timestamp(struct es58x_device *es58x_dev)
 }
 
 /* Nominal bittiming constants for ES582.1 and ES584.1 as specified in
- * the microcontroller datasheet: "SAM E701/S70/V70/V71 Family"
- * section 49.6.8 "MCAN Nominal Bit Timing and Prescaler Register"
- * from Microchip.
+ * the microcontroller datasheet: "SAM E70/S70/V70/V71 Family" section
+ * 49.6.8 "MCAN Nominal Bit Timing and Prescaler Register" from
+ * Microchip.
  *
  * The values from the specification are the hardware register
  * values. To convert them to the functional values, all ranges were
@@ -484,8 +483,8 @@ static const struct can_bittiming_const es58x_fd_nom_bittiming_const = {
 };
 
 /* Data bittiming constants for ES582.1 and ES584.1 as specified in
- * the microcontroller datasheet: "SAM E701/S70/V70/V71 Family"
- * section 49.6.4 "MCAN Data Bit Timing and Prescaler Register" from
+ * the microcontroller datasheet: "SAM E70/S70/V70/V71 Family" section
+ * 49.6.4 "MCAN Data Bit Timing and Prescaler Register" from
  * Microchip.
  */
 static const struct can_bittiming_const es58x_fd_data_bittiming_const = {
@@ -501,9 +500,9 @@ static const struct can_bittiming_const es58x_fd_data_bittiming_const = {
 };
 
 /* Transmission Delay Compensation constants for ES582.1 and ES584.1
- * as specified in the microcontroller datasheet: "SAM
- * E701/S70/V70/V71 Family" section 49.6.15 "MCAN Transmitter Delay
- * Compensation Register" from Microchip.
+ * as specified in the microcontroller datasheet: "SAM E70/S70/V70/V71
+ * Family" section 49.6.15 "MCAN Transmitter Delay Compensation
+ * Register" from Microchip.
  */
 static const struct can_tdc_const es58x_tdc_const = {
 	.tdcv_max = 0, /* Manual mode not supported. */
diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.h b/drivers/net/can/usb/etas_es58x/es58x_fd.h
index ee18a87e40c0..a191891b8777 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_fd.h
+++ b/drivers/net/can/usb/etas_es58x/es58x_fd.h
@@ -96,23 +96,14 @@ struct es58x_fd_bittiming {
  * @ctrlmode: type enum es58x_fd_ctrlmode.
  * @canfd_enabled: boolean (0: Classical CAN, 1: CAN and/or CANFD).
  * @data_bittiming: Bittiming for flexible data-rate transmission.
- * @tdc_enabled: Transmitter Delay Compensation switch (0: disabled,
- *	1: enabled). On very high bitrates, the delay between when the
- *	bit is sent and received on the CANTX and CANRX pins of the
- *	transceiver start to be significant enough for errors to occur
- *	and thus need to be compensated.
- * @tdco: Transmitter Delay Compensation Offset. Offset value, in time
- *	quanta, defining the delay between the start of the bit
- *	reception on the CANRX pin of the transceiver and the SSP
- *	(Secondary Sample Point). Valid values: 0 to 127.
- * @tdcf: Transmitter Delay Compensation Filter window. Defines the
- *	minimum value for the SSP position, in time quanta. The
- *	feature is enabled when TDCF is configured to a value greater
- *	than TDCO. Valid values: 0 to 127.
+ * @tdc_enabled: Transmitter Delay Compensation switch (0: TDC is
+ *	disabled, 1: TDC is enabled).
+ * @tdco: Transmitter Delay Compensation Offset.
+ * @tdcf: Transmitter Delay Compensation Filter window.
  *
- * Please refer to the microcontroller datasheet: "SAM
- * E701/S70/V70/V71 Family" section 49 "Controller Area Network
- * (MCAN)" for additional information.
+ * Please refer to the microcontroller datasheet: "SAM E70/S70/V70/V71
+ * Family" section 49 "Controller Area Network (MCAN)" for additional
+ * information.
  */
 struct es58x_fd_tx_conf_msg {
 	struct es58x_fd_bittiming nominal_bittiming;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 899a3d21b77f..837b3fecd71e 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -63,6 +63,8 @@
 
 #define PCAN_USB_MSG_HEADER_LEN		2
 
+#define PCAN_USB_MSG_TX_CAN		2	/* Tx msg is a CAN frame */
+
 /* PCAN-USB adapter internal clock (MHz) */
 #define PCAN_USB_CRYSTAL_HZ		16000000
 
@@ -73,6 +75,10 @@
 #define PCAN_USB_STATUSLEN_RTR		(1 << 4)
 #define PCAN_USB_STATUSLEN_DLC		(0xf)
 
+/* PCAN-USB 4.1 CAN Id tx extended flags */
+#define PCAN_USB_TX_SRR			0x01	/* SJA1000 SRR command */
+#define PCAN_USB_TX_AT			0x02	/* SJA1000 AT command */
+
 /* PCAN-USB error flags */
 #define PCAN_USB_ERROR_TXFULL		0x01
 #define PCAN_USB_ERROR_RXQOVR		0x02
@@ -385,7 +391,8 @@ static int pcan_usb_get_device_id(struct peak_usb_device *dev, u32 *device_id)
 	if (err)
 		netdev_err(dev->netdev, "getting device id failure: %d\n", err);
 
-	*device_id = args[0];
+	else
+		*device_id = args[0];
 
 	return err;
 }
@@ -446,145 +453,65 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n,
 {
 	struct sk_buff *skb;
 	struct can_frame *cf;
-	enum can_state new_state;
+	enum can_state new_state = CAN_STATE_ERROR_ACTIVE;
 
 	/* ignore this error until 1st ts received */
 	if (n == PCAN_USB_ERROR_QOVR)
 		if (!mc->pdev->time_ref.tick_count)
 			return 0;
 
-	new_state = mc->pdev->dev.can.state;
-
-	switch (mc->pdev->dev.can.state) {
-	case CAN_STATE_ERROR_ACTIVE:
-		if (n & PCAN_USB_ERROR_BUS_LIGHT) {
-			new_state = CAN_STATE_ERROR_WARNING;
-			break;
-		}
-		fallthrough;
-
-	case CAN_STATE_ERROR_WARNING:
-		if (n & PCAN_USB_ERROR_BUS_HEAVY) {
-			new_state = CAN_STATE_ERROR_PASSIVE;
-			break;
-		}
-		if (n & PCAN_USB_ERROR_BUS_OFF) {
-			new_state = CAN_STATE_BUS_OFF;
-			break;
-		}
-		if (n & ~PCAN_USB_ERROR_BUS) {
-			/*
-			 * trick to bypass next comparison and process other
-			 * errors
-			 */
-			new_state = CAN_STATE_MAX;
-			break;
-		}
-		if ((n & PCAN_USB_ERROR_BUS_LIGHT) == 0) {
-			/* no error (back to active state) */
-			new_state = CAN_STATE_ERROR_ACTIVE;
-			break;
-		}
-		break;
-
-	case CAN_STATE_ERROR_PASSIVE:
-		if (n & PCAN_USB_ERROR_BUS_OFF) {
-			new_state = CAN_STATE_BUS_OFF;
-			break;
-		}
-		if (n & PCAN_USB_ERROR_BUS_LIGHT) {
-			new_state = CAN_STATE_ERROR_WARNING;
-			break;
-		}
-		if (n & ~PCAN_USB_ERROR_BUS) {
-			/*
-			 * trick to bypass next comparison and process other
-			 * errors
-			 */
-			new_state = CAN_STATE_MAX;
-			break;
-		}
-
-		if ((n & PCAN_USB_ERROR_BUS_HEAVY) == 0) {
-			/* no error (back to warning state) */
-			new_state = CAN_STATE_ERROR_WARNING;
-			break;
-		}
-		break;
-
-	default:
-		/* do nothing waiting for restart */
-		return 0;
-	}
-
-	/* donot post any error if current state didn't change */
-	if (mc->pdev->dev.can.state == new_state)
-		return 0;
-
 	/* allocate an skb to store the error frame */
 	skb = alloc_can_err_skb(mc->netdev, &cf);
-	if (!skb)
-		return -ENOMEM;
-
-	switch (new_state) {
-	case CAN_STATE_BUS_OFF:
-		cf->can_id |= CAN_ERR_BUSOFF;
-		mc->pdev->dev.can.can_stats.bus_off++;
-		can_bus_off(mc->netdev);
-		break;
-
-	case CAN_STATE_ERROR_PASSIVE:
-		cf->can_id |= CAN_ERR_CRTL;
-		cf->data[1] = (mc->pdev->bec.txerr > mc->pdev->bec.rxerr) ?
-				CAN_ERR_CRTL_TX_PASSIVE :
-				CAN_ERR_CRTL_RX_PASSIVE;
-		cf->data[6] = mc->pdev->bec.txerr;
-		cf->data[7] = mc->pdev->bec.rxerr;
-
-		mc->pdev->dev.can.can_stats.error_passive++;
-		break;
-
-	case CAN_STATE_ERROR_WARNING:
-		cf->can_id |= CAN_ERR_CRTL;
-		cf->data[1] = (mc->pdev->bec.txerr > mc->pdev->bec.rxerr) ?
-				CAN_ERR_CRTL_TX_WARNING :
-				CAN_ERR_CRTL_RX_WARNING;
-		cf->data[6] = mc->pdev->bec.txerr;
-		cf->data[7] = mc->pdev->bec.rxerr;
-
-		mc->pdev->dev.can.can_stats.error_warning++;
-		break;
 
-	case CAN_STATE_ERROR_ACTIVE:
-		cf->can_id |= CAN_ERR_CRTL;
-		cf->data[1] = CAN_ERR_CRTL_ACTIVE;
-
-		/* sync local copies of rxerr/txerr counters */
-		mc->pdev->bec.txerr = 0;
-		mc->pdev->bec.rxerr = 0;
-		break;
-
-	default:
-		/* CAN_STATE_MAX (trick to handle other errors) */
-		if (n & PCAN_USB_ERROR_TXQFULL)
-			netdev_dbg(mc->netdev, "device Tx queue full)\n");
-
-		if (n & PCAN_USB_ERROR_RXQOVR) {
-			netdev_dbg(mc->netdev, "data overrun interrupt\n");
+	if (n & PCAN_USB_ERROR_RXQOVR) {
+		/* data overrun interrupt */
+		netdev_dbg(mc->netdev, "data overrun interrupt\n");
+		mc->netdev->stats.rx_over_errors++;
+		mc->netdev->stats.rx_errors++;
+		if (cf) {
 			cf->can_id |= CAN_ERR_CRTL;
 			cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW;
-			mc->netdev->stats.rx_over_errors++;
-			mc->netdev->stats.rx_errors++;
 		}
+	}
 
-		cf->data[6] = mc->pdev->bec.txerr;
-		cf->data[7] = mc->pdev->bec.rxerr;
+	if (n & PCAN_USB_ERROR_TXQFULL)
+		netdev_dbg(mc->netdev, "device Tx queue full)\n");
 
-		new_state = mc->pdev->dev.can.state;
-		break;
+	if (n & PCAN_USB_ERROR_BUS_OFF) {
+		new_state = CAN_STATE_BUS_OFF;
+	} else if (n & PCAN_USB_ERROR_BUS_HEAVY) {
+		new_state = ((mc->pdev->bec.txerr >= 128) ||
+			     (mc->pdev->bec.rxerr >= 128)) ?
+				CAN_STATE_ERROR_PASSIVE :
+				CAN_STATE_ERROR_WARNING;
+	} else {
+		new_state = CAN_STATE_ERROR_ACTIVE;
 	}
 
-	mc->pdev->dev.can.state = new_state;
+	/* handle change of state */
+	if (new_state != mc->pdev->dev.can.state) {
+		enum can_state tx_state =
+			(mc->pdev->bec.txerr >= mc->pdev->bec.rxerr) ?
+				new_state : 0;
+		enum can_state rx_state =
+			(mc->pdev->bec.txerr <= mc->pdev->bec.rxerr) ?
+				new_state : 0;
+
+		can_change_state(mc->netdev, cf, tx_state, rx_state);
+
+		if (new_state == CAN_STATE_BUS_OFF) {
+			can_bus_off(mc->netdev);
+		} else if (cf && (cf->can_id & CAN_ERR_CRTL)) {
+			/* Supply TX/RX error counters in case of
+			 * controller error.
+			 */
+			cf->data[6] = mc->pdev->bec.txerr;
+			cf->data[7] = mc->pdev->bec.rxerr;
+		}
+	}
+
+	if (!skb)
+		return -ENOMEM;
 
 	if (status_len & PCAN_USB_STATUSLEN_TIMESTAMP) {
 		struct skb_shared_hwtstamps *hwts = skb_hwtstamps(skb);
@@ -706,6 +633,7 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len)
 	struct sk_buff *skb;
 	struct can_frame *cf;
 	struct skb_shared_hwtstamps *hwts;
+	u32 can_id_flags;
 
 	skb = alloc_can_skb(mc->netdev, &cf);
 	if (!skb)
@@ -715,13 +643,15 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len)
 		if ((mc->ptr + 4) > mc->end)
 			goto decode_failed;
 
-		cf->can_id = get_unaligned_le32(mc->ptr) >> 3 | CAN_EFF_FLAG;
+		can_id_flags = get_unaligned_le32(mc->ptr);
+		cf->can_id = can_id_flags >> 3 | CAN_EFF_FLAG;
 		mc->ptr += 4;
 	} else {
 		if ((mc->ptr + 2) > mc->end)
 			goto decode_failed;
 
-		cf->can_id = get_unaligned_le16(mc->ptr) >> 5;
+		can_id_flags = get_unaligned_le16(mc->ptr);
+		cf->can_id = can_id_flags >> 5;
 		mc->ptr += 2;
 	}
 
@@ -744,6 +674,10 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len)
 
 		memcpy(cf->data, mc->ptr, cf->len);
 		mc->ptr += rec_len;
+
+		/* Ignore next byte (client private id) if SRR bit is set */
+		if (can_id_flags & PCAN_USB_TX_SRR)
+			mc->ptr++;
 	}
 
 	/* convert timestamp into kernel time */
@@ -821,10 +755,11 @@ static int pcan_usb_encode_msg(struct peak_usb_device *dev, struct sk_buff *skb,
 	struct net_device *netdev = dev->netdev;
 	struct net_device_stats *stats = &netdev->stats;
 	struct can_frame *cf = (struct can_frame *)skb->data;
+	u32 can_id_flags = cf->can_id & CAN_ERR_MASK;
 	u8 *pc;
 
-	obuf[0] = 2;
-	obuf[1] = 1;
+	obuf[0] = PCAN_USB_MSG_TX_CAN;
+	obuf[1] = 1;	/* only one CAN frame is stored in the packet */
 
 	pc = obuf + PCAN_USB_MSG_HEADER_LEN;
 
@@ -839,12 +774,28 @@ static int pcan_usb_encode_msg(struct peak_usb_device *dev, struct sk_buff *skb,
 		*pc |= PCAN_USB_STATUSLEN_EXT_ID;
 		pc++;
 
-		put_unaligned_le32((cf->can_id & CAN_ERR_MASK) << 3, pc);
+		can_id_flags <<= 3;
+
+		if (dev->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
+			can_id_flags |= PCAN_USB_TX_SRR;
+
+		if (dev->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT)
+			can_id_flags |= PCAN_USB_TX_AT;
+
+		put_unaligned_le32(can_id_flags, pc);
 		pc += 4;
 	} else {
 		pc++;
 
-		put_unaligned_le16((cf->can_id & CAN_ERR_MASK) << 5, pc);
+		can_id_flags <<= 5;
+
+		if (dev->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
+			can_id_flags |= PCAN_USB_TX_SRR;
+
+		if (dev->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT)
+			can_id_flags |= PCAN_USB_TX_AT;
+
+		put_unaligned_le16(can_id_flags, pc);
 		pc += 2;
 	}
 
@@ -854,6 +805,10 @@ static int pcan_usb_encode_msg(struct peak_usb_device *dev, struct sk_buff *skb,
 		pc += cf->len;
 	}
 
+	/* SRR bit needs a writer id (useless here) */
+	if (can_id_flags & PCAN_USB_TX_SRR)
+		*pc++ = 0x80;
+
 	obuf[(*size)-1] = (u8)(stats->tx_packets & 0xff);
 
 	return 0;
@@ -928,6 +883,19 @@ static int pcan_usb_init(struct peak_usb_device *dev)
 		return err;
 	}
 
+	/* Since rev 4.1, PCAN-USB is able to make single-shot as well as
+	 * looped back frames.
+	 */
+	if (dev->device_rev >= 41) {
+		struct can_priv *priv = netdev_priv(dev->netdev);
+
+		priv->ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT |
+					    CAN_CTRLMODE_LOOPBACK;
+	} else {
+		dev_info(dev->netdev->dev.parent,
+			 "Firmware update available. Please contact support@peak-system.com\n");
+	}
+
 	dev_info(dev->netdev->dev.parent,
 		 "PEAK-System %s adapter hwrev %u serial %08X (%u channel)\n",
 		 pcan_usb.name, dev->device_rev, serial_number,
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index b23e3488695b..bd1417a66cbf 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -2016,15 +2016,6 @@ int b53_br_flags(struct dsa_switch *ds, int port,
 }
 EXPORT_SYMBOL(b53_br_flags);
 
-int b53_set_mrouter(struct dsa_switch *ds, int port, bool mrouter,
-		    struct netlink_ext_ack *extack)
-{
-	b53_port_set_mcast_flood(ds->priv, port, mrouter);
-
-	return 0;
-}
-EXPORT_SYMBOL(b53_set_mrouter);
-
 static bool b53_possible_cpu_port(struct dsa_switch *ds, int port)
 {
 	/* Broadcom switches will accept enabling Broadcom tags on the
@@ -2268,7 +2259,6 @@ static const struct dsa_switch_ops b53_switch_ops = {
 	.port_bridge_leave	= b53_br_leave,
 	.port_pre_bridge_flags	= b53_br_flags_pre,
 	.port_bridge_flags	= b53_br_flags,
-	.port_set_mrouter	= b53_set_mrouter,
 	.port_stp_state_set	= b53_br_set_stp_state,
 	.port_fast_age		= b53_br_fast_age,
 	.port_vlan_filtering	= b53_vlan_filtering,
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 82700a5714c1..9bf8319342b0 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -328,8 +328,6 @@ int b53_br_flags_pre(struct dsa_switch *ds, int port,
 int b53_br_flags(struct dsa_switch *ds, int port,
 		 struct switchdev_brport_flags flags,
 		 struct netlink_ext_ack *extack);
-int b53_set_mrouter(struct dsa_switch *ds, int port, bool mrouter,
-		    struct netlink_ext_ack *extack);
 int b53_setup_devlink_resources(struct dsa_switch *ds);
 void b53_port_event(struct dsa_switch *ds, int port);
 void b53_phylink_validate(struct dsa_switch *ds, int port,
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 3b018fcf4412..6ce9ec1283e0 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1199,7 +1199,6 @@ static const struct dsa_switch_ops bcm_sf2_ops = {
 	.port_pre_bridge_flags	= b53_br_flags_pre,
 	.port_bridge_flags	= b53_br_flags,
 	.port_stp_state_set	= b53_br_set_stp_state,
-	.port_set_mrouter	= b53_set_mrouter,
 	.port_fast_age		= b53_br_fast_age,
 	.port_vlan_filtering	= b53_vlan_filtering,
 	.port_vlan_add		= b53_vlan_add,
diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c
index 7062db6a083c..542cfc4ccb08 100644
--- a/drivers/net/dsa/hirschmann/hellcreek.c
+++ b/drivers/net/dsa/hirschmann/hellcreek.c
@@ -1345,6 +1345,7 @@ static int hellcreek_setup(struct dsa_switch *ds)
 	 * filtering setups are not supported.
 	 */
 	ds->vlan_filtering_is_global = true;
+	ds->needs_standalone_vlan_filtering = true;
 
 	/* Intercept _all_ PTP multicast traffic */
 	ret = hellcreek_setup_fdb(hellcreek);
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 632f0fcc5aa7..d0cba2d1cd68 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -367,8 +367,8 @@ mt7530_fdb_write(struct mt7530_priv *priv, u16 vid,
 	int i;
 
 	reg[1] |= vid & CVID_MASK;
-	if (vid > 1)
-		reg[1] |= ATA2_IVL;
+	reg[1] |= ATA2_IVL;
+	reg[1] |= ATA2_FID(FID_BRIDGED);
 	reg[2] |= (aging & AGE_TIMER_MASK) << AGE_TIMER;
 	reg[2] |= (port_mask & PORT_MAP_MASK) << PORT_MAP;
 	/* STATIC_ENT indicate that entry is static wouldn't
@@ -1022,6 +1022,10 @@ mt753x_cpu_port_enable(struct dsa_switch *ds, int port)
 	mt7530_write(priv, MT7530_PCR_P(port),
 		     PCR_MATRIX(dsa_user_ports(priv->ds)));
 
+	/* Set to fallback mode for independent VLAN learning */
+	mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
+		   MT7530_PORT_FALLBACK_MODE);
+
 	return 0;
 }
 
@@ -1144,7 +1148,8 @@ mt7530_stp_state_set(struct dsa_switch *ds, int port, u8 state)
 		break;
 	}
 
-	mt7530_rmw(priv, MT7530_SSP_P(port), FID_PST_MASK, stp_state);
+	mt7530_rmw(priv, MT7530_SSP_P(port), FID_PST_MASK(FID_BRIDGED),
+		   FID_PST(FID_BRIDGED, stp_state));
 }
 
 static int
@@ -1186,18 +1191,6 @@ mt7530_port_bridge_flags(struct dsa_switch *ds, int port,
 }
 
 static int
-mt7530_port_set_mrouter(struct dsa_switch *ds, int port, bool mrouter,
-			struct netlink_ext_ack *extack)
-{
-	struct mt7530_priv *priv = ds->priv;
-
-	mt7530_rmw(priv, MT7530_MFC, UNM_FFP(BIT(port)),
-		   mrouter ? UNM_FFP(BIT(port)) : 0);
-
-	return 0;
-}
-
-static int
 mt7530_port_bridge_join(struct dsa_switch *ds, int port,
 			struct net_device *bridge)
 {
@@ -1230,6 +1223,10 @@ mt7530_port_bridge_join(struct dsa_switch *ds, int port,
 			   PCR_MATRIX_MASK, PCR_MATRIX(port_bitmap));
 	priv->ports[port].pm |= PCR_MATRIX(port_bitmap);
 
+	/* Set to fallback mode for independent VLAN learning */
+	mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
+		   MT7530_PORT_FALLBACK_MODE);
+
 	mutex_unlock(&priv->reg_mutex);
 
 	return 0;
@@ -1242,15 +1239,22 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port)
 	bool all_user_ports_removed = true;
 	int i;
 
-	/* When a port is removed from the bridge, the port would be set up
-	 * back to the default as is at initial boot which is a VLAN-unaware
-	 * port.
+	/* This is called after .port_bridge_leave when leaving a VLAN-aware
+	 * bridge. Don't set standalone ports to fallback mode.
 	 */
-	mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
-		   MT7530_PORT_MATRIX_MODE);
-	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK,
+	if (dsa_to_port(ds, port)->bridge_dev)
+		mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
+			   MT7530_PORT_FALLBACK_MODE);
+
+	mt7530_rmw(priv, MT7530_PVC_P(port),
+		   VLAN_ATTR_MASK | PVC_EG_TAG_MASK | ACC_FRM_MASK,
 		   VLAN_ATTR(MT7530_VLAN_TRANSPARENT) |
-		   PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
+		   PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT) |
+		   MT7530_VLAN_ACC_ALL);
+
+	/* Set PVID to 0 */
+	mt7530_rmw(priv, MT7530_PPBV1_P(port), G0_PORT_VID_MASK,
+		   G0_PORT_VID_DEF);
 
 	for (i = 0; i < MT7530_NUM_PORTS; i++) {
 		if (dsa_is_user_port(ds, i) &&
@@ -1277,15 +1281,19 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port)
 	struct mt7530_priv *priv = ds->priv;
 
 	/* Trapped into security mode allows packet forwarding through VLAN
-	 * table lookup. CPU port is set to fallback mode to let untagged
-	 * frames pass through.
+	 * table lookup.
 	 */
-	if (dsa_is_cpu_port(ds, port))
-		mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
-			   MT7530_PORT_FALLBACK_MODE);
-	else
+	if (dsa_is_user_port(ds, port)) {
 		mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
 			   MT7530_PORT_SECURITY_MODE);
+		mt7530_rmw(priv, MT7530_PPBV1_P(port), G0_PORT_VID_MASK,
+			   G0_PORT_VID(priv->ports[port].pvid));
+
+		/* Only accept tagged frames if PVID is not set */
+		if (!priv->ports[port].pvid)
+			mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK,
+				   MT7530_VLAN_ACC_TAGGED);
+	}
 
 	/* Set the port as a user port which is to be able to recognize VID
 	 * from incoming packets before fetching entry within the VLAN table.
@@ -1308,11 +1316,8 @@ mt7530_port_bridge_leave(struct dsa_switch *ds, int port,
 		/* Remove this port from the port matrix of the other ports
 		 * in the same bridge. If the port is disabled, port matrix
 		 * is kept and not being setup until the port becomes enabled.
-		 * And the other port's port matrix cannot be broken when the
-		 * other port is still a VLAN-aware port.
 		 */
-		if (dsa_is_user_port(ds, i) && i != port &&
-		   !dsa_port_is_vlan_filtering(dsa_to_port(ds, i))) {
+		if (dsa_is_user_port(ds, i) && i != port) {
 			if (dsa_to_port(ds, i)->bridge_dev != bridge)
 				continue;
 			if (priv->ports[i].enable)
@@ -1330,6 +1335,13 @@ mt7530_port_bridge_leave(struct dsa_switch *ds, int port,
 			   PCR_MATRIX(BIT(MT7530_CPU_PORT)));
 	priv->ports[port].pm = PCR_MATRIX(BIT(MT7530_CPU_PORT));
 
+	/* When a port is removed from the bridge, the port would be set up
+	 * back to the default as is at initial boot which is a VLAN-unaware
+	 * port.
+	 */
+	mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
+		   MT7530_PORT_MATRIX_MODE);
+
 	mutex_unlock(&priv->reg_mutex);
 }
 
@@ -1512,7 +1524,8 @@ mt7530_hw_vlan_add(struct mt7530_priv *priv,
 	/* Validate the entry with independent learning, create egress tag per
 	 * VLAN and joining the port as one of the port members.
 	 */
-	val = IVL_MAC | VTAG_EN | PORT_MEM(new_members) | VLAN_VALID;
+	val = IVL_MAC | VTAG_EN | PORT_MEM(new_members) | FID(FID_BRIDGED) |
+	      VLAN_VALID;
 	mt7530_write(priv, MT7530_VAWD1, val);
 
 	/* Decide whether adding tag or not for those outgoing packets from the
@@ -1587,6 +1600,21 @@ mt7530_hw_vlan_update(struct mt7530_priv *priv, u16 vid,
 }
 
 static int
+mt7530_setup_vlan0(struct mt7530_priv *priv)
+{
+	u32 val;
+
+	/* Validate the entry with independent learning, keep the original
+	 * ingress tag attribute.
+	 */
+	val = IVL_MAC | EG_CON | PORT_MEM(MT7530_ALL_MEMBERS) | FID(FID_BRIDGED) |
+	      VLAN_VALID;
+	mt7530_write(priv, MT7530_VAWD1, val);
+
+	return mt7530_vlan_cmd(priv, MT7530_VTCR_WR_VID, 0);
+}
+
+static int
 mt7530_port_vlan_add(struct dsa_switch *ds, int port,
 		     const struct switchdev_obj_port_vlan *vlan,
 		     struct netlink_ext_ack *extack)
@@ -1602,9 +1630,28 @@ mt7530_port_vlan_add(struct dsa_switch *ds, int port,
 	mt7530_hw_vlan_update(priv, vlan->vid, &new_entry, mt7530_hw_vlan_add);
 
 	if (pvid) {
-		mt7530_rmw(priv, MT7530_PPBV1_P(port), G0_PORT_VID_MASK,
-			   G0_PORT_VID(vlan->vid));
 		priv->ports[port].pvid = vlan->vid;
+
+		/* Accept all frames if PVID is set */
+		mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK,
+			   MT7530_VLAN_ACC_ALL);
+
+		/* Only configure PVID if VLAN filtering is enabled */
+		if (dsa_port_is_vlan_filtering(dsa_to_port(ds, port)))
+			mt7530_rmw(priv, MT7530_PPBV1_P(port),
+				   G0_PORT_VID_MASK,
+				   G0_PORT_VID(vlan->vid));
+	} else if (vlan->vid && priv->ports[port].pvid == vlan->vid) {
+		/* This VLAN is overwritten without PVID, so unset it */
+		priv->ports[port].pvid = G0_PORT_VID_DEF;
+
+		/* Only accept tagged frames if the port is VLAN-aware */
+		if (dsa_port_is_vlan_filtering(dsa_to_port(ds, port)))
+			mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK,
+				   MT7530_VLAN_ACC_TAGGED);
+
+		mt7530_rmw(priv, MT7530_PPBV1_P(port), G0_PORT_VID_MASK,
+			   G0_PORT_VID_DEF);
 	}
 
 	mutex_unlock(&priv->reg_mutex);
@@ -1618,11 +1665,9 @@ mt7530_port_vlan_del(struct dsa_switch *ds, int port,
 {
 	struct mt7530_hw_vlan_entry target_entry;
 	struct mt7530_priv *priv = ds->priv;
-	u16 pvid;
 
 	mutex_lock(&priv->reg_mutex);
 
-	pvid = priv->ports[port].pvid;
 	mt7530_hw_vlan_entry_init(&target_entry, port, 0);
 	mt7530_hw_vlan_update(priv, vlan->vid, &target_entry,
 			      mt7530_hw_vlan_del);
@@ -1630,11 +1675,18 @@ mt7530_port_vlan_del(struct dsa_switch *ds, int port,
 	/* PVID is being restored to the default whenever the PVID port
 	 * is being removed from the VLAN.
 	 */
-	if (pvid == vlan->vid)
-		pvid = G0_PORT_VID_DEF;
+	if (priv->ports[port].pvid == vlan->vid) {
+		priv->ports[port].pvid = G0_PORT_VID_DEF;
+
+		/* Only accept tagged frames if the port is VLAN-aware */
+		if (dsa_port_is_vlan_filtering(dsa_to_port(ds, port)))
+			mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK,
+				   MT7530_VLAN_ACC_TAGGED);
+
+		mt7530_rmw(priv, MT7530_PPBV1_P(port), G0_PORT_VID_MASK,
+			   G0_PORT_VID_DEF);
+	}
 
-	mt7530_rmw(priv, MT7530_PPBV1_P(port), G0_PORT_VID_MASK, pvid);
-	priv->ports[port].pvid = pvid;
 
 	mutex_unlock(&priv->reg_mutex);
 
@@ -1718,15 +1770,7 @@ static enum dsa_tag_protocol
 mtk_get_tag_protocol(struct dsa_switch *ds, int port,
 		     enum dsa_tag_protocol mp)
 {
-	struct mt7530_priv *priv = ds->priv;
-
-	if (port != MT7530_CPU_PORT) {
-		dev_warn(priv->dev,
-			 "port not matched with tagging CPU port\n");
-		return DSA_TAG_PROTO_NONE;
-	} else {
-		return DSA_TAG_PROTO_MTK;
-	}
+	return DSA_TAG_PROTO_MTK;
 }
 
 #ifdef CONFIG_GPIOLIB
@@ -2055,6 +2099,7 @@ mt7530_setup(struct dsa_switch *ds)
 	 * as two netdev instances.
 	 */
 	dn = dsa_to_port(ds, MT7530_CPU_PORT)->master->dev.of_node->parent;
+	ds->assisted_learning_on_cpu_port = true;
 	ds->mtu_enforcement_ingress = true;
 
 	if (priv->id == ID_MT7530) {
@@ -2125,6 +2170,9 @@ mt7530_setup(struct dsa_switch *ds)
 		mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK,
 			   PCR_MATRIX_CLR);
 
+		/* Disable learning by default on all ports */
+		mt7530_set(priv, MT7530_PSC_P(i), SA_DIS);
+
 		if (dsa_is_cpu_port(ds, i)) {
 			ret = mt753x_cpu_port_enable(ds, i);
 			if (ret)
@@ -2132,14 +2180,20 @@ mt7530_setup(struct dsa_switch *ds)
 		} else {
 			mt7530_port_disable(ds, i);
 
-			/* Disable learning by default on all user ports */
-			mt7530_set(priv, MT7530_PSC_P(i), SA_DIS);
+			/* Set default PVID to 0 on all user ports */
+			mt7530_rmw(priv, MT7530_PPBV1_P(i), G0_PORT_VID_MASK,
+				   G0_PORT_VID_DEF);
 		}
 		/* Enable consistent egress tag */
 		mt7530_rmw(priv, MT7530_PVC_P(i), PVC_EG_TAG_MASK,
 			   PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 	}
 
+	/* Setup VLAN ID 0 for VLAN-unaware bridges */
+	ret = mt7530_setup_vlan0(priv);
+	if (ret)
+		return ret;
+
 	/* Setup port 5 */
 	priv->p5_intf_sel = P5_DISABLED;
 	interface = PHY_INTERFACE_MODE_NA;
@@ -2290,6 +2344,9 @@ mt7531_setup(struct dsa_switch *ds)
 		mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK,
 			   PCR_MATRIX_CLR);
 
+		/* Disable learning by default on all ports */
+		mt7530_set(priv, MT7530_PSC_P(i), SA_DIS);
+
 		mt7530_set(priv, MT7531_DBG_CNT(i), MT7531_DIS_CLR);
 
 		if (dsa_is_cpu_port(ds, i)) {
@@ -2299,8 +2356,9 @@ mt7531_setup(struct dsa_switch *ds)
 		} else {
 			mt7530_port_disable(ds, i);
 
-			/* Disable learning by default on all user ports */
-			mt7530_set(priv, MT7530_PSC_P(i), SA_DIS);
+			/* Set default PVID to 0 on all user ports */
+			mt7530_rmw(priv, MT7530_PPBV1_P(i), G0_PORT_VID_MASK,
+				   G0_PORT_VID_DEF);
 		}
 
 		/* Enable consistent egress tag */
@@ -2308,6 +2366,12 @@ mt7531_setup(struct dsa_switch *ds)
 			   PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 	}
 
+	/* Setup VLAN ID 0 for VLAN-unaware bridges */
+	ret = mt7530_setup_vlan0(priv);
+	if (ret)
+		return ret;
+
+	ds->assisted_learning_on_cpu_port = true;
 	ds->mtu_enforcement_ingress = true;
 
 	/* Flush the FDB table */
@@ -3061,7 +3125,6 @@ static const struct dsa_switch_ops mt7530_switch_ops = {
 	.port_stp_state_set	= mt7530_stp_state_set,
 	.port_pre_bridge_flags	= mt7530_port_pre_bridge_flags,
 	.port_bridge_flags	= mt7530_port_bridge_flags,
-	.port_set_mrouter	= mt7530_port_set_mrouter,
 	.port_bridge_join	= mt7530_port_bridge_join,
 	.port_bridge_leave	= mt7530_port_bridge_leave,
 	.port_fdb_add		= mt7530_port_fdb_add,
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index b19b389ff10a..91508e2feef9 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -80,6 +80,7 @@ enum mt753x_bpdu_port_fw {
 #define  STATIC_ENT			3
 #define MT7530_ATA2			0x78
 #define  ATA2_IVL			BIT(15)
+#define  ATA2_FID(x)			(((x) & 0x7) << 12)
 
 /* Register for address table write data */
 #define MT7530_ATWD			0x7c
@@ -144,15 +145,24 @@ enum mt7530_vlan_cmd {
 #define  PORT_STAG			BIT(31)
 /* Independent VLAN Learning */
 #define  IVL_MAC			BIT(30)
+/* Egress Tag Consistent */
+#define  EG_CON				BIT(29)
 /* Per VLAN Egress Tag Control */
 #define  VTAG_EN			BIT(28)
 /* VLAN Member Control */
 #define  PORT_MEM(x)			(((x) & 0xff) << 16)
+/* Filter ID */
+#define  FID(x)				(((x) & 0x7) << 1)
 /* VLAN Entry Valid */
 #define  VLAN_VALID			BIT(0)
 #define  PORT_MEM_SHFT			16
 #define  PORT_MEM_MASK			0xff
 
+enum mt7530_fid {
+	FID_STANDALONE = 0,
+	FID_BRIDGED = 1,
+};
+
 #define MT7530_VAWD2			0x98
 /* Egress Tag Control */
 #define  ETAG_CTRL_P(p, x)		(((x) & 0x3) << ((p) << 1))
@@ -179,8 +189,8 @@ enum mt7530_vlan_egress_attr {
 
 /* Register for port STP state control */
 #define MT7530_SSP_P(x)			(0x2000 + ((x) * 0x100))
-#define  FID_PST(x)			((x) & 0x3)
-#define  FID_PST_MASK			FID_PST(0x3)
+#define  FID_PST(fid, state)		(((state) & 0x3) << ((fid) * 2))
+#define  FID_PST_MASK(fid)		FID_PST(fid, 0x3)
 
 enum mt7530_stp_state {
 	MT7530_STP_DISABLED = 0,
@@ -230,6 +240,7 @@ enum mt7530_port_mode {
 #define  PVC_EG_TAG_MASK		PVC_EG_TAG(7)
 #define  VLAN_ATTR(x)			(((x) & 0x3) << 6)
 #define  VLAN_ATTR_MASK			VLAN_ATTR(3)
+#define  ACC_FRM_MASK			GENMASK(1, 0)
 
 enum mt7530_vlan_port_eg_tag {
 	MT7530_VLAN_EG_DISABLED = 0,
@@ -241,13 +252,19 @@ enum mt7530_vlan_port_attr {
 	MT7530_VLAN_TRANSPARENT = 3,
 };
 
+enum mt7530_vlan_port_acc_frm {
+	MT7530_VLAN_ACC_ALL = 0,
+	MT7530_VLAN_ACC_TAGGED = 1,
+	MT7530_VLAN_ACC_UNTAGGED = 2,
+};
+
 #define  STAG_VPID			(((x) & 0xffff) << 16)
 
 /* Register for port port-and-protocol based vlan 1 control */
 #define MT7530_PPBV1_P(x)		(0x2014 + ((x) * 0x100))
 #define  G0_PORT_VID(x)			(((x) & 0xfff) << 0)
 #define  G0_PORT_VID_MASK		G0_PORT_VID(0xfff)
-#define  G0_PORT_VID_DEF		G0_PORT_VID(1)
+#define  G0_PORT_VID_DEF		G0_PORT_VID(0)
 
 /* Register for port MAC control register */
 #define MT7530_PMCR_P(x)		(0x3000 + ((x) * 0x100))
diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig
index 634a48e6616b..7a2445a34eb7 100644
--- a/drivers/net/dsa/mv88e6xxx/Kconfig
+++ b/drivers/net/dsa/mv88e6xxx/Kconfig
@@ -2,6 +2,7 @@
 config NET_DSA_MV88E6XXX
 	tristate "Marvell 88E6xxx Ethernet switch fabric support"
 	depends on NET_DSA
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select IRQ_DOMAIN
 	select NET_DSA_TAG_EDSA
 	select NET_DSA_TAG_DSA
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 272b0535d946..c45ca2473743 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -1221,14 +1221,36 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port)
 	bool found = false;
 	u16 pvlan;
 
-	list_for_each_entry(dp, &dst->ports, list) {
-		if (dp->ds->index == dev && dp->index == port) {
+	/* dev is a physical switch */
+	if (dev <= dst->last_switch) {
+		list_for_each_entry(dp, &dst->ports, list) {
+			if (dp->ds->index == dev && dp->index == port) {
+				/* dp might be a DSA link or a user port, so it
+				 * might or might not have a bridge_dev
+				 * pointer. Use the "found" variable for both
+				 * cases.
+				 */
+				br = dp->bridge_dev;
+				found = true;
+				break;
+			}
+		}
+	/* dev is a virtual bridge */
+	} else {
+		list_for_each_entry(dp, &dst->ports, list) {
+			if (dp->bridge_num < 0)
+				continue;
+
+			if (dp->bridge_num + 1 + dst->last_switch != dev)
+				continue;
+
+			br = dp->bridge_dev;
 			found = true;
 			break;
 		}
 	}
 
-	/* Prevent frames from unknown switch or port */
+	/* Prevent frames from unknown switch or virtual bridge */
 	if (!found)
 		return 0;
 
@@ -1236,7 +1258,6 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port)
 	if (dp->type == DSA_PORT_TYPE_CPU || dp->type == DSA_PORT_TYPE_DSA)
 		return mv88e6xxx_port_mask(chip);
 
-	br = dp->bridge_dev;
 	pvlan = 0;
 
 	/* Frames from user ports can egress any local DSA links and CPU ports,
@@ -2422,6 +2443,44 @@ static void mv88e6xxx_crosschip_bridge_leave(struct dsa_switch *ds,
 	mv88e6xxx_reg_unlock(chip);
 }
 
+/* Treat the software bridge as a virtual single-port switch behind the
+ * CPU and map in the PVT. First dst->last_switch elements are taken by
+ * physical switches, so start from beyond that range.
+ */
+static int mv88e6xxx_map_virtual_bridge_to_pvt(struct dsa_switch *ds,
+					       int bridge_num)
+{
+	u8 dev = bridge_num + ds->dst->last_switch + 1;
+	struct mv88e6xxx_chip *chip = ds->priv;
+	int err;
+
+	mv88e6xxx_reg_lock(chip);
+	err = mv88e6xxx_pvt_map(chip, dev, 0);
+	mv88e6xxx_reg_unlock(chip);
+
+	return err;
+}
+
+static int mv88e6xxx_bridge_tx_fwd_offload(struct dsa_switch *ds, int port,
+					   struct net_device *br,
+					   int bridge_num)
+{
+	return mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge_num);
+}
+
+static void mv88e6xxx_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port,
+					      struct net_device *br,
+					      int bridge_num)
+{
+	int err;
+
+	err = mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge_num);
+	if (err) {
+		dev_err(ds->dev, "failed to remap cross-chip Port VLAN: %pe\n",
+			ERR_PTR(err));
+	}
+}
+
 static int mv88e6xxx_software_reset(struct mv88e6xxx_chip *chip)
 {
 	if (chip->info->ops->reset)
@@ -3025,6 +3084,15 @@ static int mv88e6xxx_setup(struct dsa_switch *ds)
 	chip->ds = ds;
 	ds->slave_mii_bus = mv88e6xxx_default_mdio_bus(chip);
 
+	/* Since virtual bridges are mapped in the PVT, the number we support
+	 * depends on the physical switch topology. We need to let DSA figure
+	 * that out and therefore we cannot set this at dsa_register_switch()
+	 * time.
+	 */
+	if (mv88e6xxx_has_pvt(chip))
+		ds->num_fwd_offloading_bridges = MV88E6XXX_MAX_PVT_SWITCHES -
+						 ds->dst->last_switch - 1;
+
 	mv88e6xxx_reg_lock(chip);
 
 	if (chip->info->ops->setup_errata) {
@@ -5729,7 +5797,6 @@ static int mv88e6xxx_port_bridge_flags(struct dsa_switch *ds, int port,
 				       struct netlink_ext_ack *extack)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
-	bool do_fast_age = false;
 	int err = -EOPNOTSUPP;
 
 	mv88e6xxx_reg_lock(chip);
@@ -5741,9 +5808,6 @@ static int mv88e6xxx_port_bridge_flags(struct dsa_switch *ds, int port,
 		err = mv88e6xxx_port_set_assoc_vector(chip, port, pav);
 		if (err)
 			goto out;
-
-		if (!learning)
-			do_fast_age = true;
 	}
 
 	if (flags.mask & BR_FLOOD) {
@@ -5775,26 +5839,6 @@ static int mv88e6xxx_port_bridge_flags(struct dsa_switch *ds, int port,
 out:
 	mv88e6xxx_reg_unlock(chip);
 
-	if (do_fast_age)
-		mv88e6xxx_port_fast_age(ds, port);
-
-	return err;
-}
-
-static int mv88e6xxx_port_set_mrouter(struct dsa_switch *ds, int port,
-				      bool mrouter,
-				      struct netlink_ext_ack *extack)
-{
-	struct mv88e6xxx_chip *chip = ds->priv;
-	int err;
-
-	if (!chip->info->ops->port_set_mcast_flood)
-		return -EOPNOTSUPP;
-
-	mv88e6xxx_reg_lock(chip);
-	err = chip->info->ops->port_set_mcast_flood(chip, port, mrouter);
-	mv88e6xxx_reg_unlock(chip);
-
 	return err;
 }
 
@@ -6099,7 +6143,6 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = {
 	.port_bridge_leave	= mv88e6xxx_port_bridge_leave,
 	.port_pre_bridge_flags	= mv88e6xxx_port_pre_bridge_flags,
 	.port_bridge_flags	= mv88e6xxx_port_bridge_flags,
-	.port_set_mrouter	= mv88e6xxx_port_set_mrouter,
 	.port_stp_state_set	= mv88e6xxx_port_stp_state_set,
 	.port_fast_age		= mv88e6xxx_port_fast_age,
 	.port_vlan_filtering	= mv88e6xxx_port_vlan_filtering,
@@ -6128,6 +6171,8 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = {
 	.crosschip_lag_change	= mv88e6xxx_crosschip_lag_change,
 	.crosschip_lag_join	= mv88e6xxx_crosschip_lag_join,
 	.crosschip_lag_leave	= mv88e6xxx_crosschip_lag_leave,
+	.port_bridge_tx_fwd_offload = mv88e6xxx_bridge_tx_fwd_offload,
+	.port_bridge_tx_fwd_unoffload = mv88e6xxx_bridge_tx_fwd_unoffload,
 };
 
 static int mv88e6xxx_register_switch(struct mv88e6xxx_chip *chip)
diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig
index 932b6b6fe817..9948544ba1c4 100644
--- a/drivers/net/dsa/ocelot/Kconfig
+++ b/drivers/net/dsa/ocelot/Kconfig
@@ -5,6 +5,7 @@ config NET_DSA_MSCC_FELIX
 	depends on NET_VENDOR_MICROSEMI
 	depends on NET_VENDOR_FREESCALE
 	depends on HAS_IOMEM
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select MSCC_OCELOT_SWITCH_LIB
 	select NET_DSA_TAG_OCELOT_8021Q
 	select NET_DSA_TAG_OCELOT
@@ -19,6 +20,7 @@ config NET_DSA_MSCC_SEVILLE
 	depends on NET_DSA
 	depends on NET_VENDOR_MICROSEMI
 	depends on HAS_IOMEM
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select MSCC_OCELOT_SWITCH_LIB
 	select NET_DSA_TAG_OCELOT_8021Q
 	select NET_DSA_TAG_OCELOT
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index a2a15919b960..3656e67af789 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -231,11 +231,6 @@ static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid)
 	return 0;
 }
 
-static const struct dsa_8021q_ops felix_tag_8021q_ops = {
-	.vlan_add	= felix_tag_8021q_vlan_add,
-	.vlan_del	= felix_tag_8021q_vlan_del,
-};
-
 /* Alternatively to using the NPI functionality, that same hardware MAC
  * connected internally to the enetc or fman DSA master can be configured to
  * use the software-defined tag_8021q frame format. As far as the hardware is
@@ -425,29 +420,18 @@ static int felix_setup_tag_8021q(struct dsa_switch *ds, int cpu)
 	ocelot_rmw_rix(ocelot, 0, cpu_flood, ANA_PGID_PGID, PGID_MC);
 	ocelot_rmw_rix(ocelot, 0, cpu_flood, ANA_PGID_PGID, PGID_BC);
 
-	felix->dsa_8021q_ctx = kzalloc(sizeof(*felix->dsa_8021q_ctx),
-				       GFP_KERNEL);
-	if (!felix->dsa_8021q_ctx)
-		return -ENOMEM;
-
-	felix->dsa_8021q_ctx->ops = &felix_tag_8021q_ops;
-	felix->dsa_8021q_ctx->proto = htons(ETH_P_8021AD);
-	felix->dsa_8021q_ctx->ds = ds;
-
-	err = dsa_8021q_setup(felix->dsa_8021q_ctx, true);
+	err = dsa_tag_8021q_register(ds, htons(ETH_P_8021AD));
 	if (err)
-		goto out_free_dsa_8021_ctx;
+		return err;
 
 	err = felix_setup_mmio_filtering(felix);
 	if (err)
-		goto out_teardown_dsa_8021q;
+		goto out_tag_8021q_unregister;
 
 	return 0;
 
-out_teardown_dsa_8021q:
-	dsa_8021q_setup(felix->dsa_8021q_ctx, false);
-out_free_dsa_8021_ctx:
-	kfree(felix->dsa_8021q_ctx);
+out_tag_8021q_unregister:
+	dsa_tag_8021q_unregister(ds);
 	return err;
 }
 
@@ -462,11 +446,7 @@ static void felix_teardown_tag_8021q(struct dsa_switch *ds, int cpu)
 		dev_err(ds->dev, "felix_teardown_mmio_filtering returned %d",
 			err);
 
-	err = dsa_8021q_setup(felix->dsa_8021q_ctx, false);
-	if (err)
-		dev_err(ds->dev, "dsa_8021q_setup returned %d", err);
-
-	kfree(felix->dsa_8021q_ctx);
+	dsa_tag_8021q_unregister(ds);
 
 	for (port = 0; port < ds->num_ports; port++) {
 		if (dsa_is_unused_port(ds, port))
@@ -762,7 +742,8 @@ static int felix_lag_change(struct dsa_switch *ds, int port)
 }
 
 static int felix_vlan_prepare(struct dsa_switch *ds, int port,
-			      const struct switchdev_obj_port_vlan *vlan)
+			      const struct switchdev_obj_port_vlan *vlan,
+			      struct netlink_ext_ack *extack)
 {
 	struct ocelot *ocelot = ds->priv;
 	u16 flags = vlan->flags;
@@ -780,7 +761,8 @@ static int felix_vlan_prepare(struct dsa_switch *ds, int port,
 
 	return ocelot_vlan_prepare(ocelot, port, vlan->vid,
 				   flags & BRIDGE_VLAN_INFO_PVID,
-				   flags & BRIDGE_VLAN_INFO_UNTAGGED);
+				   flags & BRIDGE_VLAN_INFO_UNTAGGED,
+				   extack);
 }
 
 static int felix_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
@@ -788,7 +770,7 @@ static int felix_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
 {
 	struct ocelot *ocelot = ds->priv;
 
-	return ocelot_port_vlan_filtering(ocelot, port, enabled);
+	return ocelot_port_vlan_filtering(ocelot, port, enabled, extack);
 }
 
 static int felix_vlan_add(struct dsa_switch *ds, int port,
@@ -799,7 +781,7 @@ static int felix_vlan_add(struct dsa_switch *ds, int port,
 	u16 flags = vlan->flags;
 	int err;
 
-	err = felix_vlan_prepare(ds, port, vlan);
+	err = felix_vlan_prepare(ds, port, vlan, extack);
 	if (err)
 		return err;
 
@@ -816,23 +798,6 @@ static int felix_vlan_del(struct dsa_switch *ds, int port,
 	return ocelot_vlan_del(ocelot, port, vlan->vid);
 }
 
-static int felix_port_enable(struct dsa_switch *ds, int port,
-			     struct phy_device *phy)
-{
-	struct ocelot *ocelot = ds->priv;
-
-	ocelot_port_enable(ocelot, port, phy);
-
-	return 0;
-}
-
-static void felix_port_disable(struct dsa_switch *ds, int port)
-{
-	struct ocelot *ocelot = ds->priv;
-
-	return ocelot_port_disable(ocelot, port);
-}
-
 static void felix_phylink_validate(struct dsa_switch *ds, int port,
 				   unsigned long *supported,
 				   struct phylink_link_state *state)
@@ -861,25 +826,9 @@ static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port,
 					phy_interface_t interface)
 {
 	struct ocelot *ocelot = ds->priv;
-	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	int err;
-
-	ocelot_port_rmwl(ocelot_port, 0, DEV_MAC_ENA_CFG_RX_ENA,
-			 DEV_MAC_ENA_CFG);
 
-	ocelot_fields_write(ocelot, port, QSYS_SWITCH_PORT_MODE_PORT_ENA, 0);
-
-	err = ocelot_port_flush(ocelot, port);
-	if (err)
-		dev_err(ocelot->dev, "failed to flush port %d: %d\n",
-			port, err);
-
-	/* Put the port in reset. */
-	ocelot_port_writel(ocelot_port,
-			   DEV_CLOCK_CFG_MAC_TX_RST |
-			   DEV_CLOCK_CFG_MAC_RX_RST |
-			   DEV_CLOCK_CFG_LINK_SPEED(OCELOT_SPEED_1000),
-			   DEV_CLOCK_CFG);
+	ocelot_phylink_mac_link_down(ocelot, port, link_an_mode, interface,
+				     FELIX_MAC_QUIRKS);
 }
 
 static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port,
@@ -890,75 +839,11 @@ static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port,
 				      bool tx_pause, bool rx_pause)
 {
 	struct ocelot *ocelot = ds->priv;
-	struct ocelot_port *ocelot_port = ocelot->ports[port];
 	struct felix *felix = ocelot_to_felix(ocelot);
-	u32 mac_fc_cfg;
-
-	/* Take port out of reset by clearing the MAC_TX_RST, MAC_RX_RST and
-	 * PORT_RST bits in DEV_CLOCK_CFG. Note that the way this system is
-	 * integrated is that the MAC speed is fixed and it's the PCS who is
-	 * performing the rate adaptation, so we have to write "1000Mbps" into
-	 * the LINK_SPEED field of DEV_CLOCK_CFG (which is also its default
-	 * value).
-	 */
-	ocelot_port_writel(ocelot_port,
-			   DEV_CLOCK_CFG_LINK_SPEED(OCELOT_SPEED_1000),
-			   DEV_CLOCK_CFG);
-
-	switch (speed) {
-	case SPEED_10:
-		mac_fc_cfg = SYS_MAC_FC_CFG_FC_LINK_SPEED(3);
-		break;
-	case SPEED_100:
-		mac_fc_cfg = SYS_MAC_FC_CFG_FC_LINK_SPEED(2);
-		break;
-	case SPEED_1000:
-	case SPEED_2500:
-		mac_fc_cfg = SYS_MAC_FC_CFG_FC_LINK_SPEED(1);
-		break;
-	default:
-		dev_err(ocelot->dev, "Unsupported speed on port %d: %d\n",
-			port, speed);
-		return;
-	}
-
-	/* handle Rx pause in all cases, with 2500base-X this is used for rate
-	 * adaptation.
-	 */
-	mac_fc_cfg |= SYS_MAC_FC_CFG_RX_FC_ENA;
-
-	if (tx_pause)
-		mac_fc_cfg |= SYS_MAC_FC_CFG_TX_FC_ENA |
-			      SYS_MAC_FC_CFG_PAUSE_VAL_CFG(0xffff) |
-			      SYS_MAC_FC_CFG_FC_LATENCY_CFG(0x7) |
-			      SYS_MAC_FC_CFG_ZERO_PAUSE_ENA;
-
-	/* Flow control. Link speed is only used here to evaluate the time
-	 * specification in incoming pause frames.
-	 */
-	ocelot_write_rix(ocelot, mac_fc_cfg, SYS_MAC_FC_CFG, port);
-
-	ocelot_write_rix(ocelot, 0, ANA_POL_FLOWC, port);
-
-	ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, tx_pause);
-
-	/* Undo the effects of felix_phylink_mac_link_down:
-	 * enable MAC module
-	 */
-	ocelot_port_writel(ocelot_port, DEV_MAC_ENA_CFG_RX_ENA |
-			   DEV_MAC_ENA_CFG_TX_ENA, DEV_MAC_ENA_CFG);
-
-	/* Enable receiving frames on the port, and activate auto-learning of
-	 * MAC addresses.
-	 */
-	ocelot_write_gix(ocelot, ANA_PORT_PORT_CFG_LEARNAUTO |
-			 ANA_PORT_PORT_CFG_RECV_ENA |
-			 ANA_PORT_PORT_CFG_PORTID_VAL(port),
-			 ANA_PORT_PORT_CFG, port);
 
-	/* Core: Enable port for frame transfer */
-	ocelot_fields_write(ocelot, port,
-			    QSYS_SWITCH_PORT_MODE_PORT_ENA, 1);
+	ocelot_phylink_mac_link_up(ocelot, port, phydev, link_an_mode,
+				   interface, speed, duplex, tx_pause, rx_pause,
+				   FELIX_MAC_QUIRKS);
 
 	if (felix->info->port_sched_speed_set)
 		felix->info->port_sched_speed_set(ocelot, port, speed);
@@ -1635,8 +1520,6 @@ const struct dsa_switch_ops felix_switch_ops = {
 	.phylink_mac_config		= felix_phylink_mac_config,
 	.phylink_mac_link_down		= felix_phylink_mac_link_down,
 	.phylink_mac_link_up		= felix_phylink_mac_link_up,
-	.port_enable			= felix_port_enable,
-	.port_disable			= felix_port_disable,
 	.port_fdb_dump			= felix_fdb_dump,
 	.port_fdb_add			= felix_fdb_add,
 	.port_fdb_del			= felix_fdb_del,
@@ -1679,6 +1562,8 @@ const struct dsa_switch_ops felix_switch_ops = {
 	.port_mrp_del			= felix_mrp_del,
 	.port_mrp_add_ring_role		= felix_mrp_add_ring_role,
 	.port_mrp_del_ring_role		= felix_mrp_del_ring_role,
+	.tag_8021q_vlan_add		= felix_tag_8021q_vlan_add,
+	.tag_8021q_vlan_del		= felix_tag_8021q_vlan_del,
 };
 
 struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port)
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index 4d96cad815d5..5854bab43327 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -5,6 +5,7 @@
 #define _MSCC_FELIX_H
 
 #define ocelot_to_felix(o)		container_of((o), struct felix, ocelot)
+#define FELIX_MAC_QUIRKS		OCELOT_QUIRK_PCS_PERFORMS_RATE_ADAPTATION
 
 /* Platform-specific information */
 struct felix_info {
@@ -60,7 +61,6 @@ struct felix {
 	struct lynx_pcs			**pcs;
 	resource_size_t			switch_base;
 	resource_size_t			imdio_base;
-	struct dsa_8021q_context	*dsa_8021q_ctx;
 	enum dsa_tag_protocol		tag_proto;
 };
 
diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig
index b29d41e5e1e7..1291bba3f3b6 100644
--- a/drivers/net/dsa/sja1105/Kconfig
+++ b/drivers/net/dsa/sja1105/Kconfig
@@ -2,6 +2,7 @@
 config NET_DSA_SJA1105
 tristate "NXP SJA1105 Ethernet switch family support"
 	depends on NET_DSA && SPI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select NET_DSA_TAG_SJA1105
 	select PCS_XPCS
 	select PACKING
diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
index 221c7abdef0e..5e5d24e7c02b 100644
--- a/drivers/net/dsa/sja1105/sja1105.h
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -115,12 +115,6 @@ struct sja1105_info {
 	const struct sja1105_dynamic_table_ops *dyn_ops;
 	const struct sja1105_table_ops *static_ops;
 	const struct sja1105_regs *regs;
-	/* Both E/T and P/Q/R/S have quirks when it comes to popping the S-Tag
-	 * from double-tagged frames. E/T will pop it only when it's equal to
-	 * TPID from the General Parameters Table, while P/Q/R/S will only
-	 * pop it when it's equal to TPID2.
-	 */
-	u16 qinq_tpid;
 	bool can_limit_mcast_flood;
 	int (*reset_cmd)(struct dsa_switch *ds);
 	int (*setup_rgmii_delay)(const void *ctx, int port);
@@ -226,28 +220,13 @@ struct sja1105_flow_block {
 	int num_virtual_links;
 };
 
-struct sja1105_bridge_vlan {
-	struct list_head list;
-	int port;
-	u16 vid;
-	bool pvid;
-	bool untagged;
-};
-
-enum sja1105_vlan_state {
-	SJA1105_VLAN_UNAWARE,
-	SJA1105_VLAN_BEST_EFFORT,
-	SJA1105_VLAN_FILTERING_FULL,
-};
-
 struct sja1105_private {
 	struct sja1105_static_config static_config;
 	bool rgmii_rx_delay[SJA1105_MAX_NUM_PORTS];
 	bool rgmii_tx_delay[SJA1105_MAX_NUM_PORTS];
 	phy_interface_t phy_mode[SJA1105_MAX_NUM_PORTS];
 	bool fixed_link[SJA1105_MAX_NUM_PORTS];
-	bool best_effort_vlan_filtering;
-	unsigned long learn_ena;
+	bool vlan_aware;
 	unsigned long ucast_egress_floods;
 	unsigned long bcast_egress_floods;
 	const struct sja1105_info *info;
@@ -255,16 +234,14 @@ struct sja1105_private {
 	struct gpio_desc *reset_gpio;
 	struct spi_device *spidev;
 	struct dsa_switch *ds;
-	struct list_head dsa_8021q_vlans;
-	struct list_head bridge_vlans;
+	u16 bridge_pvid[SJA1105_MAX_NUM_PORTS];
+	u16 tag_8021q_pvid[SJA1105_MAX_NUM_PORTS];
 	struct sja1105_flow_block flow_block;
 	struct sja1105_port ports[SJA1105_MAX_NUM_PORTS];
 	/* Serializes transmission of management frames so that
 	 * the switch doesn't confuse them with one another.
 	 */
 	struct mutex mgmt_lock;
-	struct dsa_8021q_context *dsa_8021q_ctx;
-	enum sja1105_vlan_state vlan_state;
 	struct devlink_region **regions;
 	struct sja1105_cbs_entry *cbs;
 	struct mii_bus *mdio_base_t1;
@@ -311,10 +288,6 @@ int sja1110_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val);
 /* From sja1105_devlink.c */
 int sja1105_devlink_setup(struct dsa_switch *ds);
 void sja1105_devlink_teardown(struct dsa_switch *ds);
-int sja1105_devlink_param_get(struct dsa_switch *ds, u32 id,
-			      struct devlink_param_gset_ctx *ctx);
-int sja1105_devlink_param_set(struct dsa_switch *ds, u32 id,
-			      struct devlink_param_gset_ctx *ctx);
 int sja1105_devlink_info_get(struct dsa_switch *ds,
 			     struct devlink_info_req *req,
 			     struct netlink_ext_ack *extack);
diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c
index b6a4a16b8c7e..05c7f4ca3b1a 100644
--- a/drivers/net/dsa/sja1105/sja1105_devlink.c
+++ b/drivers/net/dsa/sja1105/sja1105_devlink.c
@@ -115,105 +115,6 @@ static void sja1105_teardown_devlink_regions(struct dsa_switch *ds)
 	kfree(priv->regions);
 }
 
-static int sja1105_best_effort_vlan_filtering_get(struct sja1105_private *priv,
-						  bool *be_vlan)
-{
-	*be_vlan = priv->best_effort_vlan_filtering;
-
-	return 0;
-}
-
-static int sja1105_best_effort_vlan_filtering_set(struct sja1105_private *priv,
-						  bool be_vlan)
-{
-	struct dsa_switch *ds = priv->ds;
-	bool vlan_filtering;
-	int port;
-	int rc;
-
-	priv->best_effort_vlan_filtering = be_vlan;
-
-	rtnl_lock();
-	for (port = 0; port < ds->num_ports; port++) {
-		struct dsa_port *dp;
-
-		if (!dsa_is_user_port(ds, port))
-			continue;
-
-		dp = dsa_to_port(ds, port);
-		vlan_filtering = dsa_port_is_vlan_filtering(dp);
-
-		rc = sja1105_vlan_filtering(ds, port, vlan_filtering, NULL);
-		if (rc)
-			break;
-	}
-	rtnl_unlock();
-
-	return rc;
-}
-
-enum sja1105_devlink_param_id {
-	SJA1105_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
-	SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING,
-};
-
-int sja1105_devlink_param_get(struct dsa_switch *ds, u32 id,
-			      struct devlink_param_gset_ctx *ctx)
-{
-	struct sja1105_private *priv = ds->priv;
-	int err;
-
-	switch (id) {
-	case SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING:
-		err = sja1105_best_effort_vlan_filtering_get(priv,
-							     &ctx->val.vbool);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		break;
-	}
-
-	return err;
-}
-
-int sja1105_devlink_param_set(struct dsa_switch *ds, u32 id,
-			      struct devlink_param_gset_ctx *ctx)
-{
-	struct sja1105_private *priv = ds->priv;
-	int err;
-
-	switch (id) {
-	case SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING:
-		err = sja1105_best_effort_vlan_filtering_set(priv,
-							     ctx->val.vbool);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		break;
-	}
-
-	return err;
-}
-
-static const struct devlink_param sja1105_devlink_params[] = {
-	DSA_DEVLINK_PARAM_DRIVER(SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING,
-				 "best_effort_vlan_filtering",
-				 DEVLINK_PARAM_TYPE_BOOL,
-				 BIT(DEVLINK_PARAM_CMODE_RUNTIME)),
-};
-
-static int sja1105_setup_devlink_params(struct dsa_switch *ds)
-{
-	return dsa_devlink_params_register(ds, sja1105_devlink_params,
-					   ARRAY_SIZE(sja1105_devlink_params));
-}
-
-static void sja1105_teardown_devlink_params(struct dsa_switch *ds)
-{
-	dsa_devlink_params_unregister(ds, sja1105_devlink_params,
-				      ARRAY_SIZE(sja1105_devlink_params));
-}
-
 int sja1105_devlink_info_get(struct dsa_switch *ds,
 			     struct devlink_info_req *req,
 			     struct netlink_ext_ack *extack)
@@ -233,23 +134,10 @@ int sja1105_devlink_info_get(struct dsa_switch *ds,
 
 int sja1105_devlink_setup(struct dsa_switch *ds)
 {
-	int rc;
-
-	rc = sja1105_setup_devlink_params(ds);
-	if (rc)
-		return rc;
-
-	rc = sja1105_setup_devlink_regions(ds);
-	if (rc < 0) {
-		sja1105_teardown_devlink_params(ds);
-		return rc;
-	}
-
-	return 0;
+	return sja1105_setup_devlink_regions(ds);
 }
 
 void sja1105_devlink_teardown(struct dsa_switch *ds)
 {
-	sja1105_teardown_devlink_params(ds);
 	sja1105_teardown_devlink_regions(ds);
 }
diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
index 147709131c13..f2049f52833c 100644
--- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
+++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
@@ -1355,14 +1355,14 @@ u8 sja1105et_fdb_hash(struct sja1105_private *priv, const u8 *addr, u16 vid)
 {
 	struct sja1105_l2_lookup_params_entry *l2_lookup_params =
 		priv->static_config.tables[BLK_IDX_L2_LOOKUP_PARAMS].entries;
-	u64 poly_koopman = l2_lookup_params->poly;
+	u64 input, poly_koopman = l2_lookup_params->poly;
 	/* Convert polynomial from Koopman to 'normal' notation */
 	u8 poly = (u8)(1 + (poly_koopman << 1));
-	u64 vlanid = l2_lookup_params->shared_learn ? 0 : vid;
-	u64 input = (vlanid << 48) | ether_addr_to_u64(addr);
 	u8 crc = 0; /* seed */
 	int i;
 
+	input = ((u64)vid << 48) | ether_addr_to_u64(addr);
+
 	/* Mask the eight bytes starting from MSB one at a time */
 	for (i = 56; i >= 0; i -= 8) {
 		u8 byte = (input & (0xffull << i)) >> i;
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 49eb0ac41b7d..2f8cc6686c38 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -26,9 +26,6 @@
 #include "sja1105_tas.h"
 
 #define SJA1105_UNKNOWN_MULTICAST	0x010000000000ull
-#define SJA1105_DEFAULT_VLAN		(VLAN_N_VID - 1)
-
-static const struct dsa_switch_ops sja1105_switch_ops;
 
 static void sja1105_hw_reset(struct gpio_desc *gpio, unsigned int pulse_len,
 			     unsigned int startup_delay)
@@ -57,6 +54,93 @@ static bool sja1105_can_forward(struct sja1105_l2_forwarding_entry *l2_fwd,
 	return !!(l2_fwd[from].reach_port & BIT(to));
 }
 
+static int sja1105_is_vlan_configured(struct sja1105_private *priv, u16 vid)
+{
+	struct sja1105_vlan_lookup_entry *vlan;
+	int count, i;
+
+	vlan = priv->static_config.tables[BLK_IDX_VLAN_LOOKUP].entries;
+	count = priv->static_config.tables[BLK_IDX_VLAN_LOOKUP].entry_count;
+
+	for (i = 0; i < count; i++)
+		if (vlan[i].vlanid == vid)
+			return i;
+
+	/* Return an invalid entry index if not found */
+	return -1;
+}
+
+static int sja1105_drop_untagged(struct dsa_switch *ds, int port, bool drop)
+{
+	struct sja1105_private *priv = ds->priv;
+	struct sja1105_mac_config_entry *mac;
+
+	mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
+
+	if (mac[port].drpuntag == drop)
+		return 0;
+
+	mac[port].drpuntag = drop;
+
+	return sja1105_dynamic_config_write(priv, BLK_IDX_MAC_CONFIG, port,
+					    &mac[port], true);
+}
+
+static int sja1105_pvid_apply(struct sja1105_private *priv, int port, u16 pvid)
+{
+	struct sja1105_mac_config_entry *mac;
+
+	mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
+
+	if (mac[port].vlanid == pvid)
+		return 0;
+
+	mac[port].vlanid = pvid;
+
+	return sja1105_dynamic_config_write(priv, BLK_IDX_MAC_CONFIG, port,
+					    &mac[port], true);
+}
+
+static int sja1105_commit_pvid(struct dsa_switch *ds, int port)
+{
+	struct dsa_port *dp = dsa_to_port(ds, port);
+	struct sja1105_private *priv = ds->priv;
+	struct sja1105_vlan_lookup_entry *vlan;
+	bool drop_untagged = false;
+	int match, rc;
+	u16 pvid;
+
+	if (dp->bridge_dev && br_vlan_enabled(dp->bridge_dev))
+		pvid = priv->bridge_pvid[port];
+	else
+		pvid = priv->tag_8021q_pvid[port];
+
+	rc = sja1105_pvid_apply(priv, port, pvid);
+	if (rc)
+		return rc;
+
+	/* Only force dropping of untagged packets when the port is under a
+	 * VLAN-aware bridge. When the tag_8021q pvid is used, we are
+	 * deliberately removing the RX VLAN from the port's VMEMB_PORT list,
+	 * to prevent DSA tag spoofing from the link partner. Untagged packets
+	 * are the only ones that should be received with tag_8021q, so
+	 * definitely don't drop them.
+	 */
+	if (pvid == priv->bridge_pvid[port]) {
+		vlan = priv->static_config.tables[BLK_IDX_VLAN_LOOKUP].entries;
+
+		match = sja1105_is_vlan_configured(priv, pvid);
+
+		if (match < 0 || !(vlan[match].vmemb_port & BIT(port)))
+			drop_untagged = true;
+	}
+
+	if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
+		drop_untagged = true;
+
+	return sja1105_drop_untagged(ds, port, drop_untagged);
+}
+
 static int sja1105_init_mac_settings(struct sja1105_private *priv)
 {
 	struct sja1105_mac_config_entry default_mac = {
@@ -101,7 +185,7 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv)
 	struct sja1105_mac_config_entry *mac;
 	struct dsa_switch *ds = priv->ds;
 	struct sja1105_table *table;
-	int i;
+	struct dsa_port *dp;
 
 	table = &priv->static_config.tables[BLK_IDX_MAC_CONFIG];
 
@@ -120,14 +204,27 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv)
 
 	mac = table->entries;
 
-	for (i = 0; i < ds->num_ports; i++) {
-		mac[i] = default_mac;
+	list_for_each_entry(dp, &ds->dst->ports, list) {
+		if (dp->ds != ds)
+			continue;
+
+		mac[dp->index] = default_mac;
 
 		/* Let sja1105_bridge_stp_state_set() keep address learning
-		 * enabled for the CPU port.
+		 * enabled for the DSA ports. CPU ports use software-assisted
+		 * learning to ensure that only FDB entries belonging to the
+		 * bridge are learned, and that they are learned towards all
+		 * CPU ports in a cross-chip topology if multiple CPU ports
+		 * exist.
+		 */
+		if (dsa_port_is_dsa(dp))
+			dp->learning = true;
+
+		/* Disallow untagged packets from being received on the
+		 * CPU and DSA ports.
 		 */
-		if (dsa_is_cpu_port(ds, i))
-			priv->learn_ena |= BIT(i);
+		if (dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))
+			mac[dp->index].drpuntag = true;
 	}
 
 	return 0;
@@ -378,8 +475,6 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv)
 	table->entry_count = 1;
 
 	for (port = 0; port < ds->num_ports; port++) {
-		struct sja1105_bridge_vlan *v;
-
 		if (dsa_is_unused_port(ds, port))
 			continue;
 
@@ -387,22 +482,10 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv)
 		pvid.vlan_bc |= BIT(port);
 		pvid.tag_port &= ~BIT(port);
 
-		v = kzalloc(sizeof(*v), GFP_KERNEL);
-		if (!v)
-			return -ENOMEM;
-
-		v->port = port;
-		v->vid = SJA1105_DEFAULT_VLAN;
-		v->untagged = true;
-		if (dsa_is_cpu_port(ds, port))
-			v->pvid = true;
-		list_add(&v->list, &priv->dsa_8021q_vlans);
-
-		v = kmemdup(v, sizeof(*v), GFP_KERNEL);
-		if (!v)
-			return -ENOMEM;
-
-		list_add(&v->list, &priv->bridge_vlans);
+		if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) {
+			priv->tag_8021q_pvid[port] = SJA1105_DEFAULT_VLAN;
+			priv->bridge_pvid[port] = SJA1105_DEFAULT_VLAN;
+		}
 	}
 
 	((struct sja1105_vlan_lookup_entry *)table->entries)[0] = pvid;
@@ -413,8 +496,11 @@ static int sja1105_init_l2_forwarding(struct sja1105_private *priv)
 {
 	struct sja1105_l2_forwarding_entry *l2fwd;
 	struct dsa_switch *ds = priv->ds;
+	struct dsa_switch_tree *dst;
 	struct sja1105_table *table;
-	int i, j;
+	struct dsa_link *dl;
+	int port, tc;
+	int from, to;
 
 	table = &priv->static_config.tables[BLK_IDX_L2_FORWARDING];
 
@@ -432,47 +518,109 @@ static int sja1105_init_l2_forwarding(struct sja1105_private *priv)
 
 	l2fwd = table->entries;
 
-	/* First 5 entries define the forwarding rules */
-	for (i = 0; i < ds->num_ports; i++) {
-		unsigned int upstream = dsa_upstream_port(priv->ds, i);
+	/* First 5 entries in the L2 Forwarding Table define the forwarding
+	 * rules and the VLAN PCP to ingress queue mapping.
+	 * Set up the ingress queue mapping first.
+	 */
+	for (port = 0; port < ds->num_ports; port++) {
+		if (dsa_is_unused_port(ds, port))
+			continue;
+
+		for (tc = 0; tc < SJA1105_NUM_TC; tc++)
+			l2fwd[port].vlan_pmap[tc] = tc;
+	}
 
-		if (dsa_is_unused_port(ds, i))
+	/* Then manage the forwarding domain for user ports. These can forward
+	 * only to the always-on domain (CPU port and DSA links)
+	 */
+	for (from = 0; from < ds->num_ports; from++) {
+		if (!dsa_is_user_port(ds, from))
 			continue;
 
-		for (j = 0; j < SJA1105_NUM_TC; j++)
-			l2fwd[i].vlan_pmap[j] = j;
+		for (to = 0; to < ds->num_ports; to++) {
+			if (!dsa_is_cpu_port(ds, to) &&
+			    !dsa_is_dsa_port(ds, to))
+				continue;
 
-		/* All ports start up with egress flooding enabled,
-		 * including the CPU port.
-		 */
-		priv->ucast_egress_floods |= BIT(i);
-		priv->bcast_egress_floods |= BIT(i);
+			l2fwd[from].bc_domain |= BIT(to);
+			l2fwd[from].fl_domain |= BIT(to);
 
-		if (i == upstream)
+			sja1105_port_allow_traffic(l2fwd, from, to, true);
+		}
+	}
+
+	/* Then manage the forwarding domain for DSA links and CPU ports (the
+	 * always-on domain). These can send packets to any enabled port except
+	 * themselves.
+	 */
+	for (from = 0; from < ds->num_ports; from++) {
+		if (!dsa_is_cpu_port(ds, from) && !dsa_is_dsa_port(ds, from))
 			continue;
 
-		sja1105_port_allow_traffic(l2fwd, i, upstream, true);
-		sja1105_port_allow_traffic(l2fwd, upstream, i, true);
+		for (to = 0; to < ds->num_ports; to++) {
+			if (dsa_is_unused_port(ds, to))
+				continue;
 
-		l2fwd[i].bc_domain = BIT(upstream);
-		l2fwd[i].fl_domain = BIT(upstream);
+			if (from == to)
+				continue;
 
-		l2fwd[upstream].bc_domain |= BIT(i);
-		l2fwd[upstream].fl_domain |= BIT(i);
+			l2fwd[from].bc_domain |= BIT(to);
+			l2fwd[from].fl_domain |= BIT(to);
+
+			sja1105_port_allow_traffic(l2fwd, from, to, true);
+		}
+	}
+
+	/* In odd topologies ("H" connections where there is a DSA link to
+	 * another switch which also has its own CPU port), TX packets can loop
+	 * back into the system (they are flooded from CPU port 1 to the DSA
+	 * link, and from there to CPU port 2). Prevent this from happening by
+	 * cutting RX from DSA links towards our CPU port, if the remote switch
+	 * has its own CPU port and therefore doesn't need ours for network
+	 * stack termination.
+	 */
+	dst = ds->dst;
+
+	list_for_each_entry(dl, &dst->rtable, list) {
+		if (dl->dp->ds != ds || dl->link_dp->cpu_dp == dl->dp->cpu_dp)
+			continue;
+
+		from = dl->dp->index;
+		to = dsa_upstream_port(ds, from);
+
+		dev_warn(ds->dev,
+			 "H topology detected, cutting RX from DSA link %d to CPU port %d to prevent TX packet loops\n",
+			 from, to);
+
+		sja1105_port_allow_traffic(l2fwd, from, to, false);
+
+		l2fwd[from].bc_domain &= ~BIT(to);
+		l2fwd[from].fl_domain &= ~BIT(to);
+	}
+
+	/* Finally, manage the egress flooding domain. All ports start up with
+	 * flooding enabled, including the CPU port and DSA links.
+	 */
+	for (port = 0; port < ds->num_ports; port++) {
+		if (dsa_is_unused_port(ds, port))
+			continue;
+
+		priv->ucast_egress_floods |= BIT(port);
+		priv->bcast_egress_floods |= BIT(port);
 	}
 
 	/* Next 8 entries define VLAN PCP mapping from ingress to egress.
 	 * Create a one-to-one mapping.
 	 */
-	for (i = 0; i < SJA1105_NUM_TC; i++) {
-		for (j = 0; j < ds->num_ports; j++) {
-			if (dsa_is_unused_port(ds, j))
+	for (tc = 0; tc < SJA1105_NUM_TC; tc++) {
+		for (port = 0; port < ds->num_ports; port++) {
+			if (dsa_is_unused_port(ds, port))
 				continue;
 
-			l2fwd[ds->num_ports + i].vlan_pmap[j] = i;
+			l2fwd[ds->num_ports + tc].vlan_pmap[port] = tc;
 		}
 
-		l2fwd[ds->num_ports + i].type_egrpcp2outputq = true;
+		l2fwd[ds->num_ports + tc].type_egrpcp2outputq = true;
 	}
 
 	return 0;
@@ -551,18 +699,11 @@ void sja1105_frame_memory_partitioning(struct sja1105_private *priv)
 {
 	struct sja1105_l2_forwarding_params_entry *l2_fwd_params;
 	struct sja1105_vl_forwarding_params_entry *vl_fwd_params;
-	int max_mem = priv->info->max_frame_mem;
 	struct sja1105_table *table;
 
-	/* VLAN retagging is implemented using a loopback port that consumes
-	 * frame buffers. That leaves less for us.
-	 */
-	if (priv->vlan_state == SJA1105_VLAN_BEST_EFFORT)
-		max_mem -= SJA1105_FRAME_MEMORY_RETAGGING_OVERHEAD;
-
 	table = &priv->static_config.tables[BLK_IDX_L2_FORWARDING_PARAMS];
 	l2_fwd_params = table->entries;
-	l2_fwd_params->part_spc[0] = max_mem;
+	l2_fwd_params->part_spc[0] = SJA1105_MAX_FRAME_MEMORY;
 
 	/* If we have any critical-traffic virtual links, we need to reserve
 	 * some frame buffer memory for them. At the moment, hardcode the value
@@ -634,6 +775,72 @@ static void sja1110_select_tdmaconfigidx(struct sja1105_private *priv)
 	general_params->tdmaconfigidx = tdmaconfigidx;
 }
 
+static int sja1105_init_topology(struct sja1105_private *priv,
+				 struct sja1105_general_params_entry *general_params)
+{
+	struct dsa_switch *ds = priv->ds;
+	int port;
+
+	/* The host port is the destination for traffic matching mac_fltres1
+	 * and mac_fltres0 on all ports except itself. Default to an invalid
+	 * value.
+	 */
+	general_params->host_port = ds->num_ports;
+
+	/* Link-local traffic received on casc_port will be forwarded
+	 * to host_port without embedding the source port and device ID
+	 * info in the destination MAC address, and no RX timestamps will be
+	 * taken either (presumably because it is a cascaded port and a
+	 * downstream SJA switch already did that).
+	 * To disable the feature, we need to do different things depending on
+	 * switch generation. On SJA1105 we need to set an invalid port, while
+	 * on SJA1110 which support multiple cascaded ports, this field is a
+	 * bitmask so it must be left zero.
+	 */
+	if (!priv->info->multiple_cascade_ports)
+		general_params->casc_port = ds->num_ports;
+
+	for (port = 0; port < ds->num_ports; port++) {
+		bool is_upstream = dsa_is_upstream_port(ds, port);
+		bool is_dsa_link = dsa_is_dsa_port(ds, port);
+
+		/* Upstream ports can be dedicated CPU ports or
+		 * upstream-facing DSA links
+		 */
+		if (is_upstream) {
+			if (general_params->host_port == ds->num_ports) {
+				general_params->host_port = port;
+			} else {
+				dev_err(ds->dev,
+					"Port %llu is already a host port, configuring %d as one too is not supported\n",
+					general_params->host_port, port);
+				return -EINVAL;
+			}
+		}
+
+		/* Cascade ports are downstream-facing DSA links */
+		if (is_dsa_link && !is_upstream) {
+			if (priv->info->multiple_cascade_ports) {
+				general_params->casc_port |= BIT(port);
+			} else if (general_params->casc_port == ds->num_ports) {
+				general_params->casc_port = port;
+			} else {
+				dev_err(ds->dev,
+					"Port %llu is already a cascade port, configuring %d as one too is not supported\n",
+					general_params->casc_port, port);
+				return -EINVAL;
+			}
+		}
+	}
+
+	if (general_params->host_port == ds->num_ports) {
+		dev_err(ds->dev, "No host port configured\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int sja1105_init_general_params(struct sja1105_private *priv)
 {
 	struct sja1105_general_params_entry default_general_params = {
@@ -652,12 +859,6 @@ static int sja1105_init_general_params(struct sja1105_private *priv)
 		.mac_flt0    = SJA1105_LINKLOCAL_FILTER_B_MASK,
 		.incl_srcpt0 = false,
 		.send_meta0  = false,
-		/* The destination for traffic matching mac_fltres1 and
-		 * mac_fltres0 on all ports except host_port. Such traffic
-		 * receieved on host_port itself would be dropped, except
-		 * by installing a temporary 'management route'
-		 */
-		.host_port = priv->ds->num_ports,
 		/* Default to an invalid value */
 		.mirr_port = priv->ds->num_ports,
 		/* No TTEthernet */
@@ -677,16 +878,12 @@ static int sja1105_init_general_params(struct sja1105_private *priv)
 		.header_type = ETH_P_SJA1110,
 	};
 	struct sja1105_general_params_entry *general_params;
-	struct dsa_switch *ds = priv->ds;
 	struct sja1105_table *table;
-	int port;
+	int rc;
 
-	for (port = 0; port < ds->num_ports; port++) {
-		if (dsa_is_cpu_port(ds, port)) {
-			default_general_params.host_port = port;
-			break;
-		}
-	}
+	rc = sja1105_init_topology(priv, &default_general_params);
+	if (rc)
+		return rc;
 
 	table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS];
 
@@ -709,19 +906,6 @@ static int sja1105_init_general_params(struct sja1105_private *priv)
 
 	sja1110_select_tdmaconfigidx(priv);
 
-	/* Link-local traffic received on casc_port will be forwarded
-	 * to host_port without embedding the source port and device ID
-	 * info in the destination MAC address, and no RX timestamps will be
-	 * taken either (presumably because it is a cascaded port and a
-	 * downstream SJA switch already did that).
-	 * To disable the feature, we need to do different things depending on
-	 * switch generation. On SJA1105 we need to set an invalid port, while
-	 * on SJA1110 which support multiple cascaded ports, this field is a
-	 * bitmask so it must be left zero.
-	 */
-	if (!priv->info->multiple_cascade_ports)
-		general_params->casc_port = ds->num_ports;
-
 	return 0;
 }
 
@@ -849,7 +1033,7 @@ static int sja1105_init_l2_policing(struct sja1105_private *priv)
 	for (port = 0; port < ds->num_ports; port++) {
 		int mtu = VLAN_ETH_FRAME_LEN + ETH_FCS_LEN;
 
-		if (dsa_is_cpu_port(priv->ds, port))
+		if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
 			mtu += VLAN_HLEN;
 
 		policing[port].smax = 65535; /* Burst size in bytes */
@@ -1568,18 +1752,6 @@ static int sja1105_fdb_add(struct dsa_switch *ds, int port,
 {
 	struct sja1105_private *priv = ds->priv;
 
-	/* dsa_8021q is in effect when the bridge's vlan_filtering isn't,
-	 * so the switch still does some VLAN processing internally.
-	 * But Shared VLAN Learning (SVL) is also active, and it will take
-	 * care of autonomous forwarding between the unique pvid's of each
-	 * port.  Here we just make sure that users can't add duplicate FDB
-	 * entries when in this mode - the actual VID doesn't matter except
-	 * for what gets printed in 'bridge fdb show'.  In the case of zero,
-	 * no VID gets printed at all.
-	 */
-	if (priv->vlan_state != SJA1105_VLAN_FILTERING_FULL)
-		vid = 0;
-
 	return priv->info->fdb_add_cmd(ds, port, addr, vid);
 }
 
@@ -1588,9 +1760,6 @@ static int sja1105_fdb_del(struct dsa_switch *ds, int port,
 {
 	struct sja1105_private *priv = ds->priv;
 
-	if (priv->vlan_state != SJA1105_VLAN_FILTERING_FULL)
-		vid = 0;
-
 	return priv->info->fdb_del_cmd(ds, port, addr, vid);
 }
 
@@ -1633,7 +1802,7 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port,
 		u64_to_ether_addr(l2_lookup.macaddr, macaddr);
 
 		/* We need to hide the dsa_8021q VLANs from the user. */
-		if (priv->vlan_state == SJA1105_VLAN_UNAWARE)
+		if (!priv->vlan_aware)
 			l2_lookup.vlanid = 0;
 		rc = cb(macaddr, l2_lookup.vlanid, l2_lookup.lockeds, data);
 		if (rc)
@@ -1642,6 +1811,46 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port,
 	return 0;
 }
 
+static void sja1105_fast_age(struct dsa_switch *ds, int port)
+{
+	struct sja1105_private *priv = ds->priv;
+	int i;
+
+	for (i = 0; i < SJA1105_MAX_L2_LOOKUP_COUNT; i++) {
+		struct sja1105_l2_lookup_entry l2_lookup = {0};
+		u8 macaddr[ETH_ALEN];
+		int rc;
+
+		rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP,
+						 i, &l2_lookup);
+		/* No fdb entry at i, not an issue */
+		if (rc == -ENOENT)
+			continue;
+		if (rc) {
+			dev_err(ds->dev, "Failed to read FDB: %pe\n",
+				ERR_PTR(rc));
+			return;
+		}
+
+		if (!(l2_lookup.destports & BIT(port)))
+			continue;
+
+		/* Don't delete static FDB entries */
+		if (l2_lookup.lockeds)
+			continue;
+
+		u64_to_ether_addr(l2_lookup.macaddr, macaddr);
+
+		rc = sja1105_fdb_del(ds, port, macaddr, l2_lookup.vlanid);
+		if (rc) {
+			dev_err(ds->dev,
+				"Failed to delete FDB entry %pM vid %lld: %pe\n",
+				macaddr, l2_lookup.vlanid, ERR_PTR(rc));
+			return;
+		}
+	}
+}
+
 static int sja1105_mdb_add(struct dsa_switch *ds, int port,
 			   const struct switchdev_obj_port_mdb *mdb)
 {
@@ -1740,12 +1949,17 @@ static int sja1105_bridge_member(struct dsa_switch *ds, int port,
 	if (rc)
 		return rc;
 
+	rc = sja1105_commit_pvid(ds, port);
+	if (rc)
+		return rc;
+
 	return sja1105_manage_flood_domains(priv);
 }
 
 static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port,
 					 u8 state)
 {
+	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct sja1105_private *priv = ds->priv;
 	struct sja1105_mac_config_entry *mac;
 
@@ -1771,12 +1985,12 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port,
 	case BR_STATE_LEARNING:
 		mac[port].ingress   = true;
 		mac[port].egress    = false;
-		mac[port].dyn_learn = !!(priv->learn_ena & BIT(port));
+		mac[port].dyn_learn = dp->learning;
 		break;
 	case BR_STATE_FORWARDING:
 		mac[port].ingress   = true;
 		mac[port].egress    = true;
-		mac[port].dyn_learn = !!(priv->learn_ena & BIT(port));
+		mac[port].dyn_learn = dp->learning;
 		break;
 	default:
 		dev_err(ds->dev, "invalid STP state: %d\n", state);
@@ -2039,97 +2253,6 @@ out:
 	return rc;
 }
 
-static int sja1105_pvid_apply(struct sja1105_private *priv, int port, u16 pvid)
-{
-	struct sja1105_mac_config_entry *mac;
-
-	mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
-
-	mac[port].vlanid = pvid;
-
-	return sja1105_dynamic_config_write(priv, BLK_IDX_MAC_CONFIG, port,
-					   &mac[port], true);
-}
-
-static int sja1105_crosschip_bridge_join(struct dsa_switch *ds,
-					 int tree_index, int sw_index,
-					 int other_port, struct net_device *br)
-{
-	struct dsa_switch *other_ds = dsa_switch_find(tree_index, sw_index);
-	struct sja1105_private *other_priv = other_ds->priv;
-	struct sja1105_private *priv = ds->priv;
-	int port, rc;
-
-	if (other_ds->ops != &sja1105_switch_ops)
-		return 0;
-
-	for (port = 0; port < ds->num_ports; port++) {
-		if (!dsa_is_user_port(ds, port))
-			continue;
-		if (dsa_to_port(ds, port)->bridge_dev != br)
-			continue;
-
-		rc = dsa_8021q_crosschip_bridge_join(priv->dsa_8021q_ctx,
-						     port,
-						     other_priv->dsa_8021q_ctx,
-						     other_port);
-		if (rc)
-			return rc;
-
-		rc = dsa_8021q_crosschip_bridge_join(other_priv->dsa_8021q_ctx,
-						     other_port,
-						     priv->dsa_8021q_ctx,
-						     port);
-		if (rc)
-			return rc;
-	}
-
-	return 0;
-}
-
-static void sja1105_crosschip_bridge_leave(struct dsa_switch *ds,
-					   int tree_index, int sw_index,
-					   int other_port,
-					   struct net_device *br)
-{
-	struct dsa_switch *other_ds = dsa_switch_find(tree_index, sw_index);
-	struct sja1105_private *other_priv = other_ds->priv;
-	struct sja1105_private *priv = ds->priv;
-	int port;
-
-	if (other_ds->ops != &sja1105_switch_ops)
-		return;
-
-	for (port = 0; port < ds->num_ports; port++) {
-		if (!dsa_is_user_port(ds, port))
-			continue;
-		if (dsa_to_port(ds, port)->bridge_dev != br)
-			continue;
-
-		dsa_8021q_crosschip_bridge_leave(priv->dsa_8021q_ctx, port,
-						 other_priv->dsa_8021q_ctx,
-						 other_port);
-
-		dsa_8021q_crosschip_bridge_leave(other_priv->dsa_8021q_ctx,
-						 other_port,
-						 priv->dsa_8021q_ctx, port);
-	}
-}
-
-static int sja1105_setup_8021q_tagging(struct dsa_switch *ds, bool enabled)
-{
-	struct sja1105_private *priv = ds->priv;
-	int rc;
-
-	rc = dsa_8021q_setup(priv->dsa_8021q_ctx, enabled);
-	if (rc)
-		return rc;
-
-	dev_info(ds->dev, "%s switch tagging\n",
-		 enabled ? "Enabled" : "Disabled");
-	return 0;
-}
-
 static enum dsa_tag_protocol
 sja1105_get_tag_protocol(struct dsa_switch *ds, int port,
 			 enum dsa_tag_protocol mp)
@@ -2139,669 +2262,6 @@ sja1105_get_tag_protocol(struct dsa_switch *ds, int port,
 	return priv->info->tag_proto;
 }
 
-static int sja1105_find_free_subvlan(u16 *subvlan_map, bool pvid)
-{
-	int subvlan;
-
-	if (pvid)
-		return 0;
-
-	for (subvlan = 1; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++)
-		if (subvlan_map[subvlan] == VLAN_N_VID)
-			return subvlan;
-
-	return -1;
-}
-
-static int sja1105_find_subvlan(u16 *subvlan_map, u16 vid)
-{
-	int subvlan;
-
-	for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++)
-		if (subvlan_map[subvlan] == vid)
-			return subvlan;
-
-	return -1;
-}
-
-static int sja1105_find_committed_subvlan(struct sja1105_private *priv,
-					  int port, u16 vid)
-{
-	struct sja1105_port *sp = &priv->ports[port];
-
-	return sja1105_find_subvlan(sp->subvlan_map, vid);
-}
-
-static void sja1105_init_subvlan_map(u16 *subvlan_map)
-{
-	int subvlan;
-
-	for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++)
-		subvlan_map[subvlan] = VLAN_N_VID;
-}
-
-static void sja1105_commit_subvlan_map(struct sja1105_private *priv, int port,
-				       u16 *subvlan_map)
-{
-	struct sja1105_port *sp = &priv->ports[port];
-	int subvlan;
-
-	for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++)
-		sp->subvlan_map[subvlan] = subvlan_map[subvlan];
-}
-
-static int sja1105_is_vlan_configured(struct sja1105_private *priv, u16 vid)
-{
-	struct sja1105_vlan_lookup_entry *vlan;
-	int count, i;
-
-	vlan = priv->static_config.tables[BLK_IDX_VLAN_LOOKUP].entries;
-	count = priv->static_config.tables[BLK_IDX_VLAN_LOOKUP].entry_count;
-
-	for (i = 0; i < count; i++)
-		if (vlan[i].vlanid == vid)
-			return i;
-
-	/* Return an invalid entry index if not found */
-	return -1;
-}
-
-static int
-sja1105_find_retagging_entry(struct sja1105_retagging_entry *retagging,
-			     int count, int from_port, u16 from_vid,
-			     u16 to_vid)
-{
-	int i;
-
-	for (i = 0; i < count; i++)
-		if (retagging[i].ing_port == BIT(from_port) &&
-		    retagging[i].vlan_ing == from_vid &&
-		    retagging[i].vlan_egr == to_vid)
-			return i;
-
-	/* Return an invalid entry index if not found */
-	return -1;
-}
-
-static int sja1105_commit_vlans(struct sja1105_private *priv,
-				struct sja1105_vlan_lookup_entry *new_vlan,
-				struct sja1105_retagging_entry *new_retagging,
-				int num_retagging)
-{
-	struct sja1105_retagging_entry *retagging;
-	struct sja1105_vlan_lookup_entry *vlan;
-	struct sja1105_table *table;
-	int num_vlans = 0;
-	int rc, i, k = 0;
-
-	/* VLAN table */
-	table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP];
-	vlan = table->entries;
-
-	for (i = 0; i < VLAN_N_VID; i++) {
-		int match = sja1105_is_vlan_configured(priv, i);
-
-		if (new_vlan[i].vlanid != VLAN_N_VID)
-			num_vlans++;
-
-		if (new_vlan[i].vlanid == VLAN_N_VID && match >= 0) {
-			/* Was there before, no longer is. Delete */
-			dev_dbg(priv->ds->dev, "Deleting VLAN %d\n", i);
-			rc = sja1105_dynamic_config_write(priv,
-							  BLK_IDX_VLAN_LOOKUP,
-							  i, &vlan[match], false);
-			if (rc < 0)
-				return rc;
-		} else if (new_vlan[i].vlanid != VLAN_N_VID) {
-			/* Nothing changed, don't do anything */
-			if (match >= 0 &&
-			    vlan[match].vlanid == new_vlan[i].vlanid &&
-			    vlan[match].tag_port == new_vlan[i].tag_port &&
-			    vlan[match].vlan_bc == new_vlan[i].vlan_bc &&
-			    vlan[match].vmemb_port == new_vlan[i].vmemb_port)
-				continue;
-			/* Update entry */
-			dev_dbg(priv->ds->dev, "Updating VLAN %d\n", i);
-			rc = sja1105_dynamic_config_write(priv,
-							  BLK_IDX_VLAN_LOOKUP,
-							  i, &new_vlan[i],
-							  true);
-			if (rc < 0)
-				return rc;
-		}
-	}
-
-	if (table->entry_count)
-		kfree(table->entries);
-
-	table->entries = kcalloc(num_vlans, table->ops->unpacked_entry_size,
-				 GFP_KERNEL);
-	if (!table->entries)
-		return -ENOMEM;
-
-	table->entry_count = num_vlans;
-	vlan = table->entries;
-
-	for (i = 0; i < VLAN_N_VID; i++) {
-		if (new_vlan[i].vlanid == VLAN_N_VID)
-			continue;
-		vlan[k++] = new_vlan[i];
-	}
-
-	/* VLAN Retagging Table */
-	table = &priv->static_config.tables[BLK_IDX_RETAGGING];
-	retagging = table->entries;
-
-	for (i = 0; i < table->entry_count; i++) {
-		rc = sja1105_dynamic_config_write(priv, BLK_IDX_RETAGGING,
-						  i, &retagging[i], false);
-		if (rc)
-			return rc;
-	}
-
-	if (table->entry_count)
-		kfree(table->entries);
-
-	table->entries = kcalloc(num_retagging, table->ops->unpacked_entry_size,
-				 GFP_KERNEL);
-	if (!table->entries)
-		return -ENOMEM;
-
-	table->entry_count = num_retagging;
-	retagging = table->entries;
-
-	for (i = 0; i < num_retagging; i++) {
-		retagging[i] = new_retagging[i];
-
-		/* Update entry */
-		rc = sja1105_dynamic_config_write(priv, BLK_IDX_RETAGGING,
-						  i, &retagging[i], true);
-		if (rc < 0)
-			return rc;
-	}
-
-	return 0;
-}
-
-struct sja1105_crosschip_vlan {
-	struct list_head list;
-	u16 vid;
-	bool untagged;
-	int port;
-	int other_port;
-	struct dsa_8021q_context *other_ctx;
-};
-
-struct sja1105_crosschip_switch {
-	struct list_head list;
-	struct dsa_8021q_context *other_ctx;
-};
-
-static int sja1105_commit_pvid(struct sja1105_private *priv)
-{
-	struct sja1105_bridge_vlan *v;
-	struct list_head *vlan_list;
-	int rc = 0;
-
-	if (priv->vlan_state == SJA1105_VLAN_FILTERING_FULL)
-		vlan_list = &priv->bridge_vlans;
-	else
-		vlan_list = &priv->dsa_8021q_vlans;
-
-	list_for_each_entry(v, vlan_list, list) {
-		if (v->pvid) {
-			rc = sja1105_pvid_apply(priv, v->port, v->vid);
-			if (rc)
-				break;
-		}
-	}
-
-	return rc;
-}
-
-static int
-sja1105_build_bridge_vlans(struct sja1105_private *priv,
-			   struct sja1105_vlan_lookup_entry *new_vlan)
-{
-	struct sja1105_bridge_vlan *v;
-
-	if (priv->vlan_state == SJA1105_VLAN_UNAWARE)
-		return 0;
-
-	list_for_each_entry(v, &priv->bridge_vlans, list) {
-		int match = v->vid;
-
-		new_vlan[match].vlanid = v->vid;
-		new_vlan[match].vmemb_port |= BIT(v->port);
-		new_vlan[match].vlan_bc |= BIT(v->port);
-		if (!v->untagged)
-			new_vlan[match].tag_port |= BIT(v->port);
-		new_vlan[match].type_entry = SJA1110_VLAN_D_TAG;
-	}
-
-	return 0;
-}
-
-static int
-sja1105_build_dsa_8021q_vlans(struct sja1105_private *priv,
-			      struct sja1105_vlan_lookup_entry *new_vlan)
-{
-	struct sja1105_bridge_vlan *v;
-
-	if (priv->vlan_state == SJA1105_VLAN_FILTERING_FULL)
-		return 0;
-
-	list_for_each_entry(v, &priv->dsa_8021q_vlans, list) {
-		int match = v->vid;
-
-		new_vlan[match].vlanid = v->vid;
-		new_vlan[match].vmemb_port |= BIT(v->port);
-		new_vlan[match].vlan_bc |= BIT(v->port);
-		if (!v->untagged)
-			new_vlan[match].tag_port |= BIT(v->port);
-		new_vlan[match].type_entry = SJA1110_VLAN_D_TAG;
-	}
-
-	return 0;
-}
-
-static int sja1105_build_subvlans(struct sja1105_private *priv,
-				  u16 subvlan_map[][DSA_8021Q_N_SUBVLAN],
-				  struct sja1105_vlan_lookup_entry *new_vlan,
-				  struct sja1105_retagging_entry *new_retagging,
-				  int *num_retagging)
-{
-	struct sja1105_bridge_vlan *v;
-	int k = *num_retagging;
-
-	if (priv->vlan_state != SJA1105_VLAN_BEST_EFFORT)
-		return 0;
-
-	list_for_each_entry(v, &priv->bridge_vlans, list) {
-		int upstream = dsa_upstream_port(priv->ds, v->port);
-		int match, subvlan;
-		u16 rx_vid;
-
-		/* Only sub-VLANs on user ports need to be applied.
-		 * Bridge VLANs also include VLANs added automatically
-		 * by DSA on the CPU port.
-		 */
-		if (!dsa_is_user_port(priv->ds, v->port))
-			continue;
-
-		subvlan = sja1105_find_subvlan(subvlan_map[v->port],
-					       v->vid);
-		if (subvlan < 0) {
-			subvlan = sja1105_find_free_subvlan(subvlan_map[v->port],
-							    v->pvid);
-			if (subvlan < 0) {
-				dev_err(priv->ds->dev, "No more free subvlans\n");
-				return -ENOSPC;
-			}
-		}
-
-		rx_vid = dsa_8021q_rx_vid_subvlan(priv->ds, v->port, subvlan);
-
-		/* @v->vid on @v->port needs to be retagged to @rx_vid
-		 * on @upstream. Assume @v->vid on @v->port and on
-		 * @upstream was already configured by the previous
-		 * iteration over bridge_vlans.
-		 */
-		match = rx_vid;
-		new_vlan[match].vlanid = rx_vid;
-		new_vlan[match].vmemb_port |= BIT(v->port);
-		new_vlan[match].vmemb_port |= BIT(upstream);
-		new_vlan[match].vlan_bc |= BIT(v->port);
-		new_vlan[match].vlan_bc |= BIT(upstream);
-		/* The "untagged" flag is set the same as for the
-		 * original VLAN
-		 */
-		if (!v->untagged)
-			new_vlan[match].tag_port |= BIT(v->port);
-		/* But it's always tagged towards the CPU */
-		new_vlan[match].tag_port |= BIT(upstream);
-		new_vlan[match].type_entry = SJA1110_VLAN_D_TAG;
-
-		/* The Retagging Table generates packet *clones* with
-		 * the new VLAN. This is a very odd hardware quirk
-		 * which we need to suppress by dropping the original
-		 * packet.
-		 * Deny egress of the original VLAN towards the CPU
-		 * port. This will force the switch to drop it, and
-		 * we'll see only the retagged packets.
-		 */
-		match = v->vid;
-		new_vlan[match].vlan_bc &= ~BIT(upstream);
-
-		/* And the retagging itself */
-		new_retagging[k].vlan_ing = v->vid;
-		new_retagging[k].vlan_egr = rx_vid;
-		new_retagging[k].ing_port = BIT(v->port);
-		new_retagging[k].egr_port = BIT(upstream);
-		if (k++ == SJA1105_MAX_RETAGGING_COUNT) {
-			dev_err(priv->ds->dev, "No more retagging rules\n");
-			return -ENOSPC;
-		}
-
-		subvlan_map[v->port][subvlan] = v->vid;
-	}
-
-	*num_retagging = k;
-
-	return 0;
-}
-
-/* Sadly, in crosschip scenarios where the CPU port is also the link to another
- * switch, we should retag backwards (the dsa_8021q vid to the original vid) on
- * the CPU port of neighbour switches.
- */
-static int
-sja1105_build_crosschip_subvlans(struct sja1105_private *priv,
-				 struct sja1105_vlan_lookup_entry *new_vlan,
-				 struct sja1105_retagging_entry *new_retagging,
-				 int *num_retagging)
-{
-	struct sja1105_crosschip_vlan *tmp, *pos;
-	struct dsa_8021q_crosschip_link *c;
-	struct sja1105_bridge_vlan *v, *w;
-	struct list_head crosschip_vlans;
-	int k = *num_retagging;
-	int rc = 0;
-
-	if (priv->vlan_state != SJA1105_VLAN_BEST_EFFORT)
-		return 0;
-
-	INIT_LIST_HEAD(&crosschip_vlans);
-
-	list_for_each_entry(c, &priv->dsa_8021q_ctx->crosschip_links, list) {
-		struct sja1105_private *other_priv = c->other_ctx->ds->priv;
-
-		if (other_priv->vlan_state == SJA1105_VLAN_FILTERING_FULL)
-			continue;
-
-		/* Crosschip links are also added to the CPU ports.
-		 * Ignore those.
-		 */
-		if (!dsa_is_user_port(priv->ds, c->port))
-			continue;
-		if (!dsa_is_user_port(c->other_ctx->ds, c->other_port))
-			continue;
-
-		/* Search for VLANs on the remote port */
-		list_for_each_entry(v, &other_priv->bridge_vlans, list) {
-			bool already_added = false;
-			bool we_have_it = false;
-
-			if (v->port != c->other_port)
-				continue;
-
-			/* If @v is a pvid on @other_ds, it does not need
-			 * re-retagging, because its SVL field is 0 and we
-			 * already allow that, via the dsa_8021q crosschip
-			 * links.
-			 */
-			if (v->pvid)
-				continue;
-
-			/* Search for the VLAN on our local port */
-			list_for_each_entry(w, &priv->bridge_vlans, list) {
-				if (w->port == c->port && w->vid == v->vid) {
-					we_have_it = true;
-					break;
-				}
-			}
-
-			if (!we_have_it)
-				continue;
-
-			list_for_each_entry(tmp, &crosschip_vlans, list) {
-				if (tmp->vid == v->vid &&
-				    tmp->untagged == v->untagged &&
-				    tmp->port == c->port &&
-				    tmp->other_port == v->port &&
-				    tmp->other_ctx == c->other_ctx) {
-					already_added = true;
-					break;
-				}
-			}
-
-			if (already_added)
-				continue;
-
-			tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
-			if (!tmp) {
-				dev_err(priv->ds->dev, "Failed to allocate memory\n");
-				rc = -ENOMEM;
-				goto out;
-			}
-			tmp->vid = v->vid;
-			tmp->port = c->port;
-			tmp->other_port = v->port;
-			tmp->other_ctx = c->other_ctx;
-			tmp->untagged = v->untagged;
-			list_add(&tmp->list, &crosschip_vlans);
-		}
-	}
-
-	list_for_each_entry(tmp, &crosschip_vlans, list) {
-		struct sja1105_private *other_priv = tmp->other_ctx->ds->priv;
-		int upstream = dsa_upstream_port(priv->ds, tmp->port);
-		int match, subvlan;
-		u16 rx_vid;
-
-		subvlan = sja1105_find_committed_subvlan(other_priv,
-							 tmp->other_port,
-							 tmp->vid);
-		/* If this happens, it's a bug. The neighbour switch does not
-		 * have a subvlan for tmp->vid on tmp->other_port, but it
-		 * should, since we already checked for its vlan_state.
-		 */
-		if (WARN_ON(subvlan < 0)) {
-			rc = -EINVAL;
-			goto out;
-		}
-
-		rx_vid = dsa_8021q_rx_vid_subvlan(tmp->other_ctx->ds,
-						  tmp->other_port,
-						  subvlan);
-
-		/* The @rx_vid retagged from @tmp->vid on
-		 * {@tmp->other_ds, @tmp->other_port} needs to be
-		 * re-retagged to @tmp->vid on the way back to us.
-		 *
-		 * Assume the original @tmp->vid is already configured
-		 * on this local switch, otherwise we wouldn't be
-		 * retagging its subvlan on the other switch in the
-		 * first place. We just need to add a reverse retagging
-		 * rule for @rx_vid and install @rx_vid on our ports.
-		 */
-		match = rx_vid;
-		new_vlan[match].vlanid = rx_vid;
-		new_vlan[match].vmemb_port |= BIT(tmp->port);
-		new_vlan[match].vmemb_port |= BIT(upstream);
-		/* The "untagged" flag is set the same as for the
-		 * original VLAN. And towards the CPU, it doesn't
-		 * really matter, because @rx_vid will only receive
-		 * traffic on that port. For consistency with other dsa_8021q
-		 * VLANs, we'll keep the CPU port tagged.
-		 */
-		if (!tmp->untagged)
-			new_vlan[match].tag_port |= BIT(tmp->port);
-		new_vlan[match].tag_port |= BIT(upstream);
-		new_vlan[match].type_entry = SJA1110_VLAN_D_TAG;
-		/* Deny egress of @rx_vid towards our front-panel port.
-		 * This will force the switch to drop it, and we'll see
-		 * only the re-retagged packets (having the original,
-		 * pre-initial-retagging, VLAN @tmp->vid).
-		 */
-		new_vlan[match].vlan_bc &= ~BIT(tmp->port);
-
-		/* On reverse retagging, the same ingress VLAN goes to multiple
-		 * ports. So we have an opportunity to create composite rules
-		 * to not waste the limited space in the retagging table.
-		 */
-		k = sja1105_find_retagging_entry(new_retagging, *num_retagging,
-						 upstream, rx_vid, tmp->vid);
-		if (k < 0) {
-			if (*num_retagging == SJA1105_MAX_RETAGGING_COUNT) {
-				dev_err(priv->ds->dev, "No more retagging rules\n");
-				rc = -ENOSPC;
-				goto out;
-			}
-			k = (*num_retagging)++;
-		}
-		/* And the retagging itself */
-		new_retagging[k].vlan_ing = rx_vid;
-		new_retagging[k].vlan_egr = tmp->vid;
-		new_retagging[k].ing_port = BIT(upstream);
-		new_retagging[k].egr_port |= BIT(tmp->port);
-	}
-
-out:
-	list_for_each_entry_safe(tmp, pos, &crosschip_vlans, list) {
-		list_del(&tmp->list);
-		kfree(tmp);
-	}
-
-	return rc;
-}
-
-static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify);
-
-static int sja1105_notify_crosschip_switches(struct sja1105_private *priv)
-{
-	struct sja1105_crosschip_switch *s, *pos;
-	struct list_head crosschip_switches;
-	struct dsa_8021q_crosschip_link *c;
-	int rc = 0;
-
-	INIT_LIST_HEAD(&crosschip_switches);
-
-	list_for_each_entry(c, &priv->dsa_8021q_ctx->crosschip_links, list) {
-		bool already_added = false;
-
-		list_for_each_entry(s, &crosschip_switches, list) {
-			if (s->other_ctx == c->other_ctx) {
-				already_added = true;
-				break;
-			}
-		}
-
-		if (already_added)
-			continue;
-
-		s = kzalloc(sizeof(*s), GFP_KERNEL);
-		if (!s) {
-			dev_err(priv->ds->dev, "Failed to allocate memory\n");
-			rc = -ENOMEM;
-			goto out;
-		}
-		s->other_ctx = c->other_ctx;
-		list_add(&s->list, &crosschip_switches);
-	}
-
-	list_for_each_entry(s, &crosschip_switches, list) {
-		struct sja1105_private *other_priv = s->other_ctx->ds->priv;
-
-		rc = sja1105_build_vlan_table(other_priv, false);
-		if (rc)
-			goto out;
-	}
-
-out:
-	list_for_each_entry_safe(s, pos, &crosschip_switches, list) {
-		list_del(&s->list);
-		kfree(s);
-	}
-
-	return rc;
-}
-
-static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify)
-{
-	u16 subvlan_map[SJA1105_MAX_NUM_PORTS][DSA_8021Q_N_SUBVLAN];
-	struct sja1105_retagging_entry *new_retagging;
-	struct sja1105_vlan_lookup_entry *new_vlan;
-	struct sja1105_table *table;
-	int i, num_retagging = 0;
-	int rc;
-
-	table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP];
-	new_vlan = kcalloc(VLAN_N_VID,
-			   table->ops->unpacked_entry_size, GFP_KERNEL);
-	if (!new_vlan)
-		return -ENOMEM;
-
-	table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP];
-	new_retagging = kcalloc(SJA1105_MAX_RETAGGING_COUNT,
-				table->ops->unpacked_entry_size, GFP_KERNEL);
-	if (!new_retagging) {
-		kfree(new_vlan);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < VLAN_N_VID; i++)
-		new_vlan[i].vlanid = VLAN_N_VID;
-
-	for (i = 0; i < SJA1105_MAX_RETAGGING_COUNT; i++)
-		new_retagging[i].vlan_ing = VLAN_N_VID;
-
-	for (i = 0; i < priv->ds->num_ports; i++)
-		sja1105_init_subvlan_map(subvlan_map[i]);
-
-	/* Bridge VLANs */
-	rc = sja1105_build_bridge_vlans(priv, new_vlan);
-	if (rc)
-		goto out;
-
-	/* VLANs necessary for dsa_8021q operation, given to us by tag_8021q.c:
-	 * - RX VLANs
-	 * - TX VLANs
-	 * - Crosschip links
-	 */
-	rc = sja1105_build_dsa_8021q_vlans(priv, new_vlan);
-	if (rc)
-		goto out;
-
-	/* Private VLANs necessary for dsa_8021q operation, which we need to
-	 * determine on our own:
-	 * - Sub-VLANs
-	 * - Sub-VLANs of crosschip switches
-	 */
-	rc = sja1105_build_subvlans(priv, subvlan_map, new_vlan, new_retagging,
-				    &num_retagging);
-	if (rc)
-		goto out;
-
-	rc = sja1105_build_crosschip_subvlans(priv, new_vlan, new_retagging,
-					      &num_retagging);
-	if (rc)
-		goto out;
-
-	rc = sja1105_commit_vlans(priv, new_vlan, new_retagging, num_retagging);
-	if (rc)
-		goto out;
-
-	rc = sja1105_commit_pvid(priv);
-	if (rc)
-		goto out;
-
-	for (i = 0; i < priv->ds->num_ports; i++)
-		sja1105_commit_subvlan_map(priv, i, subvlan_map[i]);
-
-	if (notify) {
-		rc = sja1105_notify_crosschip_switches(priv);
-		if (rc)
-			goto out;
-	}
-
-out:
-	kfree(new_vlan);
-	kfree(new_retagging);
-
-	return rc;
-}
-
 /* The TPID setting belongs to the General Parameters table,
  * which can only be partially reconfigured at runtime (and not the TPID).
  * So a switch reset is required.
@@ -2812,10 +2272,8 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
 	struct sja1105_l2_lookup_params_entry *l2_lookup_params;
 	struct sja1105_general_params_entry *general_params;
 	struct sja1105_private *priv = ds->priv;
-	enum sja1105_vlan_state state;
 	struct sja1105_table *table;
 	struct sja1105_rule *rule;
-	bool want_tagging;
 	u16 tpid, tpid2;
 	int rc;
 
@@ -2837,28 +2295,10 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
 		tpid2 = ETH_P_SJA1105;
 	}
 
-	for (port = 0; port < ds->num_ports; port++) {
-		struct sja1105_port *sp = &priv->ports[port];
-
-		if (enabled)
-			sp->xmit_tpid = priv->info->qinq_tpid;
-		else
-			sp->xmit_tpid = ETH_P_SJA1105;
-	}
-
-	if (!enabled)
-		state = SJA1105_VLAN_UNAWARE;
-	else if (priv->best_effort_vlan_filtering)
-		state = SJA1105_VLAN_BEST_EFFORT;
-	else
-		state = SJA1105_VLAN_FILTERING_FULL;
-
-	if (priv->vlan_state == state)
+	if (priv->vlan_aware == enabled)
 		return 0;
 
-	priv->vlan_state = state;
-	want_tagging = (state == SJA1105_VLAN_UNAWARE ||
-			state == SJA1105_VLAN_BEST_EFFORT);
+	priv->vlan_aware = enabled;
 
 	table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS];
 	general_params = table->entries;
@@ -2872,8 +2312,6 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
 	general_params->incl_srcpt1 = enabled;
 	general_params->incl_srcpt0 = enabled;
 
-	want_tagging = priv->best_effort_vlan_filtering || !enabled;
-
 	/* VLAN filtering => independent VLAN learning.
 	 * No VLAN filtering (or best effort) => shared VLAN learning.
 	 *
@@ -2894,314 +2332,205 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
 	 */
 	table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP_PARAMS];
 	l2_lookup_params = table->entries;
-	l2_lookup_params->shared_learn = want_tagging;
+	l2_lookup_params->shared_learn = !priv->vlan_aware;
 
-	sja1105_frame_memory_partitioning(priv);
+	for (port = 0; port < ds->num_ports; port++) {
+		if (dsa_is_unused_port(ds, port))
+			continue;
 
-	rc = sja1105_build_vlan_table(priv, false);
-	if (rc)
-		return rc;
+		rc = sja1105_commit_pvid(ds, port);
+		if (rc)
+			return rc;
+	}
 
 	rc = sja1105_static_config_reload(priv, SJA1105_VLAN_FILTERING);
 	if (rc)
 		NL_SET_ERR_MSG_MOD(extack, "Failed to change VLAN Ethertype");
 
-	/* Switch port identification based on 802.1Q is only passable
-	 * if we are not under a vlan_filtering bridge. So make sure
-	 * the two configurations are mutually exclusive (of course, the
-	 * user may know better, i.e. best_effort_vlan_filtering).
-	 */
-	return sja1105_setup_8021q_tagging(ds, want_tagging);
+	return rc;
 }
 
-/* Returns number of VLANs added (0 or 1) on success,
- * or a negative error code.
- */
-static int sja1105_vlan_add_one(struct dsa_switch *ds, int port, u16 vid,
-				u16 flags, struct list_head *vlan_list)
-{
-	bool untagged = flags & BRIDGE_VLAN_INFO_UNTAGGED;
-	bool pvid = flags & BRIDGE_VLAN_INFO_PVID;
-	struct sja1105_bridge_vlan *v;
-
-	list_for_each_entry(v, vlan_list, list) {
-		if (v->port == port && v->vid == vid) {
-			/* Already added */
-			if (v->untagged == untagged && v->pvid == pvid)
-				/* Nothing changed */
-				return 0;
-
-			/* It's the same VLAN, but some of the flags changed
-			 * and the user did not bother to delete it first.
-			 * Update it and trigger sja1105_build_vlan_table.
-			 */
-			v->untagged = untagged;
-			v->pvid = pvid;
-			return 1;
-		}
-	}
+static int sja1105_vlan_add(struct sja1105_private *priv, int port, u16 vid,
+			    u16 flags, bool allowed_ingress)
+{
+	struct sja1105_vlan_lookup_entry *vlan;
+	struct sja1105_table *table;
+	int match, rc;
 
-	v = kzalloc(sizeof(*v), GFP_KERNEL);
-	if (!v) {
-		dev_err(ds->dev, "Out of memory while storing VLAN\n");
-		return -ENOMEM;
+	table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP];
+
+	match = sja1105_is_vlan_configured(priv, vid);
+	if (match < 0) {
+		rc = sja1105_table_resize(table, table->entry_count + 1);
+		if (rc)
+			return rc;
+		match = table->entry_count - 1;
 	}
 
-	v->port = port;
-	v->vid = vid;
-	v->untagged = untagged;
-	v->pvid = pvid;
-	list_add(&v->list, vlan_list);
+	/* Assign pointer after the resize (it's new memory) */
+	vlan = table->entries;
+
+	vlan[match].type_entry = SJA1110_VLAN_D_TAG;
+	vlan[match].vlanid = vid;
+	vlan[match].vlan_bc |= BIT(port);
+
+	if (allowed_ingress)
+		vlan[match].vmemb_port |= BIT(port);
+	else
+		vlan[match].vmemb_port &= ~BIT(port);
+
+	if (flags & BRIDGE_VLAN_INFO_UNTAGGED)
+		vlan[match].tag_port &= ~BIT(port);
+	else
+		vlan[match].tag_port |= BIT(port);
 
-	return 1;
+	return sja1105_dynamic_config_write(priv, BLK_IDX_VLAN_LOOKUP, vid,
+					    &vlan[match], true);
 }
 
-/* Returns number of VLANs deleted (0 or 1) */
-static int sja1105_vlan_del_one(struct dsa_switch *ds, int port, u16 vid,
-				struct list_head *vlan_list)
+static int sja1105_vlan_del(struct sja1105_private *priv, int port, u16 vid)
 {
-	struct sja1105_bridge_vlan *v, *n;
+	struct sja1105_vlan_lookup_entry *vlan;
+	struct sja1105_table *table;
+	bool keep = true;
+	int match, rc;
 
-	list_for_each_entry_safe(v, n, vlan_list, list) {
-		if (v->port == port && v->vid == vid) {
-			list_del(&v->list);
-			kfree(v);
-			return 1;
-		}
-	}
+	table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP];
+
+	match = sja1105_is_vlan_configured(priv, vid);
+	/* Can't delete a missing entry. */
+	if (match < 0)
+		return 0;
+
+	/* Assign pointer after the resize (it's new memory) */
+	vlan = table->entries;
+
+	vlan[match].vlanid = vid;
+	vlan[match].vlan_bc &= ~BIT(port);
+	vlan[match].vmemb_port &= ~BIT(port);
+	/* Also unset tag_port, just so we don't have a confusing bitmap
+	 * (no practical purpose).
+	 */
+	vlan[match].tag_port &= ~BIT(port);
+
+	/* If there's no port left as member of this VLAN,
+	 * it's time for it to go.
+	 */
+	if (!vlan[match].vmemb_port)
+		keep = false;
+
+	rc = sja1105_dynamic_config_write(priv, BLK_IDX_VLAN_LOOKUP, vid,
+					  &vlan[match], keep);
+	if (rc < 0)
+		return rc;
+
+	if (!keep)
+		return sja1105_table_delete_entry(table, match);
 
 	return 0;
 }
 
-static int sja1105_vlan_add(struct dsa_switch *ds, int port,
-			    const struct switchdev_obj_port_vlan *vlan,
-			    struct netlink_ext_ack *extack)
+static int sja1105_bridge_vlan_add(struct dsa_switch *ds, int port,
+				   const struct switchdev_obj_port_vlan *vlan,
+				   struct netlink_ext_ack *extack)
 {
 	struct sja1105_private *priv = ds->priv;
-	bool vlan_table_changed = false;
+	u16 flags = vlan->flags;
 	int rc;
 
-	/* If the user wants best-effort VLAN filtering (aka vlan_filtering
-	 * bridge plus tagging), be sure to at least deny alterations to the
-	 * configuration done by dsa_8021q.
+	/* Be sure to deny alterations to the configuration done by tag_8021q.
 	 */
-	if (priv->vlan_state != SJA1105_VLAN_FILTERING_FULL &&
-	    vid_is_dsa_8021q(vlan->vid)) {
+	if (vid_is_dsa_8021q(vlan->vid)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Range 1024-3071 reserved for dsa_8021q operation");
 		return -EBUSY;
 	}
 
-	rc = sja1105_vlan_add_one(ds, port, vlan->vid, vlan->flags,
-				  &priv->bridge_vlans);
-	if (rc < 0)
+	/* Always install bridge VLANs as egress-tagged on CPU and DSA ports */
+	if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
+		flags = 0;
+
+	rc = sja1105_vlan_add(priv, port, vlan->vid, flags, true);
+	if (rc)
 		return rc;
-	if (rc > 0)
-		vlan_table_changed = true;
 
-	if (!vlan_table_changed)
-		return 0;
+	if (vlan->flags & BRIDGE_VLAN_INFO_PVID)
+		priv->bridge_pvid[port] = vlan->vid;
 
-	return sja1105_build_vlan_table(priv, true);
+	return sja1105_commit_pvid(ds, port);
 }
 
-static int sja1105_vlan_del(struct dsa_switch *ds, int port,
-			    const struct switchdev_obj_port_vlan *vlan)
+static int sja1105_bridge_vlan_del(struct dsa_switch *ds, int port,
+				   const struct switchdev_obj_port_vlan *vlan)
 {
 	struct sja1105_private *priv = ds->priv;
-	bool vlan_table_changed = false;
 	int rc;
 
-	rc = sja1105_vlan_del_one(ds, port, vlan->vid, &priv->bridge_vlans);
-	if (rc > 0)
-		vlan_table_changed = true;
-
-	if (!vlan_table_changed)
-		return 0;
+	rc = sja1105_vlan_del(priv, port, vlan->vid);
+	if (rc)
+		return rc;
 
-	return sja1105_build_vlan_table(priv, true);
+	/* In case the pvid was deleted, make sure that untagged packets will
+	 * be dropped.
+	 */
+	return sja1105_commit_pvid(ds, port);
 }
 
 static int sja1105_dsa_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,
 				      u16 flags)
 {
 	struct sja1105_private *priv = ds->priv;
+	bool allowed_ingress = true;
 	int rc;
 
-	rc = sja1105_vlan_add_one(ds, port, vid, flags, &priv->dsa_8021q_vlans);
-	if (rc <= 0)
+	/* Prevent attackers from trying to inject a DSA tag from
+	 * the outside world.
+	 */
+	if (dsa_is_user_port(ds, port))
+		allowed_ingress = false;
+
+	rc = sja1105_vlan_add(priv, port, vid, flags, allowed_ingress);
+	if (rc)
 		return rc;
 
-	return sja1105_build_vlan_table(priv, true);
+	if (flags & BRIDGE_VLAN_INFO_PVID)
+		priv->tag_8021q_pvid[port] = vid;
+
+	return sja1105_commit_pvid(ds, port);
 }
 
 static int sja1105_dsa_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid)
 {
 	struct sja1105_private *priv = ds->priv;
-	int rc;
-
-	rc = sja1105_vlan_del_one(ds, port, vid, &priv->dsa_8021q_vlans);
-	if (!rc)
-		return 0;
 
-	return sja1105_build_vlan_table(priv, true);
+	return sja1105_vlan_del(priv, port, vid);
 }
 
-static const struct dsa_8021q_ops sja1105_dsa_8021q_ops = {
-	.vlan_add	= sja1105_dsa_8021q_vlan_add,
-	.vlan_del	= sja1105_dsa_8021q_vlan_del,
-};
-
-/* The programming model for the SJA1105 switch is "all-at-once" via static
- * configuration tables. Some of these can be dynamically modified at runtime,
- * but not the xMII mode parameters table.
- * Furthermode, some PHYs may not have crystals for generating their clocks
- * (e.g. RMII). Instead, their 50MHz clock is supplied via the SJA1105 port's
- * ref_clk pin. So port clocking needs to be initialized early, before
- * connecting to PHYs is attempted, otherwise they won't respond through MDIO.
- * Setting correct PHY link speed does not matter now.
- * But dsa_slave_phy_setup is called later than sja1105_setup, so the PHY
- * bindings are not yet parsed by DSA core. We need to parse early so that we
- * can populate the xMII mode parameters table.
- */
-static int sja1105_setup(struct dsa_switch *ds)
+static int sja1105_prechangeupper(struct dsa_switch *ds, int port,
+				  struct netdev_notifier_changeupper_info *info)
 {
-	struct sja1105_private *priv = ds->priv;
-	int rc;
+	struct netlink_ext_ack *extack = info->info.extack;
+	struct net_device *upper = info->upper_dev;
+	struct dsa_switch_tree *dst = ds->dst;
+	struct dsa_port *dp;
 
-	rc = sja1105_parse_dt(priv);
-	if (rc < 0) {
-		dev_err(ds->dev, "Failed to parse DT: %d\n", rc);
-		return rc;
-	}
-
-	/* Error out early if internal delays are required through DT
-	 * and we can't apply them.
-	 */
-	rc = sja1105_parse_rgmii_delays(priv);
-	if (rc < 0) {
-		dev_err(ds->dev, "RGMII delay not supported\n");
-		return rc;
-	}
-
-	rc = sja1105_ptp_clock_register(ds);
-	if (rc < 0) {
-		dev_err(ds->dev, "Failed to register PTP clock: %d\n", rc);
-		return rc;
-	}
-
-	rc = sja1105_mdiobus_register(ds);
-	if (rc < 0) {
-		dev_err(ds->dev, "Failed to register MDIO bus: %pe\n",
-			ERR_PTR(rc));
-		goto out_ptp_clock_unregister;
-	}
-
-	if (priv->info->disable_microcontroller) {
-		rc = priv->info->disable_microcontroller(priv);
-		if (rc < 0) {
-			dev_err(ds->dev,
-				"Failed to disable microcontroller: %pe\n",
-				ERR_PTR(rc));
-			goto out_mdiobus_unregister;
-		}
-	}
-
-	/* Create and send configuration down to device */
-	rc = sja1105_static_config_load(priv);
-	if (rc < 0) {
-		dev_err(ds->dev, "Failed to load static config: %d\n", rc);
-		goto out_mdiobus_unregister;
+	if (is_vlan_dev(upper)) {
+		NL_SET_ERR_MSG_MOD(extack, "8021q uppers are not supported");
+		return -EBUSY;
 	}
 
-	/* Configure the CGU (PHY link modes and speeds) */
-	if (priv->info->clocking_setup) {
-		rc = priv->info->clocking_setup(priv);
-		if (rc < 0) {
-			dev_err(ds->dev,
-				"Failed to configure MII clocking: %pe\n",
-				ERR_PTR(rc));
-			goto out_static_config_free;
+	if (netif_is_bridge_master(upper)) {
+		list_for_each_entry(dp, &dst->ports, list) {
+			if (dp->bridge_dev && dp->bridge_dev != upper &&
+			    br_vlan_enabled(dp->bridge_dev)) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Only one VLAN-aware bridge is supported");
+				return -EBUSY;
+			}
 		}
 	}
 
-	/* On SJA1105, VLAN filtering per se is always enabled in hardware.
-	 * The only thing we can do to disable it is lie about what the 802.1Q
-	 * EtherType is.
-	 * So it will still try to apply VLAN filtering, but all ingress
-	 * traffic (except frames received with EtherType of ETH_P_SJA1105)
-	 * will be internally tagged with a distorted VLAN header where the
-	 * TPID is ETH_P_SJA1105, and the VLAN ID is the port pvid.
-	 */
-	ds->vlan_filtering_is_global = true;
-
-	/* Advertise the 8 egress queues */
-	ds->num_tx_queues = SJA1105_NUM_TC;
-
-	ds->mtu_enforcement_ingress = true;
-
-	priv->best_effort_vlan_filtering = true;
-
-	rc = sja1105_devlink_setup(ds);
-	if (rc < 0)
-		goto out_static_config_free;
-
-	/* The DSA/switchdev model brings up switch ports in standalone mode by
-	 * default, and that means vlan_filtering is 0 since they're not under
-	 * a bridge, so it's safe to set up switch tagging at this time.
-	 */
-	rtnl_lock();
-	rc = sja1105_setup_8021q_tagging(ds, true);
-	rtnl_unlock();
-	if (rc)
-		goto out_devlink_teardown;
-
 	return 0;
-
-out_devlink_teardown:
-	sja1105_devlink_teardown(ds);
-out_mdiobus_unregister:
-	sja1105_mdiobus_unregister(ds);
-out_ptp_clock_unregister:
-	sja1105_ptp_clock_unregister(ds);
-out_static_config_free:
-	sja1105_static_config_free(&priv->static_config);
-
-	return rc;
-}
-
-static void sja1105_teardown(struct dsa_switch *ds)
-{
-	struct sja1105_private *priv = ds->priv;
-	struct sja1105_bridge_vlan *v, *n;
-	int port;
-
-	for (port = 0; port < ds->num_ports; port++) {
-		struct sja1105_port *sp = &priv->ports[port];
-
-		if (!dsa_is_user_port(ds, port))
-			continue;
-
-		if (sp->xmit_worker)
-			kthread_destroy_worker(sp->xmit_worker);
-	}
-
-	sja1105_devlink_teardown(ds);
-	sja1105_mdiobus_unregister(ds);
-	sja1105_flower_teardown(ds);
-	sja1105_tas_teardown(ds);
-	sja1105_ptp_clock_unregister(ds);
-	sja1105_static_config_free(&priv->static_config);
-
-	list_for_each_entry_safe(v, n, &priv->dsa_8021q_vlans, list) {
-		list_del(&v->list);
-		kfree(v);
-	}
-
-	list_for_each_entry_safe(v, n, &priv->bridge_vlans, list) {
-		list_del(&v->list);
-		kfree(v);
-	}
 }
 
 static void sja1105_port_disable(struct dsa_switch *ds, int port)
@@ -3337,7 +2666,7 @@ static int sja1105_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 
 	new_mtu += VLAN_ETH_HLEN + ETH_FCS_LEN;
 
-	if (dsa_is_cpu_port(ds, port))
+	if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
 		new_mtu += VLAN_HLEN;
 
 	policing = priv->static_config.tables[BLK_IDX_L2_POLICING].entries;
@@ -3484,23 +2813,13 @@ static int sja1105_port_set_learning(struct sja1105_private *priv, int port,
 				     bool enabled)
 {
 	struct sja1105_mac_config_entry *mac;
-	int rc;
 
 	mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
 
 	mac[port].dyn_learn = enabled;
 
-	rc = sja1105_dynamic_config_write(priv, BLK_IDX_MAC_CONFIG, port,
-					  &mac[port], true);
-	if (rc)
-		return rc;
-
-	if (enabled)
-		priv->learn_ena |= BIT(port);
-	else
-		priv->learn_ena &= ~BIT(port);
-
-	return 0;
+	return sja1105_dynamic_config_write(priv, BLK_IDX_MAC_CONFIG, port,
+					    &mac[port], true);
 }
 
 static int sja1105_port_ucast_bcast_flood(struct sja1105_private *priv, int to,
@@ -3616,7 +2935,189 @@ static int sja1105_port_bridge_flags(struct dsa_switch *ds, int port,
 	return 0;
 }
 
-static const struct dsa_switch_ops sja1105_switch_ops = {
+static void sja1105_teardown_ports(struct sja1105_private *priv)
+{
+	struct dsa_switch *ds = priv->ds;
+	int port;
+
+	for (port = 0; port < ds->num_ports; port++) {
+		struct sja1105_port *sp = &priv->ports[port];
+
+		if (sp->xmit_worker)
+			kthread_destroy_worker(sp->xmit_worker);
+	}
+}
+
+static int sja1105_setup_ports(struct sja1105_private *priv)
+{
+	struct sja1105_tagger_data *tagger_data = &priv->tagger_data;
+	struct dsa_switch *ds = priv->ds;
+	int port, rc;
+
+	/* Connections between dsa_port and sja1105_port */
+	for (port = 0; port < ds->num_ports; port++) {
+		struct sja1105_port *sp = &priv->ports[port];
+		struct dsa_port *dp = dsa_to_port(ds, port);
+		struct kthread_worker *worker;
+		struct net_device *slave;
+
+		if (!dsa_port_is_user(dp))
+			continue;
+
+		dp->priv = sp;
+		sp->dp = dp;
+		sp->data = tagger_data;
+		slave = dp->slave;
+		kthread_init_work(&sp->xmit_work, sja1105_port_deferred_xmit);
+		worker = kthread_create_worker(0, "%s_xmit", slave->name);
+		if (IS_ERR(worker)) {
+			rc = PTR_ERR(worker);
+			dev_err(ds->dev,
+				"failed to create deferred xmit thread: %d\n",
+				rc);
+			goto out_destroy_workers;
+		}
+		sp->xmit_worker = worker;
+		skb_queue_head_init(&sp->xmit_queue);
+	}
+
+	return 0;
+
+out_destroy_workers:
+	sja1105_teardown_ports(priv);
+	return rc;
+}
+
+/* The programming model for the SJA1105 switch is "all-at-once" via static
+ * configuration tables. Some of these can be dynamically modified at runtime,
+ * but not the xMII mode parameters table.
+ * Furthermode, some PHYs may not have crystals for generating their clocks
+ * (e.g. RMII). Instead, their 50MHz clock is supplied via the SJA1105 port's
+ * ref_clk pin. So port clocking needs to be initialized early, before
+ * connecting to PHYs is attempted, otherwise they won't respond through MDIO.
+ * Setting correct PHY link speed does not matter now.
+ * But dsa_slave_phy_setup is called later than sja1105_setup, so the PHY
+ * bindings are not yet parsed by DSA core. We need to parse early so that we
+ * can populate the xMII mode parameters table.
+ */
+static int sja1105_setup(struct dsa_switch *ds)
+{
+	struct sja1105_private *priv = ds->priv;
+	int rc;
+
+	if (priv->info->disable_microcontroller) {
+		rc = priv->info->disable_microcontroller(priv);
+		if (rc < 0) {
+			dev_err(ds->dev,
+				"Failed to disable microcontroller: %pe\n",
+				ERR_PTR(rc));
+			return rc;
+		}
+	}
+
+	/* Create and send configuration down to device */
+	rc = sja1105_static_config_load(priv);
+	if (rc < 0) {
+		dev_err(ds->dev, "Failed to load static config: %d\n", rc);
+		return rc;
+	}
+
+	/* Configure the CGU (PHY link modes and speeds) */
+	if (priv->info->clocking_setup) {
+		rc = priv->info->clocking_setup(priv);
+		if (rc < 0) {
+			dev_err(ds->dev,
+				"Failed to configure MII clocking: %pe\n",
+				ERR_PTR(rc));
+			goto out_static_config_free;
+		}
+	}
+
+	rc = sja1105_setup_ports(priv);
+	if (rc)
+		goto out_static_config_free;
+
+	sja1105_tas_setup(ds);
+	sja1105_flower_setup(ds);
+
+	rc = sja1105_ptp_clock_register(ds);
+	if (rc < 0) {
+		dev_err(ds->dev, "Failed to register PTP clock: %d\n", rc);
+		goto out_flower_teardown;
+	}
+
+	rc = sja1105_mdiobus_register(ds);
+	if (rc < 0) {
+		dev_err(ds->dev, "Failed to register MDIO bus: %pe\n",
+			ERR_PTR(rc));
+		goto out_ptp_clock_unregister;
+	}
+
+	rc = sja1105_devlink_setup(ds);
+	if (rc < 0)
+		goto out_mdiobus_unregister;
+
+	rtnl_lock();
+	rc = dsa_tag_8021q_register(ds, htons(ETH_P_8021Q));
+	rtnl_unlock();
+	if (rc)
+		goto out_devlink_teardown;
+
+	/* On SJA1105, VLAN filtering per se is always enabled in hardware.
+	 * The only thing we can do to disable it is lie about what the 802.1Q
+	 * EtherType is.
+	 * So it will still try to apply VLAN filtering, but all ingress
+	 * traffic (except frames received with EtherType of ETH_P_SJA1105)
+	 * will be internally tagged with a distorted VLAN header where the
+	 * TPID is ETH_P_SJA1105, and the VLAN ID is the port pvid.
+	 */
+	ds->vlan_filtering_is_global = true;
+	ds->untag_bridge_pvid = true;
+	/* tag_8021q has 3 bits for the VBID, and the value 0 is reserved */
+	ds->num_fwd_offloading_bridges = 7;
+
+	/* Advertise the 8 egress queues */
+	ds->num_tx_queues = SJA1105_NUM_TC;
+
+	ds->mtu_enforcement_ingress = true;
+	ds->assisted_learning_on_cpu_port = true;
+
+	return 0;
+
+out_devlink_teardown:
+	sja1105_devlink_teardown(ds);
+out_mdiobus_unregister:
+	sja1105_mdiobus_unregister(ds);
+out_ptp_clock_unregister:
+	sja1105_ptp_clock_unregister(ds);
+out_flower_teardown:
+	sja1105_flower_teardown(ds);
+	sja1105_tas_teardown(ds);
+	sja1105_teardown_ports(priv);
+out_static_config_free:
+	sja1105_static_config_free(&priv->static_config);
+
+	return rc;
+}
+
+static void sja1105_teardown(struct dsa_switch *ds)
+{
+	struct sja1105_private *priv = ds->priv;
+
+	rtnl_lock();
+	dsa_tag_8021q_unregister(ds);
+	rtnl_unlock();
+
+	sja1105_devlink_teardown(ds);
+	sja1105_mdiobus_unregister(ds);
+	sja1105_ptp_clock_unregister(ds);
+	sja1105_flower_teardown(ds);
+	sja1105_tas_teardown(ds);
+	sja1105_teardown_ports(priv);
+	sja1105_static_config_free(&priv->static_config);
+}
+
+const struct dsa_switch_ops sja1105_switch_ops = {
 	.get_tag_protocol	= sja1105_get_tag_protocol,
 	.setup			= sja1105_setup,
 	.teardown		= sja1105_teardown,
@@ -3635,14 +3136,15 @@ static const struct dsa_switch_ops sja1105_switch_ops = {
 	.port_fdb_dump		= sja1105_fdb_dump,
 	.port_fdb_add		= sja1105_fdb_add,
 	.port_fdb_del		= sja1105_fdb_del,
+	.port_fast_age		= sja1105_fast_age,
 	.port_bridge_join	= sja1105_bridge_join,
 	.port_bridge_leave	= sja1105_bridge_leave,
 	.port_pre_bridge_flags	= sja1105_port_pre_bridge_flags,
 	.port_bridge_flags	= sja1105_port_bridge_flags,
 	.port_stp_state_set	= sja1105_bridge_stp_state_set,
 	.port_vlan_filtering	= sja1105_vlan_filtering,
-	.port_vlan_add		= sja1105_vlan_add,
-	.port_vlan_del		= sja1105_vlan_del,
+	.port_vlan_add		= sja1105_bridge_vlan_add,
+	.port_vlan_del		= sja1105_bridge_vlan_del,
 	.port_mdb_add		= sja1105_mdb_add,
 	.port_mdb_del		= sja1105_mdb_del,
 	.port_hwtstamp_get	= sja1105_hwtstamp_get,
@@ -3657,12 +3159,14 @@ static const struct dsa_switch_ops sja1105_switch_ops = {
 	.cls_flower_add		= sja1105_cls_flower_add,
 	.cls_flower_del		= sja1105_cls_flower_del,
 	.cls_flower_stats	= sja1105_cls_flower_stats,
-	.crosschip_bridge_join	= sja1105_crosschip_bridge_join,
-	.crosschip_bridge_leave	= sja1105_crosschip_bridge_leave,
-	.devlink_param_get	= sja1105_devlink_param_get,
-	.devlink_param_set	= sja1105_devlink_param_set,
 	.devlink_info_get	= sja1105_devlink_info_get,
+	.tag_8021q_vlan_add	= sja1105_dsa_8021q_vlan_add,
+	.tag_8021q_vlan_del	= sja1105_dsa_8021q_vlan_del,
+	.port_prechangeupper	= sja1105_prechangeupper,
+	.port_bridge_tx_fwd_offload = dsa_tag_8021q_bridge_tx_fwd_offload,
+	.port_bridge_tx_fwd_unoffload = dsa_tag_8021q_bridge_tx_fwd_unoffload,
 };
+EXPORT_SYMBOL_GPL(sja1105_switch_ops);
 
 static const struct of_device_id sja1105_dt_ids[];
 
@@ -3715,12 +3219,11 @@ static int sja1105_check_device_id(struct sja1105_private *priv)
 
 static int sja1105_probe(struct spi_device *spi)
 {
-	struct sja1105_tagger_data *tagger_data;
 	struct device *dev = &spi->dev;
 	struct sja1105_private *priv;
 	size_t max_xfer, max_msg;
 	struct dsa_switch *ds;
-	int rc, port;
+	int rc;
 
 	if (!dev->of_node) {
 		dev_err(dev, "No DTS bindings for SJA1105 driver\n");
@@ -3800,95 +3303,42 @@ static int sja1105_probe(struct spi_device *spi)
 	ds->priv = priv;
 	priv->ds = ds;
 
-	tagger_data = &priv->tagger_data;
-
 	mutex_init(&priv->ptp_data.lock);
 	mutex_init(&priv->mgmt_lock);
 
-	priv->dsa_8021q_ctx = devm_kzalloc(dev, sizeof(*priv->dsa_8021q_ctx),
-					   GFP_KERNEL);
-	if (!priv->dsa_8021q_ctx)
-		return -ENOMEM;
-
-	priv->dsa_8021q_ctx->ops = &sja1105_dsa_8021q_ops;
-	priv->dsa_8021q_ctx->proto = htons(ETH_P_8021Q);
-	priv->dsa_8021q_ctx->ds = ds;
-
-	INIT_LIST_HEAD(&priv->dsa_8021q_ctx->crosschip_links);
-	INIT_LIST_HEAD(&priv->bridge_vlans);
-	INIT_LIST_HEAD(&priv->dsa_8021q_vlans);
-
-	sja1105_tas_setup(ds);
-	sja1105_flower_setup(ds);
+	rc = sja1105_parse_dt(priv);
+	if (rc < 0) {
+		dev_err(ds->dev, "Failed to parse DT: %d\n", rc);
+		return rc;
+	}
 
-	rc = dsa_register_switch(priv->ds);
-	if (rc)
+	/* Error out early if internal delays are required through DT
+	 * and we can't apply them.
+	 */
+	rc = sja1105_parse_rgmii_delays(priv);
+	if (rc < 0) {
+		dev_err(ds->dev, "RGMII delay not supported\n");
 		return rc;
+	}
 
 	if (IS_ENABLED(CONFIG_NET_SCH_CBS)) {
 		priv->cbs = devm_kcalloc(dev, priv->info->num_cbs_shapers,
 					 sizeof(struct sja1105_cbs_entry),
 					 GFP_KERNEL);
-		if (!priv->cbs) {
-			rc = -ENOMEM;
-			goto out_unregister_switch;
-		}
-	}
-
-	/* Connections between dsa_port and sja1105_port */
-	for (port = 0; port < ds->num_ports; port++) {
-		struct sja1105_port *sp = &priv->ports[port];
-		struct dsa_port *dp = dsa_to_port(ds, port);
-		struct net_device *slave;
-		int subvlan;
-
-		if (!dsa_is_user_port(ds, port))
-			continue;
-
-		dp->priv = sp;
-		sp->dp = dp;
-		sp->data = tagger_data;
-		slave = dp->slave;
-		kthread_init_work(&sp->xmit_work, sja1105_port_deferred_xmit);
-		sp->xmit_worker = kthread_create_worker(0, "%s_xmit",
-							slave->name);
-		if (IS_ERR(sp->xmit_worker)) {
-			rc = PTR_ERR(sp->xmit_worker);
-			dev_err(ds->dev,
-				"failed to create deferred xmit thread: %d\n",
-				rc);
-			goto out_destroy_workers;
-		}
-		skb_queue_head_init(&sp->xmit_queue);
-		sp->xmit_tpid = ETH_P_SJA1105;
-
-		for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++)
-			sp->subvlan_map[subvlan] = VLAN_N_VID;
-	}
-
-	return 0;
-
-out_destroy_workers:
-	while (port-- > 0) {
-		struct sja1105_port *sp = &priv->ports[port];
-
-		if (!dsa_is_user_port(ds, port))
-			continue;
-
-		kthread_destroy_worker(sp->xmit_worker);
+		if (!priv->cbs)
+			return -ENOMEM;
 	}
 
-out_unregister_switch:
-	dsa_unregister_switch(ds);
-
-	return rc;
+	return dsa_register_switch(priv->ds);
 }
 
 static int sja1105_remove(struct spi_device *spi)
 {
 	struct sja1105_private *priv = spi_get_drvdata(spi);
+	struct dsa_switch *ds = priv->ds;
+
+	dsa_unregister_switch(ds);
 
-	dsa_unregister_switch(priv->ds);
 	return 0;
 }
 
diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c
index 08cc5dbf2fa6..d60a530d0272 100644
--- a/drivers/net/dsa/sja1105/sja1105_spi.c
+++ b/drivers/net/dsa/sja1105/sja1105_spi.c
@@ -575,7 +575,6 @@ const struct sja1105_info sja1105e_info = {
 	.part_no		= SJA1105ET_PART_NO,
 	.static_ops		= sja1105e_table_ops,
 	.dyn_ops		= sja1105et_dyn_ops,
-	.qinq_tpid		= ETH_P_8021Q,
 	.tag_proto		= DSA_TAG_PROTO_SJA1105,
 	.can_limit_mcast_flood	= false,
 	.ptp_ts_bits		= 24,
@@ -608,7 +607,6 @@ const struct sja1105_info sja1105t_info = {
 	.part_no		= SJA1105ET_PART_NO,
 	.static_ops		= sja1105t_table_ops,
 	.dyn_ops		= sja1105et_dyn_ops,
-	.qinq_tpid		= ETH_P_8021Q,
 	.tag_proto		= DSA_TAG_PROTO_SJA1105,
 	.can_limit_mcast_flood	= false,
 	.ptp_ts_bits		= 24,
@@ -641,7 +639,6 @@ const struct sja1105_info sja1105p_info = {
 	.part_no		= SJA1105P_PART_NO,
 	.static_ops		= sja1105p_table_ops,
 	.dyn_ops		= sja1105pqrs_dyn_ops,
-	.qinq_tpid		= ETH_P_8021AD,
 	.tag_proto		= DSA_TAG_PROTO_SJA1105,
 	.can_limit_mcast_flood	= true,
 	.ptp_ts_bits		= 32,
@@ -675,7 +672,6 @@ const struct sja1105_info sja1105q_info = {
 	.part_no		= SJA1105Q_PART_NO,
 	.static_ops		= sja1105q_table_ops,
 	.dyn_ops		= sja1105pqrs_dyn_ops,
-	.qinq_tpid		= ETH_P_8021AD,
 	.tag_proto		= DSA_TAG_PROTO_SJA1105,
 	.can_limit_mcast_flood	= true,
 	.ptp_ts_bits		= 32,
@@ -709,7 +705,6 @@ const struct sja1105_info sja1105r_info = {
 	.part_no		= SJA1105R_PART_NO,
 	.static_ops		= sja1105r_table_ops,
 	.dyn_ops		= sja1105pqrs_dyn_ops,
-	.qinq_tpid		= ETH_P_8021AD,
 	.tag_proto		= DSA_TAG_PROTO_SJA1105,
 	.can_limit_mcast_flood	= true,
 	.ptp_ts_bits		= 32,
@@ -747,7 +742,6 @@ const struct sja1105_info sja1105s_info = {
 	.static_ops		= sja1105s_table_ops,
 	.dyn_ops		= sja1105pqrs_dyn_ops,
 	.regs			= &sja1105pqrs_regs,
-	.qinq_tpid		= ETH_P_8021AD,
 	.tag_proto		= DSA_TAG_PROTO_SJA1105,
 	.can_limit_mcast_flood	= true,
 	.ptp_ts_bits		= 32,
@@ -784,7 +778,6 @@ const struct sja1105_info sja1110a_info = {
 	.static_ops		= sja1110_table_ops,
 	.dyn_ops		= sja1110_dyn_ops,
 	.regs			= &sja1110_regs,
-	.qinq_tpid		= ETH_P_8021AD,
 	.tag_proto		= DSA_TAG_PROTO_SJA1110,
 	.can_limit_mcast_flood	= true,
 	.multiple_cascade_ports	= true,
@@ -835,7 +828,6 @@ const struct sja1105_info sja1110b_info = {
 	.static_ops		= sja1110_table_ops,
 	.dyn_ops		= sja1110_dyn_ops,
 	.regs			= &sja1110_regs,
-	.qinq_tpid		= ETH_P_8021AD,
 	.tag_proto		= DSA_TAG_PROTO_SJA1110,
 	.can_limit_mcast_flood	= true,
 	.multiple_cascade_ports	= true,
@@ -886,7 +878,6 @@ const struct sja1105_info sja1110c_info = {
 	.static_ops		= sja1110_table_ops,
 	.dyn_ops		= sja1110_dyn_ops,
 	.regs			= &sja1110_regs,
-	.qinq_tpid		= ETH_P_8021AD,
 	.tag_proto		= DSA_TAG_PROTO_SJA1110,
 	.can_limit_mcast_flood	= true,
 	.multiple_cascade_ports	= true,
@@ -937,7 +928,6 @@ const struct sja1105_info sja1110d_info = {
 	.static_ops		= sja1110_table_ops,
 	.dyn_ops		= sja1110_dyn_ops,
 	.regs			= &sja1110_regs,
-	.qinq_tpid		= ETH_P_8021AD,
 	.tag_proto		= DSA_TAG_PROTO_SJA1110,
 	.can_limit_mcast_flood	= true,
 	.multiple_cascade_ports	= true,
diff --git a/drivers/net/dsa/sja1105/sja1105_vl.c b/drivers/net/dsa/sja1105/sja1105_vl.c
index f6e13e6c6a18..ec7b65daec20 100644
--- a/drivers/net/dsa/sja1105/sja1105_vl.c
+++ b/drivers/net/dsa/sja1105/sja1105_vl.c
@@ -496,14 +496,11 @@ int sja1105_vl_redirect(struct sja1105_private *priv, int port,
 	struct sja1105_rule *rule = sja1105_rule_find(priv, cookie);
 	int rc;
 
-	if (priv->vlan_state == SJA1105_VLAN_UNAWARE &&
-	    key->type != SJA1105_KEY_VLAN_UNAWARE_VL) {
+	if (!priv->vlan_aware && key->type != SJA1105_KEY_VLAN_UNAWARE_VL) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can only redirect based on DMAC");
 		return -EOPNOTSUPP;
-	} else if ((priv->vlan_state == SJA1105_VLAN_BEST_EFFORT ||
-		    priv->vlan_state == SJA1105_VLAN_FILTERING_FULL) &&
-		   key->type != SJA1105_KEY_VLAN_AWARE_VL) {
+	} else if (priv->vlan_aware && key->type != SJA1105_KEY_VLAN_AWARE_VL) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can only redirect based on {DMAC, VID, PCP}");
 		return -EOPNOTSUPP;
@@ -595,14 +592,11 @@ int sja1105_vl_gate(struct sja1105_private *priv, int port,
 		return -ERANGE;
 	}
 
-	if (priv->vlan_state == SJA1105_VLAN_UNAWARE &&
-	    key->type != SJA1105_KEY_VLAN_UNAWARE_VL) {
+	if (!priv->vlan_aware && key->type != SJA1105_KEY_VLAN_UNAWARE_VL) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can only gate based on DMAC");
 		return -EOPNOTSUPP;
-	} else if ((priv->vlan_state == SJA1105_VLAN_BEST_EFFORT ||
-		    priv->vlan_state == SJA1105_VLAN_FILTERING_FULL) &&
-		   key->type != SJA1105_KEY_VLAN_AWARE_VL) {
+	} else if (priv->vlan_aware && key->type != SJA1105_KEY_VLAN_AWARE_VL) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can only gate based on {DMAC, VID, PCP}");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/eql.c b/drivers/net/eql.c
index 74263f8efe1a..8ef34901c2d8 100644
--- a/drivers/net/eql.c
+++ b/drivers/net/eql.c
@@ -113,6 +113,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/compat.h>
 #include <linux/capability.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -131,7 +132,8 @@
 
 static int eql_open(struct net_device *dev);
 static int eql_close(struct net_device *dev);
-static int eql_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
+static int eql_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			      void __user *data, int cmd);
 static netdev_tx_t eql_slave_xmit(struct sk_buff *skb, struct net_device *dev);
 
 #define eql_is_slave(dev)	((dev->flags & IFF_SLAVE) == IFF_SLAVE)
@@ -170,7 +172,7 @@ static const char version[] __initconst =
 static const struct net_device_ops eql_netdev_ops = {
 	.ndo_open	= eql_open,
 	.ndo_stop	= eql_close,
-	.ndo_do_ioctl	= eql_ioctl,
+	.ndo_siocdevprivate = eql_siocdevprivate,
 	.ndo_start_xmit	= eql_slave_xmit,
 };
 
@@ -268,25 +270,29 @@ static int eql_s_slave_cfg(struct net_device *dev, slave_config_t __user *sc);
 static int eql_g_master_cfg(struct net_device *dev, master_config_t __user *mc);
 static int eql_s_master_cfg(struct net_device *dev, master_config_t __user *mc);
 
-static int eql_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int eql_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			      void __user *data, int cmd)
 {
 	if (cmd != EQL_GETMASTRCFG && cmd != EQL_GETSLAVECFG &&
 	    !capable(CAP_NET_ADMIN))
 	  	return -EPERM;
 
+	if (in_compat_syscall()) /* to be implemented */
+		return -EOPNOTSUPP;
+
 	switch (cmd) {
 		case EQL_ENSLAVE:
-			return eql_enslave(dev, ifr->ifr_data);
+			return eql_enslave(dev, data);
 		case EQL_EMANCIPATE:
-			return eql_emancipate(dev, ifr->ifr_data);
+			return eql_emancipate(dev, data);
 		case EQL_GETSLAVECFG:
-			return eql_g_slave_cfg(dev, ifr->ifr_data);
+			return eql_g_slave_cfg(dev, data);
 		case EQL_SETSLAVECFG:
-			return eql_s_slave_cfg(dev, ifr->ifr_data);
+			return eql_s_slave_cfg(dev, data);
 		case EQL_GETMASTRCFG:
-			return eql_g_master_cfg(dev, ifr->ifr_data);
+			return eql_g_master_cfg(dev, data);
 		case EQL_SETMASTRCFG:
-			return eql_s_master_cfg(dev, ifr->ifr_data);
+			return eql_s_master_cfg(dev, data);
 		default:
 			return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c
index 96cc5fc36eb5..87c906e744fb 100644
--- a/drivers/net/ethernet/3com/3c509.c
+++ b/drivers/net/ethernet/3com/3c509.c
@@ -302,7 +302,6 @@ static int el3_isa_match(struct device *pdev, unsigned int ndev)
 		return -ENOMEM;
 
 	SET_NETDEV_DEV(dev, pdev);
-	netdev_boot_setup_check(dev);
 
 	if (!request_region(ioaddr, EL3_IO_EXTENT, "3c509-isa")) {
 		free_netdev(dev);
@@ -421,7 +420,6 @@ static int el3_pnp_probe(struct pnp_dev *pdev, const struct pnp_device_id *id)
 		return -ENOMEM;
 	}
 	SET_NETDEV_DEV(dev, &pdev->dev);
-	netdev_boot_setup_check(dev);
 
 	el3_dev_fill(dev, phys_addr, ioaddr, irq, if_port, EL3_PNP);
 	pnp_set_drvdata(pdev, dev);
@@ -514,7 +512,9 @@ static int el3_common_init(struct net_device *dev)
 {
 	struct el3_private *lp = netdev_priv(dev);
 	int err;
-	const char *if_names[] = {"10baseT", "AUI", "undefined", "BNC"};
+	static const char * const if_names[] = {
+		"10baseT", "AUI", "undefined", "BNC"
+	};
 
 	spin_lock_init(&lp->lock);
 
@@ -588,7 +588,6 @@ static int el3_eisa_probe(struct device *device)
 	}
 
 	SET_NETDEV_DEV(dev, device);
-	netdev_boot_setup_check(dev);
 
 	el3_dev_fill(dev, phys_addr, ioaddr, irq, if_port, EL3_EISA);
 	eisa_set_drvdata (edev, dev);
diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c
index 47b4215bb93b..8d90fed5d33e 100644
--- a/drivers/net/ethernet/3com/3c515.c
+++ b/drivers/net/ethernet/3com/3c515.c
@@ -407,7 +407,7 @@ MODULE_PARM_DESC(max_interrupt_work, "3c515 maximum events handled per interrupt
 /* we will need locking (and refcounting) if we ever use it for more */
 static LIST_HEAD(root_corkscrew_dev);
 
-int init_module(void)
+static int corkscrew_init_module(void)
 {
 	int found = 0;
 	if (debug >= 0)
@@ -416,6 +416,7 @@ int init_module(void)
 		found++;
 	return found ? 0 : -ENODEV;
 }
+module_init(corkscrew_init_module);
 
 #else
 struct net_device *tc515_probe(int unit)
diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c
index f66e7fb9a2bb..dd4d3c48b98d 100644
--- a/drivers/net/ethernet/3com/3c574_cs.c
+++ b/drivers/net/ethernet/3com/3c574_cs.c
@@ -252,7 +252,7 @@ static const struct net_device_ops el3_netdev_ops = {
 	.ndo_start_xmit		= el3_start_xmit,
 	.ndo_tx_timeout 	= el3_tx_timeout,
 	.ndo_get_stats		= el3_get_stats,
-	.ndo_do_ioctl		= el3_ioctl,
+	.ndo_eth_ioctl		= el3_ioctl,
 	.ndo_set_rx_mode	= set_multicast_list,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 7d7d3ffe25c3..17c16333a412 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -1052,7 +1052,7 @@ static const struct net_device_ops boomrang_netdev_ops = {
 	.ndo_tx_timeout		= vortex_tx_timeout,
 	.ndo_get_stats		= vortex_get_stats,
 #ifdef CONFIG_PCI
-	.ndo_do_ioctl 		= vortex_ioctl,
+	.ndo_eth_ioctl		= vortex_ioctl,
 #endif
 	.ndo_set_rx_mode	= set_rx_mode,
 	.ndo_set_mac_address 	= eth_mac_addr,
@@ -1069,7 +1069,7 @@ static const struct net_device_ops vortex_netdev_ops = {
 	.ndo_tx_timeout		= vortex_tx_timeout,
 	.ndo_get_stats		= vortex_get_stats,
 #ifdef CONFIG_PCI
-	.ndo_do_ioctl 		= vortex_ioctl,
+	.ndo_eth_ioctl		= vortex_ioctl,
 #endif
 	.ndo_set_rx_mode	= set_rx_mode,
 	.ndo_set_mac_address 	= eth_mac_addr,
diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig
index a52a3740f0c9..706bd59bf645 100644
--- a/drivers/net/ethernet/3com/Kconfig
+++ b/drivers/net/ethernet/3com/Kconfig
@@ -34,6 +34,7 @@ config EL3
 config 3C515
 	tristate "3c515 ISA \"Fast EtherLink\""
 	depends on ISA && ISA_DMA_API && !PPC32
+	select NETDEV_LEGACY_INIT
 	help
 	  If you have a 3Com ISA EtherLink XL "Corkscrew" 3c515 Fast Ethernet
 	  network card, say Y here.
diff --git a/drivers/net/ethernet/8390/Kconfig b/drivers/net/ethernet/8390/Kconfig
index 9f4b302fd2ce..a4130e643342 100644
--- a/drivers/net/ethernet/8390/Kconfig
+++ b/drivers/net/ethernet/8390/Kconfig
@@ -102,6 +102,7 @@ config MCF8390
 config NE2000
 	tristate "NE2000/NE1000 support"
 	depends on (ISA || (Q40 && m) || MACH_TX49XX || ATARI_ETHERNEC)
+	select NETDEV_LEGACY_INIT if ISA
 	select CRC32
 	help
 	  If you have a network (Ethernet) card of this type, say Y here.
@@ -169,6 +170,7 @@ config STNIC
 config ULTRA
 	tristate "SMC Ultra support"
 	depends on ISA
+	select NETDEV_LEGACY_INIT
 	select CRC32
 	help
 	  If you have a network (Ethernet) card of this type, say Y here.
@@ -186,6 +188,7 @@ config ULTRA
 config WD80x3
 	tristate "WD80*3 support"
 	depends on ISA
+	select NETDEV_LEGACY_INIT
 	select CRC32
 	help
 	  If you have a network (Ethernet) card of this type, say Y here.
diff --git a/drivers/net/ethernet/8390/apne.c b/drivers/net/ethernet/8390/apne.c
index fe6c834c422e..da1ae37a9d73 100644
--- a/drivers/net/ethernet/8390/apne.c
+++ b/drivers/net/ethernet/8390/apne.c
@@ -75,7 +75,6 @@
 #define NESM_STOP_PG	0x80	/* Last page +1 of RX ring */
 
 
-struct net_device * __init apne_probe(int unit);
 static int apne_probe1(struct net_device *dev, int ioaddr);
 
 static void apne_reset_8390(struct net_device *dev);
@@ -120,7 +119,7 @@ static u32 apne_msg_enable;
 module_param_named(msg_enable, apne_msg_enable, uint, 0444);
 MODULE_PARM_DESC(msg_enable, "Debug message level (see linux/netdevice.h for bitmap)");
 
-struct net_device * __init apne_probe(int unit)
+static struct net_device * __init apne_probe(void)
 {
 	struct net_device *dev;
 	struct ei_device *ei_local;
@@ -150,10 +149,6 @@ struct net_device * __init apne_probe(int unit)
 	dev = alloc_ei_netdev();
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
-	if (unit >= 0) {
-		sprintf(dev->name, "eth%d", unit);
-		netdev_boot_setup_check(dev);
-	}
 	ei_local = netdev_priv(dev);
 	ei_local->msg_enable = apne_msg_enable;
 
@@ -554,12 +549,11 @@ static irqreturn_t apne_interrupt(int irq, void *dev_id)
     return IRQ_HANDLED;
 }
 
-#ifdef MODULE
 static struct net_device *apne_dev;
 
 static int __init apne_module_init(void)
 {
-	apne_dev = apne_probe(-1);
+	apne_dev = apne_probe();
 	return PTR_ERR_OR_ZERO(apne_dev);
 }
 
@@ -579,7 +573,6 @@ static void __exit apne_module_exit(void)
 }
 module_init(apne_module_init);
 module_exit(apne_module_exit);
-#endif
 
 static int init_pcmcia(void)
 {
diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c
index 172947fc051a..6c6bdd5913ec 100644
--- a/drivers/net/ethernet/8390/ax88796.c
+++ b/drivers/net/ethernet/8390/ax88796.c
@@ -101,6 +101,13 @@ static inline struct ax_device *to_ax_dev(struct net_device *dev)
 	return (struct ax_device *)(ei_local + 1);
 }
 
+void ax_NS8390_reinit(struct net_device *dev)
+{
+	ax_NS8390_init(dev, 1);
+}
+
+EXPORT_SYMBOL_GPL(ax_NS8390_reinit);
+
 /*
  * ax_initial_check
  *
@@ -635,7 +642,7 @@ static void ax_eeprom_register_write(struct eeprom_93cx6 *eeprom)
 static const struct net_device_ops ax_netdev_ops = {
 	.ndo_open		= ax_open,
 	.ndo_stop		= ax_close,
-	.ndo_do_ioctl		= ax_ioctl,
+	.ndo_eth_ioctl		= ax_ioctl,
 
 	.ndo_start_xmit		= ax_ei_start_xmit,
 	.ndo_tx_timeout		= ax_ei_tx_timeout,
diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c
index 8c321dfc7b3b..3c370e686ec3 100644
--- a/drivers/net/ethernet/8390/axnet_cs.c
+++ b/drivers/net/ethernet/8390/axnet_cs.c
@@ -128,7 +128,7 @@ static inline struct axnet_dev *PRIV(struct net_device *dev)
 static const struct net_device_ops axnet_netdev_ops = {
 	.ndo_open 		= axnet_open,
 	.ndo_stop		= axnet_close,
-	.ndo_do_ioctl		= axnet_ioctl,
+	.ndo_eth_ioctl		= axnet_ioctl,
 	.ndo_start_xmit		= axnet_start_xmit,
 	.ndo_tx_timeout		= axnet_tx_timeout,
 	.ndo_get_stats		= get_stats,
diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c
index e9756d0ea5b8..53660bc8d6ff 100644
--- a/drivers/net/ethernet/8390/ne.c
+++ b/drivers/net/ethernet/8390/ne.c
@@ -923,7 +923,7 @@ static void __init ne_add_devices(void)
 }
 
 #ifdef MODULE
-int __init init_module(void)
+static int __init ne_init(void)
 {
 	int retval;
 	ne_add_devices();
@@ -940,6 +940,7 @@ int __init init_module(void)
 	ne_loop_rm_unreg(0);
 	return retval;
 }
+module_init(ne_init);
 #else /* MODULE */
 static int __init ne_init(void)
 {
@@ -951,6 +952,7 @@ static int __init ne_init(void)
 }
 module_init(ne_init);
 
+#ifdef CONFIG_NETDEV_LEGACY_INIT
 struct net_device * __init ne_probe(int unit)
 {
 	int this_dev;
@@ -991,6 +993,7 @@ struct net_device * __init ne_probe(int unit)
 
 	return ERR_PTR(-ENODEV);
 }
+#endif
 #endif /* MODULE */
 
 static void __exit ne_exit(void)
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index cac036706382..96ad72abd373 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -223,7 +223,7 @@ static const struct net_device_ops pcnet_netdev_ops = {
 	.ndo_set_config		= set_config,
 	.ndo_start_xmit 	= ei_start_xmit,
 	.ndo_get_stats		= ei_get_stats,
-	.ndo_do_ioctl 		= ei_ioctl,
+	.ndo_eth_ioctl		= ei_ioctl,
 	.ndo_set_rx_mode	= ei_set_multicast_list,
 	.ndo_tx_timeout 	= ei_tx_timeout,
 	.ndo_set_mac_address 	= eth_mac_addr,
diff --git a/drivers/net/ethernet/8390/smc-ultra.c b/drivers/net/ethernet/8390/smc-ultra.c
index 1d8ed7357b7f..0890fa493f70 100644
--- a/drivers/net/ethernet/8390/smc-ultra.c
+++ b/drivers/net/ethernet/8390/smc-ultra.c
@@ -522,7 +522,6 @@ static void ultra_pio_input(struct net_device *dev, int count,
 	/* We know skbuffs are padded to at least word alignment. */
 	insw(ioaddr + IOPD, buf, (count+1)>>1);
 }
-
 static void ultra_pio_output(struct net_device *dev, int count,
 							const unsigned char *buf, const int start_page)
 {
@@ -572,8 +571,7 @@ MODULE_LICENSE("GPL");
 
 /* This is set up so that only a single autoprobe takes place per call.
 ISA device autoprobes on a running machine are not recommended. */
-int __init
-init_module(void)
+static int __init ultra_init_module(void)
 {
 	struct net_device *dev;
 	int this_dev, found = 0;
@@ -600,6 +598,7 @@ init_module(void)
 		return 0;
 	return -ENXIO;
 }
+module_init(ultra_init_module);
 
 static void cleanup_card(struct net_device *dev)
 {
@@ -613,8 +612,7 @@ static void cleanup_card(struct net_device *dev)
 	iounmap(ei_status.mem);
 }
 
-void __exit
-cleanup_module(void)
+static void __exit ultra_cleanup_module(void)
 {
 	int this_dev;
 
@@ -627,4 +625,5 @@ cleanup_module(void)
 		}
 	}
 }
+module_exit(ultra_cleanup_module);
 #endif /* MODULE */
diff --git a/drivers/net/ethernet/8390/wd.c b/drivers/net/ethernet/8390/wd.c
index c834123560f1..263a942d81fa 100644
--- a/drivers/net/ethernet/8390/wd.c
+++ b/drivers/net/ethernet/8390/wd.c
@@ -519,7 +519,7 @@ MODULE_LICENSE("GPL");
 /* This is set up so that only a single autoprobe takes place per call.
 ISA device autoprobes on a running machine are not recommended. */
 
-int __init init_module(void)
+static int __init wd_init_module(void)
 {
 	struct net_device *dev;
 	int this_dev, found = 0;
@@ -548,6 +548,7 @@ int __init init_module(void)
 		return 0;
 	return -ENXIO;
 }
+module_init(wd_init_module);
 
 static void cleanup_card(struct net_device *dev)
 {
@@ -556,8 +557,7 @@ static void cleanup_card(struct net_device *dev)
 	iounmap(ei_status.mem);
 }
 
-void __exit
-cleanup_module(void)
+static void __exit wd_cleanup_module(void)
 {
 	int this_dev;
 
@@ -570,4 +570,5 @@ cleanup_module(void)
 		}
 	}
 }
+module_exit(wd_cleanup_module);
 #endif /* MODULE */
diff --git a/drivers/net/ethernet/8390/xsurf100.c b/drivers/net/ethernet/8390/xsurf100.c
index e2c963821ffe..fe7a74707aa4 100644
--- a/drivers/net/ethernet/8390/xsurf100.c
+++ b/drivers/net/ethernet/8390/xsurf100.c
@@ -22,8 +22,6 @@
 #define XS100_8390_DATA_WRITE32_BASE 0x0C80
 #define XS100_8390_DATA_AREA_SIZE 0x80
 
-#define __NS8390_init ax_NS8390_init
-
 /* force unsigned long back to 'void __iomem *' */
 #define ax_convert_addr(_a) ((void __force __iomem *)(_a))
 
@@ -42,10 +40,7 @@
 /* Ensure we have our RCR base value */
 #define AX88796_PLATFORM
 
-static unsigned char version[] =
-		"ax88796.c: Copyright 2005,2007 Simtec Electronics\n";
-
-#include "lib8390.c"
+#include "8390.h"
 
 /* from ne.c */
 #define NE_CMD		EI_SHIFT(0x00)
@@ -232,7 +227,7 @@ static void xs100_block_output(struct net_device *dev, int count,
 		if (jiffies - dma_start > 2 * HZ / 100) {	/* 20ms */
 			netdev_warn(dev, "timeout waiting for Tx RDC.\n");
 			ei_local->reset_8390(dev);
-			ax_NS8390_init(dev, 1);
+			ax_NS8390_reinit(dev);
 			break;
 		}
 	}
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 1cdff1dca790..d796684ec9ca 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -118,6 +118,7 @@ config LANTIQ_XRX200
 	  Support for the PMAC of the Gigabit switch (GSWIP) inside the
 	  Lantiq / Intel VRX200 VDSL SoC
 
+source "drivers/net/ethernet/litex/Kconfig"
 source "drivers/net/ethernet/marvell/Kconfig"
 source "drivers/net/ethernet/mediatek/Kconfig"
 source "drivers/net/ethernet/mellanox/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index cb3f9084a21b..aaa5078cd7d1 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -51,6 +51,7 @@ obj-$(CONFIG_JME) += jme.o
 obj-$(CONFIG_KORINA) += korina.o
 obj-$(CONFIG_LANTIQ_ETOP) += lantiq_etop.o
 obj-$(CONFIG_LANTIQ_XRX200) += lantiq_xrx200.o
+obj-$(CONFIG_NET_VENDOR_LITEX) += litex/
 obj-$(CONFIG_NET_VENDOR_MARVELL) += marvell/
 obj-$(CONFIG_NET_VENDOR_MEDIATEK) += mediatek/
 obj-$(CONFIG_NET_VENDOR_MELLANOX) += mellanox/
diff --git a/drivers/net/ethernet/actions/Kconfig b/drivers/net/ethernet/actions/Kconfig
index ccad6a3f4d6f..f630cac2ab6c 100644
--- a/drivers/net/ethernet/actions/Kconfig
+++ b/drivers/net/ethernet/actions/Kconfig
@@ -2,8 +2,8 @@
 
 config NET_VENDOR_ACTIONS
 	bool "Actions Semi devices"
-	default y
-	depends on ARCH_ACTIONS
+	depends on ARCH_ACTIONS || COMPILE_TEST
+	default ARCH_ACTIONS
 	help
 	  If you have a network (Ethernet) card belonging to this class, say Y.
 
diff --git a/drivers/net/ethernet/actions/owl-emac.c b/drivers/net/ethernet/actions/owl-emac.c
index b8e771c2bc40..c4ecf4fcadf8 100644
--- a/drivers/net/ethernet/actions/owl-emac.c
+++ b/drivers/net/ethernet/actions/owl-emac.c
@@ -1179,8 +1179,8 @@ static int owl_emac_ndo_set_mac_addr(struct net_device *netdev, void *addr)
 	return owl_emac_setup_frame_xmit(netdev_priv(netdev));
 }
 
-static int owl_emac_ndo_do_ioctl(struct net_device *netdev,
-				 struct ifreq *req, int cmd)
+static int owl_emac_ndo_eth_ioctl(struct net_device *netdev,
+				  struct ifreq *req, int cmd)
 {
 	if (!netif_running(netdev))
 		return -EINVAL;
@@ -1224,7 +1224,7 @@ static const struct net_device_ops owl_emac_netdev_ops = {
 	.ndo_set_rx_mode	= owl_emac_ndo_set_rx_mode,
 	.ndo_set_mac_address	= owl_emac_ndo_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= owl_emac_ndo_do_ioctl,
+	.ndo_eth_ioctl		= owl_emac_ndo_eth_ioctl,
 	.ndo_tx_timeout         = owl_emac_ndo_tx_timeout,
 	.ndo_get_stats		= owl_emac_ndo_get_stats,
 };
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index 7965e5e3c985..e0f6cc910bd2 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -625,7 +625,7 @@ static const struct net_device_ops netdev_ops = {
 	.ndo_tx_timeout		= tx_timeout,
 	.ndo_get_stats		= get_stats,
 	.ndo_set_rx_mode	= set_rx_mode,
-	.ndo_do_ioctl		= netdev_ioctl,
+	.ndo_eth_ioctl		= netdev_ioctl,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 #ifdef VLAN_SUPPORT
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 41f8821f792d..920633161174 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -3882,7 +3882,7 @@ static const struct net_device_ops et131x_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_get_stats		= et131x_stats,
-	.ndo_do_ioctl		= phy_do_ioctl,
+	.ndo_eth_ioctl		= phy_do_ioctl,
 };
 
 static int et131x_pci_setup(struct pci_dev *pdev,
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index f99ae317c188..037baea1c738 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -774,7 +774,7 @@ static const struct net_device_ops emac_netdev_ops = {
 	.ndo_start_xmit		= emac_start_xmit,
 	.ndo_tx_timeout		= emac_timeout,
 	.ndo_set_rx_mode	= emac_set_rx_mode,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= emac_set_mac_address,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 27dae632efcb..13e745cf3781 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -357,7 +357,9 @@ static int ena_get_link_ksettings(struct net_device *netdev,
 }
 
 static int ena_get_coalesce(struct net_device *net_dev,
-			    struct ethtool_coalesce *coalesce)
+			    struct ethtool_coalesce *coalesce,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct ena_adapter *adapter = netdev_priv(net_dev);
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
@@ -402,7 +404,9 @@ static void ena_update_rx_rings_nonadaptive_intr_moderation(struct ena_adapter *
 }
 
 static int ena_set_coalesce(struct net_device *net_dev,
-			    struct ethtool_coalesce *coalesce)
+			    struct ethtool_coalesce *coalesce,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct ena_adapter *adapter = netdev_priv(net_dev);
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig
index d0b0609bbe23..4786f0504691 100644
--- a/drivers/net/ethernet/amd/Kconfig
+++ b/drivers/net/ethernet/amd/Kconfig
@@ -46,6 +46,7 @@ config AMD8111_ETH
 config LANCE
 	tristate "AMD LANCE and PCnet (AT1500 and NE2100) support"
 	depends on ISA && ISA_DMA_API && !ARM && !PPC32
+	select NETDEV_LEGACY_INIT
 	help
 	  If you have a network (Ethernet) card of this type, say Y here.
 	  Some LinkSys cards are of this type.
@@ -132,6 +133,7 @@ config PCMCIA_NMCLAN
 config NI65
 	tristate "NI6510 support"
 	depends on ISA && ISA_DMA_API && !ARM && !PPC32
+	select NETDEV_LEGACY_INIT
 	help
 	  If you have a network (Ethernet) card of this type, say Y here.
 
@@ -168,11 +170,11 @@ config AMD_XGBE
 	tristate "AMD 10GbE Ethernet driver"
 	depends on ((OF_NET && OF_ADDRESS) || ACPI || PCI) && HAS_IOMEM
 	depends on X86 || ARM64 || COMPILE_TEST
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select BITREVERSE
 	select CRC32
 	select PHYLIB
 	select AMD_XGBE_HAVE_ECC if X86
-	imply PTP_1588_CLOCK
 	help
 	  This driver supports the AMD 10GbE Ethernet device found on an
 	  AMD SoC.
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index 9cac5aa75a73..92e4246dc359 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -1729,7 +1729,7 @@ static const struct net_device_ops amd8111e_netdev_ops = {
 	.ndo_set_rx_mode	= amd8111e_set_multicast_list,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= amd8111e_set_mac_address,
-	.ndo_do_ioctl		= amd8111e_ioctl,
+	.ndo_eth_ioctl		= amd8111e_ioctl,
 	.ndo_change_mtu		= amd8111e_change_mtu,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	 = amd8111e_poll,
diff --git a/drivers/net/ethernet/amd/atarilance.c b/drivers/net/ethernet/amd/atarilance.c
index 36f54d13a2eb..9d2f49fd945e 100644
--- a/drivers/net/ethernet/amd/atarilance.c
+++ b/drivers/net/ethernet/amd/atarilance.c
@@ -367,7 +367,7 @@ static void *slow_memcpy( void *dst, const void *src, size_t len )
 }
 
 
-struct net_device * __init atarilance_probe(int unit)
+struct net_device * __init atarilance_probe(void)
 {
 	int i;
 	static int found;
@@ -382,10 +382,6 @@ struct net_device * __init atarilance_probe(int unit)
 	dev = alloc_etherdev(sizeof(struct lance_private));
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
-	if (unit >= 0) {
-		sprintf(dev->name, "eth%d", unit);
-		netdev_boot_setup_check(dev);
-	}
 
 	for( i = 0; i < N_LANCE_ADDR; ++i ) {
 		if (lance_probe1( dev, &lance_addr_list[i] )) {
@@ -1137,13 +1133,11 @@ static int lance_set_mac_address( struct net_device *dev, void *addr )
 	return 0;
 }
 
-
-#ifdef MODULE
 static struct net_device *atarilance_dev;
 
 static int __init atarilance_module_init(void)
 {
-	atarilance_dev = atarilance_probe(-1);
+	atarilance_dev = atarilance_probe();
 	return PTR_ERR_OR_ZERO(atarilance_dev);
 }
 
@@ -1155,4 +1149,3 @@ static void __exit atarilance_module_exit(void)
 }
 module_init(atarilance_module_init);
 module_exit(atarilance_module_exit);
-#endif /* MODULE */
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index 19e195420e24..9c1636222b99 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -1051,7 +1051,7 @@ static const struct net_device_ops au1000_netdev_ops = {
 	.ndo_stop		= au1000_close,
 	.ndo_start_xmit		= au1000_tx,
 	.ndo_set_rx_mode	= au1000_multicast_list,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_tx_timeout		= au1000_tx_timeout,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c
index 2178e6b89dbd..945bf1d87507 100644
--- a/drivers/net/ethernet/amd/lance.c
+++ b/drivers/net/ethernet/amd/lance.c
@@ -327,7 +327,7 @@ MODULE_PARM_DESC(dma, "LANCE/PCnet ISA DMA channel (ignored for some devices)");
 MODULE_PARM_DESC(irq, "LANCE/PCnet IRQ number (ignored for some devices)");
 MODULE_PARM_DESC(lance_debug, "LANCE/PCnet debug level (0-7)");
 
-int __init init_module(void)
+static int __init lance_init_module(void)
 {
 	struct net_device *dev;
 	int this_dev, found = 0;
@@ -356,6 +356,7 @@ int __init init_module(void)
 		return 0;
 	return -ENXIO;
 }
+module_init(lance_init_module);
 
 static void cleanup_card(struct net_device *dev)
 {
@@ -368,7 +369,7 @@ static void cleanup_card(struct net_device *dev)
 	kfree(lp);
 }
 
-void __exit cleanup_module(void)
+static void __exit lance_cleanup_module(void)
 {
 	int this_dev;
 
@@ -381,6 +382,7 @@ void __exit cleanup_module(void)
 		}
 	}
 }
+module_exit(lance_cleanup_module);
 #endif /* MODULE */
 MODULE_LICENSE("GPL");
 
diff --git a/drivers/net/ethernet/amd/mvme147.c b/drivers/net/ethernet/amd/mvme147.c
index 3f2e4cdd0b83..da97fccea9ea 100644
--- a/drivers/net/ethernet/amd/mvme147.c
+++ b/drivers/net/ethernet/amd/mvme147.c
@@ -68,7 +68,7 @@ static const struct net_device_ops lance_netdev_ops = {
 };
 
 /* Initialise the one and only on-board 7990 */
-struct net_device * __init mvme147lance_probe(int unit)
+static struct net_device * __init mvme147lance_probe(void)
 {
 	struct net_device *dev;
 	static int called;
@@ -86,9 +86,6 @@ struct net_device * __init mvme147lance_probe(int unit)
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	if (unit >= 0)
-		sprintf(dev->name, "eth%d", unit);
-
 	/* Fill the dev fields */
 	dev->base_addr = (unsigned long)MVME147_LANCE_BASE;
 	dev->netdev_ops = &lance_netdev_ops;
@@ -179,22 +176,21 @@ static int m147lance_close(struct net_device *dev)
 	return 0;
 }
 
-#ifdef MODULE
 MODULE_LICENSE("GPL");
 
 static struct net_device *dev_mvme147_lance;
-int __init init_module(void)
+static int __init m147lance_init(void)
 {
-	dev_mvme147_lance = mvme147lance_probe(-1);
+	dev_mvme147_lance = mvme147lance_probe();
 	return PTR_ERR_OR_ZERO(dev_mvme147_lance);
 }
+module_init(m147lance_init);
 
-void __exit cleanup_module(void)
+static void __exit m147lance_exit(void)
 {
 	struct m147lance_private *lp = netdev_priv(dev_mvme147_lance);
 	unregister_netdev(dev_mvme147_lance);
 	free_pages(lp->ram, 3);
 	free_netdev(dev_mvme147_lance);
 }
-
-#endif /* MODULE */
+module_exit(m147lance_exit);
diff --git a/drivers/net/ethernet/amd/ni65.c b/drivers/net/ethernet/amd/ni65.c
index 5c1cfb0c4a42..b5df7ad5a83f 100644
--- a/drivers/net/ethernet/amd/ni65.c
+++ b/drivers/net/ethernet/amd/ni65.c
@@ -1230,18 +1230,20 @@ MODULE_PARM_DESC(irq, "ni6510 IRQ number (ignored for some cards)");
 MODULE_PARM_DESC(io, "ni6510 I/O base address");
 MODULE_PARM_DESC(dma, "ni6510 ISA DMA channel (ignored for some cards)");
 
-int __init init_module(void)
+static int __init ni65_init_module(void)
 {
 	dev_ni65 = ni65_probe(-1);
 	return PTR_ERR_OR_ZERO(dev_ni65);
 }
+module_init(ni65_init_module);
 
-void __exit cleanup_module(void)
+static void __exit ni65_cleanup_module(void)
 {
 	unregister_netdev(dev_ni65);
 	cleanup_card(dev_ni65);
 	free_netdev(dev_ni65);
 }
+module_exit(ni65_cleanup_module);
 #endif /* MODULE */
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index 4100ab07e6b7..70d76fdb9f56 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -1572,7 +1572,7 @@ static const struct net_device_ops pcnet32_netdev_ops = {
 	.ndo_tx_timeout		= pcnet32_tx_timeout,
 	.ndo_get_stats		= pcnet32_get_stats,
 	.ndo_set_rx_mode	= pcnet32_set_multicast_list,
-	.ndo_do_ioctl		= pcnet32_ioctl,
+	.ndo_eth_ioctl		= pcnet32_ioctl,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/amd/sun3lance.c b/drivers/net/ethernet/amd/sun3lance.c
index f8d7a9387a56..4a845bc071b2 100644
--- a/drivers/net/ethernet/amd/sun3lance.c
+++ b/drivers/net/ethernet/amd/sun3lance.c
@@ -245,7 +245,7 @@ static void set_multicast_list( struct net_device *dev );
 
 /************************* End of Prototypes **************************/
 
-struct net_device * __init sun3lance_probe(int unit)
+static struct net_device * __init sun3lance_probe(void)
 {
 	struct net_device *dev;
 	static int found;
@@ -272,10 +272,6 @@ struct net_device * __init sun3lance_probe(int unit)
 	dev = alloc_etherdev(sizeof(struct lance_private));
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
-	if (unit >= 0) {
-		sprintf(dev->name, "eth%d", unit);
-		netdev_boot_setup_check(dev);
-	}
 
 	if (!lance_probe(dev))
 		goto out;
@@ -924,17 +920,16 @@ static void set_multicast_list( struct net_device *dev )
 }
 
 
-#ifdef MODULE
-
 static struct net_device *sun3lance_dev;
 
-int __init init_module(void)
+static int __init sun3lance_init(void)
 {
-	sun3lance_dev = sun3lance_probe(-1);
+	sun3lance_dev = sun3lance_probe();
 	return PTR_ERR_OR_ZERO(sun3lance_dev);
 }
+module_init(sun3lance_init);
 
-void __exit cleanup_module(void)
+static void __exit sun3lance_cleanup(void)
 {
 	unregister_netdev(sun3lance_dev);
 #ifdef CONFIG_SUN3
@@ -942,6 +937,4 @@ void __exit cleanup_module(void)
 #endif
 	free_netdev(sun3lance_dev);
 }
-
-#endif /* MODULE */
-
+module_exit(sun3lance_cleanup);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 4f714f874c4f..17a585adfb49 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -2284,7 +2284,7 @@ static const struct net_device_ops xgbe_netdev_ops = {
 	.ndo_set_rx_mode	= xgbe_set_rx_mode,
 	.ndo_set_mac_address	= xgbe_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= xgbe_ioctl,
+	.ndo_eth_ioctl		= xgbe_ioctl,
 	.ndo_change_mtu		= xgbe_change_mtu,
 	.ndo_tx_timeout		= xgbe_tx_timeout,
 	.ndo_get_stats64	= xgbe_get_stats64,
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
index 61f39a0e04f9..bafc51c34e0b 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
@@ -428,7 +428,9 @@ static void xgbe_set_msglevel(struct net_device *netdev, u32 msglevel)
 }
 
 static int xgbe_get_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *ec)
+			     struct ethtool_coalesce *ec,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 
@@ -443,7 +445,9 @@ static int xgbe_get_coalesce(struct net_device *netdev,
 }
 
 static int xgbe_set_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *ec)
+			     struct ethtool_coalesce *ec,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index de2a9348bc3f..a9ef0544e30f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -547,7 +547,9 @@ static int aq_ethtool_set_rxnfc(struct net_device *ndev,
 }
 
 static int aq_ethtool_get_coalesce(struct net_device *ndev,
-				   struct ethtool_coalesce *coal)
+				   struct ethtool_coalesce *coal,
+				   struct kernel_ethtool_coalesce *kernel_coal,
+				   struct netlink_ext_ack *extack)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
 	struct aq_nic_cfg_s *cfg;
@@ -571,7 +573,9 @@ static int aq_ethtool_get_coalesce(struct net_device *ndev,
 }
 
 static int aq_ethtool_set_coalesce(struct net_device *ndev,
-				   struct ethtool_coalesce *coal)
+				   struct ethtool_coalesce *coal,
+				   struct kernel_ethtool_coalesce *kernel_coal,
+				   struct netlink_ext_ack *extack)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
 	struct aq_nic_cfg_s *cfg;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index 4af0cd9530de..e22935ce9573 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -421,7 +421,7 @@ static const struct net_device_ops aq_ndev_ops = {
 	.ndo_change_mtu = aq_ndev_change_mtu,
 	.ndo_set_mac_address = aq_ndev_set_mac_address,
 	.ndo_set_features = aq_ndev_set_features,
-	.ndo_do_ioctl = aq_ndev_ioctl,
+	.ndo_eth_ioctl = aq_ndev_ioctl,
 	.ndo_vlan_rx_add_vid = aq_ndo_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = aq_ndo_vlan_rx_kill_vid,
 	.ndo_setup_tc = aq_ndo_setup_tc,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index 59253846e885..dee9ff74d6d6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -119,16 +119,10 @@ static int aq_pci_func_init(struct pci_dev *pdev)
 {
 	int err;
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (!err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (err)
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 	if (err) {
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (!err)
-			err = pci_set_consistent_dma_mask(pdev,
-							  DMA_BIT_MASK(32));
-	}
-	if (err != 0) {
 		err = -ENOSR;
 		goto err_exit;
 	}
@@ -417,6 +411,9 @@ static int atl_resume_common(struct device *dev, bool deep)
 	pci_restore_state(pdev);
 
 	if (deep) {
+		/* Reinitialize Nic/Vecs objects */
+		aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol);
+
 		ret = aq_nic_init(nic);
 		if (ret)
 			goto err_exit;
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index 67b8113a2b53..38c288ec9059 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -844,7 +844,7 @@ static const struct net_device_ops arc_emac_netdev_ops = {
 	.ndo_set_mac_address	= arc_emac_set_address,
 	.ndo_get_stats		= arc_emac_stats,
 	.ndo_set_rx_mode	= arc_emac_set_rx_mode,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= arc_emac_poll_controller,
 #endif
diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 1ba81b1eb6fd..02ae98aabf91 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1851,7 +1851,7 @@ static const struct net_device_ops ag71xx_netdev_ops = {
 	.ndo_open		= ag71xx_open,
 	.ndo_stop		= ag71xx_stop,
 	.ndo_start_xmit		= ag71xx_hard_start_xmit,
-	.ndo_do_ioctl		= phy_do_ioctl,
+	.ndo_eth_ioctl		= phy_do_ioctl,
 	.ndo_tx_timeout		= ag71xx_tx_timeout,
 	.ndo_change_mtu		= ag71xx_change_mtu,
 	.ndo_set_mac_address	= eth_mac_addr,
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 11ef1fbe7aee..4ea157efca86 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1701,7 +1701,7 @@ static const struct net_device_ops alx_netdev_ops = {
 	.ndo_validate_addr      = eth_validate_addr,
 	.ndo_set_mac_address    = alx_set_mac_address,
 	.ndo_change_mtu         = alx_change_mtu,
-	.ndo_do_ioctl           = alx_ioctl,
+	.ndo_eth_ioctl           = alx_ioctl,
 	.ndo_tx_timeout         = alx_tx_timeout,
 	.ndo_fix_features	= alx_fix_features,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 1c6246a5dc22..3b51b172b317 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -2609,7 +2609,7 @@ static const struct net_device_ops atl1c_netdev_ops = {
 	.ndo_change_mtu		= atl1c_change_mtu,
 	.ndo_fix_features	= atl1c_fix_features,
 	.ndo_set_features	= atl1c_set_features,
-	.ndo_do_ioctl		= atl1c_ioctl,
+	.ndo_eth_ioctl		= atl1c_ioctl,
 	.ndo_tx_timeout		= atl1c_tx_timeout,
 	.ndo_get_stats		= atl1c_get_stats,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 2eb0a2ab69f6..753973ac922e 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -2247,7 +2247,7 @@ static const struct net_device_ops atl1e_netdev_ops = {
 	.ndo_fix_features	= atl1e_fix_features,
 	.ndo_set_features	= atl1e_set_features,
 	.ndo_change_mtu		= atl1e_change_mtu,
-	.ndo_do_ioctl		= atl1e_ioctl,
+	.ndo_eth_ioctl		= atl1e_ioctl,
 	.ndo_tx_timeout		= atl1e_tx_timeout,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= atl1e_netpoll,
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index c67201a13cf5..68f6c0bbd945 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -2885,7 +2885,7 @@ static const struct net_device_ops atl1_netdev_ops = {
 	.ndo_change_mtu		= atl1_change_mtu,
 	.ndo_fix_features	= atlx_fix_features,
 	.ndo_set_features	= atlx_set_features,
-	.ndo_do_ioctl		= atlx_ioctl,
+	.ndo_eth_ioctl		= atlx_ioctl,
 	.ndo_tx_timeout		= atlx_tx_timeout,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= atl1_poll_controller,
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index 0cc0db04c27d..b69298ddb647 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -1293,7 +1293,7 @@ static const struct net_device_ops atl2_netdev_ops = {
 	.ndo_change_mtu		= atl2_change_mtu,
 	.ndo_fix_features	= atl2_fix_features,
 	.ndo_set_features	= atl2_set_features,
-	.ndo_do_ioctl		= atl2_ioctl,
+	.ndo_eth_ioctl		= atl2_ioctl,
 	.ndo_tx_timeout		= atl2_tx_timeout,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= atl2_poll_controller,
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 1a02ca600b71..56e0fb07aec7 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -122,8 +122,8 @@ config SB1250_MAC
 config TIGON3
 	tristate "Broadcom Tigon3 support"
 	depends on PCI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select PHYLIB
-	imply PTP_1588_CLOCK
 	help
 	  This driver supports Broadcom Tigon3 based gigabit Ethernet cards.
 
@@ -140,7 +140,7 @@ config TIGON3_HWMON
 config BNX2X
 	tristate "Broadcom NetXtremeII 10Gb support"
 	depends on PCI
-	imply PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select FW_LOADER
 	select ZLIB_INFLATE
 	select LIBCRC32C
@@ -206,7 +206,7 @@ config SYSTEMPORT
 config BNXT
 	tristate "Broadcom NetXtreme-C/E support"
 	depends on PCI
-	imply PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select FW_LOADER
 	select LIBCRC32C
 	select NET_DEVLINK
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index ad2655efe423..fa784953c601 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -2198,7 +2198,7 @@ static const struct net_device_ops b44_netdev_ops = {
 	.ndo_set_rx_mode	= b44_set_rx_mode,
 	.ndo_set_mac_address	= b44_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= b44_ioctl,
+	.ndo_eth_ioctl		= b44_ioctl,
 	.ndo_tx_timeout		= b44_tx_timeout,
 	.ndo_change_mtu		= b44_change_mtu,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 977f097fc7bf..d56886300ecf 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -1699,7 +1699,7 @@ static const struct net_device_ops bcm_enet_ops = {
 	.ndo_start_xmit		= bcm_enet_start_xmit,
 	.ndo_set_mac_address	= bcm_enet_set_mac_address,
 	.ndo_set_rx_mode	= bcm_enet_set_multicast_list,
-	.ndo_do_ioctl		= bcm_enet_ioctl,
+	.ndo_eth_ioctl		= bcm_enet_ioctl,
 	.ndo_change_mtu		= bcm_enet_change_mtu,
 };
 
@@ -2446,7 +2446,7 @@ static const struct net_device_ops bcm_enetsw_ops = {
 	.ndo_stop		= bcm_enetsw_stop,
 	.ndo_start_xmit		= bcm_enet_start_xmit,
 	.ndo_change_mtu		= bcm_enet_change_mtu,
-	.ndo_do_ioctl		= bcm_enetsw_ioctl,
+	.ndo_eth_ioctl		= bcm_enetsw_ioctl,
 };
 
 
@@ -2649,7 +2649,6 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
 	if (!res_mem || irq_rx < 0)
 		return -ENODEV;
 
-	ret = 0;
 	dev = alloc_etherdev(sizeof(*priv));
 	if (!dev)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index d9f0f0df8f7b..7fa1b695400d 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -607,7 +607,9 @@ static void bcm_sysport_set_tx_coalesce(struct bcm_sysport_tx_ring *ring,
 }
 
 static int bcm_sysport_get_coalesce(struct net_device *dev,
-				    struct ethtool_coalesce *ec)
+				    struct ethtool_coalesce *ec,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	u32 reg;
@@ -627,7 +629,9 @@ static int bcm_sysport_get_coalesce(struct net_device *dev,
 }
 
 static int bcm_sysport_set_coalesce(struct net_device *dev,
-				    struct ethtool_coalesce *ec)
+				    struct ethtool_coalesce *ec,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct dim_cq_moder moder;
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 075f6e146b29..fe4d99abd548 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1263,7 +1263,7 @@ static const struct net_device_ops bgmac_netdev_ops = {
 	.ndo_set_rx_mode	= bgmac_set_rx_mode,
 	.ndo_set_mac_address	= bgmac_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl           = phy_do_ioctl_running,
+	.ndo_eth_ioctl           = phy_do_ioctl_running,
 	.ndo_change_mtu		= bgmac_change_mtu,
 };
 
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index bee6cfad9fc6..a705e2615307 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -2730,7 +2730,7 @@ bnx2_alloc_rx_page(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, u16 index, gf
 	if (!page)
 		return -ENOMEM;
 	mapping = dma_map_page(&bp->pdev->dev, page, 0, PAGE_SIZE,
-			       PCI_DMA_FROMDEVICE);
+			       DMA_FROM_DEVICE);
 	if (dma_mapping_error(&bp->pdev->dev, mapping)) {
 		__free_page(page);
 		return -EIO;
@@ -2753,7 +2753,7 @@ bnx2_free_rx_page(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, u16 index)
 		return;
 
 	dma_unmap_page(&bp->pdev->dev, dma_unmap_addr(rx_pg, mapping),
-		       PAGE_SIZE, PCI_DMA_FROMDEVICE);
+		       PAGE_SIZE, DMA_FROM_DEVICE);
 
 	__free_page(page);
 	rx_pg->page = NULL;
@@ -2775,7 +2775,7 @@ bnx2_alloc_rx_data(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, u16 index, gf
 	mapping = dma_map_single(&bp->pdev->dev,
 				 get_l2_fhdr(data),
 				 bp->rx_buf_use_size,
-				 PCI_DMA_FROMDEVICE);
+				 DMA_FROM_DEVICE);
 	if (dma_mapping_error(&bp->pdev->dev, mapping)) {
 		kfree(data);
 		return -EIO;
@@ -2881,7 +2881,7 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 		}
 
 		dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(tx_buf, mapping),
-			skb_headlen(skb), PCI_DMA_TODEVICE);
+			skb_headlen(skb), DMA_TO_DEVICE);
 
 		tx_buf->skb = NULL;
 		last = tx_buf->nr_frags;
@@ -2895,7 +2895,7 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 			dma_unmap_page(&bp->pdev->dev,
 				dma_unmap_addr(tx_buf, mapping),
 				skb_frag_size(&skb_shinfo(skb)->frags[i]),
-				PCI_DMA_TODEVICE);
+				DMA_TO_DEVICE);
 		}
 
 		sw_cons = BNX2_NEXT_TX_BD(sw_cons);
@@ -3003,7 +3003,7 @@ bnx2_reuse_rx_data(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr,
 
 	dma_sync_single_for_device(&bp->pdev->dev,
 		dma_unmap_addr(cons_rx_buf, mapping),
-		BNX2_RX_OFFSET + BNX2_RX_COPY_THRESH, PCI_DMA_FROMDEVICE);
+		BNX2_RX_OFFSET + BNX2_RX_COPY_THRESH, DMA_FROM_DEVICE);
 
 	rxr->rx_prod_bseq += bp->rx_buf_use_size;
 
@@ -3044,7 +3044,7 @@ error:
 	}
 
 	dma_unmap_single(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size,
-			 PCI_DMA_FROMDEVICE);
+			 DMA_FROM_DEVICE);
 	skb = build_skb(data, 0);
 	if (!skb) {
 		kfree(data);
@@ -3110,7 +3110,7 @@ error:
 			}
 
 			dma_unmap_page(&bp->pdev->dev, mapping_old,
-				       PAGE_SIZE, PCI_DMA_FROMDEVICE);
+				       PAGE_SIZE, DMA_FROM_DEVICE);
 
 			frag_size -= frag_len;
 			skb->data_len += frag_len;
@@ -3180,7 +3180,7 @@ bnx2_rx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 
 		dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr,
 			BNX2_RX_OFFSET + BNX2_RX_COPY_THRESH,
-			PCI_DMA_FROMDEVICE);
+			DMA_FROM_DEVICE);
 
 		next_ring_idx = BNX2_RX_RING_IDX(BNX2_NEXT_RX_BD(sw_cons));
 		next_rx_buf = &rxr->rx_buf_ring[next_ring_idx];
@@ -5449,7 +5449,7 @@ bnx2_free_tx_skbs(struct bnx2 *bp)
 			dma_unmap_single(&bp->pdev->dev,
 					 dma_unmap_addr(tx_buf, mapping),
 					 skb_headlen(skb),
-					 PCI_DMA_TODEVICE);
+					 DMA_TO_DEVICE);
 
 			tx_buf->skb = NULL;
 
@@ -5460,7 +5460,7 @@ bnx2_free_tx_skbs(struct bnx2 *bp)
 				dma_unmap_page(&bp->pdev->dev,
 					dma_unmap_addr(tx_buf, mapping),
 					skb_frag_size(&skb_shinfo(skb)->frags[k]),
-					PCI_DMA_TODEVICE);
+					DMA_TO_DEVICE);
 			}
 			dev_kfree_skb(skb);
 		}
@@ -5491,7 +5491,7 @@ bnx2_free_rx_skbs(struct bnx2 *bp)
 			dma_unmap_single(&bp->pdev->dev,
 					 dma_unmap_addr(rx_buf, mapping),
 					 bp->rx_buf_use_size,
-					 PCI_DMA_FROMDEVICE);
+					 DMA_FROM_DEVICE);
 
 			rx_buf->data = NULL;
 
@@ -5843,7 +5843,7 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode)
 		packet[i] = (unsigned char) (i & 0xff);
 
 	map = dma_map_single(&bp->pdev->dev, skb->data, pkt_size,
-			     PCI_DMA_TODEVICE);
+			     DMA_TO_DEVICE);
 	if (dma_mapping_error(&bp->pdev->dev, map)) {
 		dev_kfree_skb(skb);
 		return -EIO;
@@ -5882,7 +5882,7 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode)
 
 	udelay(5);
 
-	dma_unmap_single(&bp->pdev->dev, map, pkt_size, PCI_DMA_TODEVICE);
+	dma_unmap_single(&bp->pdev->dev, map, pkt_size, DMA_TO_DEVICE);
 	dev_kfree_skb(skb);
 
 	if (bnx2_get_hw_tx_cons(tx_napi) != txr->tx_prod)
@@ -5901,7 +5901,7 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode)
 
 	dma_sync_single_for_cpu(&bp->pdev->dev,
 		dma_unmap_addr(rx_buf, mapping),
-		bp->rx_buf_use_size, PCI_DMA_FROMDEVICE);
+		bp->rx_buf_use_size, DMA_FROM_DEVICE);
 
 	if (rx_hdr->l2_fhdr_status &
 		(L2_FHDR_ERRORS_BAD_CRC |
@@ -6660,7 +6660,8 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else
 		mss = 0;
 
-	mapping = dma_map_single(&bp->pdev->dev, skb->data, len, PCI_DMA_TODEVICE);
+	mapping = dma_map_single(&bp->pdev->dev, skb->data, len,
+				 DMA_TO_DEVICE);
 	if (dma_mapping_error(&bp->pdev->dev, mapping)) {
 		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
@@ -6741,7 +6742,7 @@ dma_error:
 	tx_buf = &txr->tx_buf_ring[ring_prod];
 	tx_buf->skb = NULL;
 	dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(tx_buf, mapping),
-			 skb_headlen(skb), PCI_DMA_TODEVICE);
+			 skb_headlen(skb), DMA_TO_DEVICE);
 
 	/* unmap remaining mapped pages */
 	for (i = 0; i < last_frag; i++) {
@@ -6750,7 +6751,7 @@ dma_error:
 		tx_buf = &txr->tx_buf_ring[ring_prod];
 		dma_unmap_page(&bp->pdev->dev, dma_unmap_addr(tx_buf, mapping),
 			       skb_frag_size(&skb_shinfo(skb)->frags[i]),
-			       PCI_DMA_TODEVICE);
+			       DMA_TO_DEVICE);
 	}
 
 	dev_kfree_skb_any(skb);
@@ -7241,8 +7242,10 @@ bnx2_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 	return rc;
 }
 
-static int
-bnx2_get_coalesce(struct net_device *dev, struct ethtool_coalesce *coal)
+static int bnx2_get_coalesce(struct net_device *dev,
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct bnx2 *bp = netdev_priv(dev);
 
@@ -7263,8 +7266,10 @@ bnx2_get_coalesce(struct net_device *dev, struct ethtool_coalesce *coal)
 	return 0;
 }
 
-static int
-bnx2_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal)
+static int bnx2_set_coalesce(struct net_device *dev,
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct bnx2 *bp = netdev_priv(dev);
 
@@ -8041,21 +8046,16 @@ bnx2_read_vpd_fw_ver(struct bnx2 *bp)
 #define BNX2_VPD_LEN		128
 #define BNX2_MAX_VER_SLEN	30
 
-	data = kmalloc(256, GFP_KERNEL);
+	data = kmalloc(BNX2_VPD_LEN, GFP_KERNEL);
 	if (!data)
 		return;
 
-	rc = bnx2_nvram_read(bp, BNX2_VPD_NVRAM_OFFSET, data + BNX2_VPD_LEN,
-			     BNX2_VPD_LEN);
+	rc = bnx2_nvram_read(bp, BNX2_VPD_NVRAM_OFFSET, data, BNX2_VPD_LEN);
 	if (rc)
 		goto vpd_done;
 
-	for (i = 0; i < BNX2_VPD_LEN; i += 4) {
-		data[i] = data[i + BNX2_VPD_LEN + 3];
-		data[i + 1] = data[i + BNX2_VPD_LEN + 2];
-		data[i + 2] = data[i + BNX2_VPD_LEN + 1];
-		data[i + 3] = data[i + BNX2_VPD_LEN];
-	}
+	for (i = 0; i < BNX2_VPD_LEN; i += 4)
+		swab32s((u32 *)&data[i]);
 
 	i = pci_vpd_find_tag(data, BNX2_VPD_LEN, PCI_VPD_LRDT_RO_DATA);
 	if (i < 0)
@@ -8224,15 +8224,15 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev)
 		persist_dma_mask = dma_mask = DMA_BIT_MASK(64);
 
 	/* Configure DMA attributes. */
-	if (pci_set_dma_mask(pdev, dma_mask) == 0) {
+	if (dma_set_mask(&pdev->dev, dma_mask) == 0) {
 		dev->features |= NETIF_F_HIGHDMA;
-		rc = pci_set_consistent_dma_mask(pdev, persist_dma_mask);
+		rc = dma_set_coherent_mask(&pdev->dev, persist_dma_mask);
 		if (rc) {
 			dev_err(&pdev->dev,
 				"pci_set_consistent_dma_mask failed, aborting\n");
 			goto err_out_unmap;
 		}
-	} else if ((rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) != 0) {
+	} else if ((rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) != 0) {
 		dev_err(&pdev->dev, "System does not support DMA, aborting\n");
 		goto err_out_unmap;
 	}
@@ -8546,7 +8546,7 @@ static const struct net_device_ops bnx2_netdev_ops = {
 	.ndo_stop		= bnx2_close,
 	.ndo_get_stats64	= bnx2_get_stats64,
 	.ndo_set_rx_mode	= bnx2_set_rx_mode,
-	.ndo_do_ioctl		= bnx2_ioctl,
+	.ndo_eth_ioctl		= bnx2_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= bnx2_change_mac_addr,
 	.ndo_change_mtu		= bnx2_change_mtu,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 32245bbe88a8..472a3a478038 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -1878,7 +1878,9 @@ static int bnx2x_set_eeprom(struct net_device *dev,
 }
 
 static int bnx2x_get_coalesce(struct net_device *dev,
-			      struct ethtool_coalesce *coal)
+			      struct ethtool_coalesce *coal,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
@@ -1891,7 +1893,9 @@ static int bnx2x_get_coalesce(struct net_device *dev,
 }
 
 static int bnx2x_set_coalesce(struct net_device *dev,
-			      struct ethtool_coalesce *coal)
+			      struct ethtool_coalesce *coal,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 2acbc73dcd18..6d98134913cd 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -13048,7 +13048,7 @@ static const struct net_device_ops bnx2x_netdev_ops = {
 	.ndo_set_rx_mode	= bnx2x_set_rx_mode,
 	.ndo_set_mac_address	= bnx2x_change_mac_addr,
 	.ndo_validate_addr	= bnx2x_validate_addr,
-	.ndo_do_ioctl		= bnx2x_ioctl,
+	.ndo_eth_ioctl		= bnx2x_ioctl,
 	.ndo_change_mtu		= bnx2x_change_mtu,
 	.ndo_fix_features	= bnx2x_fix_features,
 	.ndo_set_features	= bnx2x_set_features,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 27943b0446c2..f255fd0b16db 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1858,7 +1858,6 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
 {
 	int i;
 	int first_queue_query_index, num_queues_req;
-	dma_addr_t cur_data_offset;
 	struct stats_query_entry *cur_query_entry;
 	u8 stats_count = 0;
 	bool is_fcoe = false;
@@ -1879,10 +1878,6 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
 	       BNX2X_NUM_ETH_QUEUES(bp), is_fcoe, first_queue_query_index,
 	       first_queue_query_index + num_queues_req);
 
-	cur_data_offset = bp->fw_stats_data_mapping +
-		offsetof(struct bnx2x_fw_stats_data, queue_stats) +
-		num_queues_req * sizeof(struct per_queue_stats);
-
 	cur_query_entry = &bp->fw_stats_req->
 		query[first_queue_query_index + num_queues_req];
 
@@ -1933,7 +1928,6 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
 			       cur_query_entry->funcID,
 			       j, cur_query_entry->index);
 			cur_query_entry++;
-			cur_data_offset += sizeof(struct per_queue_stats);
 			stats_count++;
 
 			/* all stats are coalesced to the leading queue */
diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile
index 2b8ae687b3c1..c6ef7ec2c115 100644
--- a/drivers/net/ethernet/broadcom/bnxt/Makefile
+++ b/drivers/net/ethernet/broadcom/bnxt/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_BNXT) += bnxt_en.o
 
-bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_ptp.o bnxt_vfr.o bnxt_devlink.o bnxt_dim.o
+bnxt_en-y := bnxt.o bnxt_hwrm.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_ptp.o bnxt_vfr.o bnxt_devlink.o bnxt_dim.o
 bnxt_en-$(CONFIG_BNXT_FLOWER_OFFLOAD) += bnxt_tc.o
 bnxt_en-$(CONFIG_DEBUG_FS) += bnxt_debugfs.o
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 8a97640cdfe7..627f85ee3922 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -60,6 +60,7 @@
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
+#include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
 #include "bnxt_sriov.h"
 #include "bnxt_ethtool.h"
@@ -276,8 +277,11 @@ static const u16 bnxt_async_events_arr[] = {
 	ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY,
 	ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY,
 	ASYNC_EVENT_CMPL_EVENT_ID_DEBUG_NOTIFICATION,
+	ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE,
 	ASYNC_EVENT_CMPL_EVENT_ID_RING_MONITOR_MSG,
 	ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST,
+	ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP,
+	ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT,
 };
 
 static struct workqueue_struct *bnxt_pf_wq;
@@ -670,7 +674,7 @@ tx_dma_error:
 	prod = txr->tx_prod;
 	tx_buf = &txr->tx_buf_ring[prod];
 	dma_unmap_single(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
-			 skb_headlen(skb), PCI_DMA_TODEVICE);
+			 skb_headlen(skb), DMA_TO_DEVICE);
 	prod = NEXT_TX(prod);
 
 	/* unmap remaining mapped pages */
@@ -679,7 +683,7 @@ tx_dma_error:
 		tx_buf = &txr->tx_buf_ring[prod];
 		dma_unmap_page(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
 			       skb_frag_size(&skb_shinfo(skb)->frags[i]),
-			       PCI_DMA_TODEVICE);
+			       DMA_TO_DEVICE);
 	}
 
 tx_free:
@@ -718,7 +722,7 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 		}
 
 		dma_unmap_single(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
-				 skb_headlen(skb), PCI_DMA_TODEVICE);
+				 skb_headlen(skb), DMA_TO_DEVICE);
 		last = tx_buf->nr_frags;
 
 		for (j = 0; j < last; j++) {
@@ -728,7 +732,7 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 				&pdev->dev,
 				dma_unmap_addr(tx_buf, mapping),
 				skb_frag_size(&skb_shinfo(skb)->frags[j]),
-				PCI_DMA_TODEVICE);
+				DMA_TO_DEVICE);
 		}
 		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) {
 			if (bp->flags & BNXT_FLAG_CHIP_P5) {
@@ -901,7 +905,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
 	}
 
 	mapping = dma_map_page_attrs(&pdev->dev, page, offset,
-				     BNXT_RX_PAGE_SIZE, PCI_DMA_FROMDEVICE,
+				     BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE,
 				     DMA_ATTR_WEAK_ORDERING);
 	if (dma_mapping_error(&pdev->dev, mapping)) {
 		__free_page(page);
@@ -1141,7 +1145,7 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp,
 		}
 
 		dma_unmap_page_attrs(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE,
-				     PCI_DMA_FROMDEVICE,
+				     DMA_FROM_DEVICE,
 				     DMA_ATTR_WEAK_ORDERING);
 
 		skb->data_len += frag_len;
@@ -1649,6 +1653,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		skb = bnxt_copy_skb(bnapi, data_ptr, len, mapping);
 		if (!skb) {
 			bnxt_abort_tpa(cpr, idx, agg_bufs);
+			cpr->sw_stats.rx.rx_oom_discards += 1;
 			return NULL;
 		}
 	} else {
@@ -1658,6 +1663,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		new_data = __bnxt_alloc_rx_data(bp, &new_mapping, GFP_ATOMIC);
 		if (!new_data) {
 			bnxt_abort_tpa(cpr, idx, agg_bufs);
+			cpr->sw_stats.rx.rx_oom_discards += 1;
 			return NULL;
 		}
 
@@ -1673,6 +1679,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		if (!skb) {
 			kfree(data);
 			bnxt_abort_tpa(cpr, idx, agg_bufs);
+			cpr->sw_stats.rx.rx_oom_discards += 1;
 			return NULL;
 		}
 		skb_reserve(skb, bp->rx_offset);
@@ -1683,6 +1690,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		skb = bnxt_rx_pages(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;
 			return NULL;
 		}
 	}
@@ -1886,6 +1894,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			if (agg_bufs)
 				bnxt_reuse_rx_agg_bufs(cpr, cp_cons, 0,
 						       agg_bufs, false);
+			cpr->sw_stats.rx.rx_oom_discards += 1;
 			rc = -ENOMEM;
 			goto next_rx;
 		}
@@ -1899,6 +1908,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		skb = bp->rx_skb_func(bp, rxr, cons, data, data_ptr, dma_addr,
 				      payload | len);
 		if (!skb) {
+			cpr->sw_stats.rx.rx_oom_discards += 1;
 			rc = -ENOMEM;
 			goto next_rx;
 		}
@@ -1907,6 +1917,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	if (agg_bufs) {
 		skb = bnxt_rx_pages(bp, cpr, skb, cp_cons, agg_bufs, false);
 		if (!skb) {
+			cpr->sw_stats.rx.rx_oom_discards += 1;
 			rc = -ENOMEM;
 			goto next_rx;
 		}
@@ -2001,6 +2012,7 @@ static int bnxt_force_rx_discard(struct bnxt *bp,
 	struct rx_cmp *rxcmp;
 	u16 cp_cons;
 	u8 cmp_type;
+	int rc;
 
 	cp_cons = RING_CMP(tmp_raw_cons);
 	rxcmp = (struct rx_cmp *)
@@ -2029,7 +2041,10 @@ static int bnxt_force_rx_discard(struct bnxt *bp,
 		tpa_end1->rx_tpa_end_cmp_errors_v2 |=
 			cpu_to_le32(RX_TPA_END_CMP_ERRORS);
 	}
-	return bnxt_rx_pkt(bp, cpr, raw_cons, event);
+	rc = bnxt_rx_pkt(bp, cpr, raw_cons, event);
+	if (rc && rc != -EBUSY)
+		cpr->sw_stats.rx.rx_netpoll_discards += 1;
+	return rc;
 }
 
 u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx)
@@ -2074,6 +2089,19 @@ static u16 bnxt_agg_ring_id_to_grp_idx(struct bnxt *bp, u16 ring_id)
 	return INVALID_HW_RING_ID;
 }
 
+static void bnxt_event_error_report(struct bnxt *bp, u32 data1, u32 data2)
+{
+	switch (BNXT_EVENT_ERROR_REPORT_TYPE(data1)) {
+	case ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL:
+		netdev_err(bp->dev, "1PPS: Received invalid signal on pin%lu from the external source. Please fix the signal and reconfigure the pin\n",
+			   BNXT_EVENT_INVALID_SIGNAL_DATA(data2));
+		break;
+	default:
+		netdev_err(bp->dev, "FW reported unknown error type\n");
+		break;
+	}
+}
+
 #define BNXT_GET_EVENT_PORT(data)	\
 	((data) &			\
 	 ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_MASK)
@@ -2234,6 +2262,20 @@ static int bnxt_async_event_process(struct bnxt *bp,
 		}
 		goto async_event_process_exit;
 	}
+	case ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP: {
+		bnxt_ptp_pps_event(bp, data1, data2);
+		goto async_event_process_exit;
+	}
+	case ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT: {
+		bnxt_event_error_report(bp, data1, data2);
+		goto async_event_process_exit;
+	}
+	case ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE: {
+		u16 seq_id = le32_to_cpu(cmpl->event_data2) & 0xffff;
+
+		hwrm_update_token(bp, seq_id, BNXT_HWRM_DEFERRED);
+		goto async_event_process_exit;
+	}
 	default:
 		goto async_event_process_exit;
 	}
@@ -2253,10 +2295,7 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp)
 	switch (cmpl_type) {
 	case CMPL_BASE_TYPE_HWRM_DONE:
 		seq_id = le16_to_cpu(h_cmpl->sequence_id);
-		if (seq_id == bp->hwrm_intr_seq_id)
-			bp->hwrm_intr_seq_id = (u16)~bp->hwrm_intr_seq_id;
-		else
-			netdev_err(bp->dev, "Invalid hwrm seq id %d\n", seq_id);
+		hwrm_update_token(bp, seq_id, BNXT_HWRM_COMPLETE);
 		break;
 
 	case CMPL_BASE_TYPE_HWRM_FWD_REQ:
@@ -2690,7 +2729,7 @@ static void bnxt_free_tx_skbs(struct bnxt *bp)
 				dma_unmap_single(&pdev->dev,
 					dma_unmap_addr(tx_buf, mapping),
 					dma_unmap_len(tx_buf, len),
-					PCI_DMA_TODEVICE);
+					DMA_TO_DEVICE);
 				xdp_return_frame(tx_buf->xdpf);
 				tx_buf->action = 0;
 				tx_buf->xdpf = NULL;
@@ -2715,7 +2754,7 @@ static void bnxt_free_tx_skbs(struct bnxt *bp)
 			dma_unmap_single(&pdev->dev,
 					 dma_unmap_addr(tx_buf, mapping),
 					 skb_headlen(skb),
-					 PCI_DMA_TODEVICE);
+					 DMA_TO_DEVICE);
 
 			last = tx_buf->nr_frags;
 			j += 2;
@@ -2727,7 +2766,7 @@ static void bnxt_free_tx_skbs(struct bnxt *bp)
 				dma_unmap_page(
 					&pdev->dev,
 					dma_unmap_addr(tx_buf, mapping),
-					skb_frag_size(frag), PCI_DMA_TODEVICE);
+					skb_frag_size(frag), DMA_TO_DEVICE);
 			}
 			dev_kfree_skb(skb);
 		}
@@ -2794,7 +2833,7 @@ skip_rx_tpa_free:
 			continue;
 
 		dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping,
-				     BNXT_RX_PAGE_SIZE, PCI_DMA_FROMDEVICE,
+				     BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE,
 				     DMA_ATTR_WEAK_ORDERING);
 
 		rx_agg_buf->page = NULL;
@@ -3176,6 +3215,58 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 	return 0;
 }
 
+static void bnxt_free_cp_arrays(struct bnxt_cp_ring_info *cpr)
+{
+	kfree(cpr->cp_desc_ring);
+	cpr->cp_desc_ring = NULL;
+	kfree(cpr->cp_desc_mapping);
+	cpr->cp_desc_mapping = NULL;
+}
+
+static int bnxt_alloc_cp_arrays(struct bnxt_cp_ring_info *cpr, int n)
+{
+	cpr->cp_desc_ring = kcalloc(n, sizeof(*cpr->cp_desc_ring), GFP_KERNEL);
+	if (!cpr->cp_desc_ring)
+		return -ENOMEM;
+	cpr->cp_desc_mapping = kcalloc(n, sizeof(*cpr->cp_desc_mapping),
+				       GFP_KERNEL);
+	if (!cpr->cp_desc_mapping)
+		return -ENOMEM;
+	return 0;
+}
+
+static void bnxt_free_all_cp_arrays(struct bnxt *bp)
+{
+	int i;
+
+	if (!bp->bnapi)
+		return;
+	for (i = 0; i < bp->cp_nr_rings; i++) {
+		struct bnxt_napi *bnapi = bp->bnapi[i];
+
+		if (!bnapi)
+			continue;
+		bnxt_free_cp_arrays(&bnapi->cp_ring);
+	}
+}
+
+static int bnxt_alloc_all_cp_arrays(struct bnxt *bp)
+{
+	int i, n = bp->cp_nr_pages;
+
+	for (i = 0; i < bp->cp_nr_rings; i++) {
+		struct bnxt_napi *bnapi = bp->bnapi[i];
+		int rc;
+
+		if (!bnapi)
+			continue;
+		rc = bnxt_alloc_cp_arrays(&bnapi->cp_ring, n);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
 static void bnxt_free_cp_rings(struct bnxt *bp)
 {
 	int i;
@@ -3203,6 +3294,7 @@ static void bnxt_free_cp_rings(struct bnxt *bp)
 			if (cpr2) {
 				ring = &cpr2->cp_ring_struct;
 				bnxt_free_ring(bp, &ring->ring_mem);
+				bnxt_free_cp_arrays(cpr2);
 				kfree(cpr2);
 				cpr->cp_ring_arr[j] = NULL;
 			}
@@ -3221,6 +3313,12 @@ static struct bnxt_cp_ring_info *bnxt_alloc_cp_sub_ring(struct bnxt *bp)
 	if (!cpr)
 		return NULL;
 
+	rc = bnxt_alloc_cp_arrays(cpr, bp->cp_nr_pages);
+	if (rc) {
+		bnxt_free_cp_arrays(cpr);
+		kfree(cpr);
+		return NULL;
+	}
 	ring = &cpr->cp_ring_struct;
 	rmem = &ring->ring_mem;
 	rmem->nr_pages = bp->cp_nr_pages;
@@ -3231,6 +3329,7 @@ static struct bnxt_cp_ring_info *bnxt_alloc_cp_sub_ring(struct bnxt *bp)
 	rc = bnxt_alloc_ring(bp, rmem);
 	if (rc) {
 		bnxt_free_ring(bp, rmem);
+		bnxt_free_cp_arrays(cpr);
 		kfree(cpr);
 		cpr = NULL;
 	}
@@ -3663,9 +3762,15 @@ void bnxt_set_ring_params(struct bnxt *bp)
 		if (jumbo_factor > agg_factor)
 			agg_factor = jumbo_factor;
 	}
-	agg_ring_size = ring_size * agg_factor;
+	if (agg_factor) {
+		if (ring_size > BNXT_MAX_RX_DESC_CNT_JUM_ENA) {
+			ring_size = BNXT_MAX_RX_DESC_CNT_JUM_ENA;
+			netdev_warn(bp->dev, "RX ring size reduced from %d to %d because the jumbo ring is now enabled\n",
+				    bp->rx_ring_size, ring_size);
+			bp->rx_ring_size = ring_size;
+		}
+		agg_ring_size = ring_size * agg_factor;
 
-	if (agg_ring_size) {
 		bp->rx_agg_nr_pages = bnxt_calc_nr_ring_pages(agg_ring_size,
 							RX_DESC_CNT);
 		if (bp->rx_agg_nr_pages > MAX_RX_AGG_PAGES) {
@@ -3855,77 +3960,26 @@ out:
 
 static void bnxt_free_hwrm_resources(struct bnxt *bp)
 {
-	struct pci_dev *pdev = bp->pdev;
-
-	if (bp->hwrm_cmd_resp_addr) {
-		dma_free_coherent(&pdev->dev, PAGE_SIZE, bp->hwrm_cmd_resp_addr,
-				  bp->hwrm_cmd_resp_dma_addr);
-		bp->hwrm_cmd_resp_addr = NULL;
-	}
-
-	if (bp->hwrm_cmd_kong_resp_addr) {
-		dma_free_coherent(&pdev->dev, PAGE_SIZE,
-				  bp->hwrm_cmd_kong_resp_addr,
-				  bp->hwrm_cmd_kong_resp_dma_addr);
-		bp->hwrm_cmd_kong_resp_addr = NULL;
-	}
-}
+	struct bnxt_hwrm_wait_token *token;
 
-static int bnxt_alloc_kong_hwrm_resources(struct bnxt *bp)
-{
-	struct pci_dev *pdev = bp->pdev;
+	dma_pool_destroy(bp->hwrm_dma_pool);
+	bp->hwrm_dma_pool = NULL;
 
-	if (bp->hwrm_cmd_kong_resp_addr)
-		return 0;
-
-	bp->hwrm_cmd_kong_resp_addr =
-		dma_alloc_coherent(&pdev->dev, PAGE_SIZE,
-				   &bp->hwrm_cmd_kong_resp_dma_addr,
-				   GFP_KERNEL);
-	if (!bp->hwrm_cmd_kong_resp_addr)
-		return -ENOMEM;
-
-	return 0;
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(token, &bp->hwrm_pending_list, node)
+		WRITE_ONCE(token->state, BNXT_HWRM_CANCELLED);
+	rcu_read_unlock();
 }
 
 static int bnxt_alloc_hwrm_resources(struct bnxt *bp)
 {
-	struct pci_dev *pdev = bp->pdev;
-
-	bp->hwrm_cmd_resp_addr = dma_alloc_coherent(&pdev->dev, PAGE_SIZE,
-						   &bp->hwrm_cmd_resp_dma_addr,
-						   GFP_KERNEL);
-	if (!bp->hwrm_cmd_resp_addr)
+	bp->hwrm_dma_pool = dma_pool_create("bnxt_hwrm", &bp->pdev->dev,
+					    BNXT_HWRM_DMA_SIZE,
+					    BNXT_HWRM_DMA_ALIGN, 0);
+	if (!bp->hwrm_dma_pool)
 		return -ENOMEM;
 
-	return 0;
-}
-
-static void bnxt_free_hwrm_short_cmd_req(struct bnxt *bp)
-{
-	if (bp->hwrm_short_cmd_req_addr) {
-		struct pci_dev *pdev = bp->pdev;
-
-		dma_free_coherent(&pdev->dev, bp->hwrm_max_ext_req_len,
-				  bp->hwrm_short_cmd_req_addr,
-				  bp->hwrm_short_cmd_req_dma_addr);
-		bp->hwrm_short_cmd_req_addr = NULL;
-	}
-}
-
-static int bnxt_alloc_hwrm_short_cmd_req(struct bnxt *bp)
-{
-	struct pci_dev *pdev = bp->pdev;
-
-	if (bp->hwrm_short_cmd_req_addr)
-		return 0;
-
-	bp->hwrm_short_cmd_req_addr =
-		dma_alloc_coherent(&pdev->dev, bp->hwrm_max_ext_req_len,
-				   &bp->hwrm_short_cmd_req_dma_addr,
-				   GFP_KERNEL);
-	if (!bp->hwrm_short_cmd_req_addr)
-		return -ENOMEM;
+	INIT_HLIST_HEAD(&bp->hwrm_pending_list);
 
 	return 0;
 }
@@ -3986,8 +4040,8 @@ static void bnxt_copy_hw_masks(u64 *mask_arr, __le64 *hw_mask_arr, int count)
 static int bnxt_hwrm_func_qstat_ext(struct bnxt *bp,
 				    struct bnxt_stats_mem *stats)
 {
-	struct hwrm_func_qstats_ext_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_func_qstats_ext_input req = {0};
+	struct hwrm_func_qstats_ext_output *resp;
+	struct hwrm_func_qstats_ext_input *req;
 	__le64 *hw_masks;
 	int rc;
 
@@ -3995,19 +4049,20 @@ static int bnxt_hwrm_func_qstat_ext(struct bnxt *bp,
 	    !(bp->flags & BNXT_FLAG_CHIP_P5))
 		return -EOPNOTSUPP;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QSTATS_EXT, -1, -1);
-	req.fid = cpu_to_le16(0xffff);
-	req.flags = FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK;
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_QSTATS_EXT);
 	if (rc)
-		goto qstat_exit;
+		return rc;
 
-	hw_masks = &resp->rx_ucast_pkts;
-	bnxt_copy_hw_masks(stats->hw_masks, hw_masks, stats->len / 8);
+	req->fid = cpu_to_le16(0xffff);
+	req->flags = FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK;
 
-qstat_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
+	if (!rc) {
+		hw_masks = &resp->rx_ucast_pkts;
+		bnxt_copy_hw_masks(stats->hw_masks, hw_masks, stats->len / 8);
+	}
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -4266,6 +4321,7 @@ static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init)
 	bnxt_free_tx_rings(bp);
 	bnxt_free_rx_rings(bp);
 	bnxt_free_cp_rings(bp);
+	bnxt_free_all_cp_arrays(bp);
 	bnxt_free_ntp_fltrs(bp, irq_re_init);
 	if (irq_re_init) {
 		bnxt_free_ring_stats(bp);
@@ -4386,6 +4442,10 @@ static int bnxt_alloc_mem(struct bnxt *bp, bool irq_re_init)
 			goto alloc_mem_err;
 	}
 
+	rc = bnxt_alloc_all_cp_arrays(bp);
+	if (rc)
+		goto alloc_mem_err;
+
 	bnxt_init_ring_struct(bp);
 
 	rc = bnxt_alloc_rx_rings(bp);
@@ -4468,313 +4528,38 @@ static void bnxt_enable_int(struct bnxt *bp)
 	}
 }
 
-void bnxt_hwrm_cmd_hdr_init(struct bnxt *bp, void *request, u16 req_type,
-			    u16 cmpl_ring, u16 target_id)
-{
-	struct input *req = request;
-
-	req->req_type = cpu_to_le16(req_type);
-	req->cmpl_ring = cpu_to_le16(cmpl_ring);
-	req->target_id = cpu_to_le16(target_id);
-	if (bnxt_kong_hwrm_message(bp, req))
-		req->resp_addr = cpu_to_le64(bp->hwrm_cmd_kong_resp_dma_addr);
-	else
-		req->resp_addr = cpu_to_le64(bp->hwrm_cmd_resp_dma_addr);
-}
-
-static int bnxt_hwrm_to_stderr(u32 hwrm_err)
-{
-	switch (hwrm_err) {
-	case HWRM_ERR_CODE_SUCCESS:
-		return 0;
-	case HWRM_ERR_CODE_RESOURCE_LOCKED:
-		return -EROFS;
-	case HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED:
-		return -EACCES;
-	case HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR:
-		return -ENOSPC;
-	case HWRM_ERR_CODE_INVALID_PARAMS:
-	case HWRM_ERR_CODE_INVALID_FLAGS:
-	case HWRM_ERR_CODE_INVALID_ENABLES:
-	case HWRM_ERR_CODE_UNSUPPORTED_TLV:
-	case HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR:
-		return -EINVAL;
-	case HWRM_ERR_CODE_NO_BUFFER:
-		return -ENOMEM;
-	case HWRM_ERR_CODE_HOT_RESET_PROGRESS:
-	case HWRM_ERR_CODE_BUSY:
-		return -EAGAIN;
-	case HWRM_ERR_CODE_CMD_NOT_SUPPORTED:
-		return -EOPNOTSUPP;
-	default:
-		return -EIO;
-	}
-}
-
-static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
-				 int timeout, bool silent)
-{
-	int i, intr_process, rc, tmo_count;
-	struct input *req = msg;
-	u32 *data = msg;
-	u8 *valid;
-	u16 cp_ring_id, len = 0;
-	struct hwrm_err_output *resp = bp->hwrm_cmd_resp_addr;
-	u16 max_req_len = BNXT_HWRM_MAX_REQ_LEN;
-	struct hwrm_short_input short_input = {0};
-	u32 doorbell_offset = BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER;
-	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
-	u16 dst = BNXT_HWRM_CHNL_CHIMP;
-
-	if (BNXT_NO_FW_ACCESS(bp) &&
-	    le16_to_cpu(req->req_type) != HWRM_FUNC_RESET)
-		return -EBUSY;
-
-	if (msg_len > BNXT_HWRM_MAX_REQ_LEN) {
-		if (msg_len > bp->hwrm_max_ext_req_len ||
-		    !bp->hwrm_short_cmd_req_addr)
-			return -EINVAL;
-	}
-
-	if (bnxt_hwrm_kong_chnl(bp, req)) {
-		dst = BNXT_HWRM_CHNL_KONG;
-		bar_offset = BNXT_GRCPF_REG_KONG_COMM;
-		doorbell_offset = BNXT_GRCPF_REG_KONG_COMM_TRIGGER;
-		resp = bp->hwrm_cmd_kong_resp_addr;
-	}
-
-	memset(resp, 0, PAGE_SIZE);
-	cp_ring_id = le16_to_cpu(req->cmpl_ring);
-	intr_process = (cp_ring_id == INVALID_HW_RING_ID) ? 0 : 1;
-
-	req->seq_id = cpu_to_le16(bnxt_get_hwrm_seq_id(bp, dst));
-	/* currently supports only one outstanding message */
-	if (intr_process)
-		bp->hwrm_intr_seq_id = le16_to_cpu(req->seq_id);
-
-	if ((bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) ||
-	    msg_len > BNXT_HWRM_MAX_REQ_LEN) {
-		void *short_cmd_req = bp->hwrm_short_cmd_req_addr;
-		u16 max_msg_len;
-
-		/* Set boundary for maximum extended request length for short
-		 * cmd format. If passed up from device use the max supported
-		 * internal req length.
-		 */
-		max_msg_len = bp->hwrm_max_ext_req_len;
-
-		memcpy(short_cmd_req, req, msg_len);
-		if (msg_len < max_msg_len)
-			memset(short_cmd_req + msg_len, 0,
-			       max_msg_len - msg_len);
-
-		short_input.req_type = req->req_type;
-		short_input.signature =
-				cpu_to_le16(SHORT_REQ_SIGNATURE_SHORT_CMD);
-		short_input.size = cpu_to_le16(msg_len);
-		short_input.req_addr =
-			cpu_to_le64(bp->hwrm_short_cmd_req_dma_addr);
-
-		data = (u32 *)&short_input;
-		msg_len = sizeof(short_input);
-
-		/* Sync memory write before updating doorbell */
-		wmb();
-
-		max_req_len = BNXT_HWRM_SHORT_REQ_LEN;
-	}
-
-	/* Write request msg to hwrm channel */
-	__iowrite32_copy(bp->bar0 + bar_offset, data, msg_len / 4);
-
-	for (i = msg_len; i < max_req_len; i += 4)
-		writel(0, bp->bar0 + bar_offset + i);
-
-	/* Ring channel doorbell */
-	writel(1, bp->bar0 + doorbell_offset);
-
-	if (!pci_is_enabled(bp->pdev))
-		return -ENODEV;
-
-	if (!timeout)
-		timeout = DFLT_HWRM_CMD_TIMEOUT;
-	/* Limit timeout to an upper limit */
-	timeout = min(timeout, HWRM_CMD_MAX_TIMEOUT);
-	/* convert timeout to usec */
-	timeout *= 1000;
-
-	i = 0;
-	/* Short timeout for the first few iterations:
-	 * number of loops = number of loops for short timeout +
-	 * number of loops for standard timeout.
-	 */
-	tmo_count = HWRM_SHORT_TIMEOUT_COUNTER;
-	timeout = timeout - HWRM_SHORT_MIN_TIMEOUT * HWRM_SHORT_TIMEOUT_COUNTER;
-	tmo_count += DIV_ROUND_UP(timeout, HWRM_MIN_TIMEOUT);
-
-	if (intr_process) {
-		u16 seq_id = bp->hwrm_intr_seq_id;
-
-		/* Wait until hwrm response cmpl interrupt is processed */
-		while (bp->hwrm_intr_seq_id != (u16)~seq_id &&
-		       i++ < tmo_count) {
-			/* Abort the wait for completion if the FW health
-			 * check has failed.
-			 */
-			if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
-				return -EBUSY;
-			/* on first few passes, just barely sleep */
-			if (i < HWRM_SHORT_TIMEOUT_COUNTER) {
-				usleep_range(HWRM_SHORT_MIN_TIMEOUT,
-					     HWRM_SHORT_MAX_TIMEOUT);
-			} else {
-				if (HWRM_WAIT_MUST_ABORT(bp, req))
-					break;
-				usleep_range(HWRM_MIN_TIMEOUT,
-					     HWRM_MAX_TIMEOUT);
-			}
-		}
-
-		if (bp->hwrm_intr_seq_id != (u16)~seq_id) {
-			if (!silent)
-				netdev_err(bp->dev, "Resp cmpl intr err msg: 0x%x\n",
-					   le16_to_cpu(req->req_type));
-			return -EBUSY;
-		}
-		len = le16_to_cpu(resp->resp_len);
-		valid = ((u8 *)resp) + len - 1;
-	} else {
-		int j;
-
-		/* Check if response len is updated */
-		for (i = 0; i < tmo_count; i++) {
-			/* Abort the wait for completion if the FW health
-			 * check has failed.
-			 */
-			if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
-				return -EBUSY;
-			len = le16_to_cpu(resp->resp_len);
-			if (len)
-				break;
-			/* on first few passes, just barely sleep */
-			if (i < HWRM_SHORT_TIMEOUT_COUNTER) {
-				usleep_range(HWRM_SHORT_MIN_TIMEOUT,
-					     HWRM_SHORT_MAX_TIMEOUT);
-			} else {
-				if (HWRM_WAIT_MUST_ABORT(bp, req))
-					goto timeout_abort;
-				usleep_range(HWRM_MIN_TIMEOUT,
-					     HWRM_MAX_TIMEOUT);
-			}
-		}
-
-		if (i >= tmo_count) {
-timeout_abort:
-			if (!silent)
-				netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d\n",
-					   HWRM_TOTAL_TIMEOUT(i),
-					   le16_to_cpu(req->req_type),
-					   le16_to_cpu(req->seq_id), len);
-			return -EBUSY;
-		}
-
-		/* Last byte of resp contains valid bit */
-		valid = ((u8 *)resp) + len - 1;
-		for (j = 0; j < HWRM_VALID_BIT_DELAY_USEC; j++) {
-			/* make sure we read from updated DMA memory */
-			dma_rmb();
-			if (*valid)
-				break;
-			usleep_range(1, 5);
-		}
-
-		if (j >= HWRM_VALID_BIT_DELAY_USEC) {
-			if (!silent)
-				netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d v:%d\n",
-					   HWRM_TOTAL_TIMEOUT(i),
-					   le16_to_cpu(req->req_type),
-					   le16_to_cpu(req->seq_id), len,
-					   *valid);
-			return -EBUSY;
-		}
-	}
-
-	/* Zero valid bit for compatibility.  Valid bit in an older spec
-	 * may become a new field in a newer spec.  We must make sure that
-	 * a new field not implemented by old spec will read zero.
-	 */
-	*valid = 0;
-	rc = le16_to_cpu(resp->error_code);
-	if (rc && !silent)
-		netdev_err(bp->dev, "hwrm req_type 0x%x seq id 0x%x error 0x%x\n",
-			   le16_to_cpu(resp->req_type),
-			   le16_to_cpu(resp->seq_id), rc);
-	return bnxt_hwrm_to_stderr(rc);
-}
-
-int _hwrm_send_message(struct bnxt *bp, void *msg, u32 msg_len, int timeout)
-{
-	return bnxt_hwrm_do_send_msg(bp, msg, msg_len, timeout, false);
-}
-
-int _hwrm_send_message_silent(struct bnxt *bp, void *msg, u32 msg_len,
-			      int timeout)
-{
-	return bnxt_hwrm_do_send_msg(bp, msg, msg_len, timeout, true);
-}
-
-int hwrm_send_message(struct bnxt *bp, void *msg, u32 msg_len, int timeout)
-{
-	int rc;
-
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, msg, msg_len, timeout);
-	mutex_unlock(&bp->hwrm_cmd_lock);
-	return rc;
-}
-
-int hwrm_send_message_silent(struct bnxt *bp, void *msg, u32 msg_len,
-			     int timeout)
-{
-	int rc;
-
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = bnxt_hwrm_do_send_msg(bp, msg, msg_len, timeout, true);
-	mutex_unlock(&bp->hwrm_cmd_lock);
-	return rc;
-}
-
 int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size,
 			    bool async_only)
 {
-	struct hwrm_func_drv_rgtr_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_func_drv_rgtr_input req = {0};
 	DECLARE_BITMAP(async_events_bmap, 256);
 	u32 *events = (u32 *)async_events_bmap;
+	struct hwrm_func_drv_rgtr_output *resp;
+	struct hwrm_func_drv_rgtr_input *req;
 	u32 flags;
 	int rc, i;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_RGTR, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_DRV_RGTR);
+	if (rc)
+		return rc;
 
-	req.enables =
-		cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE |
-			    FUNC_DRV_RGTR_REQ_ENABLES_VER |
-			    FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD);
+	req->enables = cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE |
+				   FUNC_DRV_RGTR_REQ_ENABLES_VER |
+				   FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD);
 
-	req.os_type = cpu_to_le16(FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX);
+	req->os_type = cpu_to_le16(FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX);
 	flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE;
 	if (bp->fw_cap & BNXT_FW_CAP_HOT_RESET)
 		flags |= FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT;
 	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;
-	req.flags = cpu_to_le32(flags);
-	req.ver_maj_8b = DRV_VER_MAJ;
-	req.ver_min_8b = DRV_VER_MIN;
-	req.ver_upd_8b = DRV_VER_UPD;
-	req.ver_maj = cpu_to_le16(DRV_VER_MAJ);
-	req.ver_min = cpu_to_le16(DRV_VER_MIN);
-	req.ver_upd = cpu_to_le16(DRV_VER_UPD);
+	req->flags = cpu_to_le32(flags);
+	req->ver_maj_8b = DRV_VER_MAJ;
+	req->ver_min_8b = DRV_VER_MIN;
+	req->ver_upd_8b = DRV_VER_UPD;
+	req->ver_maj = cpu_to_le16(DRV_VER_MAJ);
+	req->ver_min = cpu_to_le16(DRV_VER_MIN);
+	req->ver_upd = cpu_to_le16(DRV_VER_UPD);
 
 	if (BNXT_PF(bp)) {
 		u32 data[8];
@@ -4791,14 +4576,14 @@ int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size,
 		}
 
 		for (i = 0; i < 8; i++)
-			req.vf_req_fwd[i] = cpu_to_le32(data[i]);
+			req->vf_req_fwd[i] = cpu_to_le32(data[i]);
 
-		req.enables |=
+		req->enables |=
 			cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD);
 	}
 
 	if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE)
-		req.flags |= cpu_to_le32(
+		req->flags |= cpu_to_le32(
 			FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE);
 
 	memset(async_events_bmap, 0, sizeof(async_events_bmap));
@@ -4817,57 +4602,63 @@ int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size,
 		}
 	}
 	for (i = 0; i < 8; i++)
-		req.async_event_fwd[i] |= cpu_to_le32(events[i]);
+		req->async_event_fwd[i] |= cpu_to_le32(events[i]);
 
 	if (async_only)
-		req.enables =
+		req->enables =
 			cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc) {
 		set_bit(BNXT_STATE_DRV_REGISTERED, &bp->state);
 		if (resp->flags &
 		    cpu_to_le32(FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED))
 			bp->fw_cap |= BNXT_FW_CAP_IF_CHANGE;
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 static int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp)
 {
-	struct hwrm_func_drv_unrgtr_input req = {0};
+	struct hwrm_func_drv_unrgtr_input *req;
+	int rc;
 
 	if (!test_and_clear_bit(BNXT_STATE_DRV_REGISTERED, &bp->state))
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_UNRGTR, -1, -1);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_DRV_UNRGTR);
+	if (rc)
+		return rc;
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_hwrm_tunnel_dst_port_free(struct bnxt *bp, u8 tunnel_type)
 {
-	u32 rc = 0;
-	struct hwrm_tunnel_dst_port_free_input req = {0};
+	struct hwrm_tunnel_dst_port_free_input *req;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_TUNNEL_DST_PORT_FREE);
+	if (rc)
+		return rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TUNNEL_DST_PORT_FREE, -1, -1);
-	req.tunnel_type = tunnel_type;
+	req->tunnel_type = tunnel_type;
 
 	switch (tunnel_type) {
 	case TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN:
-		req.tunnel_dst_port_id = cpu_to_le16(bp->vxlan_fw_dst_port_id);
+		req->tunnel_dst_port_id = cpu_to_le16(bp->vxlan_fw_dst_port_id);
 		bp->vxlan_fw_dst_port_id = INVALID_HW_RING_ID;
 		break;
 	case TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE:
-		req.tunnel_dst_port_id = cpu_to_le16(bp->nge_fw_dst_port_id);
+		req->tunnel_dst_port_id = cpu_to_le16(bp->nge_fw_dst_port_id);
 		bp->nge_fw_dst_port_id = INVALID_HW_RING_ID;
 		break;
 	default:
 		break;
 	}
 
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_send(bp, req);
 	if (rc)
 		netdev_err(bp->dev, "hwrm_tunnel_dst_port_free failed. rc:%d\n",
 			   rc);
@@ -4877,17 +4668,19 @@ static int bnxt_hwrm_tunnel_dst_port_free(struct bnxt *bp, u8 tunnel_type)
 static int bnxt_hwrm_tunnel_dst_port_alloc(struct bnxt *bp, __be16 port,
 					   u8 tunnel_type)
 {
-	u32 rc = 0;
-	struct hwrm_tunnel_dst_port_alloc_input req = {0};
-	struct hwrm_tunnel_dst_port_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_tunnel_dst_port_alloc_output *resp;
+	struct hwrm_tunnel_dst_port_alloc_input *req;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TUNNEL_DST_PORT_ALLOC, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_TUNNEL_DST_PORT_ALLOC);
+	if (rc)
+		return rc;
 
-	req.tunnel_type = tunnel_type;
-	req.tunnel_dst_port_val = port;
+	req->tunnel_type = tunnel_type;
+	req->tunnel_dst_port_val = port;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc) {
 		netdev_err(bp->dev, "hwrm_tunnel_dst_port_alloc failed. rc:%d\n",
 			   rc);
@@ -4907,33 +4700,40 @@ static int bnxt_hwrm_tunnel_dst_port_alloc(struct bnxt *bp, __be16 port,
 	}
 
 err_out:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 static int bnxt_hwrm_cfa_l2_set_rx_mask(struct bnxt *bp, u16 vnic_id)
 {
-	struct hwrm_cfa_l2_set_rx_mask_input req = {0};
+	struct hwrm_cfa_l2_set_rx_mask_input *req;
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_L2_SET_RX_MASK, -1, -1);
-	req.vnic_id = cpu_to_le32(vnic->fw_vnic_id);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_SET_RX_MASK);
+	if (rc)
+		return rc;
 
-	req.num_mc_entries = cpu_to_le32(vnic->mc_list_count);
-	req.mc_tbl_addr = cpu_to_le64(vnic->mc_list_mapping);
-	req.mask = cpu_to_le32(vnic->rx_mask);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
+	req->num_mc_entries = cpu_to_le32(vnic->mc_list_count);
+	req->mc_tbl_addr = cpu_to_le64(vnic->mc_list_mapping);
+	req->mask = cpu_to_le32(vnic->rx_mask);
+	return hwrm_req_send_silent(bp, req);
 }
 
 #ifdef CONFIG_RFS_ACCEL
 static int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
 					    struct bnxt_ntuple_filter *fltr)
 {
-	struct hwrm_cfa_ntuple_filter_free_input req = {0};
+	struct hwrm_cfa_ntuple_filter_free_input *req;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_NTUPLE_FILTER_FREE, -1, -1);
-	req.ntuple_filter_id = fltr->filter_id;
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_NTUPLE_FILTER_FREE);
+	if (rc)
+		return rc;
+
+	req->ntuple_filter_id = fltr->filter_id;
+	return hwrm_req_send(bp, req);
 }
 
 #define BNXT_NTP_FLTR_FLAGS					\
@@ -4958,69 +4758,70 @@ static int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
 static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 					     struct bnxt_ntuple_filter *fltr)
 {
-	struct hwrm_cfa_ntuple_filter_alloc_input req = {0};
 	struct hwrm_cfa_ntuple_filter_alloc_output *resp;
+	struct hwrm_cfa_ntuple_filter_alloc_input *req;
 	struct flow_keys *keys = &fltr->fkeys;
 	struct bnxt_vnic_info *vnic;
 	u32 flags = 0;
-	int rc = 0;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_CFA_NTUPLE_FILTER_ALLOC);
+	if (rc)
+		return rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_NTUPLE_FILTER_ALLOC, -1, -1);
-	req.l2_filter_id = bp->vnic_info[0].fw_l2_filter_id[fltr->l2_fltr_idx];
+	req->l2_filter_id = bp->vnic_info[0].fw_l2_filter_id[fltr->l2_fltr_idx];
 
 	if (bp->fw_cap & BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2) {
 		flags = CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_RFS_RING_IDX;
-		req.dst_id = cpu_to_le16(fltr->rxq);
+		req->dst_id = cpu_to_le16(fltr->rxq);
 	} else {
 		vnic = &bp->vnic_info[fltr->rxq + 1];
-		req.dst_id = cpu_to_le16(vnic->fw_vnic_id);
+		req->dst_id = cpu_to_le16(vnic->fw_vnic_id);
 	}
-	req.flags = cpu_to_le32(flags);
-	req.enables = cpu_to_le32(BNXT_NTP_FLTR_FLAGS);
+	req->flags = cpu_to_le32(flags);
+	req->enables = cpu_to_le32(BNXT_NTP_FLTR_FLAGS);
 
-	req.ethertype = htons(ETH_P_IP);
-	memcpy(req.src_macaddr, fltr->src_mac_addr, ETH_ALEN);
-	req.ip_addr_type = CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4;
-	req.ip_protocol = keys->basic.ip_proto;
+	req->ethertype = htons(ETH_P_IP);
+	memcpy(req->src_macaddr, fltr->src_mac_addr, ETH_ALEN);
+	req->ip_addr_type = CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4;
+	req->ip_protocol = keys->basic.ip_proto;
 
 	if (keys->basic.n_proto == htons(ETH_P_IPV6)) {
 		int i;
 
-		req.ethertype = htons(ETH_P_IPV6);
-		req.ip_addr_type =
+		req->ethertype = htons(ETH_P_IPV6);
+		req->ip_addr_type =
 			CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6;
-		*(struct in6_addr *)&req.src_ipaddr[0] =
+		*(struct in6_addr *)&req->src_ipaddr[0] =
 			keys->addrs.v6addrs.src;
-		*(struct in6_addr *)&req.dst_ipaddr[0] =
+		*(struct in6_addr *)&req->dst_ipaddr[0] =
 			keys->addrs.v6addrs.dst;
 		for (i = 0; i < 4; i++) {
-			req.src_ipaddr_mask[i] = cpu_to_be32(0xffffffff);
-			req.dst_ipaddr_mask[i] = cpu_to_be32(0xffffffff);
+			req->src_ipaddr_mask[i] = cpu_to_be32(0xffffffff);
+			req->dst_ipaddr_mask[i] = cpu_to_be32(0xffffffff);
 		}
 	} else {
-		req.src_ipaddr[0] = keys->addrs.v4addrs.src;
-		req.src_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
-		req.dst_ipaddr[0] = keys->addrs.v4addrs.dst;
-		req.dst_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
+		req->src_ipaddr[0] = keys->addrs.v4addrs.src;
+		req->src_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
+		req->dst_ipaddr[0] = keys->addrs.v4addrs.dst;
+		req->dst_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
 	}
 	if (keys->control.flags & FLOW_DIS_ENCAPSULATION) {
-		req.enables |= cpu_to_le32(BNXT_NTP_TUNNEL_FLTR_FLAG);
-		req.tunnel_type =
+		req->enables |= cpu_to_le32(BNXT_NTP_TUNNEL_FLTR_FLAG);
+		req->tunnel_type =
 			CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL;
 	}
 
-	req.src_port = keys->ports.src;
-	req.src_port_mask = cpu_to_be16(0xffff);
-	req.dst_port = keys->ports.dst;
-	req.dst_port_mask = cpu_to_be16(0xffff);
+	req->src_port = keys->ports.src;
+	req->src_port_mask = cpu_to_be16(0xffff);
+	req->dst_port = keys->ports.dst;
+	req->dst_port_mask = cpu_to_be16(0xffff);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc) {
-		resp = bnxt_get_hwrm_resp_addr(bp, &req);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
+	if (!rc)
 		fltr->filter_id = resp->ntuple_filter_id;
-	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 #endif
@@ -5028,62 +4829,62 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 static int bnxt_hwrm_set_vnic_filter(struct bnxt *bp, u16 vnic_id, u16 idx,
 				     u8 *mac_addr)
 {
-	u32 rc = 0;
-	struct hwrm_cfa_l2_filter_alloc_input req = {0};
-	struct hwrm_cfa_l2_filter_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_cfa_l2_filter_alloc_output *resp;
+	struct hwrm_cfa_l2_filter_alloc_input *req;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_L2_FILTER_ALLOC, -1, -1);
-	req.flags = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_ALLOC);
+	if (rc)
+		return rc;
+
+	req->flags = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX);
 	if (!BNXT_CHIP_TYPE_NITRO_A0(bp))
-		req.flags |=
+		req->flags |=
 			cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST);
-	req.dst_id = cpu_to_le16(bp->vnic_info[vnic_id].fw_vnic_id);
-	req.enables =
+	req->dst_id = cpu_to_le16(bp->vnic_info[vnic_id].fw_vnic_id);
+	req->enables =
 		cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR |
 			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID |
 			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK);
-	memcpy(req.l2_addr, mac_addr, ETH_ALEN);
-	req.l2_addr_mask[0] = 0xff;
-	req.l2_addr_mask[1] = 0xff;
-	req.l2_addr_mask[2] = 0xff;
-	req.l2_addr_mask[3] = 0xff;
-	req.l2_addr_mask[4] = 0xff;
-	req.l2_addr_mask[5] = 0xff;
-
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	memcpy(req->l2_addr, mac_addr, ETH_ALEN);
+	req->l2_addr_mask[0] = 0xff;
+	req->l2_addr_mask[1] = 0xff;
+	req->l2_addr_mask[2] = 0xff;
+	req->l2_addr_mask[3] = 0xff;
+	req->l2_addr_mask[4] = 0xff;
+	req->l2_addr_mask[5] = 0xff;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc)
 		bp->vnic_info[vnic_id].fw_l2_filter_id[idx] =
 							resp->l2_filter_id;
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 static int bnxt_hwrm_clear_vnic_filter(struct bnxt *bp)
 {
+	struct hwrm_cfa_l2_filter_free_input *req;
 	u16 i, j, num_of_vnics = 1; /* only vnic 0 supported */
-	int rc = 0;
+	int rc;
 
 	/* Any associated ntuple filters will also be cleared by firmware. */
-	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_FREE);
+	if (rc)
+		return rc;
+	hwrm_req_hold(bp, req);
 	for (i = 0; i < num_of_vnics; i++) {
 		struct bnxt_vnic_info *vnic = &bp->vnic_info[i];
 
 		for (j = 0; j < vnic->uc_filter_count; j++) {
-			struct hwrm_cfa_l2_filter_free_input req = {0};
-
-			bnxt_hwrm_cmd_hdr_init(bp, &req,
-					       HWRM_CFA_L2_FILTER_FREE, -1, -1);
+			req->l2_filter_id = vnic->fw_l2_filter_id[j];
 
-			req.l2_filter_id = vnic->fw_l2_filter_id[j];
-
-			rc = _hwrm_send_message(bp, &req, sizeof(req),
-						HWRM_CMD_TIMEOUT);
+			rc = hwrm_req_send(bp, req);
 		}
 		vnic->uc_filter_count = 0;
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
-
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -5091,12 +4892,15 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags)
 {
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	u16 max_aggs = VNIC_TPA_CFG_REQ_MAX_AGGS_MAX;
-	struct hwrm_vnic_tpa_cfg_input req = {0};
+	struct hwrm_vnic_tpa_cfg_input *req;
+	int rc;
 
 	if (vnic->fw_vnic_id == INVALID_HW_RING_ID)
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_TPA_CFG, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_VNIC_TPA_CFG);
+	if (rc)
+		return rc;
 
 	if (tpa_flags) {
 		u16 mss = bp->dev->mtu - 40;
@@ -5110,9 +4914,9 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags)
 		if (tpa_flags & BNXT_FLAG_GRO)
 			flags |= VNIC_TPA_CFG_REQ_FLAGS_GRO;
 
-		req.flags = cpu_to_le32(flags);
+		req->flags = cpu_to_le32(flags);
 
-		req.enables =
+		req->enables =
 			cpu_to_le32(VNIC_TPA_CFG_REQ_ENABLES_MAX_AGG_SEGS |
 				    VNIC_TPA_CFG_REQ_ENABLES_MAX_AGGS |
 				    VNIC_TPA_CFG_REQ_ENABLES_MIN_AGG_LEN);
@@ -5136,14 +4940,14 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags)
 		} else {
 			segs = ilog2(nsegs);
 		}
-		req.max_agg_segs = cpu_to_le16(segs);
-		req.max_aggs = cpu_to_le16(max_aggs);
+		req->max_agg_segs = cpu_to_le16(segs);
+		req->max_aggs = cpu_to_le16(max_aggs);
 
-		req.min_agg_len = cpu_to_le32(512);
+		req->min_agg_len = cpu_to_le32(512);
 	}
-	req.vnic_id = cpu_to_le16(vnic->fw_vnic_id);
+	req->vnic_id = cpu_to_le16(vnic->fw_vnic_id);
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
 static u16 bnxt_cp_ring_from_grp(struct bnxt *bp, struct bnxt_ring_struct *ring)
@@ -5287,86 +5091,102 @@ static void bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss)
 {
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
-	struct hwrm_vnic_rss_cfg_input req = {0};
+	struct hwrm_vnic_rss_cfg_input *req;
+	int rc;
 
 	if ((bp->flags & BNXT_FLAG_CHIP_P5) ||
 	    vnic->fw_rss_cos_lb_ctx[0] == INVALID_HW_RING_ID)
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_RSS_CFG, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_VNIC_RSS_CFG);
+	if (rc)
+		return rc;
+
 	if (set_rss) {
 		bnxt_fill_hw_rss_tbl(bp, vnic);
-		req.hash_type = cpu_to_le32(bp->rss_hash_cfg);
-		req.hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT;
-		req.ring_grp_tbl_addr = cpu_to_le64(vnic->rss_table_dma_addr);
-		req.hash_key_tbl_addr =
+		req->hash_type = cpu_to_le32(bp->rss_hash_cfg);
+		req->hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT;
+		req->ring_grp_tbl_addr = cpu_to_le64(vnic->rss_table_dma_addr);
+		req->hash_key_tbl_addr =
 			cpu_to_le64(vnic->rss_hash_key_dma_addr);
 	}
-	req.rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req->rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]);
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp, u16 vnic_id, bool set_rss)
 {
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
-	struct hwrm_vnic_rss_cfg_input req = {0};
+	struct hwrm_vnic_rss_cfg_input *req;
 	dma_addr_t ring_tbl_map;
 	u32 i, nr_ctxs;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_VNIC_RSS_CFG);
+	if (rc)
+		return rc;
+
+	req->vnic_id = cpu_to_le16(vnic->fw_vnic_id);
+	if (!set_rss)
+		return hwrm_req_send(bp, req);
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_RSS_CFG, -1, -1);
-	req.vnic_id = cpu_to_le16(vnic->fw_vnic_id);
-	if (!set_rss) {
-		hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-		return 0;
-	}
 	bnxt_fill_hw_rss_tbl(bp, vnic);
-	req.hash_type = cpu_to_le32(bp->rss_hash_cfg);
-	req.hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT;
-	req.hash_key_tbl_addr = cpu_to_le64(vnic->rss_hash_key_dma_addr);
+	req->hash_type = cpu_to_le32(bp->rss_hash_cfg);
+	req->hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT;
+	req->hash_key_tbl_addr = cpu_to_le64(vnic->rss_hash_key_dma_addr);
 	ring_tbl_map = vnic->rss_table_dma_addr;
 	nr_ctxs = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings);
-	for (i = 0; i < nr_ctxs; ring_tbl_map += BNXT_RSS_TABLE_SIZE_P5, i++) {
-		int rc;
 
-		req.ring_grp_tbl_addr = cpu_to_le64(ring_tbl_map);
-		req.ring_table_pair_index = i;
-		req.rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[i]);
-		rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	hwrm_req_hold(bp, req);
+	for (i = 0; i < nr_ctxs; ring_tbl_map += BNXT_RSS_TABLE_SIZE_P5, i++) {
+		req->ring_grp_tbl_addr = cpu_to_le64(ring_tbl_map);
+		req->ring_table_pair_index = i;
+		req->rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[i]);
+		rc = hwrm_req_send(bp, req);
 		if (rc)
-			return rc;
+			goto exit;
 	}
-	return 0;
+
+exit:
+	hwrm_req_drop(bp, req);
+	return rc;
 }
 
 static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, u16 vnic_id)
 {
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
-	struct hwrm_vnic_plcmodes_cfg_input req = {0};
+	struct hwrm_vnic_plcmodes_cfg_input *req;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_PLCMODES_CFG, -1, -1);
-	req.flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT |
-				VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 |
-				VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6);
-	req.enables =
+	rc = hwrm_req_init(bp, req, HWRM_VNIC_PLCMODES_CFG);
+	if (rc)
+		return rc;
+
+	req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT |
+				 VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 |
+				 VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6);
+	req->enables =
 		cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID |
 			    VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID);
 	/* thresholds not implemented in firmware yet */
-	req.jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
-	req.hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
-	req.vnic_id = cpu_to_le32(vnic->fw_vnic_id);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
+	req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
+	req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
+	return hwrm_req_send(bp, req);
 }
 
 static void bnxt_hwrm_vnic_ctx_free_one(struct bnxt *bp, u16 vnic_id,
 					u16 ctx_idx)
 {
-	struct hwrm_vnic_rss_cos_lb_ctx_free_input req = {0};
+	struct hwrm_vnic_rss_cos_lb_ctx_free_input *req;
+
+	if (hwrm_req_init(bp, req, HWRM_VNIC_RSS_COS_LB_CTX_FREE))
+		return;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_RSS_COS_LB_CTX_FREE, -1, -1);
-	req.rss_cos_lb_ctx_id =
+	req->rss_cos_lb_ctx_id =
 		cpu_to_le16(bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[ctx_idx]);
 
-	hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	hwrm_req_send(bp, req);
 	bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[ctx_idx] = INVALID_HW_RING_ID;
 }
 
@@ -5387,20 +5207,20 @@ static void bnxt_hwrm_vnic_ctx_free(struct bnxt *bp)
 
 static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp, u16 vnic_id, u16 ctx_idx)
 {
+	struct hwrm_vnic_rss_cos_lb_ctx_alloc_output *resp;
+	struct hwrm_vnic_rss_cos_lb_ctx_alloc_input *req;
 	int rc;
-	struct hwrm_vnic_rss_cos_lb_ctx_alloc_input req = {0};
-	struct hwrm_vnic_rss_cos_lb_ctx_alloc_output *resp =
-						bp->hwrm_cmd_resp_addr;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_RSS_COS_LB_CTX_ALLOC, -1,
-			       -1);
+	rc = hwrm_req_init(bp, req, HWRM_VNIC_RSS_COS_LB_CTX_ALLOC);
+	if (rc)
+		return rc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc)
 		bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[ctx_idx] =
 			le16_to_cpu(resp->rss_cos_lb_ctx_id);
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 
 	return rc;
 }
@@ -5414,47 +5234,50 @@ static u32 bnxt_get_roce_vnic_mode(struct bnxt *bp)
 
 int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 {
-	unsigned int ring = 0, grp_idx;
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
-	struct hwrm_vnic_cfg_input req = {0};
+	struct hwrm_vnic_cfg_input *req;
+	unsigned int ring = 0, grp_idx;
 	u16 def_vlan = 0;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_CFG, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_VNIC_CFG);
+	if (rc)
+		return rc;
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5) {
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[0];
 
-		req.default_rx_ring_id =
+		req->default_rx_ring_id =
 			cpu_to_le16(rxr->rx_ring_struct.fw_ring_id);
-		req.default_cmpl_ring_id =
+		req->default_cmpl_ring_id =
 			cpu_to_le16(bnxt_cp_ring_for_rx(bp, rxr));
-		req.enables =
+		req->enables =
 			cpu_to_le32(VNIC_CFG_REQ_ENABLES_DEFAULT_RX_RING_ID |
 				    VNIC_CFG_REQ_ENABLES_DEFAULT_CMPL_RING_ID);
 		goto vnic_mru;
 	}
-	req.enables = cpu_to_le32(VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP);
+	req->enables = cpu_to_le32(VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP);
 	/* Only RSS support for now TBD: COS & LB */
 	if (vnic->fw_rss_cos_lb_ctx[0] != INVALID_HW_RING_ID) {
-		req.rss_rule = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]);
-		req.enables |= cpu_to_le32(VNIC_CFG_REQ_ENABLES_RSS_RULE |
+		req->rss_rule = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]);
+		req->enables |= cpu_to_le32(VNIC_CFG_REQ_ENABLES_RSS_RULE |
 					   VNIC_CFG_REQ_ENABLES_MRU);
 	} else if (vnic->flags & BNXT_VNIC_RFS_NEW_RSS_FLAG) {
-		req.rss_rule =
+		req->rss_rule =
 			cpu_to_le16(bp->vnic_info[0].fw_rss_cos_lb_ctx[0]);
-		req.enables |= cpu_to_le32(VNIC_CFG_REQ_ENABLES_RSS_RULE |
+		req->enables |= cpu_to_le32(VNIC_CFG_REQ_ENABLES_RSS_RULE |
 					   VNIC_CFG_REQ_ENABLES_MRU);
-		req.flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_RSS_DFLT_CR_MODE);
+		req->flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_RSS_DFLT_CR_MODE);
 	} else {
-		req.rss_rule = cpu_to_le16(0xffff);
+		req->rss_rule = cpu_to_le16(0xffff);
 	}
 
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp) &&
 	    (vnic->fw_rss_cos_lb_ctx[0] != INVALID_HW_RING_ID)) {
-		req.cos_rule = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[1]);
-		req.enables |= cpu_to_le32(VNIC_CFG_REQ_ENABLES_COS_RULE);
+		req->cos_rule = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[1]);
+		req->enables |= cpu_to_le32(VNIC_CFG_REQ_ENABLES_COS_RULE);
 	} else {
-		req.cos_rule = cpu_to_le16(0xffff);
+		req->cos_rule = cpu_to_le16(0xffff);
 	}
 
 	if (vnic->flags & BNXT_VNIC_RSS_FLAG)
@@ -5465,34 +5288,36 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 		ring = bp->rx_nr_rings - 1;
 
 	grp_idx = bp->rx_ring[ring].bnapi->index;
-	req.dflt_ring_grp = cpu_to_le16(bp->grp_info[grp_idx].fw_grp_id);
-	req.lb_rule = cpu_to_le16(0xffff);
+	req->dflt_ring_grp = cpu_to_le16(bp->grp_info[grp_idx].fw_grp_id);
+	req->lb_rule = cpu_to_le16(0xffff);
 vnic_mru:
-	req.mru = cpu_to_le16(bp->dev->mtu + ETH_HLEN + VLAN_HLEN);
+	req->mru = cpu_to_le16(bp->dev->mtu + ETH_HLEN + VLAN_HLEN);
 
-	req.vnic_id = cpu_to_le16(vnic->fw_vnic_id);
+	req->vnic_id = cpu_to_le16(vnic->fw_vnic_id);
 #ifdef CONFIG_BNXT_SRIOV
 	if (BNXT_VF(bp))
 		def_vlan = bp->vf.vlan;
 #endif
 	if ((bp->flags & BNXT_FLAG_STRIP_VLAN) || def_vlan)
-		req.flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE);
+		req->flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE);
 	if (!vnic_id && bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP))
-		req.flags |= cpu_to_le32(bnxt_get_roce_vnic_mode(bp));
+		req->flags |= cpu_to_le32(bnxt_get_roce_vnic_mode(bp));
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
 static void bnxt_hwrm_vnic_free_one(struct bnxt *bp, u16 vnic_id)
 {
 	if (bp->vnic_info[vnic_id].fw_vnic_id != INVALID_HW_RING_ID) {
-		struct hwrm_vnic_free_input req = {0};
+		struct hwrm_vnic_free_input *req;
 
-		bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_FREE, -1, -1);
-		req.vnic_id =
+		if (hwrm_req_init(bp, req, HWRM_VNIC_FREE))
+			return;
+
+		req->vnic_id =
 			cpu_to_le32(bp->vnic_info[vnic_id].fw_vnic_id);
 
-		hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		hwrm_req_send(bp, req);
 		bp->vnic_info[vnic_id].fw_vnic_id = INVALID_HW_RING_ID;
 	}
 }
@@ -5509,11 +5334,15 @@ static int bnxt_hwrm_vnic_alloc(struct bnxt *bp, u16 vnic_id,
 				unsigned int start_rx_ring_idx,
 				unsigned int nr_rings)
 {
-	int rc = 0;
 	unsigned int i, j, grp_idx, end_idx = start_rx_ring_idx + nr_rings;
-	struct hwrm_vnic_alloc_input req = {0};
-	struct hwrm_vnic_alloc_output *resp = bp->hwrm_cmd_resp_addr;
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
+	struct hwrm_vnic_alloc_output *resp;
+	struct hwrm_vnic_alloc_input *req;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_VNIC_ALLOC);
+	if (rc)
+		return rc;
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5)
 		goto vnic_no_ring_grps;
@@ -5533,22 +5362,20 @@ vnic_no_ring_grps:
 	for (i = 0; i < BNXT_MAX_CTX_PER_VNIC; i++)
 		vnic->fw_rss_cos_lb_ctx[i] = INVALID_HW_RING_ID;
 	if (vnic_id == 0)
-		req.flags = cpu_to_le32(VNIC_ALLOC_REQ_FLAGS_DEFAULT);
+		req->flags = cpu_to_le32(VNIC_ALLOC_REQ_FLAGS_DEFAULT);
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_ALLOC, -1, -1);
-
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc)
 		vnic->fw_vnic_id = le32_to_cpu(resp->vnic_id);
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 {
-	struct hwrm_vnic_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_vnic_qcaps_input req = {0};
+	struct hwrm_vnic_qcaps_output *resp;
+	struct hwrm_vnic_qcaps_input *req;
 	int rc;
 
 	bp->hw_ring_stats_size = sizeof(struct ctx_hw_stats);
@@ -5556,9 +5383,12 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 	if (bp->hwrm_spec_code < 0x10600)
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_QCAPS, -1, -1);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_VNIC_QCAPS);
+	if (rc)
+		return rc;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc) {
 		u32 flags = le32_to_cpu(resp->flags);
 
@@ -5584,92 +5414,96 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 				bp->hw_ring_stats_size = BNXT_RING_STATS_SIZE_P5_SR2;
 		}
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 static int bnxt_hwrm_ring_grp_alloc(struct bnxt *bp)
 {
+	struct hwrm_ring_grp_alloc_output *resp;
+	struct hwrm_ring_grp_alloc_input *req;
+	int rc;
 	u16 i;
-	u32 rc = 0;
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5)
 		return 0;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = hwrm_req_init(bp, req, HWRM_RING_GRP_ALLOC);
+	if (rc)
+		return rc;
+
+	resp = hwrm_req_hold(bp, req);
 	for (i = 0; i < bp->rx_nr_rings; i++) {
-		struct hwrm_ring_grp_alloc_input req = {0};
-		struct hwrm_ring_grp_alloc_output *resp =
-					bp->hwrm_cmd_resp_addr;
 		unsigned int grp_idx = bp->rx_ring[i].bnapi->index;
 
-		bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_GRP_ALLOC, -1, -1);
+		req->cr = cpu_to_le16(bp->grp_info[grp_idx].cp_fw_ring_id);
+		req->rr = cpu_to_le16(bp->grp_info[grp_idx].rx_fw_ring_id);
+		req->ar = cpu_to_le16(bp->grp_info[grp_idx].agg_fw_ring_id);
+		req->sc = cpu_to_le16(bp->grp_info[grp_idx].fw_stats_ctx);
 
-		req.cr = cpu_to_le16(bp->grp_info[grp_idx].cp_fw_ring_id);
-		req.rr = cpu_to_le16(bp->grp_info[grp_idx].rx_fw_ring_id);
-		req.ar = cpu_to_le16(bp->grp_info[grp_idx].agg_fw_ring_id);
-		req.sc = cpu_to_le16(bp->grp_info[grp_idx].fw_stats_ctx);
+		rc = hwrm_req_send(bp, req);
 
-		rc = _hwrm_send_message(bp, &req, sizeof(req),
-					HWRM_CMD_TIMEOUT);
 		if (rc)
 			break;
 
 		bp->grp_info[grp_idx].fw_grp_id =
 			le32_to_cpu(resp->ring_group_id);
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 static void bnxt_hwrm_ring_grp_free(struct bnxt *bp)
 {
+	struct hwrm_ring_grp_free_input *req;
 	u16 i;
-	struct hwrm_ring_grp_free_input req = {0};
 
 	if (!bp->grp_info || (bp->flags & BNXT_FLAG_CHIP_P5))
 		return;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_GRP_FREE, -1, -1);
+	if (hwrm_req_init(bp, req, HWRM_RING_GRP_FREE))
+		return;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
+	hwrm_req_hold(bp, req);
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		if (bp->grp_info[i].fw_grp_id == INVALID_HW_RING_ID)
 			continue;
-		req.ring_group_id =
+		req->ring_group_id =
 			cpu_to_le32(bp->grp_info[i].fw_grp_id);
 
-		_hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		hwrm_req_send(bp, req);
 		bp->grp_info[i].fw_grp_id = INVALID_HW_RING_ID;
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 }
 
 static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 				    struct bnxt_ring_struct *ring,
 				    u32 ring_type, u32 map_index)
 {
-	int rc = 0, err = 0;
-	struct hwrm_ring_alloc_input req = {0};
-	struct hwrm_ring_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_ring_alloc_output *resp;
+	struct hwrm_ring_alloc_input *req;
 	struct bnxt_ring_mem_info *rmem = &ring->ring_mem;
 	struct bnxt_ring_grp_info *grp_info;
+	int rc, err = 0;
 	u16 ring_id;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_ALLOC, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_RING_ALLOC);
+	if (rc)
+		goto exit;
 
-	req.enables = 0;
+	req->enables = 0;
 	if (rmem->nr_pages > 1) {
-		req.page_tbl_addr = cpu_to_le64(rmem->pg_tbl_map);
+		req->page_tbl_addr = cpu_to_le64(rmem->pg_tbl_map);
 		/* Page size is in log2 units */
-		req.page_size = BNXT_PAGE_SHIFT;
-		req.page_tbl_depth = 1;
+		req->page_size = BNXT_PAGE_SHIFT;
+		req->page_tbl_depth = 1;
 	} else {
-		req.page_tbl_addr =  cpu_to_le64(rmem->dma_arr[0]);
+		req->page_tbl_addr =  cpu_to_le64(rmem->dma_arr[0]);
 	}
-	req.fbo = 0;
+	req->fbo = 0;
 	/* Association of ring index with doorbell index and MSIX number */
-	req.logical_id = cpu_to_le16(map_index);
+	req->logical_id = cpu_to_le16(map_index);
 
 	switch (ring_type) {
 	case HWRM_RING_ALLOC_TX: {
@@ -5677,67 +5511,67 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 
 		txr = container_of(ring, struct bnxt_tx_ring_info,
 				   tx_ring_struct);
-		req.ring_type = RING_ALLOC_REQ_RING_TYPE_TX;
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_TX;
 		/* Association of transmit ring with completion ring */
 		grp_info = &bp->grp_info[ring->grp_idx];
-		req.cmpl_ring_id = cpu_to_le16(bnxt_cp_ring_for_tx(bp, txr));
-		req.length = cpu_to_le32(bp->tx_ring_mask + 1);
-		req.stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
-		req.queue_id = cpu_to_le16(ring->queue_id);
+		req->cmpl_ring_id = cpu_to_le16(bnxt_cp_ring_for_tx(bp, txr));
+		req->length = cpu_to_le32(bp->tx_ring_mask + 1);
+		req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
+		req->queue_id = cpu_to_le16(ring->queue_id);
 		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);
+		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) {
 			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(
+			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);
+			req->flags = cpu_to_le16(flags);
 		}
 		break;
 	case HWRM_RING_ALLOC_AGG:
 		if (bp->flags & BNXT_FLAG_CHIP_P5) {
-			req.ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG;
+			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(
+			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->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
 		}
-		req.length = cpu_to_le32(bp->rx_agg_ring_mask + 1);
+		req->length = cpu_to_le32(bp->rx_agg_ring_mask + 1);
 		break;
 	case HWRM_RING_ALLOC_CMPL:
-		req.ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;
-		req.length = cpu_to_le32(bp->cp_ring_mask + 1);
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;
+		req->length = cpu_to_le32(bp->cp_ring_mask + 1);
 		if (bp->flags & BNXT_FLAG_CHIP_P5) {
 			/* Association of cp ring with nq */
 			grp_info = &bp->grp_info[map_index];
-			req.nq_ring_id = cpu_to_le16(grp_info->cp_fw_ring_id);
-			req.cq_handle = cpu_to_le64(ring->handle);
-			req.enables |= cpu_to_le32(
+			req->nq_ring_id = cpu_to_le16(grp_info->cp_fw_ring_id);
+			req->cq_handle = cpu_to_le64(ring->handle);
+			req->enables |= cpu_to_le32(
 				RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID);
 		} else if (bp->flags & BNXT_FLAG_USING_MSIX) {
-			req.int_mode = RING_ALLOC_REQ_INT_MODE_MSIX;
+			req->int_mode = RING_ALLOC_REQ_INT_MODE_MSIX;
 		}
 		break;
 	case HWRM_RING_ALLOC_NQ:
-		req.ring_type = RING_ALLOC_REQ_RING_TYPE_NQ;
-		req.length = cpu_to_le32(bp->cp_ring_mask + 1);
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_NQ;
+		req->length = cpu_to_le32(bp->cp_ring_mask + 1);
 		if (bp->flags & BNXT_FLAG_USING_MSIX)
-			req.int_mode = RING_ALLOC_REQ_INT_MODE_MSIX;
+			req->int_mode = RING_ALLOC_REQ_INT_MODE_MSIX;
 		break;
 	default:
 		netdev_err(bp->dev, "hwrm alloc invalid ring type %d\n",
@@ -5745,12 +5579,13 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 		return -1;
 	}
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	err = le16_to_cpu(resp->error_code);
 	ring_id = le16_to_cpu(resp->ring_id);
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 
+exit:
 	if (rc || err) {
 		netdev_err(bp->dev, "hwrm_ring_alloc type %d failed. rc:%x err:%x\n",
 			   ring_type, rc, err);
@@ -5765,23 +5600,28 @@ static int bnxt_hwrm_set_async_event_cr(struct bnxt *bp, int idx)
 	int rc;
 
 	if (BNXT_PF(bp)) {
-		struct hwrm_func_cfg_input req = {0};
+		struct hwrm_func_cfg_input *req;
 
-		bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
-		req.fid = cpu_to_le16(0xffff);
-		req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_ASYNC_EVENT_CR);
-		req.async_event_cr = cpu_to_le16(idx);
-		rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		rc = hwrm_req_init(bp, req, HWRM_FUNC_CFG);
+		if (rc)
+			return rc;
+
+		req->fid = cpu_to_le16(0xffff);
+		req->enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_ASYNC_EVENT_CR);
+		req->async_event_cr = cpu_to_le16(idx);
+		return hwrm_req_send(bp, req);
 	} else {
-		struct hwrm_func_vf_cfg_input req = {0};
+		struct hwrm_func_vf_cfg_input *req;
 
-		bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_CFG, -1, -1);
-		req.enables =
+		rc = hwrm_req_init(bp, req, HWRM_FUNC_VF_CFG);
+		if (rc)
+			return rc;
+
+		req->enables =
 			cpu_to_le32(FUNC_VF_CFG_REQ_ENABLES_ASYNC_EVENT_CR);
-		req.async_event_cr = cpu_to_le16(idx);
-		rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		req->async_event_cr = cpu_to_le16(idx);
+		return hwrm_req_send(bp, req);
 	}
-	return rc;
 }
 
 static void bnxt_set_db(struct bnxt *bp, struct bnxt_db_info *db, u32 ring_type,
@@ -5952,23 +5792,27 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp,
 				   struct bnxt_ring_struct *ring,
 				   u32 ring_type, int cmpl_ring_id)
 {
+	struct hwrm_ring_free_output *resp;
+	struct hwrm_ring_free_input *req;
+	u16 error_code = 0;
 	int rc;
-	struct hwrm_ring_free_input req = {0};
-	struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr;
-	u16 error_code;
 
 	if (BNXT_NO_FW_ACCESS(bp))
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1);
-	req.ring_type = ring_type;
-	req.ring_id = cpu_to_le16(ring->fw_ring_id);
+	rc = hwrm_req_init(bp, req, HWRM_RING_FREE);
+	if (rc)
+		goto exit;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	error_code = le16_to_cpu(resp->error_code);
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	req->cmpl_ring = cpu_to_le16(cmpl_ring_id);
+	req->ring_type = ring_type;
+	req->ring_id = cpu_to_le16(ring->fw_ring_id);
 
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
+	error_code = le16_to_cpu(resp->error_code);
+	hwrm_req_drop(bp, req);
+exit:
 	if (rc || error_code) {
 		netdev_err(bp->dev, "hwrm_ring_free type %d failed. rc:%x err:%x\n",
 			   ring_type, rc, error_code);
@@ -6083,20 +5927,23 @@ static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
 
 static int bnxt_hwrm_get_rings(struct bnxt *bp)
 {
-	struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
-	struct hwrm_func_qcfg_input req = {0};
+	struct hwrm_func_qcfg_output *resp;
+	struct hwrm_func_qcfg_input *req;
 	int rc;
 
 	if (bp->hwrm_spec_code < 0x10601)
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1);
-	req.fid = cpu_to_le16(0xffff);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_QCFG);
+	if (rc)
+		return rc;
+
+	req->fid = cpu_to_le16(0xffff);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc) {
-		mutex_unlock(&bp->hwrm_cmd_lock);
+		hwrm_req_drop(bp, req);
 		return rc;
 	}
 
@@ -6130,39 +5977,45 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 		hw_resc->resv_cp_rings = cp;
 		hw_resc->resv_stat_ctxs = stats;
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return 0;
 }
 
-/* Caller must hold bp->hwrm_cmd_lock */
 int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings)
 {
-	struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_func_qcfg_input req = {0};
+	struct hwrm_func_qcfg_output *resp;
+	struct hwrm_func_qcfg_input *req;
 	int rc;
 
 	if (bp->hwrm_spec_code < 0x10601)
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1);
-	req.fid = cpu_to_le16(fid);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_QCFG);
+	if (rc)
+		return rc;
+
+	req->fid = cpu_to_le16(fid);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc)
 		*tx_rings = le16_to_cpu(resp->alloc_tx_rings);
 
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 static bool bnxt_rfs_supported(struct bnxt *bp);
 
-static void
-__bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
-			     int tx_rings, int rx_rings, int ring_grps,
-			     int cp_rings, int stats, int vnics)
+static struct hwrm_func_cfg_input *
+__bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
+			     int ring_grps, int cp_rings, int stats, int vnics)
 {
+	struct hwrm_func_cfg_input *req;
 	u32 enables = 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, req, HWRM_FUNC_CFG, -1, -1);
+	if (hwrm_req_init(bp, req, HWRM_FUNC_CFG))
+		return NULL;
+
 	req->fid = cpu_to_le16(0xffff);
 	enables |= tx_rings ? FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS : 0;
 	req->num_tx_rings = cpu_to_le16(tx_rings);
@@ -6203,17 +6056,19 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
 		req->num_vnics = cpu_to_le16(vnics);
 	}
 	req->enables = cpu_to_le32(enables);
+	return req;
 }
 
-static void
-__bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
-			     struct hwrm_func_vf_cfg_input *req, int tx_rings,
-			     int rx_rings, int ring_grps, int cp_rings,
-			     int stats, int vnics)
+static struct hwrm_func_vf_cfg_input *
+__bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
+			     int ring_grps, int cp_rings, int stats, int vnics)
 {
+	struct hwrm_func_vf_cfg_input *req;
 	u32 enables = 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, req, HWRM_FUNC_VF_CFG, -1, -1);
+	if (hwrm_req_init(bp, req, HWRM_FUNC_VF_CFG))
+		return NULL;
+
 	enables |= tx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS : 0;
 	enables |= rx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS |
 			      FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
@@ -6245,21 +6100,27 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
 	req->num_vnics = cpu_to_le16(vnics);
 
 	req->enables = cpu_to_le32(enables);
+	return req;
 }
 
 static int
 bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 			   int ring_grps, int cp_rings, int stats, int vnics)
 {
-	struct hwrm_func_cfg_input req = {0};
+	struct hwrm_func_cfg_input *req;
 	int rc;
 
-	__bnxt_hwrm_reserve_pf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
-				     cp_rings, stats, vnics);
-	if (!req.enables)
+	req = __bnxt_hwrm_reserve_pf_rings(bp, tx_rings, rx_rings, ring_grps,
+					   cp_rings, stats, vnics);
+	if (!req)
+		return -ENOMEM;
+
+	if (!req->enables) {
+		hwrm_req_drop(bp, req);
 		return 0;
+	}
 
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_send(bp, req);
 	if (rc)
 		return rc;
 
@@ -6273,7 +6134,7 @@ static int
 bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 			   int ring_grps, int cp_rings, int stats, int vnics)
 {
-	struct hwrm_func_vf_cfg_input req = {0};
+	struct hwrm_func_vf_cfg_input *req;
 	int rc;
 
 	if (!BNXT_NEW_RM(bp)) {
@@ -6281,9 +6142,12 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 		return 0;
 	}
 
-	__bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
-				     cp_rings, stats, vnics);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req = __bnxt_hwrm_reserve_vf_rings(bp, tx_rings, rx_rings, ring_grps,
+					   cp_rings, stats, vnics);
+	if (!req)
+		return -ENOMEM;
+
+	rc = hwrm_req_send(bp, req);
 	if (rc)
 		return rc;
 
@@ -6484,14 +6348,14 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 				    int ring_grps, int cp_rings, int stats,
 				    int vnics)
 {
-	struct hwrm_func_vf_cfg_input req = {0};
+	struct hwrm_func_vf_cfg_input *req;
 	u32 flags;
 
 	if (!BNXT_NEW_RM(bp))
 		return 0;
 
-	__bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
-				     cp_rings, stats, vnics);
+	req = __bnxt_hwrm_reserve_vf_rings(bp, tx_rings, rx_rings, ring_grps,
+					   cp_rings, stats, vnics);
 	flags = FUNC_VF_CFG_REQ_FLAGS_TX_ASSETS_TEST |
 		FUNC_VF_CFG_REQ_FLAGS_RX_ASSETS_TEST |
 		FUNC_VF_CFG_REQ_FLAGS_CMPL_ASSETS_TEST |
@@ -6501,20 +6365,19 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
 		flags |= FUNC_VF_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST;
 
-	req.flags = cpu_to_le32(flags);
-	return hwrm_send_message_silent(bp, &req, sizeof(req),
-					HWRM_CMD_TIMEOUT);
+	req->flags = cpu_to_le32(flags);
+	return hwrm_req_send_silent(bp, req);
 }
 
 static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 				    int ring_grps, int cp_rings, int stats,
 				    int vnics)
 {
-	struct hwrm_func_cfg_input req = {0};
+	struct hwrm_func_cfg_input *req;
 	u32 flags;
 
-	__bnxt_hwrm_reserve_pf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
-				     cp_rings, stats, vnics);
+	req = __bnxt_hwrm_reserve_pf_rings(bp, tx_rings, rx_rings, ring_grps,
+					   cp_rings, stats, vnics);
 	flags = FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST;
 	if (BNXT_NEW_RM(bp)) {
 		flags |= FUNC_CFG_REQ_FLAGS_RX_ASSETS_TEST |
@@ -6528,9 +6391,8 @@ static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 			flags |= FUNC_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST;
 	}
 
-	req.flags = cpu_to_le32(flags);
-	return hwrm_send_message_silent(bp, &req, sizeof(req),
-					HWRM_CMD_TIMEOUT);
+	req->flags = cpu_to_le32(flags);
+	return hwrm_req_send_silent(bp, req);
 }
 
 static int bnxt_hwrm_check_rings(struct bnxt *bp, int tx_rings, int rx_rings,
@@ -6551,9 +6413,9 @@ static int bnxt_hwrm_check_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 
 static void bnxt_hwrm_coal_params_qcaps(struct bnxt *bp)
 {
-	struct hwrm_ring_aggint_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
 	struct bnxt_coal_cap *coal_cap = &bp->coal_cap;
-	struct hwrm_ring_aggint_qcaps_input req = {0};
+	struct hwrm_ring_aggint_qcaps_output *resp;
+	struct hwrm_ring_aggint_qcaps_input *req;
 	int rc;
 
 	coal_cap->cmpl_params = BNXT_LEGACY_COAL_CMPL_PARAMS;
@@ -6569,9 +6431,11 @@ static void bnxt_hwrm_coal_params_qcaps(struct bnxt *bp)
 	if (bp->hwrm_spec_code < 0x10902)
 		return;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_AGGINT_QCAPS, -1, -1);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (hwrm_req_init(bp, req, HWRM_RING_AGGINT_QCAPS))
+		return;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
 	if (!rc) {
 		coal_cap->cmpl_params = le32_to_cpu(resp->cmpl_params);
 		coal_cap->nq_params = le32_to_cpu(resp->nq_params);
@@ -6591,7 +6455,7 @@ static void bnxt_hwrm_coal_params_qcaps(struct bnxt *bp)
 			le16_to_cpu(resp->num_cmpl_aggr_int_max);
 		coal_cap->timer_units = le16_to_cpu(resp->timer_units);
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 }
 
 static u16 bnxt_usec_to_coal_tmr(struct bnxt *bp, u16 usec)
@@ -6659,37 +6523,40 @@ static void bnxt_hwrm_set_coal_params(struct bnxt *bp,
 	req->enables |= cpu_to_le16(BNXT_COAL_CMPL_ENABLES);
 }
 
-/* Caller holds bp->hwrm_cmd_lock */
 static int __bnxt_hwrm_set_coal_nq(struct bnxt *bp, struct bnxt_napi *bnapi,
 				   struct bnxt_coal *hw_coal)
 {
-	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input req = {0};
+	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req;
 	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 	struct bnxt_coal_cap *coal_cap = &bp->coal_cap;
 	u32 nq_params = coal_cap->nq_params;
 	u16 tmr;
+	int rc;
 
 	if (!(nq_params & RING_AGGINT_QCAPS_RESP_NQ_PARAMS_INT_LAT_TMR_MIN))
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS,
-			       -1, -1);
-	req.ring_id = cpu_to_le16(cpr->cp_ring_struct.fw_ring_id);
-	req.flags =
+	rc = hwrm_req_init(bp, req, HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS);
+	if (rc)
+		return rc;
+
+	req->ring_id = cpu_to_le16(cpr->cp_ring_struct.fw_ring_id);
+	req->flags =
 		cpu_to_le16(RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_IS_NQ);
 
 	tmr = bnxt_usec_to_coal_tmr(bp, hw_coal->coal_ticks) / 2;
 	tmr = clamp_t(u16, tmr, 1, coal_cap->int_lat_tmr_min_max);
-	req.int_lat_tmr_min = cpu_to_le16(tmr);
-	req.enables |= cpu_to_le16(BNXT_COAL_CMPL_MIN_TMR_ENABLE);
-	return _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req->int_lat_tmr_min = cpu_to_le16(tmr);
+	req->enables |= cpu_to_le16(BNXT_COAL_CMPL_MIN_TMR_ENABLE);
+	return hwrm_req_send(bp, req);
 }
 
 int bnxt_hwrm_set_ring_coal(struct bnxt *bp, struct bnxt_napi *bnapi)
 {
-	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input req_rx = {0};
+	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req_rx;
 	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 	struct bnxt_coal coal;
+	int rc;
 
 	/* Tick values in micro seconds.
 	 * 1 coal_buf x bufs_per_record = 1 completion record.
@@ -6702,48 +6569,53 @@ int bnxt_hwrm_set_ring_coal(struct bnxt *bp, struct bnxt_napi *bnapi)
 	if (!bnapi->rx_ring)
 		return -ENODEV;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req_rx,
-			       HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS, -1, -1);
+	rc = hwrm_req_init(bp, req_rx, HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS);
+	if (rc)
+		return rc;
 
-	bnxt_hwrm_set_coal_params(bp, &coal, &req_rx);
+	bnxt_hwrm_set_coal_params(bp, &coal, req_rx);
 
-	req_rx.ring_id = cpu_to_le16(bnxt_cp_ring_for_rx(bp, bnapi->rx_ring));
+	req_rx->ring_id = cpu_to_le16(bnxt_cp_ring_for_rx(bp, bnapi->rx_ring));
 
-	return hwrm_send_message(bp, &req_rx, sizeof(req_rx),
-				 HWRM_CMD_TIMEOUT);
+	return hwrm_req_send(bp, req_rx);
 }
 
 int bnxt_hwrm_set_coal(struct bnxt *bp)
 {
-	int i, rc = 0;
-	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input req_rx = {0},
-							   req_tx = {0}, *req;
+	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req_rx, *req_tx,
+							   *req;
+	int i, rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req_rx,
-			       HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS, -1, -1);
-	bnxt_hwrm_cmd_hdr_init(bp, &req_tx,
-			       HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS, -1, -1);
+	rc = hwrm_req_init(bp, req_rx, HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS);
+	if (rc)
+		return rc;
+
+	rc = hwrm_req_init(bp, req_tx, HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS);
+	if (rc) {
+		hwrm_req_drop(bp, req_rx);
+		return rc;
+	}
 
-	bnxt_hwrm_set_coal_params(bp, &bp->rx_coal, &req_rx);
-	bnxt_hwrm_set_coal_params(bp, &bp->tx_coal, &req_tx);
+	bnxt_hwrm_set_coal_params(bp, &bp->rx_coal, req_rx);
+	bnxt_hwrm_set_coal_params(bp, &bp->tx_coal, req_tx);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
+	hwrm_req_hold(bp, req_rx);
+	hwrm_req_hold(bp, req_tx);
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_coal *hw_coal;
 		u16 ring_id;
 
-		req = &req_rx;
+		req = req_rx;
 		if (!bnapi->rx_ring) {
 			ring_id = bnxt_cp_ring_for_tx(bp, bnapi->tx_ring);
-			req = &req_tx;
+			req = req_tx;
 		} else {
 			ring_id = bnxt_cp_ring_for_rx(bp, bnapi->rx_ring);
 		}
 		req->ring_id = cpu_to_le16(ring_id);
 
-		rc = _hwrm_send_message(bp, req, sizeof(*req),
-					HWRM_CMD_TIMEOUT);
+		rc = hwrm_req_send(bp, req);
 		if (rc)
 			break;
 
@@ -6751,11 +6623,10 @@ int bnxt_hwrm_set_coal(struct bnxt *bp)
 			continue;
 
 		if (bnapi->rx_ring && bnapi->tx_ring) {
-			req = &req_tx;
+			req = req_tx;
 			ring_id = bnxt_cp_ring_for_tx(bp, bnapi->tx_ring);
 			req->ring_id = cpu_to_le16(ring_id);
-			rc = _hwrm_send_message(bp, req, sizeof(*req),
-						HWRM_CMD_TIMEOUT);
+			rc = hwrm_req_send(bp, req);
 			if (rc)
 				break;
 		}
@@ -6765,14 +6636,15 @@ int bnxt_hwrm_set_coal(struct bnxt *bp)
 			hw_coal = &bp->tx_coal;
 		__bnxt_hwrm_set_coal_nq(bp, bnapi, hw_coal);
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req_rx);
+	hwrm_req_drop(bp, req_tx);
 	return rc;
 }
 
 static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp)
 {
-	struct hwrm_stat_ctx_clr_stats_input req0 = {0};
-	struct hwrm_stat_ctx_free_input req = {0};
+	struct hwrm_stat_ctx_clr_stats_input *req0 = NULL;
+	struct hwrm_stat_ctx_free_input *req;
 	int i;
 
 	if (!bp->bnapi)
@@ -6781,53 +6653,60 @@ static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp)
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req0, HWRM_STAT_CTX_CLR_STATS, -1, -1);
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_STAT_CTX_FREE, -1, -1);
-
-	mutex_lock(&bp->hwrm_cmd_lock);
+	if (hwrm_req_init(bp, req, HWRM_STAT_CTX_FREE))
+		return;
+	if (BNXT_FW_MAJ(bp) <= 20) {
+		if (hwrm_req_init(bp, req0, HWRM_STAT_CTX_CLR_STATS)) {
+			hwrm_req_drop(bp, req);
+			return;
+		}
+		hwrm_req_hold(bp, req0);
+	}
+	hwrm_req_hold(bp, req);
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 
 		if (cpr->hw_stats_ctx_id != INVALID_STATS_CTX_ID) {
-			req.stat_ctx_id = cpu_to_le32(cpr->hw_stats_ctx_id);
-			if (BNXT_FW_MAJ(bp) <= 20) {
-				req0.stat_ctx_id = req.stat_ctx_id;
-				_hwrm_send_message(bp, &req0, sizeof(req0),
-						   HWRM_CMD_TIMEOUT);
+			req->stat_ctx_id = cpu_to_le32(cpr->hw_stats_ctx_id);
+			if (req0) {
+				req0->stat_ctx_id = req->stat_ctx_id;
+				hwrm_req_send(bp, req0);
 			}
-			_hwrm_send_message(bp, &req, sizeof(req),
-					   HWRM_CMD_TIMEOUT);
+			hwrm_req_send(bp, req);
 
 			cpr->hw_stats_ctx_id = INVALID_STATS_CTX_ID;
 		}
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
+	if (req0)
+		hwrm_req_drop(bp, req0);
 }
 
 static int bnxt_hwrm_stat_ctx_alloc(struct bnxt *bp)
 {
-	int rc = 0, i;
-	struct hwrm_stat_ctx_alloc_input req = {0};
-	struct hwrm_stat_ctx_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_stat_ctx_alloc_output *resp;
+	struct hwrm_stat_ctx_alloc_input *req;
+	int rc, i;
 
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_STAT_CTX_ALLOC, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_STAT_CTX_ALLOC);
+	if (rc)
+		return rc;
 
-	req.stats_dma_length = cpu_to_le16(bp->hw_ring_stats_size);
-	req.update_period_ms = cpu_to_le32(bp->stats_coal_ticks / 1000);
+	req->stats_dma_length = cpu_to_le16(bp->hw_ring_stats_size);
+	req->update_period_ms = cpu_to_le32(bp->stats_coal_ticks / 1000);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
+	resp = hwrm_req_hold(bp, req);
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 
-		req.stats_dma_addr = cpu_to_le64(cpr->stats.hw_stats_map);
+		req->stats_dma_addr = cpu_to_le64(cpr->stats.hw_stats_map);
 
-		rc = _hwrm_send_message(bp, &req, sizeof(req),
-					HWRM_CMD_TIMEOUT);
+		rc = hwrm_req_send(bp, req);
 		if (rc)
 			break;
 
@@ -6835,22 +6714,25 @@ static int bnxt_hwrm_stat_ctx_alloc(struct bnxt *bp)
 
 		bp->grp_info[i].fw_stats_ctx = cpr->hw_stats_ctx_id;
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 {
-	struct hwrm_func_qcfg_input req = {0};
-	struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_func_qcfg_output *resp;
+	struct hwrm_func_qcfg_input *req;
 	u32 min_db_offset = 0;
 	u16 flags;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1);
-	req.fid = cpu_to_le16(0xffff);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_QCFG);
+	if (rc)
+		return rc;
+
+	req->fid = cpu_to_le16(0xffff);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc)
 		goto func_qcfg_exit;
 
@@ -6910,7 +6792,7 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 		bp->db_size = pci_resource_len(bp->pdev, 2);
 
 func_qcfg_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -6949,17 +6831,19 @@ static void bnxt_init_ctx_initializer(struct bnxt_ctx_mem_info *ctx,
 
 static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
 {
-	struct hwrm_func_backing_store_qcaps_input req = {0};
-	struct hwrm_func_backing_store_qcaps_output *resp =
-		bp->hwrm_cmd_resp_addr;
+	struct hwrm_func_backing_store_qcaps_output *resp;
+	struct hwrm_func_backing_store_qcaps_input *req;
 	int rc;
 
 	if (bp->hwrm_spec_code < 0x10902 || BNXT_VF(bp) || bp->ctx)
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_BACKING_STORE_QCAPS, -1, -1);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_BACKING_STORE_QCAPS);
+	if (rc)
+		return rc;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
 	if (!rc) {
 		struct bnxt_ctx_pg_info *ctx_pg;
 		struct bnxt_ctx_mem_info *ctx;
@@ -7024,7 +6908,7 @@ static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
 		rc = 0;
 	}
 ctx_err:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -7055,15 +6939,17 @@ static void bnxt_hwrm_set_pg_attr(struct bnxt_ring_mem_info *rmem, u8 *pg_attr,
 
 static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 {
-	struct hwrm_func_backing_store_cfg_input req = {0};
+	struct hwrm_func_backing_store_cfg_input *req;
 	struct bnxt_ctx_mem_info *ctx = bp->ctx;
 	struct bnxt_ctx_pg_info *ctx_pg;
-	u32 req_len = sizeof(req);
+	void **__req = (void **)&req;
+	u32 req_len = sizeof(*req);
 	__le32 *num_entries;
 	__le64 *pg_dir;
 	u32 flags = 0;
 	u8 *pg_attr;
 	u32 ena;
+	int rc;
 	int i;
 
 	if (!ctx)
@@ -7071,90 +6957,93 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 
 	if (req_len > bp->hwrm_max_ext_req_len)
 		req_len = BNXT_BACKING_STORE_CFG_LEGACY_LEN;
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_BACKING_STORE_CFG, -1, -1);
-	req.enables = cpu_to_le32(enables);
+	rc = __hwrm_req_init(bp, __req, HWRM_FUNC_BACKING_STORE_CFG, req_len);
+	if (rc)
+		return rc;
 
+	req->enables = cpu_to_le32(enables);
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP) {
 		ctx_pg = &ctx->qp_mem;
-		req.qp_num_entries = cpu_to_le32(ctx_pg->entries);
-		req.qp_num_qp1_entries = cpu_to_le16(ctx->qp_min_qp1_entries);
-		req.qp_num_l2_entries = cpu_to_le16(ctx->qp_max_l2_entries);
-		req.qp_entry_size = cpu_to_le16(ctx->qp_entry_size);
+		req->qp_num_entries = cpu_to_le32(ctx_pg->entries);
+		req->qp_num_qp1_entries = cpu_to_le16(ctx->qp_min_qp1_entries);
+		req->qp_num_l2_entries = cpu_to_le16(ctx->qp_max_l2_entries);
+		req->qp_entry_size = cpu_to_le16(ctx->qp_entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
-				      &req.qpc_pg_size_qpc_lvl,
-				      &req.qpc_page_dir);
+				      &req->qpc_pg_size_qpc_lvl,
+				      &req->qpc_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_SRQ) {
 		ctx_pg = &ctx->srq_mem;
-		req.srq_num_entries = cpu_to_le32(ctx_pg->entries);
-		req.srq_num_l2_entries = cpu_to_le16(ctx->srq_max_l2_entries);
-		req.srq_entry_size = cpu_to_le16(ctx->srq_entry_size);
+		req->srq_num_entries = cpu_to_le32(ctx_pg->entries);
+		req->srq_num_l2_entries = cpu_to_le16(ctx->srq_max_l2_entries);
+		req->srq_entry_size = cpu_to_le16(ctx->srq_entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
-				      &req.srq_pg_size_srq_lvl,
-				      &req.srq_page_dir);
+				      &req->srq_pg_size_srq_lvl,
+				      &req->srq_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_CQ) {
 		ctx_pg = &ctx->cq_mem;
-		req.cq_num_entries = cpu_to_le32(ctx_pg->entries);
-		req.cq_num_l2_entries = cpu_to_le16(ctx->cq_max_l2_entries);
-		req.cq_entry_size = cpu_to_le16(ctx->cq_entry_size);
-		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem, &req.cq_pg_size_cq_lvl,
-				      &req.cq_page_dir);
+		req->cq_num_entries = cpu_to_le32(ctx_pg->entries);
+		req->cq_num_l2_entries = cpu_to_le16(ctx->cq_max_l2_entries);
+		req->cq_entry_size = cpu_to_le16(ctx->cq_entry_size);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req->cq_pg_size_cq_lvl,
+				      &req->cq_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_VNIC) {
 		ctx_pg = &ctx->vnic_mem;
-		req.vnic_num_vnic_entries =
+		req->vnic_num_vnic_entries =
 			cpu_to_le16(ctx->vnic_max_vnic_entries);
-		req.vnic_num_ring_table_entries =
+		req->vnic_num_ring_table_entries =
 			cpu_to_le16(ctx->vnic_max_ring_table_entries);
-		req.vnic_entry_size = cpu_to_le16(ctx->vnic_entry_size);
+		req->vnic_entry_size = cpu_to_le16(ctx->vnic_entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
-				      &req.vnic_pg_size_vnic_lvl,
-				      &req.vnic_page_dir);
+				      &req->vnic_pg_size_vnic_lvl,
+				      &req->vnic_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_STAT) {
 		ctx_pg = &ctx->stat_mem;
-		req.stat_num_entries = cpu_to_le32(ctx->stat_max_entries);
-		req.stat_entry_size = cpu_to_le16(ctx->stat_entry_size);
+		req->stat_num_entries = cpu_to_le32(ctx->stat_max_entries);
+		req->stat_entry_size = cpu_to_le16(ctx->stat_entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
-				      &req.stat_pg_size_stat_lvl,
-				      &req.stat_page_dir);
+				      &req->stat_pg_size_stat_lvl,
+				      &req->stat_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV) {
 		ctx_pg = &ctx->mrav_mem;
-		req.mrav_num_entries = cpu_to_le32(ctx_pg->entries);
+		req->mrav_num_entries = cpu_to_le32(ctx_pg->entries);
 		if (ctx->mrav_num_entries_units)
 			flags |=
 			FUNC_BACKING_STORE_CFG_REQ_FLAGS_MRAV_RESERVATION_SPLIT;
-		req.mrav_entry_size = cpu_to_le16(ctx->mrav_entry_size);
+		req->mrav_entry_size = cpu_to_le16(ctx->mrav_entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
-				      &req.mrav_pg_size_mrav_lvl,
-				      &req.mrav_page_dir);
+				      &req->mrav_pg_size_mrav_lvl,
+				      &req->mrav_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM) {
 		ctx_pg = &ctx->tim_mem;
-		req.tim_num_entries = cpu_to_le32(ctx_pg->entries);
-		req.tim_entry_size = cpu_to_le16(ctx->tim_entry_size);
+		req->tim_num_entries = cpu_to_le32(ctx_pg->entries);
+		req->tim_entry_size = cpu_to_le16(ctx->tim_entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
-				      &req.tim_pg_size_tim_lvl,
-				      &req.tim_page_dir);
+				      &req->tim_pg_size_tim_lvl,
+				      &req->tim_page_dir);
 	}
-	for (i = 0, num_entries = &req.tqm_sp_num_entries,
-	     pg_attr = &req.tqm_sp_pg_size_tqm_sp_lvl,
-	     pg_dir = &req.tqm_sp_page_dir,
+	for (i = 0, num_entries = &req->tqm_sp_num_entries,
+	     pg_attr = &req->tqm_sp_pg_size_tqm_sp_lvl,
+	     pg_dir = &req->tqm_sp_page_dir,
 	     ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP;
 	     i < BNXT_MAX_TQM_RINGS;
 	     i++, num_entries++, pg_attr++, pg_dir++, ena <<= 1) {
 		if (!(enables & ena))
 			continue;
 
-		req.tqm_entry_size = cpu_to_le16(ctx->tqm_entry_size);
+		req->tqm_entry_size = cpu_to_le16(ctx->tqm_entry_size);
 		ctx_pg = ctx->tqm_mem[i];
 		*num_entries = cpu_to_le32(ctx_pg->entries);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem, pg_attr, pg_dir);
 	}
-	req.flags = cpu_to_le32(flags);
-	return hwrm_send_message(bp, &req, req_len, HWRM_CMD_TIMEOUT);
+	req->flags = cpu_to_le32(flags);
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_alloc_ctx_mem_blk(struct bnxt *bp,
@@ -7434,17 +7323,18 @@ skip_rdma:
 
 int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 {
-	struct hwrm_func_resource_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_func_resource_qcaps_input req = {0};
+	struct hwrm_func_resource_qcaps_output *resp;
+	struct hwrm_func_resource_qcaps_input *req;
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_RESOURCE_QCAPS, -1, -1);
-	req.fid = cpu_to_le16(0xffff);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_RESOURCE_QCAPS);
+	if (rc)
+		return rc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message_silent(bp, &req, sizeof(req),
-				       HWRM_CMD_TIMEOUT);
+	req->fid = cpu_to_le16(0xffff);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
 	if (rc)
 		goto hwrm_func_resc_qcaps_exit;
 
@@ -7485,15 +7375,14 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 			pf->vf_resv_strategy = BNXT_VF_RESV_STRATEGY_MAXIMAL;
 	}
 hwrm_func_resc_qcaps_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
-/* bp->hwrm_cmd_lock already held. */
 static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp)
 {
-	struct hwrm_port_mac_ptp_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_port_mac_ptp_qcfg_input req = {0};
+	struct hwrm_port_mac_ptp_qcfg_output *resp;
+	struct hwrm_port_mac_ptp_qcfg_input *req;
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 	u8 flags;
 	int rc;
@@ -7503,21 +7392,27 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp)
 		goto no_ptp;
 	}
 
-	req.port_id = cpu_to_le16(bp->pf.port_id);
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_MAC_PTP_QCFG, -1, -1);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_MAC_PTP_QCFG);
 	if (rc)
 		goto no_ptp;
 
+	req->port_id = cpu_to_le16(bp->pf.port_id);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
+	if (rc)
+		goto exit;
+
 	flags = resp->flags;
 	if (!(flags & PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS)) {
 		rc = -ENODEV;
-		goto no_ptp;
+		goto exit;
 	}
 	if (!ptp) {
 		ptp = kzalloc(sizeof(*ptp), GFP_KERNEL);
-		if (!ptp)
-			return -ENOMEM;
+		if (!ptp) {
+			rc = -ENOMEM;
+			goto exit;
+		}
 		ptp->bp = bp;
 		bp->ptp_cfg = ptp;
 	}
@@ -7529,11 +7424,18 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp)
 		ptp->refclk_regs[1] = BNXT_TS_REG_TIMESYNC_TS0_UPPER;
 	} else {
 		rc = -ENODEV;
-		goto no_ptp;
+		goto exit;
 	}
-	return 0;
+	rc = bnxt_ptp_init(bp);
+	if (rc)
+		netdev_warn(bp->dev, "PTP initialization failed.\n");
+exit:
+	hwrm_req_drop(bp, req);
+	if (!rc)
+		return 0;
 
 no_ptp:
+	bnxt_ptp_clear(bp);
 	kfree(ptp);
 	bp->ptp_cfg = NULL;
 	return rc;
@@ -7541,17 +7443,19 @@ no_ptp:
 
 static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 {
-	int rc = 0;
-	struct hwrm_func_qcaps_input req = {0};
-	struct hwrm_func_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_func_qcaps_output *resp;
+	struct hwrm_func_qcaps_input *req;
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 	u32 flags, flags_ext;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCAPS, -1, -1);
-	req.fid = cpu_to_le16(0xffff);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_QCAPS);
+	if (rc)
+		return rc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req->fid = cpu_to_le16(0xffff);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc)
 		goto hwrm_func_qcaps_exit;
 
@@ -7576,6 +7480,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 	flags_ext = le32_to_cpu(resp->flags_ext);
 	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_EXT_HW_STATS_SUPPORTED)
 		bp->fw_cap |= BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED;
+	if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PPS_SUPPORTED))
+		bp->fw_cap |= BNXT_FW_CAP_PTP_PPS;
 
 	bp->tx_push_thresh = 0;
 	if ((flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED) &&
@@ -7613,6 +7519,7 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		if (flags & FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED) {
 			__bnxt_hwrm_ptp_qcfg(bp);
 		} else {
+			bnxt_ptp_clear(bp);
 			kfree(bp->ptp_cfg);
 			bp->ptp_cfg = NULL;
 		}
@@ -7626,7 +7533,7 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 	}
 
 hwrm_func_qcaps_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -7657,19 +7564,20 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 
 static int bnxt_hwrm_cfa_adv_flow_mgnt_qcaps(struct bnxt *bp)
 {
-	struct hwrm_cfa_adv_flow_mgnt_qcaps_input req = {0};
 	struct hwrm_cfa_adv_flow_mgnt_qcaps_output *resp;
-	int rc = 0;
+	struct hwrm_cfa_adv_flow_mgnt_qcaps_input *req;
 	u32 flags;
+	int rc;
 
 	if (!(bp->fw_cap & BNXT_FW_CAP_CFA_ADV_FLOW))
 		return 0;
 
-	resp = bp->hwrm_cmd_resp_addr;
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_ADV_FLOW_MGNT_QCAPS, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_ADV_FLOW_MGNT_QCAPS);
+	if (rc)
+		return rc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc)
 		goto hwrm_cfa_adv_qcaps_exit;
 
@@ -7679,7 +7587,7 @@ static int bnxt_hwrm_cfa_adv_flow_mgnt_qcaps(struct bnxt *bp)
 		bp->fw_cap |= BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2;
 
 hwrm_cfa_adv_qcaps_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -7822,17 +7730,20 @@ static int bnxt_map_fw_health_regs(struct bnxt *bp)
 
 static int bnxt_hwrm_error_recovery_qcfg(struct bnxt *bp)
 {
-	struct hwrm_error_recovery_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
 	struct bnxt_fw_health *fw_health = bp->fw_health;
-	struct hwrm_error_recovery_qcfg_input req = {0};
+	struct hwrm_error_recovery_qcfg_output *resp;
+	struct hwrm_error_recovery_qcfg_input *req;
 	int rc, i;
 
 	if (!(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY))
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_ERROR_RECOVERY_QCFG, -1, -1);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_ERROR_RECOVERY_QCFG);
+	if (rc)
+		return rc;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc)
 		goto err_recovery_out;
 	fw_health->flags = le32_to_cpu(resp->flags);
@@ -7874,7 +7785,7 @@ static int bnxt_hwrm_error_recovery_qcfg(struct bnxt *bp)
 			resp->delay_after_reset[i];
 	}
 err_recovery_out:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	if (!rc)
 		rc = bnxt_map_fw_health_regs(bp);
 	if (rc)
@@ -7884,12 +7795,16 @@ err_recovery_out:
 
 static int bnxt_hwrm_func_reset(struct bnxt *bp)
 {
-	struct hwrm_func_reset_input req = {0};
+	struct hwrm_func_reset_input *req;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_RESET, -1, -1);
-	req.enables = 0;
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_RESET);
+	if (rc)
+		return rc;
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_RESET_TIMEOUT);
+	req->enables = 0;
+	hwrm_req_timeout(bp, req, HWRM_RESET_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
 static void bnxt_nvm_cfg_ver_get(struct bnxt *bp)
@@ -7904,16 +7819,18 @@ static void bnxt_nvm_cfg_ver_get(struct bnxt *bp)
 
 static int bnxt_hwrm_queue_qportcfg(struct bnxt *bp)
 {
-	int rc = 0;
-	struct hwrm_queue_qportcfg_input req = {0};
-	struct hwrm_queue_qportcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_queue_qportcfg_output *resp;
+	struct hwrm_queue_qportcfg_input *req;
 	u8 i, j, *qptr;
 	bool no_rdma;
+	int rc = 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_QPORTCFG, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_QUEUE_QPORTCFG);
+	if (rc)
+		return rc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc)
 		goto qportcfg_exit;
 
@@ -7947,35 +7864,48 @@ static int bnxt_hwrm_queue_qportcfg(struct bnxt *bp)
 		bp->max_lltc = bp->max_tc;
 
 qportcfg_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
-static int __bnxt_hwrm_ver_get(struct bnxt *bp, bool silent)
+static int bnxt_hwrm_poll(struct bnxt *bp)
 {
-	struct hwrm_ver_get_input req = {0};
+	struct hwrm_ver_get_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VER_GET, -1, -1);
-	req.hwrm_intf_maj = HWRM_VERSION_MAJOR;
-	req.hwrm_intf_min = HWRM_VERSION_MINOR;
-	req.hwrm_intf_upd = HWRM_VERSION_UPDATE;
+	rc = hwrm_req_init(bp, req, HWRM_VER_GET);
+	if (rc)
+		return rc;
+
+	req->hwrm_intf_maj = HWRM_VERSION_MAJOR;
+	req->hwrm_intf_min = HWRM_VERSION_MINOR;
+	req->hwrm_intf_upd = HWRM_VERSION_UPDATE;
 
-	rc = bnxt_hwrm_do_send_msg(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT,
-				   silent);
+	hwrm_req_flags(bp, req, BNXT_HWRM_CTX_SILENT | BNXT_HWRM_FULL_WAIT);
+	rc = hwrm_req_send(bp, req);
 	return rc;
 }
 
 static int bnxt_hwrm_ver_get(struct bnxt *bp)
 {
-	struct hwrm_ver_get_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_ver_get_output *resp;
+	struct hwrm_ver_get_input *req;
 	u16 fw_maj, fw_min, fw_bld, fw_rsv;
 	u32 dev_caps_cfg, hwrm_ver;
 	int rc, len;
 
+	rc = hwrm_req_init(bp, req, HWRM_VER_GET);
+	if (rc)
+		return rc;
+
+	hwrm_req_flags(bp, req, BNXT_HWRM_FULL_WAIT);
 	bp->hwrm_max_req_len = HWRM_MAX_REQ_LEN;
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = __bnxt_hwrm_ver_get(bp, false);
+	req->hwrm_intf_maj = HWRM_VERSION_MAJOR;
+	req->hwrm_intf_min = HWRM_VERSION_MINOR;
+	req->hwrm_intf_upd = HWRM_VERSION_UPDATE;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc)
 		goto hwrm_ver_get_exit;
 
@@ -8067,29 +7997,33 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 		bp->fw_cap |= BNXT_FW_CAP_CFA_ADV_FLOW;
 
 hwrm_ver_get_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 int bnxt_hwrm_fw_set_time(struct bnxt *bp)
 {
-	struct hwrm_fw_set_time_input req = {0};
+	struct hwrm_fw_set_time_input *req;
 	struct tm tm;
 	time64_t now = ktime_get_real_seconds();
+	int rc;
 
 	if ((BNXT_VF(bp) && bp->hwrm_spec_code < 0x10901) ||
 	    bp->hwrm_spec_code < 0x10400)
 		return -EOPNOTSUPP;
 
 	time64_to_tm(now, 0, &tm);
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FW_SET_TIME, -1, -1);
-	req.year = cpu_to_le16(1900 + tm.tm_year);
-	req.month = 1 + tm.tm_mon;
-	req.day = tm.tm_mday;
-	req.hour = tm.tm_hour;
-	req.minute = tm.tm_min;
-	req.second = tm.tm_sec;
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_FW_SET_TIME);
+	if (rc)
+		return rc;
+
+	req->year = cpu_to_le16(1900 + tm.tm_year);
+	req->month = 1 + tm.tm_mon;
+	req->day = tm.tm_mday;
+	req->hour = tm.tm_hour;
+	req->minute = tm.tm_min;
+	req->second = tm.tm_sec;
+	return hwrm_req_send(bp, req);
 }
 
 static void bnxt_add_one_ctr(u64 hw, u64 *sw, u64 mask)
@@ -8177,8 +8111,9 @@ static void bnxt_accumulate_all_stats(struct bnxt *bp)
 
 static int bnxt_hwrm_port_qstats(struct bnxt *bp, u8 flags)
 {
+	struct hwrm_port_qstats_input *req;
 	struct bnxt_pf_info *pf = &bp->pf;
-	struct hwrm_port_qstats_input req = {0};
+	int rc;
 
 	if (!(bp->flags & BNXT_FLAG_PORT_STATS))
 		return 0;
@@ -8186,20 +8121,24 @@ static int bnxt_hwrm_port_qstats(struct bnxt *bp, u8 flags)
 	if (flags && !(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED))
 		return -EOPNOTSUPP;
 
-	req.flags = flags;
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_QSTATS, -1, -1);
-	req.port_id = cpu_to_le16(pf->port_id);
-	req.tx_stat_host_addr = cpu_to_le64(bp->port_stats.hw_stats_map +
+	rc = hwrm_req_init(bp, req, HWRM_PORT_QSTATS);
+	if (rc)
+		return rc;
+
+	req->flags = flags;
+	req->port_id = cpu_to_le16(pf->port_id);
+	req->tx_stat_host_addr = cpu_to_le64(bp->port_stats.hw_stats_map +
 					    BNXT_TX_PORT_STATS_BYTE_OFFSET);
-	req.rx_stat_host_addr = cpu_to_le64(bp->port_stats.hw_stats_map);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req->rx_stat_host_addr = cpu_to_le64(bp->port_stats.hw_stats_map);
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp, u8 flags)
 {
-	struct hwrm_port_qstats_ext_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_queue_pri2cos_qcfg_input req2 = {0};
-	struct hwrm_port_qstats_ext_input req = {0};
+	struct hwrm_queue_pri2cos_qcfg_output *resp_qc;
+	struct hwrm_queue_pri2cos_qcfg_input *req_qc;
+	struct hwrm_port_qstats_ext_output *resp_qs;
+	struct hwrm_port_qstats_ext_input *req_qs;
 	struct bnxt_pf_info *pf = &bp->pf;
 	u32 tx_stat_size;
 	int rc;
@@ -8210,46 +8149,53 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp, u8 flags)
 	if (flags && !(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED))
 		return -EOPNOTSUPP;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_QSTATS_EXT, -1, -1);
-	req.flags = flags;
-	req.port_id = cpu_to_le16(pf->port_id);
-	req.rx_stat_size = cpu_to_le16(sizeof(struct rx_port_stats_ext));
-	req.rx_stat_host_addr = cpu_to_le64(bp->rx_port_stats_ext.hw_stats_map);
+	rc = hwrm_req_init(bp, req_qs, HWRM_PORT_QSTATS_EXT);
+	if (rc)
+		return rc;
+
+	req_qs->flags = flags;
+	req_qs->port_id = cpu_to_le16(pf->port_id);
+	req_qs->rx_stat_size = cpu_to_le16(sizeof(struct rx_port_stats_ext));
+	req_qs->rx_stat_host_addr = cpu_to_le64(bp->rx_port_stats_ext.hw_stats_map);
 	tx_stat_size = bp->tx_port_stats_ext.hw_stats ?
 		       sizeof(struct tx_port_stats_ext) : 0;
-	req.tx_stat_size = cpu_to_le16(tx_stat_size);
-	req.tx_stat_host_addr = cpu_to_le64(bp->tx_port_stats_ext.hw_stats_map);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req_qs->tx_stat_size = cpu_to_le16(tx_stat_size);
+	req_qs->tx_stat_host_addr = cpu_to_le64(bp->tx_port_stats_ext.hw_stats_map);
+	resp_qs = hwrm_req_hold(bp, req_qs);
+	rc = hwrm_req_send(bp, req_qs);
 	if (!rc) {
-		bp->fw_rx_stats_ext_size = le16_to_cpu(resp->rx_stat_size) / 8;
+		bp->fw_rx_stats_ext_size =
+			le16_to_cpu(resp_qs->rx_stat_size) / 8;
 		bp->fw_tx_stats_ext_size = tx_stat_size ?
-			le16_to_cpu(resp->tx_stat_size) / 8 : 0;
+			le16_to_cpu(resp_qs->tx_stat_size) / 8 : 0;
 	} else {
 		bp->fw_rx_stats_ext_size = 0;
 		bp->fw_tx_stats_ext_size = 0;
 	}
+	hwrm_req_drop(bp, req_qs);
+
 	if (flags)
-		goto qstats_done;
+		return rc;
 
 	if (bp->fw_tx_stats_ext_size <=
 	    offsetof(struct tx_port_stats_ext, pfc_pri0_tx_duration_us) / 8) {
-		mutex_unlock(&bp->hwrm_cmd_lock);
 		bp->pri2cos_valid = 0;
 		return rc;
 	}
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req2, HWRM_QUEUE_PRI2COS_QCFG, -1, -1);
-	req2.flags = cpu_to_le32(QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN);
+	rc = hwrm_req_init(bp, req_qc, HWRM_QUEUE_PRI2COS_QCFG);
+	if (rc)
+		return rc;
+
+	req_qc->flags = cpu_to_le32(QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN);
 
-	rc = _hwrm_send_message(bp, &req2, sizeof(req2), HWRM_CMD_TIMEOUT);
+	resp_qc = hwrm_req_hold(bp, req_qc);
+	rc = hwrm_req_send(bp, req_qc);
 	if (!rc) {
-		struct hwrm_queue_pri2cos_qcfg_output *resp2;
 		u8 *pri2cos;
 		int i, j;
 
-		resp2 = bp->hwrm_cmd_resp_addr;
-		pri2cos = &resp2->pri0_cos_queue_id;
+		pri2cos = &resp_qc->pri0_cos_queue_id;
 		for (i = 0; i < 8; i++) {
 			u8 queue_id = pri2cos[i];
 			u8 queue_idx;
@@ -8258,17 +8204,18 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp, u8 flags)
 			queue_idx = queue_id % 10;
 			if (queue_idx > BNXT_MAX_QUEUE) {
 				bp->pri2cos_valid = false;
-				goto qstats_done;
+				hwrm_req_drop(bp, req_qc);
+				return rc;
 			}
 			for (j = 0; j < bp->max_q; j++) {
 				if (bp->q_ids[j] == queue_id)
 					bp->pri2cos_idx[i] = queue_idx;
 			}
 		}
-		bp->pri2cos_valid = 1;
+		bp->pri2cos_valid = true;
 	}
-qstats_done:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req_qc);
+
 	return rc;
 }
 
@@ -8343,35 +8290,46 @@ static void bnxt_hwrm_resource_free(struct bnxt *bp, bool close_path,
 
 static int bnxt_hwrm_set_br_mode(struct bnxt *bp, u16 br_mode)
 {
-	struct hwrm_func_cfg_input req = {0};
+	struct hwrm_func_cfg_input *req;
+	u8 evb_mode;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
-	req.fid = cpu_to_le16(0xffff);
-	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_EVB_MODE);
 	if (br_mode == BRIDGE_MODE_VEB)
-		req.evb_mode = FUNC_CFG_REQ_EVB_MODE_VEB;
+		evb_mode = FUNC_CFG_REQ_EVB_MODE_VEB;
 	else if (br_mode == BRIDGE_MODE_VEPA)
-		req.evb_mode = FUNC_CFG_REQ_EVB_MODE_VEPA;
+		evb_mode = FUNC_CFG_REQ_EVB_MODE_VEPA;
 	else
 		return -EINVAL;
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_CFG);
+	if (rc)
+		return rc;
+
+	req->fid = cpu_to_le16(0xffff);
+	req->enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_EVB_MODE);
+	req->evb_mode = evb_mode;
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_hwrm_set_cache_line_size(struct bnxt *bp, int size)
 {
-	struct hwrm_func_cfg_input req = {0};
+	struct hwrm_func_cfg_input *req;
+	int rc;
 
 	if (BNXT_VF(bp) || bp->hwrm_spec_code < 0x10803)
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
-	req.fid = cpu_to_le16(0xffff);
-	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_CACHE_LINESIZE);
-	req.options = FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64;
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_CFG);
+	if (rc)
+		return rc;
+
+	req->fid = cpu_to_le16(0xffff);
+	req->enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_CACHE_LINESIZE);
+	req->options = FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64;
 	if (size == 128)
-		req.options = FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128;
+		req->options = FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128;
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
 static int __bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
@@ -9319,18 +9277,20 @@ static bool bnxt_phy_qcaps_no_speed(struct hwrm_port_phy_qcaps_output *resp)
 
 static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 {
-	int rc = 0;
-	struct hwrm_port_phy_qcaps_input req = {0};
-	struct hwrm_port_phy_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
 	struct bnxt_link_info *link_info = &bp->link_info;
+	struct hwrm_port_phy_qcaps_output *resp;
+	struct hwrm_port_phy_qcaps_input *req;
+	int rc = 0;
 
 	if (bp->hwrm_spec_code < 0x10201)
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_QCAPS, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_QCAPS);
+	if (rc)
+		return rc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc)
 		goto hwrm_phy_qcaps_exit;
 
@@ -9368,7 +9328,7 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 	bp->port_count = resp->port_cnt;
 
 hwrm_phy_qcaps_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -9381,19 +9341,21 @@ static bool bnxt_support_dropped(u16 advertising, u16 supported)
 
 int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
 {
-	int rc = 0;
 	struct bnxt_link_info *link_info = &bp->link_info;
-	struct hwrm_port_phy_qcfg_input req = {0};
-	struct hwrm_port_phy_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_port_phy_qcfg_output *resp;
+	struct hwrm_port_phy_qcfg_input *req;
 	u8 link_up = link_info->link_up;
 	bool support_changed = false;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_QCFG, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_QCFG);
+	if (rc)
+		return rc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc) {
-		mutex_unlock(&bp->hwrm_cmd_lock);
+		hwrm_req_drop(bp, req);
 		return rc;
 	}
 
@@ -9488,7 +9450,7 @@ int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
 		/* alwasy link down if not require to update link state */
 		link_info->link_up = 0;
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 
 	if (!BNXT_PHY_CFG_ABLE(bp))
 		return 0;
@@ -9598,18 +9560,20 @@ static void bnxt_hwrm_set_link_common(struct bnxt *bp, struct hwrm_port_phy_cfg_
 
 int bnxt_hwrm_set_pause(struct bnxt *bp)
 {
-	struct hwrm_port_phy_cfg_input req = {0};
+	struct hwrm_port_phy_cfg_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_CFG, -1, -1);
-	bnxt_hwrm_set_pause_common(bp, &req);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_CFG);
+	if (rc)
+		return rc;
+
+	bnxt_hwrm_set_pause_common(bp, req);
 
 	if ((bp->link_info.autoneg & BNXT_AUTONEG_FLOW_CTRL) ||
 	    bp->link_info.force_link_chng)
-		bnxt_hwrm_set_link_common(bp, &req);
+		bnxt_hwrm_set_link_common(bp, req);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_send(bp, req);
 	if (!rc && !(bp->link_info.autoneg & BNXT_AUTONEG_FLOW_CTRL)) {
 		/* since changing of pause setting doesn't trigger any link
 		 * change event, the driver needs to update the current pause
@@ -9622,7 +9586,6 @@ int bnxt_hwrm_set_pause(struct bnxt *bp)
 			bnxt_report_link(bp);
 	}
 	bp->link_info.force_link_chng = false;
-	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
 
@@ -9651,22 +9614,27 @@ static void bnxt_hwrm_set_eee(struct bnxt *bp,
 
 int bnxt_hwrm_set_link_setting(struct bnxt *bp, bool set_pause, bool set_eee)
 {
-	struct hwrm_port_phy_cfg_input req = {0};
+	struct hwrm_port_phy_cfg_input *req;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_CFG);
+	if (rc)
+		return rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_CFG, -1, -1);
 	if (set_pause)
-		bnxt_hwrm_set_pause_common(bp, &req);
+		bnxt_hwrm_set_pause_common(bp, req);
 
-	bnxt_hwrm_set_link_common(bp, &req);
+	bnxt_hwrm_set_link_common(bp, req);
 
 	if (set_eee)
-		bnxt_hwrm_set_eee(bp, &req);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		bnxt_hwrm_set_eee(bp, req);
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_hwrm_shutdown_link(struct bnxt *bp)
 {
-	struct hwrm_port_phy_cfg_input req = {0};
+	struct hwrm_port_phy_cfg_input *req;
+	int rc;
 
 	if (!BNXT_SINGLE_PF(bp))
 		return 0;
@@ -9675,9 +9643,12 @@ static int bnxt_hwrm_shutdown_link(struct bnxt *bp)
 	    !(bp->phy_flags & BNXT_PHY_FL_FW_MANAGED_LKDN))
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_CFG, -1, -1);
-	req.flags = cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DWN);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_CFG);
+	if (rc)
+		return rc;
+
+	req->flags = cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DWN);
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_fw_init_one(struct bnxt *bp);
@@ -9703,16 +9674,14 @@ static int bnxt_try_recover_fw(struct bnxt *bp)
 		int retry = 0, rc;
 		u32 sts;
 
-		mutex_lock(&bp->hwrm_cmd_lock);
 		do {
 			sts = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG);
-			rc = __bnxt_hwrm_ver_get(bp, true);
+			rc = bnxt_hwrm_poll(bp);
 			if (!BNXT_FW_IS_BOOTING(sts) &&
 			    !BNXT_FW_IS_RECOVERING(sts))
 				break;
 			retry++;
 		} while (rc == -EBUSY && retry < BNXT_FW_RETRY);
-		mutex_unlock(&bp->hwrm_cmd_lock);
 
 		if (!BNXT_FW_IS_HEALTHY(sts)) {
 			netdev_err(bp->dev,
@@ -9732,8 +9701,8 @@ static int bnxt_try_recover_fw(struct bnxt *bp)
 
 static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 {
-	struct hwrm_func_drv_if_change_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_func_drv_if_change_input req = {0};
+	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;
 	int rc, retry = 0;
@@ -9742,29 +9711,34 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 	if (!(bp->fw_cap & BNXT_FW_CAP_IF_CHANGE))
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_IF_CHANGE, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_DRV_IF_CHANGE);
+	if (rc)
+		return rc;
+
 	if (up)
-		req.flags = cpu_to_le32(FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP);
-	mutex_lock(&bp->hwrm_cmd_lock);
+		req->flags = cpu_to_le32(FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP);
+	resp = hwrm_req_hold(bp, req);
+
+	hwrm_req_flags(bp, req, BNXT_HWRM_FULL_WAIT);
 	while (retry < BNXT_FW_IF_RETRY) {
-		rc = _hwrm_send_message(bp, &req, sizeof(req),
-					HWRM_CMD_TIMEOUT);
+		rc = hwrm_req_send(bp, req);
 		if (rc != -EAGAIN)
 			break;
 
 		msleep(50);
 		retry++;
 	}
-	if (!rc)
-		flags = le32_to_cpu(resp->flags);
-	mutex_unlock(&bp->hwrm_cmd_lock);
 
-	if (rc == -EAGAIN)
+	if (rc == -EAGAIN) {
+		hwrm_req_drop(bp, req);
 		return rc;
-	if (rc && up) {
+	} else if (!rc) {
+		flags = le32_to_cpu(resp->flags);
+	} else if (up) {
 		rc = bnxt_try_recover_fw(bp);
 		fw_reset = true;
 	}
+	hwrm_req_drop(bp, req);
 	if (rc)
 		return rc;
 
@@ -9833,8 +9807,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 
 static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp)
 {
-	struct hwrm_port_led_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_port_led_qcaps_input req = {0};
+	struct hwrm_port_led_qcaps_output *resp;
+	struct hwrm_port_led_qcaps_input *req;
 	struct bnxt_pf_info *pf = &bp->pf;
 	int rc;
 
@@ -9842,12 +9816,15 @@ static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp)
 	if (BNXT_VF(bp) || bp->hwrm_spec_code < 0x10601)
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_LED_QCAPS, -1, -1);
-	req.port_id = cpu_to_le16(pf->port_id);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_LED_QCAPS);
+	if (rc)
+		return rc;
+
+	req->port_id = cpu_to_le16(pf->port_id);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc) {
-		mutex_unlock(&bp->hwrm_cmd_lock);
+		hwrm_req_drop(bp, req);
 		return rc;
 	}
 	if (resp->num_leds > 0 && resp->num_leds < BNXT_MAX_LED) {
@@ -9867,52 +9844,64 @@ static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp)
 			}
 		}
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return 0;
 }
 
 int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp)
 {
-	struct hwrm_wol_filter_alloc_input req = {0};
-	struct hwrm_wol_filter_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_wol_filter_alloc_output *resp;
+	struct hwrm_wol_filter_alloc_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_ALLOC, -1, -1);
-	req.port_id = cpu_to_le16(bp->pf.port_id);
-	req.wol_type = WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT;
-	req.enables = cpu_to_le32(WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS);
-	memcpy(req.mac_address, bp->dev->dev_addr, ETH_ALEN);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_WOL_FILTER_ALLOC);
+	if (rc)
+		return rc;
+
+	req->port_id = cpu_to_le16(bp->pf.port_id);
+	req->wol_type = WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT;
+	req->enables = cpu_to_le32(WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS);
+	memcpy(req->mac_address, bp->dev->dev_addr, ETH_ALEN);
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc)
 		bp->wol_filter_id = resp->wol_filter_id;
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 int bnxt_hwrm_free_wol_fltr(struct bnxt *bp)
 {
-	struct hwrm_wol_filter_free_input req = {0};
+	struct hwrm_wol_filter_free_input *req;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_WOL_FILTER_FREE);
+	if (rc)
+		return rc;
+
+	req->port_id = cpu_to_le16(bp->pf.port_id);
+	req->enables = cpu_to_le32(WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID);
+	req->wol_filter_id = bp->wol_filter_id;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_FREE, -1, -1);
-	req.port_id = cpu_to_le16(bp->pf.port_id);
-	req.enables = cpu_to_le32(WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID);
-	req.wol_filter_id = bp->wol_filter_id;
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
 static u16 bnxt_hwrm_get_wol_fltrs(struct bnxt *bp, u16 handle)
 {
-	struct hwrm_wol_filter_qcfg_input req = {0};
-	struct hwrm_wol_filter_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_wol_filter_qcfg_output *resp;
+	struct hwrm_wol_filter_qcfg_input *req;
 	u16 next_handle = 0;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_QCFG, -1, -1);
-	req.port_id = cpu_to_le16(bp->pf.port_id);
-	req.handle = cpu_to_le16(handle);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_WOL_FILTER_QCFG);
+	if (rc)
+		return rc;
+
+	req->port_id = cpu_to_le16(bp->pf.port_id);
+	req->handle = cpu_to_le16(handle);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc) {
 		next_handle = le16_to_cpu(resp->next_handle);
 		if (next_handle != 0) {
@@ -9923,7 +9912,7 @@ static u16 bnxt_hwrm_get_wol_fltrs(struct bnxt *bp, u16 handle)
 			}
 		}
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return next_handle;
 }
 
@@ -9944,19 +9933,20 @@ static void bnxt_get_wol_settings(struct bnxt *bp)
 static ssize_t bnxt_show_temp(struct device *dev,
 			      struct device_attribute *devattr, char *buf)
 {
-	struct hwrm_temp_monitor_query_input req = {0};
 	struct hwrm_temp_monitor_query_output *resp;
+	struct hwrm_temp_monitor_query_input *req;
 	struct bnxt *bp = dev_get_drvdata(dev);
 	u32 len = 0;
 	int rc;
 
-	resp = bp->hwrm_cmd_resp_addr;
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_TEMP_MONITOR_QUERY);
+	if (rc)
+		return rc;
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc)
 		len = sprintf(buf, "%u\n", resp->temp * 1000); /* display millidegree */
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	if (rc)
 		return rc;
 	return len;
@@ -9979,12 +9969,13 @@ static void bnxt_hwmon_close(struct bnxt *bp)
 
 static void bnxt_hwmon_open(struct bnxt *bp)
 {
-	struct hwrm_temp_monitor_query_input req = {0};
+	struct hwrm_temp_monitor_query_input *req;
 	struct pci_dev *pdev = bp->pdev;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
-	rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_TEMP_MONITOR_QUERY);
+	if (!rc)
+		rc = hwrm_req_send_silent(bp, req);
 	if (rc == -EACCES || rc == -EOPNOTSUPP) {
 		bnxt_hwmon_close(bp);
 		return;
@@ -10209,7 +10200,9 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	bnxt_tx_enable(bp);
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 	/* Poll link status and check for SFP+ module status */
+	mutex_lock(&bp->link_lock);
 	bnxt_get_port_module_status(bp);
+	mutex_unlock(&bp->link_lock);
 
 	/* VF-reps may need to be re-opened after the PF is re-opened */
 	if (BNXT_PF(bp))
@@ -10316,15 +10309,9 @@ static int bnxt_open(struct net_device *dev)
 	if (rc)
 		return rc;
 
-	if (bnxt_ptp_init(bp)) {
-		netdev_warn(dev, "PTP initialization failed.\n");
-		kfree(bp->ptp_cfg);
-		bp->ptp_cfg = NULL;
-	}
 	rc = __bnxt_open_nic(bp, true, true);
 	if (rc) {
 		bnxt_hwrm_if_change(bp, false);
-		bnxt_ptp_clear(bp);
 	} else {
 		if (test_and_clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) {
 			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
@@ -10415,7 +10402,6 @@ static int bnxt_close(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
-	bnxt_ptp_clear(bp);
 	bnxt_hwmon_close(bp);
 	bnxt_close_nic(bp, true, true);
 	bnxt_hwrm_shutdown_link(bp);
@@ -10426,53 +10412,60 @@ static int bnxt_close(struct net_device *dev)
 static int bnxt_hwrm_port_phy_read(struct bnxt *bp, u16 phy_addr, u16 reg,
 				   u16 *val)
 {
-	struct hwrm_port_phy_mdio_read_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_port_phy_mdio_read_input req = {0};
+	struct hwrm_port_phy_mdio_read_output *resp;
+	struct hwrm_port_phy_mdio_read_input *req;
 	int rc;
 
 	if (bp->hwrm_spec_code < 0x10a00)
 		return -EOPNOTSUPP;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_MDIO_READ, -1, -1);
-	req.port_id = cpu_to_le16(bp->pf.port_id);
-	req.phy_addr = phy_addr;
-	req.reg_addr = cpu_to_le16(reg & 0x1f);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_MDIO_READ);
+	if (rc)
+		return rc;
+
+	req->port_id = cpu_to_le16(bp->pf.port_id);
+	req->phy_addr = phy_addr;
+	req->reg_addr = cpu_to_le16(reg & 0x1f);
 	if (mdio_phy_id_is_c45(phy_addr)) {
-		req.cl45_mdio = 1;
-		req.phy_addr = mdio_phy_id_prtad(phy_addr);
-		req.dev_addr = mdio_phy_id_devad(phy_addr);
-		req.reg_addr = cpu_to_le16(reg);
+		req->cl45_mdio = 1;
+		req->phy_addr = mdio_phy_id_prtad(phy_addr);
+		req->dev_addr = mdio_phy_id_devad(phy_addr);
+		req->reg_addr = cpu_to_le16(reg);
 	}
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc)
 		*val = le16_to_cpu(resp->reg_data);
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 static int bnxt_hwrm_port_phy_write(struct bnxt *bp, u16 phy_addr, u16 reg,
 				    u16 val)
 {
-	struct hwrm_port_phy_mdio_write_input req = {0};
+	struct hwrm_port_phy_mdio_write_input *req;
+	int rc;
 
 	if (bp->hwrm_spec_code < 0x10a00)
 		return -EOPNOTSUPP;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_MDIO_WRITE, -1, -1);
-	req.port_id = cpu_to_le16(bp->pf.port_id);
-	req.phy_addr = phy_addr;
-	req.reg_addr = cpu_to_le16(reg & 0x1f);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_MDIO_WRITE);
+	if (rc)
+		return rc;
+
+	req->port_id = cpu_to_le16(bp->pf.port_id);
+	req->phy_addr = phy_addr;
+	req->reg_addr = cpu_to_le16(reg & 0x1f);
 	if (mdio_phy_id_is_c45(phy_addr)) {
-		req.cl45_mdio = 1;
-		req.phy_addr = mdio_phy_id_prtad(phy_addr);
-		req.dev_addr = mdio_phy_id_devad(phy_addr);
-		req.reg_addr = cpu_to_le16(reg);
+		req->cl45_mdio = 1;
+		req->phy_addr = mdio_phy_id_prtad(phy_addr);
+		req->dev_addr = mdio_phy_id_devad(phy_addr);
+		req->reg_addr = cpu_to_le16(reg);
 	}
-	req.reg_data = cpu_to_le16(val);
+	req->reg_data = cpu_to_le16(val);
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
 /* rtnl_lock held */
@@ -10551,6 +10544,10 @@ static void bnxt_get_ring_stats(struct bnxt *bp,
 		stats->multicast += BNXT_GET_RING_STATS64(sw, rx_mcast_pkts);
 
 		stats->tx_dropped += BNXT_GET_RING_STATS64(sw, tx_error_pkts);
+
+		stats->rx_dropped +=
+			cpr->sw_stats.rx.rx_netpoll_discards +
+			cpr->sw_stats.rx.rx_oom_discards;
 	}
 }
 
@@ -10565,6 +10562,7 @@ static void bnxt_add_prev_stats(struct bnxt *bp,
 	stats->tx_bytes += prev_stats->tx_bytes;
 	stats->rx_missed_errors += prev_stats->rx_missed_errors;
 	stats->multicast += prev_stats->multicast;
+	stats->rx_dropped += prev_stats->rx_dropped;
 	stats->tx_dropped += prev_stats->tx_dropped;
 }
 
@@ -10709,6 +10707,7 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 {
 	struct net_device *dev = bp->dev;
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[0];
+	struct hwrm_cfa_l2_filter_free_input *req;
 	struct netdev_hw_addr *ha;
 	int i, off = 0, rc;
 	bool uc_update;
@@ -10720,19 +10719,16 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 	if (!uc_update)
 		goto skip_uc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_FREE);
+	if (rc)
+		return rc;
+	hwrm_req_hold(bp, req);
 	for (i = 1; i < vnic->uc_filter_count; i++) {
-		struct hwrm_cfa_l2_filter_free_input req = {0};
-
-		bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_L2_FILTER_FREE, -1,
-				       -1);
+		req->l2_filter_id = vnic->fw_l2_filter_id[i];
 
-		req.l2_filter_id = vnic->fw_l2_filter_id[i];
-
-		rc = _hwrm_send_message(bp, &req, sizeof(req),
-					HWRM_CMD_TIMEOUT);
+		rc = hwrm_req_send(bp, req);
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 
 	vnic->uc_filter_count = 1;
 
@@ -11084,22 +11080,30 @@ static netdev_features_t bnxt_features_check(struct sk_buff *skb,
 int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words,
 			 u32 *reg_buf)
 {
-	struct hwrm_dbg_read_direct_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_dbg_read_direct_input req = {0};
+	struct hwrm_dbg_read_direct_output *resp;
+	struct hwrm_dbg_read_direct_input *req;
 	__le32 *dbg_reg_buf;
 	dma_addr_t mapping;
 	int rc, i;
 
-	dbg_reg_buf = dma_alloc_coherent(&bp->pdev->dev, num_words * 4,
-					 &mapping, GFP_KERNEL);
-	if (!dbg_reg_buf)
-		return -ENOMEM;
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_READ_DIRECT, -1, -1);
-	req.host_dest_addr = cpu_to_le64(mapping);
-	req.read_addr = cpu_to_le32(reg_off + CHIMP_REG_VIEW_ADDR);
-	req.read_len32 = cpu_to_le32(num_words);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_DBG_READ_DIRECT);
+	if (rc)
+		return rc;
+
+	dbg_reg_buf = hwrm_req_dma_slice(bp, req, num_words * 4,
+					 &mapping);
+	if (!dbg_reg_buf) {
+		rc = -ENOMEM;
+		goto dbg_rd_reg_exit;
+	}
+
+	req->host_dest_addr = cpu_to_le64(mapping);
+
+	resp = hwrm_req_hold(bp, req);
+	req->read_addr = cpu_to_le32(reg_off + CHIMP_REG_VIEW_ADDR);
+	req->read_len32 = cpu_to_le32(num_words);
+
+	rc = hwrm_req_send(bp, req);
 	if (rc || resp->error_code) {
 		rc = -EIO;
 		goto dbg_rd_reg_exit;
@@ -11108,28 +11112,30 @@ int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words,
 		reg_buf[i] = le32_to_cpu(dbg_reg_buf[i]);
 
 dbg_rd_reg_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
-	dma_free_coherent(&bp->pdev->dev, num_words * 4, dbg_reg_buf, mapping);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 static int bnxt_dbg_hwrm_ring_info_get(struct bnxt *bp, u8 ring_type,
 				       u32 ring_id, u32 *prod, u32 *cons)
 {
-	struct hwrm_dbg_ring_info_get_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_dbg_ring_info_get_input req = {0};
+	struct hwrm_dbg_ring_info_get_output *resp;
+	struct hwrm_dbg_ring_info_get_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_RING_INFO_GET, -1, -1);
-	req.ring_type = ring_type;
-	req.fw_ring_id = cpu_to_le32(ring_id);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_DBG_RING_INFO_GET);
+	if (rc)
+		return rc;
+
+	req->ring_type = ring_type;
+	req->fw_ring_id = cpu_to_le32(ring_id);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc) {
 		*prod = le32_to_cpu(resp->producer_index);
 		*cons = le32_to_cpu(resp->consumer_index);
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -11187,18 +11193,22 @@ static void bnxt_dbg_dump_states(struct bnxt *bp)
 static int bnxt_hwrm_rx_ring_reset(struct bnxt *bp, int ring_nr)
 {
 	struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr];
-	struct hwrm_ring_reset_input req = {0};
+	struct hwrm_ring_reset_input *req;
 	struct bnxt_napi *bnapi = rxr->bnapi;
 	struct bnxt_cp_ring_info *cpr;
 	u16 cp_ring_id;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_RING_RESET);
+	if (rc)
+		return rc;
 
 	cpr = &bnapi->cp_ring;
 	cp_ring_id = cpr->cp_ring_struct.fw_ring_id;
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_RESET, cp_ring_id, -1);
-	req.ring_type = RING_RESET_REQ_RING_TYPE_RX_RING_GRP;
-	req.ring_id = cpu_to_le16(bp->grp_info[bnapi->index].fw_grp_id);
-	return hwrm_send_message_silent(bp, &req, sizeof(req),
-					HWRM_CMD_TIMEOUT);
+	req->cmpl_ring = cpu_to_le16(cp_ring_id);
+	req->ring_type = RING_RESET_REQ_RING_TYPE_RX_RING_GRP;
+	req->ring_id = cpu_to_le16(bp->grp_info[bnapi->index].fw_grp_id);
+	return hwrm_req_send_silent(bp, req);
 }
 
 static void bnxt_reset_task(struct bnxt *bp, bool silent)
@@ -11405,7 +11415,6 @@ static void bnxt_fw_reset_close(struct bnxt *bp)
 		bnxt_clear_int_mode(bp);
 		pci_disable_device(bp->pdev);
 	}
-	bnxt_ptp_clear(bp);
 	__bnxt_close_nic(bp, true, false);
 	bnxt_vf_reps_free(bp);
 	bnxt_clear_int_mode(bp);
@@ -11441,13 +11450,20 @@ static bool is_bnxt_fw_ok(struct bnxt *bp)
 static void bnxt_force_fw_reset(struct bnxt *bp)
 {
 	struct bnxt_fw_health *fw_health = bp->fw_health;
+	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 	u32 wait_dsecs;
 
 	if (!test_bit(BNXT_STATE_OPEN, &bp->state) ||
 	    test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 		return;
 
-	set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+	if (ptp) {
+		spin_lock_bh(&ptp->ptp_lock);
+		set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+		spin_unlock_bh(&ptp->ptp_lock);
+	} else {
+		set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+	}
 	bnxt_fw_reset_close(bp);
 	wait_dsecs = fw_health->master_func_wait_dsecs;
 	if (fw_health->master) {
@@ -11503,9 +11519,16 @@ void bnxt_fw_reset(struct bnxt *bp)
 	bnxt_rtnl_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;
 		int n = 0, tmo;
 
-		set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+		if (ptp) {
+			spin_lock_bh(&ptp->ptp_lock);
+			set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+			spin_unlock_bh(&ptp->ptp_lock);
+		} else {
+			set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+		}
 		if (bp->pf.active_vfs &&
 		    !test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
 			n = bnxt_get_registered_vfs(bp);
@@ -11614,12 +11637,15 @@ static void bnxt_init_ethtool_link_settings(struct bnxt *bp)
 static void bnxt_fw_echo_reply(struct bnxt *bp)
 {
 	struct bnxt_fw_health *fw_health = bp->fw_health;
-	struct hwrm_func_echo_response_input req = {0};
+	struct hwrm_func_echo_response_input *req;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_ECHO_RESPONSE, -1, -1);
-	req.event_data1 = cpu_to_le32(fw_health->echo_req_data1);
-	req.event_data2 = cpu_to_le32(fw_health->echo_req_data2);
-	hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_ECHO_RESPONSE);
+	if (rc)
+		return;
+	req->event_data1 = cpu_to_le32(fw_health->echo_req_data1);
+	req->event_data2 = cpu_to_le32(fw_health->echo_req_data2);
+	hwrm_req_send(bp, req);
 }
 
 static void bnxt_sp_task(struct work_struct *work)
@@ -11824,18 +11850,6 @@ static int bnxt_fw_init_one_p1(struct bnxt *bp)
 			return rc;
 	}
 
-	if (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL) {
-		rc = bnxt_alloc_kong_hwrm_resources(bp);
-		if (rc)
-			bp->fw_cap &= ~BNXT_FW_CAP_KONG_MB_CHNL;
-	}
-
-	if ((bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) ||
-	    bp->hwrm_max_ext_req_len > BNXT_HWRM_MAX_REQ_LEN) {
-		rc = bnxt_alloc_hwrm_short_cmd_req(bp);
-		if (rc)
-			return rc;
-	}
 	bnxt_nvm_cfg_ver_get(bp);
 
 	rc = bnxt_hwrm_func_reset(bp);
@@ -12010,14 +12024,16 @@ static void bnxt_reset_all(struct bnxt *bp)
 		for (i = 0; i < fw_health->fw_reset_seq_cnt; i++)
 			bnxt_fw_reset_writel(bp, i);
 	} else if (fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU) {
-		struct hwrm_fw_reset_input req = {0};
-
-		bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FW_RESET, -1, -1);
-		req.resp_addr = cpu_to_le64(bp->hwrm_cmd_kong_resp_dma_addr);
-		req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP;
-		req.selfrst_status = FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP;
-		req.flags = FW_RESET_REQ_FLAGS_RESET_GRACEFUL;
-		rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		struct hwrm_fw_reset_input *req;
+
+		rc = hwrm_req_init(bp, req, HWRM_FW_RESET);
+		if (!rc) {
+			req->target_id = cpu_to_le16(HWRM_TARGET_ID_KONG);
+			req->embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP;
+			req->selfrst_status = FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP;
+			req->flags = FW_RESET_REQ_FLAGS_RESET_GRACEFUL;
+			rc = hwrm_req_send(bp, req);
+		}
 		if (rc != -ENODEV)
 			netdev_warn(bp->dev, "Unable to reset FW rc=%d\n", rc);
 	}
@@ -12144,7 +12160,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		fallthrough;
 	case BNXT_FW_RESET_STATE_POLL_FW:
 		bp->hwrm_cmd_timeout = SHORT_HWRM_CMD_TIMEOUT;
-		rc = __bnxt_hwrm_ver_get(bp, true);
+		rc = bnxt_hwrm_poll(bp);
 		if (rc) {
 			if (bnxt_fw_reset_timeout(bp)) {
 				netdev_err(bp->dev, "Firmware reset aborted\n");
@@ -12177,6 +12193,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		bnxt_reenable_sriov(bp);
 		bnxt_vf_reps_alloc(bp);
 		bnxt_vf_reps_open(bp);
+		bnxt_ptp_reapply_pps(bp);
 		bnxt_dl_health_recovery_done(bp);
 		bnxt_dl_health_status_update(bp, true);
 		rtnl_unlock();
@@ -12708,7 +12725,7 @@ static const struct net_device_ops bnxt_netdev_ops = {
 	.ndo_stop		= bnxt_close,
 	.ndo_get_stats64	= bnxt_get_stats64,
 	.ndo_set_rx_mode	= bnxt_set_rx_mode,
-	.ndo_do_ioctl		= bnxt_ioctl,
+	.ndo_eth_ioctl		= bnxt_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= bnxt_change_mac_addr,
 	.ndo_change_mtu		= bnxt_change_mtu,
@@ -12747,6 +12764,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	if (BNXT_PF(bp))
 		devlink_port_type_clear(&bp->dl_port);
 
+	bnxt_ptp_clear(bp);
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
@@ -12762,7 +12780,6 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bnxt_clear_int_mode(bp);
 	bnxt_hwrm_func_drv_unrgtr(bp);
 	bnxt_free_hwrm_resources(bp);
-	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_ethtool_free(bp);
 	bnxt_dcb_free(bp);
 	kfree(bp->edev);
@@ -12800,8 +12817,10 @@ static int bnxt_probe_phy(struct bnxt *bp, bool fw_dflt)
 	if (!fw_dflt)
 		return 0;
 
+	mutex_lock(&bp->link_lock);
 	rc = bnxt_update_link(bp, false);
 	if (rc) {
+		mutex_unlock(&bp->link_lock);
 		netdev_err(bp->dev, "Probe phy can't update link (rc: %x)\n",
 			   rc);
 		return rc;
@@ -12814,6 +12833,7 @@ static int bnxt_probe_phy(struct bnxt *bp, bool fw_dflt)
 		link_info->support_auto_speeds = link_info->support_speeds;
 
 	bnxt_init_ethtool_link_settings(bp);
+	mutex_unlock(&bp->link_lock);
 	return 0;
 }
 
@@ -13085,6 +13105,12 @@ static void bnxt_vpd_read_info(struct bnxt *bp)
 		goto exit;
 	}
 
+	i = pci_vpd_find_tag(vpd_data, vpd_size, PCI_VPD_LRDT_RO_DATA);
+	if (i < 0) {
+		netdev_err(bp->dev, "VPD READ-Only not found\n");
+		goto exit;
+	}
+
 	ro_size = pci_vpd_lrdt_size(&vpd_data[i]);
 	i += PCI_VPD_LRDT_TAG_SIZE;
 	if (i + ro_size > vpd_size)
@@ -13356,9 +13382,9 @@ init_err_cleanup:
 
 init_err_pci_clean:
 	bnxt_hwrm_func_drv_unrgtr(bp);
-	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_free_hwrm_resources(bp);
 	bnxt_ethtool_free(bp);
+	bnxt_ptp_clear(bp);
 	kfree(bp->ptp_cfg);
 	bp->ptp_cfg = NULL;
 	kfree(bp->fw_health);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index ba4e0fc38520..a8212dcdad5f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -496,6 +496,16 @@ struct rx_tpa_end_cmp_ext {
 	!!((data1) &							\
 	   ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED)
 
+#define BNXT_EVENT_ERROR_REPORT_TYPE(data1)				\
+	(((data1) &							\
+	  ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK) >>\
+	 ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT)
+
+#define BNXT_EVENT_INVALID_SIGNAL_DATA(data2)				\
+	(((data2) &							\
+	  ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_MASK) >>\
+	 ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_SFT)
+
 struct nqe_cn {
 	__le16	type;
 	#define NQ_CN_TYPE_MASK           0x3fUL
@@ -586,15 +596,17 @@ struct nqe_cn {
 #define MAX_TPA_SEGS_P5	0x3f
 
 #if (BNXT_PAGE_SHIFT == 16)
-#define MAX_RX_PAGES	1
+#define MAX_RX_PAGES_AGG_ENA	1
+#define MAX_RX_PAGES	4
 #define MAX_RX_AGG_PAGES	4
 #define MAX_TX_PAGES	1
-#define MAX_CP_PAGES	8
+#define MAX_CP_PAGES	16
 #else
-#define MAX_RX_PAGES	8
+#define MAX_RX_PAGES_AGG_ENA	8
+#define MAX_RX_PAGES	32
 #define MAX_RX_AGG_PAGES	32
 #define MAX_TX_PAGES	8
-#define MAX_CP_PAGES	64
+#define MAX_CP_PAGES	128
 #endif
 
 #define RX_DESC_CNT (BNXT_PAGE_SIZE / sizeof(struct rx_bd))
@@ -612,6 +624,7 @@ struct nqe_cn {
 #define HW_CMPD_RING_SIZE (sizeof(struct tx_cmp) * CP_DESC_CNT)
 
 #define BNXT_MAX_RX_DESC_CNT		(RX_DESC_CNT * MAX_RX_PAGES - 1)
+#define BNXT_MAX_RX_DESC_CNT_JUM_ENA	(RX_DESC_CNT * MAX_RX_PAGES_AGG_ENA - 1)
 #define BNXT_MAX_RX_JUM_DESC_CNT	(RX_DESC_CNT * MAX_RX_AGG_PAGES - 1)
 #define BNXT_MAX_TX_DESC_CNT		(TX_DESC_CNT * MAX_TX_PAGES - 1)
 
@@ -656,37 +669,7 @@ struct nqe_cn {
 #define RING_CMP(idx)		((idx) & bp->cp_ring_mask)
 #define NEXT_CMP(idx)		RING_CMP(ADV_RAW_CMP(idx, 1))
 
-#define BNXT_HWRM_MAX_REQ_LEN		(bp->hwrm_max_req_len)
-#define BNXT_HWRM_SHORT_REQ_LEN		sizeof(struct hwrm_short_input)
 #define DFLT_HWRM_CMD_TIMEOUT		500
-#define HWRM_CMD_MAX_TIMEOUT		40000
-#define SHORT_HWRM_CMD_TIMEOUT		20
-#define HWRM_CMD_TIMEOUT		(bp->hwrm_cmd_timeout)
-#define HWRM_RESET_TIMEOUT		((HWRM_CMD_TIMEOUT) * 4)
-#define HWRM_COREDUMP_TIMEOUT		((HWRM_CMD_TIMEOUT) * 12)
-#define BNXT_HWRM_REQ_MAX_SIZE		128
-#define BNXT_HWRM_REQS_PER_PAGE		(BNXT_PAGE_SIZE /	\
-					 BNXT_HWRM_REQ_MAX_SIZE)
-#define HWRM_SHORT_MIN_TIMEOUT		3
-#define HWRM_SHORT_MAX_TIMEOUT		10
-#define HWRM_SHORT_TIMEOUT_COUNTER	5
-
-#define HWRM_MIN_TIMEOUT		25
-#define HWRM_MAX_TIMEOUT		40
-
-#define HWRM_WAIT_MUST_ABORT(bp, req)					\
-	(le16_to_cpu((req)->req_type) != HWRM_VER_GET &&		\
-	 !bnxt_is_fw_healthy(bp))
-
-#define HWRM_TOTAL_TIMEOUT(n)	(((n) <= HWRM_SHORT_TIMEOUT_COUNTER) ?	\
-	((n) * HWRM_SHORT_MIN_TIMEOUT) :				\
-	(HWRM_SHORT_TIMEOUT_COUNTER * HWRM_SHORT_MIN_TIMEOUT +		\
-	 ((n) - HWRM_SHORT_TIMEOUT_COUNTER) * HWRM_MIN_TIMEOUT))
-
-#define HWRM_VALID_BIT_DELAY_USEC	150
-
-#define BNXT_HWRM_CHNL_CHIMP	0
-#define BNXT_HWRM_CHNL_KONG	1
 
 #define BNXT_RX_EVENT		1
 #define BNXT_AGG_EVENT		2
@@ -926,6 +909,8 @@ struct bnxt_rx_sw_stats {
 	u64			rx_l4_csum_errors;
 	u64			rx_resets;
 	u64			rx_buf_errors;
+	u64			rx_oom_discards;
+	u64			rx_netpoll_discards;
 };
 
 struct bnxt_cmn_sw_stats {
@@ -963,11 +948,11 @@ struct bnxt_cp_ring_info {
 	struct dim		dim;
 
 	union {
-		struct tx_cmp	*cp_desc_ring[MAX_CP_PAGES];
-		struct nqe_cn	*nq_desc_ring[MAX_CP_PAGES];
+		struct tx_cmp	**cp_desc_ring;
+		struct nqe_cn	**nq_desc_ring;
 	};
 
-	dma_addr_t		cp_desc_mapping[MAX_CP_PAGES];
+	dma_addr_t		*cp_desc_mapping;
 
 	struct bnxt_stats_mem	stats;
 	u32			hw_stats_ctx_id;
@@ -1888,19 +1873,15 @@ struct bnxt {
 	#define BNXT_FW_CAP_VLAN_RX_STRIP		0x01000000
 	#define BNXT_FW_CAP_VLAN_TX_INSERT		0x02000000
 	#define BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED	0x04000000
+	#define BNXT_FW_CAP_PTP_PPS			0x10000000
 	#define BNXT_FW_CAP_RING_MONITOR		0x40000000
 
 #define BNXT_NEW_RM(bp)		((bp)->fw_cap & BNXT_FW_CAP_NEW_RM)
 	u32			hwrm_spec_code;
 	u16			hwrm_cmd_seq;
 	u16                     hwrm_cmd_kong_seq;
-	u16			hwrm_intr_seq_id;
-	void			*hwrm_short_cmd_req_addr;
-	dma_addr_t		hwrm_short_cmd_req_dma_addr;
-	void			*hwrm_cmd_resp_addr;
-	dma_addr_t		hwrm_cmd_resp_dma_addr;
-	void			*hwrm_cmd_kong_resp_addr;
-	dma_addr_t		hwrm_cmd_kong_resp_dma_addr;
+	struct dma_pool		*hwrm_dma_pool;
+	struct hlist_head	hwrm_pending_list;
 
 	struct rtnl_link_stats64	net_stats_prev;
 	struct bnxt_stats_mem	port_stats;
@@ -2000,7 +1981,7 @@ struct bnxt {
 	struct mutex		sriov_lock;
 #endif
 
-#if BITS_PER_LONG == 32
+#ifndef writeq
 	/* ensure atomic 64-bit doorbell writes on 32-bit systems. */
 	spinlock_t		db_lock;
 #endif
@@ -2129,7 +2110,7 @@ static inline u32 bnxt_tx_avail(struct bnxt *bp, struct bnxt_tx_ring_info *txr)
 		((txr->tx_prod - txr->tx_cons) & bp->tx_ring_mask);
 }
 
-#if BITS_PER_LONG == 32
+#ifndef writeq
 #define writeq(val64, db)			\
 do {						\
 	spin_lock(&bp->db_lock);		\
@@ -2171,63 +2152,6 @@ static inline void bnxt_db_write(struct bnxt *bp, struct bnxt_db_info *db,
 	}
 }
 
-static inline bool bnxt_cfa_hwrm_message(u16 req_type)
-{
-	switch (req_type) {
-	case HWRM_CFA_ENCAP_RECORD_ALLOC:
-	case HWRM_CFA_ENCAP_RECORD_FREE:
-	case HWRM_CFA_DECAP_FILTER_ALLOC:
-	case HWRM_CFA_DECAP_FILTER_FREE:
-	case HWRM_CFA_EM_FLOW_ALLOC:
-	case HWRM_CFA_EM_FLOW_FREE:
-	case HWRM_CFA_EM_FLOW_CFG:
-	case HWRM_CFA_FLOW_ALLOC:
-	case HWRM_CFA_FLOW_FREE:
-	case HWRM_CFA_FLOW_INFO:
-	case HWRM_CFA_FLOW_FLUSH:
-	case HWRM_CFA_FLOW_STATS:
-	case HWRM_CFA_METER_PROFILE_ALLOC:
-	case HWRM_CFA_METER_PROFILE_FREE:
-	case HWRM_CFA_METER_PROFILE_CFG:
-	case HWRM_CFA_METER_INSTANCE_ALLOC:
-	case HWRM_CFA_METER_INSTANCE_FREE:
-		return true;
-	default:
-		return false;
-	}
-}
-
-static inline bool bnxt_kong_hwrm_message(struct bnxt *bp, struct input *req)
-{
-	return (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL &&
-		bnxt_cfa_hwrm_message(le16_to_cpu(req->req_type)));
-}
-
-static inline bool bnxt_hwrm_kong_chnl(struct bnxt *bp, struct input *req)
-{
-	return (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL &&
-		req->resp_addr == cpu_to_le64(bp->hwrm_cmd_kong_resp_dma_addr));
-}
-
-static inline void *bnxt_get_hwrm_resp_addr(struct bnxt *bp, void *req)
-{
-	if (bnxt_hwrm_kong_chnl(bp, (struct input *)req))
-		return bp->hwrm_cmd_kong_resp_addr;
-	else
-		return bp->hwrm_cmd_resp_addr;
-}
-
-static inline u16 bnxt_get_hwrm_seq_id(struct bnxt *bp, u16 dst)
-{
-	u16 seq_id;
-
-	if (dst == BNXT_HWRM_CHNL_CHIMP)
-		seq_id = bp->hwrm_cmd_seq++;
-	else
-		seq_id = bp->hwrm_cmd_kong_seq++;
-	return seq_id;
-}
-
 extern const u16 bnxt_lhint_arr[];
 
 int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
@@ -2237,11 +2161,6 @@ u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx);
 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_hwrm_cmd_hdr_init(struct bnxt *, void *, u16, u16, u16);
-int _hwrm_send_message(struct bnxt *, void *, u32, int);
-int _hwrm_send_message_silent(struct bnxt *bp, void *msg, u32 len, int timeout);
-int hwrm_send_message(struct bnxt *, void *, u32, int);
-int hwrm_send_message_silent(struct bnxt *, void *, u32, int);
 int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap,
 			    int bmap_size, bool async_only);
 int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 8a68df4d9e59..228a5db7e143 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -18,6 +18,7 @@
 #include <rdma/ib_verbs.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
+#include "bnxt_hwrm.h"
 #include "bnxt_dcb.h"
 
 #ifdef CONFIG_BNXT_DCB
@@ -38,38 +39,43 @@ static int bnxt_queue_to_tc(struct bnxt *bp, u8 queue_id)
 
 static int bnxt_hwrm_queue_pri2cos_cfg(struct bnxt *bp, struct ieee_ets *ets)
 {
-	struct hwrm_queue_pri2cos_cfg_input req = {0};
+	struct hwrm_queue_pri2cos_cfg_input *req;
 	u8 *pri2cos;
-	int i;
+	int rc, i;
+
+	rc = hwrm_req_init(bp, req, HWRM_QUEUE_PRI2COS_CFG);
+	if (rc)
+		return rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_PRI2COS_CFG, -1, -1);
-	req.flags = cpu_to_le32(QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_BIDIR |
-				QUEUE_PRI2COS_CFG_REQ_FLAGS_IVLAN);
+	req->flags = cpu_to_le32(QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_BIDIR |
+				 QUEUE_PRI2COS_CFG_REQ_FLAGS_IVLAN);
 
-	pri2cos = &req.pri0_cos_queue_id;
+	pri2cos = &req->pri0_cos_queue_id;
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
 		u8 qidx;
 
-		req.enables |= cpu_to_le32(
+		req->enables |= cpu_to_le32(
 			QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI0_COS_QUEUE_ID << i);
 
 		qidx = bp->tc_to_qidx[ets->prio_tc[i]];
 		pri2cos[i] = bp->q_info[qidx].queue_id;
 	}
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_hwrm_queue_pri2cos_qcfg(struct bnxt *bp, struct ieee_ets *ets)
 {
-	struct hwrm_queue_pri2cos_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_queue_pri2cos_qcfg_input req = {0};
-	int rc = 0;
+	struct hwrm_queue_pri2cos_qcfg_output *resp;
+	struct hwrm_queue_pri2cos_qcfg_input *req;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_PRI2COS_QCFG, -1, -1);
-	req.flags = cpu_to_le32(QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN);
+	rc = hwrm_req_init(bp, req, HWRM_QUEUE_PRI2COS_QCFG);
+	if (rc)
+		return rc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req->flags = cpu_to_le32(QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc) {
 		u8 *pri2cos = &resp->pri0_cos_queue_id;
 		int i;
@@ -83,23 +89,26 @@ static int bnxt_hwrm_queue_pri2cos_qcfg(struct bnxt *bp, struct ieee_ets *ets)
 				ets->prio_tc[i] = tc;
 		}
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 static int bnxt_hwrm_queue_cos2bw_cfg(struct bnxt *bp, struct ieee_ets *ets,
 				      u8 max_tc)
 {
-	struct hwrm_queue_cos2bw_cfg_input req = {0};
+	struct hwrm_queue_cos2bw_cfg_input *req;
 	struct bnxt_cos2bw_cfg cos2bw;
 	void *data;
-	int i;
+	int rc, i;
+
+	rc = hwrm_req_init(bp, req, HWRM_QUEUE_COS2BW_CFG);
+	if (rc)
+		return rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_COS2BW_CFG, -1, -1);
 	for (i = 0; i < max_tc; i++) {
 		u8 qidx = bp->tc_to_qidx[i];
 
-		req.enables |= cpu_to_le32(
+		req->enables |= cpu_to_le32(
 			QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID <<
 			qidx);
 
@@ -120,30 +129,32 @@ static int bnxt_hwrm_queue_cos2bw_cfg(struct bnxt *bp, struct ieee_ets *ets,
 				cpu_to_le32((ets->tc_tx_bw[i] * 100) |
 					    BW_VALUE_UNIT_PERCENT1_100);
 		}
-		data = &req.unused_0 + qidx * (sizeof(cos2bw) - 4);
+		data = &req->unused_0 + qidx * (sizeof(cos2bw) - 4);
 		memcpy(data, &cos2bw.queue_id, sizeof(cos2bw) - 4);
 		if (qidx == 0) {
-			req.queue_id0 = cos2bw.queue_id;
-			req.unused_0 = 0;
+			req->queue_id0 = cos2bw.queue_id;
+			req->unused_0 = 0;
 		}
 	}
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_hwrm_queue_cos2bw_qcfg(struct bnxt *bp, struct ieee_ets *ets)
 {
-	struct hwrm_queue_cos2bw_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_queue_cos2bw_qcfg_input req = {0};
+	struct hwrm_queue_cos2bw_qcfg_output *resp;
+	struct hwrm_queue_cos2bw_qcfg_input *req;
 	struct bnxt_cos2bw_cfg cos2bw;
 	void *data;
 	int rc, i;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_COS2BW_QCFG, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_QUEUE_COS2BW_QCFG);
+	if (rc)
+		return rc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc) {
-		mutex_unlock(&bp->hwrm_cmd_lock);
+		hwrm_req_drop(bp, req);
 		return rc;
 	}
 
@@ -167,7 +178,7 @@ static int bnxt_hwrm_queue_cos2bw_qcfg(struct bnxt *bp, struct ieee_ets *ets)
 			ets->tc_tx_bw[tc] = cos2bw.bw_weight;
 		}
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return 0;
 }
 
@@ -229,11 +240,12 @@ static int bnxt_queue_remap(struct bnxt *bp, unsigned int lltc_mask)
 
 static int bnxt_hwrm_queue_pfc_cfg(struct bnxt *bp, struct ieee_pfc *pfc)
 {
-	struct hwrm_queue_pfcenable_cfg_input req = {0};
+	struct hwrm_queue_pfcenable_cfg_input *req;
 	struct ieee_ets *my_ets = bp->ieee_ets;
 	unsigned int tc_mask = 0, pri_mask = 0;
 	u8 i, pri, lltc_count = 0;
 	bool need_q_remap = false;
+	int rc;
 
 	if (!my_ets)
 		return -EINVAL;
@@ -266,38 +278,43 @@ static int bnxt_hwrm_queue_pfc_cfg(struct bnxt *bp, struct ieee_pfc *pfc)
 	if (need_q_remap)
 		bnxt_queue_remap(bp, tc_mask);
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_PFCENABLE_CFG, -1, -1);
-	req.flags = cpu_to_le32(pri_mask);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_QUEUE_PFCENABLE_CFG);
+	if (rc)
+		return rc;
+
+	req->flags = cpu_to_le32(pri_mask);
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_hwrm_queue_pfc_qcfg(struct bnxt *bp, struct ieee_pfc *pfc)
 {
-	struct hwrm_queue_pfcenable_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_queue_pfcenable_qcfg_input req = {0};
+	struct hwrm_queue_pfcenable_qcfg_output *resp;
+	struct hwrm_queue_pfcenable_qcfg_input *req;
 	u8 pri_mask;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_PFCENABLE_QCFG, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_QUEUE_PFCENABLE_QCFG);
+	if (rc)
+		return rc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (rc) {
-		mutex_unlock(&bp->hwrm_cmd_lock);
+		hwrm_req_drop(bp, req);
 		return rc;
 	}
 
 	pri_mask = le32_to_cpu(resp->flags);
 	pfc->pfc_en = pri_mask;
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return 0;
 }
 
 static int bnxt_hwrm_set_dcbx_app(struct bnxt *bp, struct dcb_app *app,
 				  bool add)
 {
-	struct hwrm_fw_set_structured_data_input set = {0};
-	struct hwrm_fw_get_structured_data_input get = {0};
+	struct hwrm_fw_set_structured_data_input *set;
+	struct hwrm_fw_get_structured_data_input *get;
 	struct hwrm_struct_data_dcbx_app *fw_app;
 	struct hwrm_struct_hdr *data;
 	dma_addr_t mapping;
@@ -307,19 +324,26 @@ static int bnxt_hwrm_set_dcbx_app(struct bnxt *bp, struct dcb_app *app,
 	if (bp->hwrm_spec_code < 0x10601)
 		return 0;
 
+	rc = hwrm_req_init(bp, get, HWRM_FW_GET_STRUCTURED_DATA);
+	if (rc)
+		return rc;
+
+	hwrm_req_hold(bp, get);
+	hwrm_req_alloc_flags(bp, get, GFP_KERNEL | __GFP_ZERO);
+
 	n = IEEE_8021QAZ_MAX_TCS;
 	data_len = sizeof(*data) + sizeof(*fw_app) * n;
-	data = dma_alloc_coherent(&bp->pdev->dev, data_len, &mapping,
-				  GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
+	data = hwrm_req_dma_slice(bp, get, data_len, &mapping);
+	if (!data) {
+		rc = -ENOMEM;
+		goto set_app_exit;
+	}
 
-	bnxt_hwrm_cmd_hdr_init(bp, &get, HWRM_FW_GET_STRUCTURED_DATA, -1, -1);
-	get.dest_data_addr = cpu_to_le64(mapping);
-	get.structure_id = cpu_to_le16(STRUCT_HDR_STRUCT_ID_DCBX_APP);
-	get.subtype = cpu_to_le16(HWRM_STRUCT_DATA_SUBTYPE_HOST_OPERATIONAL);
-	get.count = 0;
-	rc = hwrm_send_message(bp, &get, sizeof(get), HWRM_CMD_TIMEOUT);
+	get->dest_data_addr = cpu_to_le64(mapping);
+	get->structure_id = cpu_to_le16(STRUCT_HDR_STRUCT_ID_DCBX_APP);
+	get->subtype = cpu_to_le16(HWRM_STRUCT_DATA_SUBTYPE_HOST_OPERATIONAL);
+	get->count = 0;
+	rc = hwrm_req_send(bp, get);
 	if (rc)
 		goto set_app_exit;
 
@@ -365,44 +389,49 @@ static int bnxt_hwrm_set_dcbx_app(struct bnxt *bp, struct dcb_app *app,
 	data->len = cpu_to_le16(sizeof(*fw_app) * n);
 	data->subtype = cpu_to_le16(HWRM_STRUCT_DATA_SUBTYPE_HOST_OPERATIONAL);
 
-	bnxt_hwrm_cmd_hdr_init(bp, &set, HWRM_FW_SET_STRUCTURED_DATA, -1, -1);
-	set.src_data_addr = cpu_to_le64(mapping);
-	set.data_len = cpu_to_le16(sizeof(*data) + sizeof(*fw_app) * n);
-	set.hdr_cnt = 1;
-	rc = hwrm_send_message(bp, &set, sizeof(set), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, set, HWRM_FW_SET_STRUCTURED_DATA);
+	if (rc)
+		goto set_app_exit;
+
+	set->src_data_addr = cpu_to_le64(mapping);
+	set->data_len = cpu_to_le16(sizeof(*data) + sizeof(*fw_app) * n);
+	set->hdr_cnt = 1;
+	rc = hwrm_req_send(bp, set);
 
 set_app_exit:
-	dma_free_coherent(&bp->pdev->dev, data_len, data, mapping);
+	hwrm_req_drop(bp, get); /* dropping get request and associated slice */
 	return rc;
 }
 
 static int bnxt_hwrm_queue_dscp_qcaps(struct bnxt *bp)
 {
-	struct hwrm_queue_dscp_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_queue_dscp_qcaps_input req = {0};
+	struct hwrm_queue_dscp_qcaps_output *resp;
+	struct hwrm_queue_dscp_qcaps_input *req;
 	int rc;
 
 	bp->max_dscp_value = 0;
 	if (bp->hwrm_spec_code < 0x10800 || BNXT_VF(bp))
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_DSCP_QCAPS, -1, -1);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_QUEUE_DSCP_QCAPS);
+	if (rc)
+		return rc;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
 	if (!rc) {
 		bp->max_dscp_value = (1 << resp->num_dscp_bits) - 1;
 		if (bp->max_dscp_value < 0x3f)
 			bp->max_dscp_value = 0;
 	}
-
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
 static int bnxt_hwrm_queue_dscp2pri_cfg(struct bnxt *bp, struct dcb_app *app,
 					bool add)
 {
-	struct hwrm_queue_dscp2pri_cfg_input req = {0};
+	struct hwrm_queue_dscp2pri_cfg_input *req;
 	struct bnxt_dscp2pri_entry *dscp2pri;
 	dma_addr_t mapping;
 	int rc;
@@ -410,23 +439,25 @@ static int bnxt_hwrm_queue_dscp2pri_cfg(struct bnxt *bp, struct dcb_app *app,
 	if (bp->hwrm_spec_code < 0x10800)
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_DSCP2PRI_CFG, -1, -1);
-	dscp2pri = dma_alloc_coherent(&bp->pdev->dev, sizeof(*dscp2pri),
-				      &mapping, GFP_KERNEL);
-	if (!dscp2pri)
+	rc = hwrm_req_init(bp, req, HWRM_QUEUE_DSCP2PRI_CFG);
+	if (rc)
+		return rc;
+
+	dscp2pri = hwrm_req_dma_slice(bp, req, sizeof(*dscp2pri), &mapping);
+	if (!dscp2pri) {
+		hwrm_req_drop(bp, req);
 		return -ENOMEM;
+	}
 
-	req.src_data_addr = cpu_to_le64(mapping);
+	req->src_data_addr = cpu_to_le64(mapping);
 	dscp2pri->dscp = app->protocol;
 	if (add)
 		dscp2pri->mask = 0x3f;
 	else
 		dscp2pri->mask = 0;
 	dscp2pri->pri = app->priority;
-	req.entry_cnt = cpu_to_le16(1);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	dma_free_coherent(&bp->pdev->dev, sizeof(*dscp2pri), dscp2pri,
-			  mapping);
+	req->entry_cnt = cpu_to_le16(1);
+	rc = hwrm_req_send(bp, req);
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 64381be935a8..1423cc617d93 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -12,6 +12,7 @@
 #include <net/devlink.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
+#include "bnxt_hwrm.h"
 #include "bnxt_vfr.h"
 #include "bnxt_devlink.h"
 #include "bnxt_ethtool.h"
@@ -354,28 +355,34 @@ static void bnxt_copy_from_nvm_data(union devlink_param_value *dst,
 static int bnxt_hwrm_get_nvm_cfg_ver(struct bnxt *bp,
 				     union devlink_param_value *nvm_cfg_ver)
 {
-	struct hwrm_nvm_get_variable_input req = {0};
+	struct hwrm_nvm_get_variable_input *req;
 	union bnxt_nvm_data *data;
 	dma_addr_t data_dma_addr;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_VARIABLE, -1, -1);
-	data = dma_alloc_coherent(&bp->pdev->dev, sizeof(*data),
-				  &data_dma_addr, GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
+	rc = hwrm_req_init(bp, req, HWRM_NVM_GET_VARIABLE);
+	if (rc)
+		return rc;
+
+	data = hwrm_req_dma_slice(bp, req, sizeof(*data), &data_dma_addr);
+	if (!data) {
+		rc = -ENOMEM;
+		goto exit;
+	}
 
-	req.dest_data_addr = cpu_to_le64(data_dma_addr);
-	req.data_len = cpu_to_le16(BNXT_NVM_CFG_VER_BITS);
-	req.option_num = cpu_to_le16(NVM_OFF_NVM_CFG_VER);
+	hwrm_req_hold(bp, req);
+	req->dest_data_addr = cpu_to_le64(data_dma_addr);
+	req->data_len = cpu_to_le16(BNXT_NVM_CFG_VER_BITS);
+	req->option_num = cpu_to_le16(NVM_OFF_NVM_CFG_VER);
 
-	rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_send_silent(bp, req);
 	if (!rc)
 		bnxt_copy_from_nvm_data(nvm_cfg_ver, data,
 					BNXT_NVM_CFG_VER_BITS,
 					BNXT_NVM_CFG_VER_BYTES);
 
-	dma_free_coherent(&bp->pdev->dev, sizeof(*data), data, data_dma_addr);
+exit:
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -562,17 +569,20 @@ 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,
-			     int msg_len, union devlink_param_value *val)
+			     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))
+	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) {
@@ -581,18 +591,22 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 		}
 	}
 
-	if (i == ARRAY_SIZE(nvm_params))
+	if (i == ARRAY_SIZE(nvm_params)) {
+		hwrm_req_drop(bp, req);
 		return -EOPNOTSUPP;
+	}
 
 	if (nvm_param.dir_type == BNXT_NVM_PORT_CFG)
 		idx = bp->pf.port_id;
 	else if (nvm_param.dir_type == BNXT_NVM_FUNC_CFG)
 		idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID;
 
-	data = dma_alloc_coherent(&bp->pdev->dev, sizeof(*data),
-				  &data_dma_addr, GFP_KERNEL);
-	if (!data)
+	data = hwrm_req_dma_slice(bp, req, sizeof(*data), &data_dma_addr);
+
+	if (!data) {
+		hwrm_req_drop(bp, req);
 		return -ENOMEM;
+	}
 
 	req->dest_data_addr = cpu_to_le64(data_dma_addr);
 	req->data_len = cpu_to_le16(nvm_param.nvm_num_bits);
@@ -601,26 +615,24 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 	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);
-		rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
+		rc = hwrm_req_send(bp, msg);
 	} else {
-		rc = hwrm_send_message_silent(bp, msg, msg_len,
-					      HWRM_CMD_TIMEOUT);
+		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);
 		} else {
-			struct hwrm_err_output *resp = bp->hwrm_cmd_resp_addr;
-
 			if (resp->cmd_err ==
 				NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST)
 				rc = -EOPNOTSUPP;
 		}
 	}
-	dma_free_coherent(&bp->pdev->dev, sizeof(*data), data, data_dma_addr);
+	hwrm_req_drop(bp, req);
 	if (rc == -EACCES)
 		netdev_err(bp->dev, "PF does not have admin privileges to modify NVM config\n");
 	return rc;
@@ -629,15 +641,17 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id,
 				 struct devlink_param_gset_ctx *ctx)
 {
-	struct hwrm_nvm_get_variable_input req = {0};
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
+	struct hwrm_nvm_get_variable_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_VARIABLE, -1, -1);
-	rc = bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val);
-	if (!rc)
-		if (id == BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK)
-			ctx->val.vbool = !ctx->val.vbool;
+	rc = hwrm_req_init(bp, req, HWRM_NVM_GET_VARIABLE);
+	if (rc)
+		return rc;
+
+	rc = bnxt_hwrm_nvm_req(bp, id, req, &ctx->val);
+	if (!rc && id == BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK)
+		ctx->val.vbool = !ctx->val.vbool;
 
 	return rc;
 }
@@ -645,15 +659,18 @@ static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id,
 static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id,
 				 struct devlink_param_gset_ctx *ctx)
 {
-	struct hwrm_nvm_set_variable_input req = {0};
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
+	struct hwrm_nvm_set_variable_input *req;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_SET_VARIABLE, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_NVM_SET_VARIABLE);
+	if (rc)
+		return rc;
 
 	if (id == BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK)
 		ctx->val.vbool = !ctx->val.vbool;
 
-	return bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val);
+	return bnxt_hwrm_nvm_req(bp, id, req, &ctx->val);
 }
 
 static int bnxt_dl_msix_validate(struct devlink *dl, u32 id,
@@ -743,14 +760,17 @@ static void bnxt_dl_params_unregister(struct bnxt *bp)
 
 int bnxt_dl_register(struct bnxt *bp)
 {
+	const struct devlink_ops *devlink_ops;
 	struct devlink_port_attrs attrs = {};
 	struct devlink *dl;
 	int rc;
 
 	if (BNXT_PF(bp))
-		dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
+		devlink_ops = &bnxt_dl_ops;
 	else
-		dl = devlink_alloc(&bnxt_vf_dl_ops, sizeof(struct bnxt_dl));
+		devlink_ops = &bnxt_vf_dl_ops;
+
+	dl = devlink_alloc(devlink_ops, sizeof(struct bnxt_dl), &bp->pdev->dev);
 	if (!dl) {
 		netdev_warn(bp->dev, "devlink_alloc failed\n");
 		return -ENOMEM;
@@ -763,7 +783,7 @@ int bnxt_dl_register(struct bnxt *bp)
 	    bp->hwrm_spec_code > 0x10803)
 		bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
 
-	rc = devlink_register(dl, &bp->pdev->dev);
+	rc = devlink_register(dl);
 	if (rc) {
 		netdev_warn(bp->dev, "devlink_register failed. rc=%d\n", rc);
 		goto err_dl_free;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 786ca51e669b..b056e3c29bbd 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/timecounter.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
+#include "bnxt_hwrm.h"
 #include "bnxt_xdp.h"
 #include "bnxt_ptp.h"
 #include "bnxt_ethtool.h"
@@ -49,7 +50,9 @@ static void bnxt_set_msglevel(struct net_device *dev, u32 value)
 }
 
 static int bnxt_get_coalesce(struct net_device *dev,
-			     struct ethtool_coalesce *coal)
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_coal *hw_coal;
@@ -79,7 +82,9 @@ static int bnxt_get_coalesce(struct net_device *dev,
 }
 
 static int bnxt_set_coalesce(struct net_device *dev,
-			     struct ethtool_coalesce *coal)
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	bool update_stats = false;
@@ -303,6 +308,7 @@ static const char * const bnxt_cmn_sw_stats_str[] = {
 enum {
 	RX_TOTAL_DISCARDS,
 	TX_TOTAL_DISCARDS,
+	RX_NETPOLL_DISCARDS,
 };
 
 static struct {
@@ -311,6 +317,7 @@ static struct {
 } bnxt_sw_func_stats[] = {
 	{0, "rx_total_discard_pkts"},
 	{0, "tx_total_discard_pkts"},
+	{0, "rx_total_netpoll_discards"},
 };
 
 #define NUM_RING_RX_SW_STATS		ARRAY_SIZE(bnxt_rx_sw_stats_str)
@@ -599,6 +606,8 @@ skip_tpa_ring_stats:
 			BNXT_GET_RING_STATS64(sw_stats, rx_discard_pkts);
 		bnxt_sw_func_stats[TX_TOTAL_DISCARDS].counter +=
 			BNXT_GET_RING_STATS64(sw_stats, tx_discard_pkts);
+		bnxt_sw_func_stats[RX_NETPOLL_DISCARDS].counter +=
+			cpr->sw_stats.rx.rx_netpoll_discards;
 	}
 
 	for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++, j++)
@@ -768,8 +777,13 @@ static void bnxt_get_ringparam(struct net_device *dev,
 {
 	struct bnxt *bp = netdev_priv(dev);
 
-	ering->rx_max_pending = BNXT_MAX_RX_DESC_CNT;
-	ering->rx_jumbo_max_pending = BNXT_MAX_RX_JUM_DESC_CNT;
+	if (bp->flags & BNXT_FLAG_AGG_RINGS) {
+		ering->rx_max_pending = BNXT_MAX_RX_DESC_CNT_JUM_ENA;
+		ering->rx_jumbo_max_pending = BNXT_MAX_RX_JUM_DESC_CNT;
+	} else {
+		ering->rx_max_pending = BNXT_MAX_RX_DESC_CNT;
+		ering->rx_jumbo_max_pending = 0;
+	}
 	ering->tx_max_pending = BNXT_MAX_TX_DESC_CNT;
 
 	ering->rx_pending = bp->rx_ring_size;
@@ -1352,7 +1366,7 @@ static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 			  void *_p)
 {
 	struct pcie_ctx_hw_stats *hw_pcie_stats;
-	struct hwrm_pcie_qstats_input req = {0};
+	struct hwrm_pcie_qstats_input *req;
 	struct bnxt *bp = netdev_priv(dev);
 	dma_addr_t hw_pcie_stats_addr;
 	int rc;
@@ -1363,18 +1377,21 @@ static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	if (!(bp->fw_cap & BNXT_FW_CAP_PCIE_STATS_SUPPORTED))
 		return;
 
-	hw_pcie_stats = dma_alloc_coherent(&bp->pdev->dev,
-					   sizeof(*hw_pcie_stats),
-					   &hw_pcie_stats_addr, GFP_KERNEL);
-	if (!hw_pcie_stats)
+	if (hwrm_req_init(bp, req, HWRM_PCIE_QSTATS))
 		return;
 
+	hw_pcie_stats = hwrm_req_dma_slice(bp, req, sizeof(*hw_pcie_stats),
+					   &hw_pcie_stats_addr);
+	if (!hw_pcie_stats) {
+		hwrm_req_drop(bp, req);
+		return;
+	}
+
 	regs->version = 1;
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PCIE_QSTATS, -1, -1);
-	req.pcie_stat_size = cpu_to_le16(sizeof(*hw_pcie_stats));
-	req.pcie_stat_host_addr = cpu_to_le64(hw_pcie_stats_addr);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	hwrm_req_hold(bp, req); /* hold on to slice */
+	req->pcie_stat_size = cpu_to_le16(sizeof(*hw_pcie_stats));
+	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);
@@ -1383,9 +1400,7 @@ static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 		for (i = 0; i < sizeof(*hw_pcie_stats) / sizeof(__le64); i++)
 			dst[i] = le64_to_cpu(src[i]);
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
-	dma_free_coherent(&bp->pdev->dev, sizeof(*hw_pcie_stats), hw_pcie_stats,
-			  hw_pcie_stats_addr);
+	hwrm_req_drop(bp, req);
 }
 
 static void bnxt_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
@@ -1965,7 +1980,7 @@ static u32 bnxt_ethtool_forced_fec_to_fw(struct bnxt_link_info *link_info,
 static int bnxt_set_fecparam(struct net_device *dev,
 			     struct ethtool_fecparam *fecparam)
 {
-	struct hwrm_port_phy_cfg_input req = {0};
+	struct hwrm_port_phy_cfg_input *req;
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_link_info *link_info;
 	u32 new_cfg, fec = fecparam->fec;
@@ -1997,9 +2012,11 @@ static int bnxt_set_fecparam(struct net_device *dev,
 	}
 
 apply_fec:
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_CFG, -1, -1);
-	req.flags = cpu_to_le32(new_cfg | PORT_PHY_CFG_REQ_FLAGS_RESET_PHY);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_CFG);
+	if (rc)
+		return rc;
+	req->flags = cpu_to_le32(new_cfg | PORT_PHY_CFG_REQ_FLAGS_RESET_PHY);
+	rc = hwrm_req_send(bp, req);
 	/* update current settings */
 	if (!rc) {
 		mutex_lock(&bp->link_lock);
@@ -2093,19 +2110,22 @@ static u32 bnxt_get_link(struct net_device *dev)
 int bnxt_hwrm_nvm_get_dev_info(struct bnxt *bp,
 			       struct hwrm_nvm_get_dev_info_output *nvm_dev_info)
 {
-	struct hwrm_nvm_get_dev_info_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_nvm_get_dev_info_input req = {0};
+	struct hwrm_nvm_get_dev_info_output *resp;
+	struct hwrm_nvm_get_dev_info_input *req;
 	int rc;
 
 	if (BNXT_VF(bp))
 		return -EOPNOTSUPP;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_DEV_INFO, -1, -1);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_NVM_GET_DEV_INFO);
+	if (rc)
+		return rc;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc)
 		memcpy(nvm_dev_info, resp, sizeof(*resp));
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -2118,77 +2138,67 @@ static int bnxt_find_nvram_item(struct net_device *dev, u16 type, u16 ordinal,
 				u16 ext, u16 *index, u32 *item_length,
 				u32 *data_length);
 
-static int __bnxt_flash_nvram(struct net_device *dev, u16 dir_type,
-			      u16 dir_ordinal, u16 dir_ext, u16 dir_attr,
-			      u32 dir_item_len, const u8 *data,
-			      size_t data_len)
+static int bnxt_flash_nvram(struct net_device *dev, u16 dir_type,
+			    u16 dir_ordinal, u16 dir_ext, u16 dir_attr,
+			    u32 dir_item_len, const u8 *data,
+			    size_t data_len)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	struct hwrm_nvm_write_input *req;
 	int rc;
-	struct hwrm_nvm_write_input req = {0};
-	dma_addr_t dma_handle;
-	u8 *kmem = NULL;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_WRITE, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_NVM_WRITE);
+	if (rc)
+		return rc;
 
-	req.dir_type = cpu_to_le16(dir_type);
-	req.dir_ordinal = cpu_to_le16(dir_ordinal);
-	req.dir_ext = cpu_to_le16(dir_ext);
-	req.dir_attr = cpu_to_le16(dir_attr);
-	req.dir_item_length = cpu_to_le32(dir_item_len);
 	if (data_len && data) {
-		req.dir_data_length = cpu_to_le32(data_len);
+		dma_addr_t dma_handle;
+		u8 *kmem;
 
-		kmem = dma_alloc_coherent(&bp->pdev->dev, data_len, &dma_handle,
-					  GFP_KERNEL);
-		if (!kmem)
+		kmem = hwrm_req_dma_slice(bp, req, data_len, &dma_handle);
+		if (!kmem) {
+			hwrm_req_drop(bp, req);
 			return -ENOMEM;
+		}
+
+		req->dir_data_length = cpu_to_le32(data_len);
 
 		memcpy(kmem, data, data_len);
-		req.host_src_addr = cpu_to_le64(dma_handle);
+		req->host_src_addr = cpu_to_le64(dma_handle);
 	}
 
-	rc = _hwrm_send_message(bp, &req, sizeof(req), FLASH_NVRAM_TIMEOUT);
-	if (kmem)
-		dma_free_coherent(&bp->pdev->dev, data_len, kmem, dma_handle);
+	hwrm_req_timeout(bp, req, FLASH_NVRAM_TIMEOUT);
+	req->dir_type = cpu_to_le16(dir_type);
+	req->dir_ordinal = cpu_to_le16(dir_ordinal);
+	req->dir_ext = cpu_to_le16(dir_ext);
+	req->dir_attr = cpu_to_le16(dir_attr);
+	req->dir_item_length = cpu_to_le32(dir_item_len);
+	rc = hwrm_req_send(bp, req);
 
 	if (rc == -EACCES)
 		bnxt_print_admin_err(bp);
 	return rc;
 }
 
-static int bnxt_flash_nvram(struct net_device *dev, u16 dir_type,
-			    u16 dir_ordinal, u16 dir_ext, u16 dir_attr,
-			    const u8 *data, size_t data_len)
-{
-	struct bnxt *bp = netdev_priv(dev);
-	int rc;
-
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = __bnxt_flash_nvram(dev, dir_type, dir_ordinal, dir_ext, dir_attr,
-				0, data, data_len);
-	mutex_unlock(&bp->hwrm_cmd_lock);
-	return rc;
-}
-
 static int bnxt_hwrm_firmware_reset(struct net_device *dev, u8 proc_type,
 				    u8 self_reset, u8 flags)
 {
-	struct hwrm_fw_reset_input req = {0};
 	struct bnxt *bp = netdev_priv(dev);
+	struct hwrm_fw_reset_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FW_RESET, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_FW_RESET);
+	if (rc)
+		return rc;
 
-	req.embedded_proc_type = proc_type;
-	req.selfrst_status = self_reset;
-	req.flags = flags;
+	req->embedded_proc_type = proc_type;
+	req->selfrst_status = self_reset;
+	req->flags = flags;
 
 	if (proc_type == FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP) {
-		rc = hwrm_send_message_silent(bp, &req, sizeof(req),
-					      HWRM_CMD_TIMEOUT);
+		rc = hwrm_req_send_silent(bp, req);
 	} else {
-		rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		rc = hwrm_req_send(bp, req);
 		if (rc == -EACCES)
 			bnxt_print_admin_err(bp);
 	}
@@ -2326,7 +2336,7 @@ static int bnxt_flash_firmware(struct net_device *dev,
 		return -EINVAL;
 	}
 	rc = bnxt_flash_nvram(dev, dir_type, BNX_DIR_ORDINAL_FIRST,
-			      0, 0, fw_data, fw_size);
+			      0, 0, 0, fw_data, fw_size);
 	if (rc == 0)	/* Firmware update successful */
 		rc = bnxt_firmware_reset(dev, dir_type);
 
@@ -2379,7 +2389,7 @@ static int bnxt_flash_microcode(struct net_device *dev,
 		return -EINVAL;
 	}
 	rc = bnxt_flash_nvram(dev, dir_type, BNX_DIR_ORDINAL_FIRST,
-			      0, 0, fw_data, fw_size);
+			      0, 0, 0, fw_data, fw_size);
 
 	return rc;
 }
@@ -2445,7 +2455,7 @@ static int bnxt_flash_firmware_from_file(struct net_device *dev,
 		rc = bnxt_flash_microcode(dev, dir_type, fw->data, fw->size);
 	else
 		rc = bnxt_flash_nvram(dev, dir_type, BNX_DIR_ORDINAL_FIRST,
-				      0, 0, fw->data, fw->size);
+				      0, 0, 0, fw->data, fw->size);
 	release_firmware(fw);
 	return rc;
 }
@@ -2457,21 +2467,23 @@ static int bnxt_flash_firmware_from_file(struct net_device *dev,
 int bnxt_flash_package_from_fw_obj(struct net_device *dev, const struct firmware *fw,
 				   u32 install_type)
 {
-	struct hwrm_nvm_install_update_input install = {0};
-	struct hwrm_nvm_install_update_output resp = {0};
-	struct hwrm_nvm_modify_input modify = {0};
+	struct hwrm_nvm_install_update_input *install;
+	struct hwrm_nvm_install_update_output *resp;
+	struct hwrm_nvm_modify_input *modify;
 	struct bnxt *bp = netdev_priv(dev);
 	bool defrag_attempted = false;
 	dma_addr_t dma_handle;
 	u8 *kmem = NULL;
 	u32 modify_len;
 	u32 item_len;
-	int rc = 0;
 	u16 index;
+	int rc;
 
 	bnxt_hwrm_fw_set_time(bp);
 
-	bnxt_hwrm_cmd_hdr_init(bp, &modify, HWRM_NVM_MODIFY, -1, -1);
+	rc = hwrm_req_init(bp, modify, HWRM_NVM_MODIFY);
+	if (rc)
+		return rc;
 
 	/* Try allocating a large DMA buffer first.  Older fw will
 	 * cause excessive NVRAM erases when using small blocks.
@@ -2479,22 +2491,33 @@ int bnxt_flash_package_from_fw_obj(struct net_device *dev, const struct firmware
 	modify_len = roundup_pow_of_two(fw->size);
 	modify_len = min_t(u32, modify_len, BNXT_PKG_DMA_SIZE);
 	while (1) {
-		kmem = dma_alloc_coherent(&bp->pdev->dev, modify_len,
-					  &dma_handle, GFP_KERNEL);
+		kmem = hwrm_req_dma_slice(bp, modify, modify_len, &dma_handle);
 		if (!kmem && modify_len > PAGE_SIZE)
 			modify_len /= 2;
 		else
 			break;
 	}
-	if (!kmem)
+	if (!kmem) {
+		hwrm_req_drop(bp, modify);
 		return -ENOMEM;
+	}
 
-	modify.host_src_addr = cpu_to_le64(dma_handle);
+	rc = hwrm_req_init(bp, install, HWRM_NVM_INSTALL_UPDATE);
+	if (rc) {
+		hwrm_req_drop(bp, modify);
+		return rc;
+	}
 
-	bnxt_hwrm_cmd_hdr_init(bp, &install, HWRM_NVM_INSTALL_UPDATE, -1, -1);
+	hwrm_req_timeout(bp, modify, FLASH_PACKAGE_TIMEOUT);
+	hwrm_req_timeout(bp, install, INSTALL_PACKAGE_TIMEOUT);
+
+	hwrm_req_hold(bp, modify);
+	modify->host_src_addr = cpu_to_le64(dma_handle);
+
+	resp = hwrm_req_hold(bp, install);
 	if ((install_type & 0xffff) == 0)
 		install_type >>= 16;
-	install.install_type = cpu_to_le32(install_type);
+	install->install_type = cpu_to_le32(install_type);
 
 	do {
 		u32 copied = 0, len = modify_len;
@@ -2514,76 +2537,69 @@ int bnxt_flash_package_from_fw_obj(struct net_device *dev, const struct firmware
 			break;
 		}
 
-		modify.dir_idx = cpu_to_le16(index);
+		modify->dir_idx = cpu_to_le16(index);
 
 		if (fw->size > modify_len)
-			modify.flags = BNXT_NVM_MORE_FLAG;
+			modify->flags = BNXT_NVM_MORE_FLAG;
 		while (copied < fw->size) {
 			u32 balance = fw->size - copied;
 
 			if (balance <= modify_len) {
 				len = balance;
 				if (copied)
-					modify.flags |= BNXT_NVM_LAST_FLAG;
+					modify->flags |= BNXT_NVM_LAST_FLAG;
 			}
 			memcpy(kmem, fw->data + copied, len);
-			modify.len = cpu_to_le32(len);
-			modify.offset = cpu_to_le32(copied);
-			rc = hwrm_send_message(bp, &modify, sizeof(modify),
-					       FLASH_PACKAGE_TIMEOUT);
+			modify->len = cpu_to_le32(len);
+			modify->offset = cpu_to_le32(copied);
+			rc = hwrm_req_send(bp, modify);
 			if (rc)
 				goto pkg_abort;
 			copied += len;
 		}
-		mutex_lock(&bp->hwrm_cmd_lock);
-		rc = _hwrm_send_message_silent(bp, &install, sizeof(install),
-					       INSTALL_PACKAGE_TIMEOUT);
-		memcpy(&resp, bp->hwrm_cmd_resp_addr, sizeof(resp));
+
+		rc = hwrm_req_send_silent(bp, install);
 
 		if (defrag_attempted) {
 			/* We have tried to defragment already in the previous
 			 * iteration. Return with the result for INSTALL_UPDATE
 			 */
-			mutex_unlock(&bp->hwrm_cmd_lock);
 			break;
 		}
 
-		if (rc && ((struct hwrm_err_output *)&resp)->cmd_err ==
+		if (rc && ((struct hwrm_err_output *)resp)->cmd_err ==
 		    NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
-			install.flags =
+			install->flags =
 				cpu_to_le16(NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG);
 
-			rc = _hwrm_send_message_silent(bp, &install,
-						       sizeof(install),
-						       INSTALL_PACKAGE_TIMEOUT);
-			memcpy(&resp, bp->hwrm_cmd_resp_addr, sizeof(resp));
+			rc = hwrm_req_send_silent(bp, install);
 
-			if (rc && ((struct hwrm_err_output *)&resp)->cmd_err ==
+			if (rc && ((struct hwrm_err_output *)resp)->cmd_err ==
 			    NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_SPACE) {
 				/* FW has cleared NVM area, driver will create
 				 * UPDATE directory and try the flash again
 				 */
 				defrag_attempted = true;
-				install.flags = 0;
-				rc = __bnxt_flash_nvram(bp->dev,
-							BNX_DIR_TYPE_UPDATE,
-							BNX_DIR_ORDINAL_FIRST,
-							0, 0, item_len, NULL,
-							0);
+				install->flags = 0;
+				rc = bnxt_flash_nvram(bp->dev,
+						      BNX_DIR_TYPE_UPDATE,
+						      BNX_DIR_ORDINAL_FIRST,
+						      0, 0, item_len, NULL, 0);
 			} else if (rc) {
 				netdev_err(dev, "HWRM_NVM_INSTALL_UPDATE failure rc :%x\n", rc);
 			}
 		} else if (rc) {
 			netdev_err(dev, "HWRM_NVM_INSTALL_UPDATE failure rc :%x\n", rc);
 		}
-		mutex_unlock(&bp->hwrm_cmd_lock);
 	} while (defrag_attempted && !rc);
 
 pkg_abort:
-	dma_free_coherent(&bp->pdev->dev, modify_len, kmem, dma_handle);
-	if (resp.result) {
+	hwrm_req_drop(bp, modify);
+	hwrm_req_drop(bp, install);
+
+	if (resp->result) {
 		netdev_err(dev, "PKG install error = %d, problem_item = %d\n",
-			   (s8)resp.result, (int)resp.problem_item);
+			   (s8)resp->result, (int)resp->problem_item);
 		rc = -ENOPKG;
 	}
 	if (rc == -EACCES)
@@ -2629,20 +2645,22 @@ static int bnxt_flash_device(struct net_device *dev,
 
 static int nvm_get_dir_info(struct net_device *dev, u32 *entries, u32 *length)
 {
+	struct hwrm_nvm_get_dir_info_output *output;
+	struct hwrm_nvm_get_dir_info_input *req;
 	struct bnxt *bp = netdev_priv(dev);
 	int rc;
-	struct hwrm_nvm_get_dir_info_input req = {0};
-	struct hwrm_nvm_get_dir_info_output *output = bp->hwrm_cmd_resp_addr;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_DIR_INFO, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_NVM_GET_DIR_INFO);
+	if (rc)
+		return rc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	output = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc) {
 		*entries = le32_to_cpu(output->entries);
 		*length = le32_to_cpu(output->entry_length);
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -2668,7 +2686,7 @@ static int bnxt_get_nvram_directory(struct net_device *dev, u32 len, u8 *data)
 	u8 *buf;
 	size_t buflen;
 	dma_addr_t dma_handle;
-	struct hwrm_nvm_get_dir_entries_input req = {0};
+	struct hwrm_nvm_get_dir_entries_input *req;
 
 	rc = nvm_get_dir_info(dev, &dir_entries, &entry_length);
 	if (rc != 0)
@@ -2686,20 +2704,23 @@ static int bnxt_get_nvram_directory(struct net_device *dev, u32 len, u8 *data)
 	len -= 2;
 	memset(data, 0xff, len);
 
+	rc = hwrm_req_init(bp, req, HWRM_NVM_GET_DIR_ENTRIES);
+	if (rc)
+		return rc;
+
 	buflen = dir_entries * entry_length;
-	buf = dma_alloc_coherent(&bp->pdev->dev, buflen, &dma_handle,
-				 GFP_KERNEL);
+	buf = hwrm_req_dma_slice(bp, req, buflen, &dma_handle);
 	if (!buf) {
-		netdev_err(dev, "dma_alloc_coherent failure, length = %u\n",
-			   (unsigned)buflen);
+		hwrm_req_drop(bp, req);
 		return -ENOMEM;
 	}
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_DIR_ENTRIES, -1, -1);
-	req.host_dest_addr = cpu_to_le64(dma_handle);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req->host_dest_addr = cpu_to_le64(dma_handle);
+
+	hwrm_req_hold(bp, req); /* hold the slice */
+	rc = hwrm_req_send(bp, req);
 	if (rc == 0)
 		memcpy(data, buf, len > buflen ? buflen : len);
-	dma_free_coherent(&bp->pdev->dev, buflen, buf, dma_handle);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -2710,28 +2731,31 @@ static int bnxt_get_nvram_item(struct net_device *dev, u32 index, u32 offset,
 	int rc;
 	u8 *buf;
 	dma_addr_t dma_handle;
-	struct hwrm_nvm_read_input req = {0};
+	struct hwrm_nvm_read_input *req;
 
 	if (!length)
 		return -EINVAL;
 
-	buf = dma_alloc_coherent(&bp->pdev->dev, length, &dma_handle,
-				 GFP_KERNEL);
+	rc = hwrm_req_init(bp, req, HWRM_NVM_READ);
+	if (rc)
+		return rc;
+
+	buf = hwrm_req_dma_slice(bp, req, length, &dma_handle);
 	if (!buf) {
-		netdev_err(dev, "dma_alloc_coherent failure, length = %u\n",
-			   (unsigned)length);
+		hwrm_req_drop(bp, req);
 		return -ENOMEM;
 	}
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_READ, -1, -1);
-	req.host_dest_addr = cpu_to_le64(dma_handle);
-	req.dir_idx = cpu_to_le16(index);
-	req.offset = cpu_to_le32(offset);
-	req.len = cpu_to_le32(length);
 
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req->host_dest_addr = cpu_to_le64(dma_handle);
+	req->dir_idx = cpu_to_le16(index);
+	req->offset = cpu_to_le32(offset);
+	req->len = cpu_to_le32(length);
+
+	hwrm_req_hold(bp, req); /* hold the slice */
+	rc = hwrm_req_send(bp, req);
 	if (rc == 0)
 		memcpy(data, buf, length);
-	dma_free_coherent(&bp->pdev->dev, length, buf, dma_handle);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -2739,20 +2763,23 @@ static int bnxt_find_nvram_item(struct net_device *dev, u16 type, u16 ordinal,
 				u16 ext, u16 *index, u32 *item_length,
 				u32 *data_length)
 {
+	struct hwrm_nvm_find_dir_entry_output *output;
+	struct hwrm_nvm_find_dir_entry_input *req;
 	struct bnxt *bp = netdev_priv(dev);
 	int rc;
-	struct hwrm_nvm_find_dir_entry_input req = {0};
-	struct hwrm_nvm_find_dir_entry_output *output = bp->hwrm_cmd_resp_addr;
-
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_FIND_DIR_ENTRY, -1, -1);
-	req.enables = 0;
-	req.dir_idx = 0;
-	req.dir_type = cpu_to_le16(type);
-	req.dir_ordinal = cpu_to_le16(ordinal);
-	req.dir_ext = cpu_to_le16(ext);
-	req.opt_ordinal = NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_EQ;
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+
+	rc = hwrm_req_init(bp, req, HWRM_NVM_FIND_DIR_ENTRY);
+	if (rc)
+		return rc;
+
+	req->enables = 0;
+	req->dir_idx = 0;
+	req->dir_type = cpu_to_le16(type);
+	req->dir_ordinal = cpu_to_le16(ordinal);
+	req->dir_ext = cpu_to_le16(ext);
+	req->opt_ordinal = NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_EQ;
+	output = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
 	if (rc == 0) {
 		if (index)
 			*index = le16_to_cpu(output->dir_idx);
@@ -2761,7 +2788,7 @@ static int bnxt_find_nvram_item(struct net_device *dev, u16 type, u16 ordinal,
 		if (data_length)
 			*data_length = le32_to_cpu(output->dir_data_length);
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -2856,12 +2883,16 @@ static int bnxt_get_eeprom(struct net_device *dev,
 
 static int bnxt_erase_nvram_directory(struct net_device *dev, u8 index)
 {
+	struct hwrm_nvm_erase_dir_entry_input *req;
 	struct bnxt *bp = netdev_priv(dev);
-	struct hwrm_nvm_erase_dir_entry_input req = {0};
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_ERASE_DIR_ENTRY, -1, -1);
-	req.dir_idx = cpu_to_le16(index);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_NVM_ERASE_DIR_ENTRY);
+	if (rc)
+		return rc;
+
+	req->dir_idx = cpu_to_le16(index);
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_set_eeprom(struct net_device *dev,
@@ -2901,7 +2932,7 @@ static int bnxt_set_eeprom(struct net_device *dev,
 	ordinal = eeprom->offset >> 16;
 	attr = eeprom->offset & 0xffff;
 
-	return bnxt_flash_nvram(dev, type, ordinal, ext, attr, data,
+	return bnxt_flash_nvram(dev, type, ordinal, ext, attr, 0, data,
 				eeprom->len);
 }
 
@@ -2989,31 +3020,33 @@ static int bnxt_read_sfp_module_eeprom_info(struct bnxt *bp, u16 i2c_addr,
 					    u16 page_number, u16 start_addr,
 					    u16 data_length, u8 *buf)
 {
-	struct hwrm_port_phy_i2c_read_input req = {0};
-	struct hwrm_port_phy_i2c_read_output *output = bp->hwrm_cmd_resp_addr;
+	struct hwrm_port_phy_i2c_read_output *output;
+	struct hwrm_port_phy_i2c_read_input *req;
 	int rc, byte_offset = 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_I2C_READ, -1, -1);
-	req.i2c_slave_addr = i2c_addr;
-	req.page_number = cpu_to_le16(page_number);
-	req.port_id = cpu_to_le16(bp->pf.port_id);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_I2C_READ);
+	if (rc)
+		return rc;
+
+	output = hwrm_req_hold(bp, req);
+	req->i2c_slave_addr = i2c_addr;
+	req->page_number = cpu_to_le16(page_number);
+	req->port_id = cpu_to_le16(bp->pf.port_id);
 	do {
 		u16 xfer_size;
 
 		xfer_size = min_t(u16, data_length, BNXT_MAX_PHY_I2C_RESP_SIZE);
 		data_length -= xfer_size;
-		req.page_offset = cpu_to_le16(start_addr + byte_offset);
-		req.data_length = xfer_size;
-		req.enables = cpu_to_le32(start_addr + byte_offset ?
+		req->page_offset = cpu_to_le16(start_addr + byte_offset);
+		req->data_length = xfer_size;
+		req->enables = cpu_to_le32(start_addr + byte_offset ?
 				 PORT_PHY_I2C_READ_REQ_ENABLES_PAGE_OFFSET : 0);
-		mutex_lock(&bp->hwrm_cmd_lock);
-		rc = _hwrm_send_message(bp, &req, sizeof(req),
-					HWRM_CMD_TIMEOUT);
+		rc = hwrm_req_send(bp, req);
 		if (!rc)
 			memcpy(buf + byte_offset, output->data, xfer_size);
-		mutex_unlock(&bp->hwrm_cmd_lock);
 		byte_offset += xfer_size;
 	} while (!rc && data_length > 0);
+	hwrm_req_drop(bp, req);
 
 	return rc;
 }
@@ -3122,13 +3155,13 @@ static int bnxt_nway_reset(struct net_device *dev)
 static int bnxt_set_phys_id(struct net_device *dev,
 			    enum ethtool_phys_id_state state)
 {
-	struct hwrm_port_led_cfg_input req = {0};
+	struct hwrm_port_led_cfg_input *req;
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_pf_info *pf = &bp->pf;
 	struct bnxt_led_cfg *led_cfg;
 	u8 led_state;
 	__le16 duration;
-	int i;
+	int rc, i;
 
 	if (!bp->num_leds || BNXT_VF(bp))
 		return -EOPNOTSUPP;
@@ -3142,27 +3175,35 @@ static int bnxt_set_phys_id(struct net_device *dev,
 	} else {
 		return -EINVAL;
 	}
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_LED_CFG, -1, -1);
-	req.port_id = cpu_to_le16(pf->port_id);
-	req.num_leds = bp->num_leds;
-	led_cfg = (struct bnxt_led_cfg *)&req.led0_id;
+	rc = hwrm_req_init(bp, req, HWRM_PORT_LED_CFG);
+	if (rc)
+		return rc;
+
+	req->port_id = cpu_to_le16(pf->port_id);
+	req->num_leds = bp->num_leds;
+	led_cfg = (struct bnxt_led_cfg *)&req->led0_id;
 	for (i = 0; i < bp->num_leds; i++, led_cfg++) {
-		req.enables |= BNXT_LED_DFLT_ENABLES(i);
+		req->enables |= BNXT_LED_DFLT_ENABLES(i);
 		led_cfg->led_id = bp->leds[i].led_id;
 		led_cfg->led_state = led_state;
 		led_cfg->led_blink_on = duration;
 		led_cfg->led_blink_off = duration;
 		led_cfg->led_group_id = bp->leds[i].led_group_id;
 	}
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_hwrm_selftest_irq(struct bnxt *bp, u16 cmpl_ring)
 {
-	struct hwrm_selftest_irq_input req = {0};
+	struct hwrm_selftest_irq_input *req;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_SELFTEST_IRQ);
+	if (rc)
+		return rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_IRQ, cmpl_ring, -1);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req->cmpl_ring = cpu_to_le16(cmpl_ring);
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_test_irq(struct bnxt *bp)
@@ -3182,31 +3223,37 @@ static int bnxt_test_irq(struct bnxt *bp)
 
 static int bnxt_hwrm_mac_loopback(struct bnxt *bp, bool enable)
 {
-	struct hwrm_port_mac_cfg_input req = {0};
+	struct hwrm_port_mac_cfg_input *req;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_MAC_CFG, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_MAC_CFG);
+	if (rc)
+		return rc;
 
-	req.enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_LPBK);
+	req->enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_LPBK);
 	if (enable)
-		req.lpbk = PORT_MAC_CFG_REQ_LPBK_LOCAL;
+		req->lpbk = PORT_MAC_CFG_REQ_LPBK_LOCAL;
 	else
-		req.lpbk = PORT_MAC_CFG_REQ_LPBK_NONE;
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		req->lpbk = PORT_MAC_CFG_REQ_LPBK_NONE;
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_query_force_speeds(struct bnxt *bp, u16 *force_speeds)
 {
-	struct hwrm_port_phy_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_port_phy_qcaps_input req = {0};
+	struct hwrm_port_phy_qcaps_output *resp;
+	struct hwrm_port_phy_qcaps_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_QCAPS, -1, -1);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_QCAPS);
+	if (rc)
+		return rc;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc)
 		*force_speeds = le16_to_cpu(resp->supported_speeds_force_mode);
 
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -3241,7 +3288,7 @@ static int bnxt_disable_an_for_lpbk(struct bnxt *bp,
 	req->force_link_speed = cpu_to_le16(fw_speed);
 	req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE |
 				  PORT_PHY_CFG_REQ_FLAGS_RESET_PHY);
-	rc = hwrm_send_message(bp, req, sizeof(*req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_send(bp, req);
 	req->flags = 0;
 	req->force_link_speed = cpu_to_le16(0);
 	return rc;
@@ -3249,21 +3296,29 @@ static int bnxt_disable_an_for_lpbk(struct bnxt *bp,
 
 static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable, bool ext)
 {
-	struct hwrm_port_phy_cfg_input req = {0};
+	struct hwrm_port_phy_cfg_input *req;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_CFG);
+	if (rc)
+		return rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_CFG, -1, -1);
+	/* prevent bnxt_disable_an_for_lpbk() from consuming the request */
+	hwrm_req_hold(bp, req);
 
 	if (enable) {
-		bnxt_disable_an_for_lpbk(bp, &req);
+		bnxt_disable_an_for_lpbk(bp, req);
 		if (ext)
-			req.lpbk = PORT_PHY_CFG_REQ_LPBK_EXTERNAL;
+			req->lpbk = PORT_PHY_CFG_REQ_LPBK_EXTERNAL;
 		else
-			req.lpbk = PORT_PHY_CFG_REQ_LPBK_LOCAL;
+			req->lpbk = PORT_PHY_CFG_REQ_LPBK_LOCAL;
 	} else {
-		req.lpbk = PORT_PHY_CFG_REQ_LPBK_NONE;
+		req->lpbk = PORT_PHY_CFG_REQ_LPBK_NONE;
 	}
-	req.enables = cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_LPBK);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req->enables = cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_LPBK);
+	rc = hwrm_req_send(bp, req);
+	hwrm_req_drop(bp, req);
+	return rc;
 }
 
 static int bnxt_rx_loopback(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
@@ -3361,7 +3416,7 @@ static int bnxt_run_loopback(struct bnxt *bp)
 		data[i] = (u8)(i & 0xff);
 
 	map = dma_map_single(&bp->pdev->dev, skb->data, pkt_size,
-			     PCI_DMA_TODEVICE);
+			     DMA_TO_DEVICE);
 	if (dma_mapping_error(&bp->pdev->dev, map)) {
 		dev_kfree_skb(skb);
 		return -EIO;
@@ -3374,24 +3429,28 @@ static int bnxt_run_loopback(struct bnxt *bp)
 	bnxt_db_write(bp, &txr->tx_db, txr->tx_prod);
 	rc = bnxt_poll_loopback(bp, cpr, pkt_size);
 
-	dma_unmap_single(&bp->pdev->dev, map, pkt_size, PCI_DMA_TODEVICE);
+	dma_unmap_single(&bp->pdev->dev, map, pkt_size, DMA_TO_DEVICE);
 	dev_kfree_skb(skb);
 	return rc;
 }
 
 static int bnxt_run_fw_tests(struct bnxt *bp, u8 test_mask, u8 *test_results)
 {
-	struct hwrm_selftest_exec_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_selftest_exec_input req = {0};
+	struct hwrm_selftest_exec_output *resp;
+	struct hwrm_selftest_exec_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_EXEC, -1, -1);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	resp->test_success = 0;
-	req.flags = test_mask;
-	rc = _hwrm_send_message(bp, &req, sizeof(req), bp->test_info->timeout);
+	rc = hwrm_req_init(bp, req, HWRM_SELFTEST_EXEC);
+	if (rc)
+		return rc;
+
+	hwrm_req_timeout(bp, req, bp->test_info->timeout);
+	req->flags = test_mask;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	*test_results = resp->test_success;
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -3550,32 +3609,34 @@ static int bnxt_reset(struct net_device *dev, u32 *flags)
 	return 0;
 }
 
-static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg, int msg_len,
+static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg,
 				  struct bnxt_hwrm_dbg_dma_info *info)
 {
-	struct hwrm_dbg_cmn_output *cmn_resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_dbg_cmn_input *cmn_req = msg;
 	__le16 *seq_ptr = msg + info->seq_off;
+	struct hwrm_dbg_cmn_output *cmn_resp;
 	u16 seq = 0, len, segs_off;
-	void *resp = cmn_resp;
 	dma_addr_t dma_handle;
+	void *dma_buf, *resp;
 	int rc, off = 0;
-	void *dma_buf;
 
-	dma_buf = dma_alloc_coherent(&bp->pdev->dev, info->dma_len, &dma_handle,
-				     GFP_KERNEL);
-	if (!dma_buf)
+	dma_buf = hwrm_req_dma_slice(bp, msg, info->dma_len, &dma_handle);
+	if (!dma_buf) {
+		hwrm_req_drop(bp, msg);
 		return -ENOMEM;
+	}
+
+	hwrm_req_timeout(bp, msg, HWRM_COREDUMP_TIMEOUT);
+	cmn_resp = hwrm_req_hold(bp, msg);
+	resp = cmn_resp;
 
 	segs_off = offsetof(struct hwrm_dbg_coredump_list_output,
 			    total_segments);
 	cmn_req->host_dest_addr = cpu_to_le64(dma_handle);
 	cmn_req->host_buf_len = cpu_to_le32(info->dma_len);
-	mutex_lock(&bp->hwrm_cmd_lock);
 	while (1) {
 		*seq_ptr = cpu_to_le16(seq);
-		rc = _hwrm_send_message(bp, msg, msg_len,
-					HWRM_COREDUMP_TIMEOUT);
+		rc = hwrm_req_send(bp, msg);
 		if (rc)
 			break;
 
@@ -3619,26 +3680,27 @@ static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg, int msg_len,
 		seq++;
 		off += len;
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
-	dma_free_coherent(&bp->pdev->dev, info->dma_len, dma_buf, dma_handle);
+	hwrm_req_drop(bp, msg);
 	return rc;
 }
 
 static int bnxt_hwrm_dbg_coredump_list(struct bnxt *bp,
 				       struct bnxt_coredump *coredump)
 {
-	struct hwrm_dbg_coredump_list_input req = {0};
 	struct bnxt_hwrm_dbg_dma_info info = {NULL};
+	struct hwrm_dbg_coredump_list_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_COREDUMP_LIST, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_DBG_COREDUMP_LIST);
+	if (rc)
+		return rc;
 
 	info.dma_len = COREDUMP_LIST_BUF_LEN;
 	info.seq_off = offsetof(struct hwrm_dbg_coredump_list_input, seq_no);
 	info.data_len_off = offsetof(struct hwrm_dbg_coredump_list_output,
 				     data_len);
 
-	rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info);
+	rc = bnxt_hwrm_dbg_dma_data(bp, req, &info);
 	if (!rc) {
 		coredump->data = info.dest_buf;
 		coredump->data_size = info.dest_buf_size;
@@ -3650,26 +3712,34 @@ static int bnxt_hwrm_dbg_coredump_list(struct bnxt *bp,
 static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id,
 					   u16 segment_id)
 {
-	struct hwrm_dbg_coredump_initiate_input req = {0};
+	struct hwrm_dbg_coredump_initiate_input *req;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_DBG_COREDUMP_INITIATE);
+	if (rc)
+		return rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_COREDUMP_INITIATE, -1, -1);
-	req.component_id = cpu_to_le16(component_id);
-	req.segment_id = cpu_to_le16(segment_id);
+	hwrm_req_timeout(bp, req, HWRM_COREDUMP_TIMEOUT);
+	req->component_id = cpu_to_le16(component_id);
+	req->segment_id = cpu_to_le16(segment_id);
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_COREDUMP_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
 static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id,
 					   u16 segment_id, u32 *seg_len,
 					   void *buf, u32 buf_len, u32 offset)
 {
-	struct hwrm_dbg_coredump_retrieve_input req = {0};
+	struct hwrm_dbg_coredump_retrieve_input *req;
 	struct bnxt_hwrm_dbg_dma_info info = {NULL};
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_COREDUMP_RETRIEVE, -1, -1);
-	req.component_id = cpu_to_le16(component_id);
-	req.segment_id = cpu_to_le16(segment_id);
+	rc = hwrm_req_init(bp, req, HWRM_DBG_COREDUMP_RETRIEVE);
+	if (rc)
+		return rc;
+
+	req->component_id = cpu_to_le16(component_id);
+	req->segment_id = cpu_to_le16(segment_id);
 
 	info.dma_len = COREDUMP_RETRIEVE_BUF_LEN;
 	info.seq_off = offsetof(struct hwrm_dbg_coredump_retrieve_input,
@@ -3682,7 +3752,7 @@ static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id,
 		info.seg_start = offset;
 	}
 
-	rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info);
+	rc = bnxt_hwrm_dbg_dma_data(bp, req, &info);
 	if (!rc)
 		*seg_len = info.dest_buf_size;
 
@@ -3961,8 +4031,8 @@ static int bnxt_get_ts_info(struct net_device *dev,
 
 void bnxt_ethtool_init(struct bnxt *bp)
 {
-	struct hwrm_selftest_qlist_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_selftest_qlist_input req = {0};
+	struct hwrm_selftest_qlist_output *resp;
+	struct hwrm_selftest_qlist_input *req;
 	struct bnxt_test_info *test_info;
 	struct net_device *dev = bp->dev;
 	int i, rc;
@@ -3974,19 +4044,22 @@ void bnxt_ethtool_init(struct bnxt *bp)
 	if (bp->hwrm_spec_code < 0x10704 || !BNXT_PF(bp))
 		return;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_QLIST, -1, -1);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
-		goto ethtool_init_exit;
-
 	test_info = bp->test_info;
-	if (!test_info)
+	if (!test_info) {
 		test_info = kzalloc(sizeof(*bp->test_info), GFP_KERNEL);
-	if (!test_info)
+		if (!test_info)
+			return;
+		bp->test_info = test_info;
+	}
+
+	if (hwrm_req_init(bp, req, HWRM_SELFTEST_QLIST))
+		return;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
+	if (rc)
 		goto ethtool_init_exit;
 
-	bp->test_info = test_info;
 	bp->num_tests = resp->num_tests + BNXT_DRV_TESTS;
 	if (bp->num_tests > BNXT_MAX_TEST)
 		bp->num_tests = BNXT_MAX_TEST;
@@ -4020,7 +4093,7 @@ void bnxt_ethtool_init(struct bnxt *bp)
 	}
 
 ethtool_init_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 }
 
 static void bnxt_get_eth_phy_stats(struct net_device *dev,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
new file mode 100644
index 000000000000..acef61abe35d
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
@@ -0,0 +1,763 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2020 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#include <asm/byteorder.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/errno.h>
+#include <linux/ethtool.h>
+#include <linux/if_ether.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/pci.h>
+#include <linux/skbuff.h>
+
+#include "bnxt_hsi.h"
+#include "bnxt.h"
+#include "bnxt_hwrm.h"
+
+static u64 hwrm_calc_sentinel(struct bnxt_hwrm_ctx *ctx, u16 req_type)
+{
+	return (((uintptr_t)ctx) + req_type) ^ BNXT_HWRM_SENTINEL;
+}
+
+/**
+ * __hwrm_req_init() - Initialize an HWRM request.
+ * @bp: The driver context.
+ * @req: A pointer to the request pointer to initialize.
+ * @req_type: The request type. This will be converted to the little endian
+ *	before being written to the req_type field of the returned request.
+ * @req_len: The length of the request to be allocated.
+ *
+ * Allocate DMA resources and initialize a new HWRM request object of the
+ * given type. The response address field in the request is configured with
+ * the DMA bus address that has been mapped for the response and the passed
+ * request is pointed to kernel virtual memory mapped for the request (such
+ * that short_input indirection can be accomplished without copying). The
+ * request’s target and completion ring are initialized to default values and
+ * can be overridden by writing to the returned request object directly.
+ *
+ * The initialized request can be further customized by writing to its fields
+ * directly, taking care to covert such fields to little endian. The request
+ * object will be consumed (and all its associated resources release) upon
+ * passing it to hwrm_req_send() unless ownership of the request has been
+ * claimed by the caller via a call to hwrm_req_hold(). If the request is not
+ * consumed, either because it is never sent or because ownership has been
+ * claimed, then it must be released by a call to hwrm_req_drop().
+ *
+ * Return: zero on success, negative error code otherwise:
+ *	E2BIG: the type of request pointer is too large to fit.
+ *	ENOMEM: an allocation failure occurred.
+ */
+int __hwrm_req_init(struct bnxt *bp, void **req, u16 req_type, u32 req_len)
+{
+	struct bnxt_hwrm_ctx *ctx;
+	dma_addr_t dma_handle;
+	u8 *req_addr;
+
+	if (req_len > BNXT_HWRM_CTX_OFFSET)
+		return -E2BIG;
+
+	req_addr = dma_pool_alloc(bp->hwrm_dma_pool, GFP_KERNEL | __GFP_ZERO,
+				  &dma_handle);
+	if (!req_addr)
+		return -ENOMEM;
+
+	ctx = (struct bnxt_hwrm_ctx *)(req_addr + BNXT_HWRM_CTX_OFFSET);
+	/* safety first, sentinel used to check for invalid requests */
+	ctx->sentinel = hwrm_calc_sentinel(ctx, req_type);
+	ctx->req_len = req_len;
+	ctx->req = (struct input *)req_addr;
+	ctx->resp = (struct output *)(req_addr + BNXT_HWRM_RESP_OFFSET);
+	ctx->dma_handle = dma_handle;
+	ctx->flags = 0; /* __GFP_ZERO, but be explicit regarding ownership */
+	ctx->timeout = bp->hwrm_cmd_timeout ?: DFLT_HWRM_CMD_TIMEOUT;
+	ctx->allocated = BNXT_HWRM_DMA_SIZE - BNXT_HWRM_CTX_OFFSET;
+	ctx->gfp = GFP_KERNEL;
+	ctx->slice_addr = NULL;
+
+	/* initialize common request fields */
+	ctx->req->req_type = cpu_to_le16(req_type);
+	ctx->req->resp_addr = cpu_to_le64(dma_handle + BNXT_HWRM_RESP_OFFSET);
+	ctx->req->cmpl_ring = cpu_to_le16(BNXT_HWRM_NO_CMPL_RING);
+	ctx->req->target_id = cpu_to_le16(BNXT_HWRM_TARGET);
+	*req = ctx->req;
+
+	return 0;
+}
+
+static struct bnxt_hwrm_ctx *__hwrm_ctx(struct bnxt *bp, u8 *req_addr)
+{
+	void *ctx_addr = req_addr + BNXT_HWRM_CTX_OFFSET;
+	struct input *req = (struct input *)req_addr;
+	struct bnxt_hwrm_ctx *ctx = ctx_addr;
+	u64 sentinel;
+
+	if (!req) {
+		/* can only be due to software bug, be loud */
+		netdev_err(bp->dev, "null HWRM request");
+		dump_stack();
+		return NULL;
+	}
+
+	/* HWRM API has no type safety, verify sentinel to validate address */
+	sentinel = hwrm_calc_sentinel(ctx, le16_to_cpu(req->req_type));
+	if (ctx->sentinel != sentinel) {
+		/* can only be due to software bug, be loud */
+		netdev_err(bp->dev, "HWRM sentinel mismatch, req_type = %u\n",
+			   (u32)le16_to_cpu(req->req_type));
+		dump_stack();
+		return NULL;
+	}
+
+	return ctx;
+}
+
+/**
+ * hwrm_req_timeout() - Set the completion timeout for the request.
+ * @bp: The driver context.
+ * @req: The request to set the timeout.
+ * @timeout: The timeout in milliseconds.
+ *
+ * Set the timeout associated with the request for subsequent calls to
+ * hwrm_req_send(). Some requests are long running and require a different
+ * timeout than the default.
+ */
+void hwrm_req_timeout(struct bnxt *bp, void *req, unsigned int timeout)
+{
+	struct bnxt_hwrm_ctx *ctx = __hwrm_ctx(bp, req);
+
+	if (ctx)
+		ctx->timeout = timeout;
+}
+
+/**
+ * hwrm_req_alloc_flags() - Sets GFP allocation flags for slices.
+ * @bp: The driver context.
+ * @req: The request for which calls to hwrm_req_dma_slice() will have altered
+ *	allocation flags.
+ * @flags: A bitmask of GFP flags. These flags are passed to
+ *	dma_alloc_coherent() whenever it is used to allocate backing memory
+ *	for slices. Note that calls to hwrm_req_dma_slice() will not always
+ *	result in new allocations, however, memory suballocated from the
+ *	request buffer is already __GFP_ZERO.
+ *
+ * Sets the GFP allocation flags associated with the request for subsequent
+ * calls to hwrm_req_dma_slice(). This can be useful for specifying __GFP_ZERO
+ * for slice allocations.
+ */
+void hwrm_req_alloc_flags(struct bnxt *bp, void *req, gfp_t gfp)
+{
+	struct bnxt_hwrm_ctx *ctx = __hwrm_ctx(bp, req);
+
+	if (ctx)
+		ctx->gfp = gfp;
+}
+
+/**
+ * hwrm_req_replace() - Replace request data.
+ * @bp: The driver context.
+ * @req: The request to modify. A call to hwrm_req_replace() is conceptually
+ *	an assignment of new_req to req. Subsequent calls to HWRM API functions,
+ *	such as hwrm_req_send(), should thus use req and not new_req (in fact,
+ *	calls to HWRM API functions will fail if non-managed request objects
+ *	are passed).
+ * @len: The length of new_req.
+ * @new_req: The pre-built request to copy or reference.
+ *
+ * Replaces the request data in req with that of new_req. This is useful in
+ * scenarios where a request object has already been constructed by a third
+ * party prior to creating a resource managed request using hwrm_req_init().
+ * Depending on the length, hwrm_req_replace() will either copy the new
+ * request data into the DMA memory allocated for req, or it will simply
+ * reference the new request and use it in lieu of req during subsequent
+ * calls to hwrm_req_send(). The resource management is associated with
+ * req and is independent of and does not apply to new_req. The caller must
+ * ensure that the lifetime of new_req is least as long as req. Any slices
+ * that may have been associated with the original request are released.
+ *
+ * Return: zero on success, negative error code otherwise:
+ *     E2BIG: Request is too large.
+ *     EINVAL: Invalid request to modify.
+ */
+int hwrm_req_replace(struct bnxt *bp, void *req, void *new_req, u32 len)
+{
+	struct bnxt_hwrm_ctx *ctx = __hwrm_ctx(bp, req);
+	struct input *internal_req = req;
+	u16 req_type;
+
+	if (!ctx)
+		return -EINVAL;
+
+	if (len > BNXT_HWRM_CTX_OFFSET)
+		return -E2BIG;
+
+	/* free any existing slices */
+	ctx->allocated = BNXT_HWRM_DMA_SIZE - BNXT_HWRM_CTX_OFFSET;
+	if (ctx->slice_addr) {
+		dma_free_coherent(&bp->pdev->dev, ctx->slice_size,
+				  ctx->slice_addr, ctx->slice_handle);
+		ctx->slice_addr = NULL;
+	}
+	ctx->gfp = GFP_KERNEL;
+
+	if ((bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) || len > BNXT_HWRM_MAX_REQ_LEN) {
+		memcpy(internal_req, new_req, len);
+	} else {
+		internal_req->req_type = ((struct input *)new_req)->req_type;
+		ctx->req = new_req;
+	}
+
+	ctx->req_len = len;
+	ctx->req->resp_addr = cpu_to_le64(ctx->dma_handle +
+					  BNXT_HWRM_RESP_OFFSET);
+
+	/* update sentinel for potentially new request type */
+	req_type = le16_to_cpu(internal_req->req_type);
+	ctx->sentinel = hwrm_calc_sentinel(ctx, req_type);
+
+	return 0;
+}
+
+/**
+ * hwrm_req_flags() - Set non internal flags of the ctx
+ * @bp: The driver context.
+ * @req: The request containing the HWRM command
+ * @flags: ctx flags that don't have BNXT_HWRM_INTERNAL_FLAG set
+ *
+ * ctx flags can be used by the callers to instruct how the subsequent
+ * hwrm_req_send() should behave. Example: callers can use hwrm_req_flags
+ * with BNXT_HWRM_CTX_SILENT to omit kernel prints of errors of hwrm_req_send()
+ * or with BNXT_HWRM_FULL_WAIT enforce hwrm_req_send() to wait for full timeout
+ * even if FW is not responding.
+ * This generic function can be used to set any flag that is not an internal flag
+ * of the HWRM module.
+ */
+void hwrm_req_flags(struct bnxt *bp, void *req, enum bnxt_hwrm_ctx_flags flags)
+{
+	struct bnxt_hwrm_ctx *ctx = __hwrm_ctx(bp, req);
+
+	if (ctx)
+		ctx->flags |= (flags & HWRM_API_FLAGS);
+}
+
+/**
+ * hwrm_req_hold() - Claim ownership of the request's resources.
+ * @bp: The driver context.
+ * @req: A pointer to the request to own. The request will no longer be
+ *	consumed by calls to hwrm_req_send().
+ *
+ * Take ownership of the request. Ownership places responsibility on the
+ * caller to free the resources associated with the request via a call to
+ * hwrm_req_drop(). The caller taking ownership implies that a subsequent
+ * call to hwrm_req_send() will not consume the request (ie. sending will
+ * not free the associated resources if the request is owned by the caller).
+ * Taking ownership returns a reference to the response. Retaining and
+ * accessing the response data is the most common reason to take ownership
+ * of the request. Ownership can also be acquired in order to reuse the same
+ * request object across multiple invocations of hwrm_req_send().
+ *
+ * Return: A pointer to the response object.
+ *
+ * The resources associated with the response will remain available to the
+ * caller until ownership of the request is relinquished via a call to
+ * hwrm_req_drop(). It is not possible for hwrm_req_hold() to return NULL if
+ * a valid request is provided. A returned NULL value would imply a driver
+ * bug and the implementation will complain loudly in the logs to aid in
+ * detection. It should not be necessary to check the result for NULL.
+ */
+void *hwrm_req_hold(struct bnxt *bp, void *req)
+{
+	struct bnxt_hwrm_ctx *ctx = __hwrm_ctx(bp, req);
+	struct input *input = (struct input *)req;
+
+	if (!ctx)
+		return NULL;
+
+	if (ctx->flags & BNXT_HWRM_INTERNAL_CTX_OWNED) {
+		/* can only be due to software bug, be loud */
+		netdev_err(bp->dev, "HWRM context already owned, req_type = %u\n",
+			   (u32)le16_to_cpu(input->req_type));
+		dump_stack();
+		return NULL;
+	}
+
+	ctx->flags |= BNXT_HWRM_INTERNAL_CTX_OWNED;
+	return ((u8 *)req) + BNXT_HWRM_RESP_OFFSET;
+}
+
+static void __hwrm_ctx_drop(struct bnxt *bp, struct bnxt_hwrm_ctx *ctx)
+{
+	void *addr = ((u8 *)ctx) - BNXT_HWRM_CTX_OFFSET;
+	dma_addr_t dma_handle = ctx->dma_handle; /* save before invalidate */
+
+	/* unmap any auxiliary DMA slice */
+	if (ctx->slice_addr)
+		dma_free_coherent(&bp->pdev->dev, ctx->slice_size,
+				  ctx->slice_addr, ctx->slice_handle);
+
+	/* invalidate, ensure ownership, sentinel and dma_handle are cleared */
+	memset(ctx, 0, sizeof(struct bnxt_hwrm_ctx));
+
+	/* return the buffer to the DMA pool */
+	if (dma_handle)
+		dma_pool_free(bp->hwrm_dma_pool, addr, dma_handle);
+}
+
+/**
+ * hwrm_req_drop() - Release all resources associated with the request.
+ * @bp: The driver context.
+ * @req: The request to consume, releasing the associated resources. The
+ *	request object, any slices, and its associated response are no
+ *	longer valid.
+ *
+ * It is legal to call hwrm_req_drop() on an unowned request, provided it
+ * has not already been consumed by hwrm_req_send() (for example, to release
+ * an aborted request). A given request should not be dropped more than once,
+ * nor should it be dropped after having been consumed by hwrm_req_send(). To
+ * do so is an error (the context will not be found and a stack trace will be
+ * rendered in the kernel log).
+ */
+void hwrm_req_drop(struct bnxt *bp, void *req)
+{
+	struct bnxt_hwrm_ctx *ctx = __hwrm_ctx(bp, req);
+
+	if (ctx)
+		__hwrm_ctx_drop(bp, ctx);
+}
+
+static int __hwrm_to_stderr(u32 hwrm_err)
+{
+	switch (hwrm_err) {
+	case HWRM_ERR_CODE_SUCCESS:
+		return 0;
+	case HWRM_ERR_CODE_RESOURCE_LOCKED:
+		return -EROFS;
+	case HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED:
+		return -EACCES;
+	case HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR:
+		return -ENOSPC;
+	case HWRM_ERR_CODE_INVALID_PARAMS:
+	case HWRM_ERR_CODE_INVALID_FLAGS:
+	case HWRM_ERR_CODE_INVALID_ENABLES:
+	case HWRM_ERR_CODE_UNSUPPORTED_TLV:
+	case HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR:
+		return -EINVAL;
+	case HWRM_ERR_CODE_NO_BUFFER:
+		return -ENOMEM;
+	case HWRM_ERR_CODE_HOT_RESET_PROGRESS:
+	case HWRM_ERR_CODE_BUSY:
+		return -EAGAIN;
+	case HWRM_ERR_CODE_CMD_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	default:
+		return -EIO;
+	}
+}
+
+static struct bnxt_hwrm_wait_token *
+__hwrm_acquire_token(struct bnxt *bp, enum bnxt_hwrm_chnl dst)
+{
+	struct bnxt_hwrm_wait_token *token;
+
+	token = kzalloc(sizeof(*token), GFP_KERNEL);
+	if (!token)
+		return NULL;
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+
+	token->dst = dst;
+	token->state = BNXT_HWRM_PENDING;
+	if (dst == BNXT_HWRM_CHNL_CHIMP) {
+		token->seq_id = bp->hwrm_cmd_seq++;
+		hlist_add_head_rcu(&token->node, &bp->hwrm_pending_list);
+	} else {
+		token->seq_id = bp->hwrm_cmd_kong_seq++;
+	}
+
+	return token;
+}
+
+static void
+__hwrm_release_token(struct bnxt *bp, struct bnxt_hwrm_wait_token *token)
+{
+	if (token->dst == BNXT_HWRM_CHNL_CHIMP) {
+		hlist_del_rcu(&token->node);
+		kfree_rcu(token, rcu);
+	} else {
+		kfree(token);
+	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
+}
+
+void
+hwrm_update_token(struct bnxt *bp, u16 seq_id, enum bnxt_hwrm_wait_state state)
+{
+	struct bnxt_hwrm_wait_token *token;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(token, &bp->hwrm_pending_list, node) {
+		if (token->seq_id == seq_id) {
+			WRITE_ONCE(token->state, state);
+			rcu_read_unlock();
+			return;
+		}
+	}
+	rcu_read_unlock();
+	netdev_err(bp->dev, "Invalid hwrm seq id %d\n", seq_id);
+}
+
+static int __hwrm_send(struct bnxt *bp, struct bnxt_hwrm_ctx *ctx)
+{
+	u32 doorbell_offset = BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER;
+	enum bnxt_hwrm_chnl dst = BNXT_HWRM_CHNL_CHIMP;
+	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
+	struct bnxt_hwrm_wait_token *token = NULL;
+	struct hwrm_short_input short_input = {0};
+	u16 max_req_len = BNXT_HWRM_MAX_REQ_LEN;
+	unsigned int i, timeout, tmo_count;
+	u32 *data = (u32 *)ctx->req;
+	u32 msg_len = ctx->req_len;
+	int rc = -EBUSY;
+	u32 req_type;
+	u16 len = 0;
+	u8 *valid;
+
+	if (ctx->flags & BNXT_HWRM_INTERNAL_RESP_DIRTY)
+		memset(ctx->resp, 0, PAGE_SIZE);
+
+	req_type = le16_to_cpu(ctx->req->req_type);
+	if (BNXT_NO_FW_ACCESS(bp) && req_type != HWRM_FUNC_RESET)
+		goto exit;
+
+	if (msg_len > BNXT_HWRM_MAX_REQ_LEN &&
+	    msg_len > bp->hwrm_max_ext_req_len) {
+		rc = -E2BIG;
+		goto exit;
+	}
+
+	if (bnxt_kong_hwrm_message(bp, ctx->req)) {
+		dst = BNXT_HWRM_CHNL_KONG;
+		bar_offset = BNXT_GRCPF_REG_KONG_COMM;
+		doorbell_offset = BNXT_GRCPF_REG_KONG_COMM_TRIGGER;
+		if (le16_to_cpu(ctx->req->cmpl_ring) != INVALID_HW_RING_ID) {
+			netdev_err(bp->dev, "Ring completions not supported for KONG commands, req_type = %d\n",
+				   req_type);
+			rc = -EINVAL;
+			goto exit;
+		}
+	}
+
+	token = __hwrm_acquire_token(bp, dst);
+	if (!token) {
+		rc = -ENOMEM;
+		goto exit;
+	}
+	ctx->req->seq_id = cpu_to_le16(token->seq_id);
+
+	if ((bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) ||
+	    msg_len > BNXT_HWRM_MAX_REQ_LEN) {
+		short_input.req_type = ctx->req->req_type;
+		short_input.signature =
+				cpu_to_le16(SHORT_REQ_SIGNATURE_SHORT_CMD);
+		short_input.size = cpu_to_le16(msg_len);
+		short_input.req_addr = cpu_to_le64(ctx->dma_handle);
+
+		data = (u32 *)&short_input;
+		msg_len = sizeof(short_input);
+
+		max_req_len = BNXT_HWRM_SHORT_REQ_LEN;
+	}
+
+	/* Ensure any associated DMA buffers are written before doorbell */
+	wmb();
+
+	/* Write request msg to hwrm channel */
+	__iowrite32_copy(bp->bar0 + bar_offset, data, msg_len / 4);
+
+	for (i = msg_len; i < max_req_len; i += 4)
+		writel(0, bp->bar0 + bar_offset + i);
+
+	/* Ring channel doorbell */
+	writel(1, bp->bar0 + doorbell_offset);
+
+	if (!pci_is_enabled(bp->pdev)) {
+		rc = -ENODEV;
+		goto exit;
+	}
+
+	/* Limit timeout to an upper limit */
+	timeout = min_t(uint, ctx->timeout, HWRM_CMD_MAX_TIMEOUT);
+	/* convert timeout to usec */
+	timeout *= 1000;
+
+	i = 0;
+	/* Short timeout for the first few iterations:
+	 * number of loops = number of loops for short timeout +
+	 * number of loops for standard timeout.
+	 */
+	tmo_count = HWRM_SHORT_TIMEOUT_COUNTER;
+	timeout = timeout - HWRM_SHORT_MIN_TIMEOUT * HWRM_SHORT_TIMEOUT_COUNTER;
+	tmo_count += DIV_ROUND_UP(timeout, HWRM_MIN_TIMEOUT);
+
+	if (le16_to_cpu(ctx->req->cmpl_ring) != INVALID_HW_RING_ID) {
+		/* Wait until hwrm response cmpl interrupt is processed */
+		while (READ_ONCE(token->state) < BNXT_HWRM_COMPLETE &&
+		       i++ < tmo_count) {
+			/* Abort the wait for completion if the FW health
+			 * check has failed.
+			 */
+			if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+				goto exit;
+			/* on first few passes, just barely sleep */
+			if (i < HWRM_SHORT_TIMEOUT_COUNTER) {
+				usleep_range(HWRM_SHORT_MIN_TIMEOUT,
+					     HWRM_SHORT_MAX_TIMEOUT);
+			} else {
+				if (HWRM_WAIT_MUST_ABORT(bp, ctx))
+					break;
+				usleep_range(HWRM_MIN_TIMEOUT,
+					     HWRM_MAX_TIMEOUT);
+			}
+		}
+
+		if (READ_ONCE(token->state) != BNXT_HWRM_COMPLETE) {
+			if (!(ctx->flags & BNXT_HWRM_CTX_SILENT))
+				netdev_err(bp->dev, "Resp cmpl intr err msg: 0x%x\n",
+					   le16_to_cpu(ctx->req->req_type));
+			goto exit;
+		}
+		len = le16_to_cpu(READ_ONCE(ctx->resp->resp_len));
+		valid = ((u8 *)ctx->resp) + len - 1;
+	} else {
+		__le16 seen_out_of_seq = ctx->req->seq_id; /* will never see */
+		int j;
+
+		/* Check if response len is updated */
+		for (i = 0; i < tmo_count; i++) {
+			/* Abort the wait for completion if the FW health
+			 * check has failed.
+			 */
+			if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+				goto exit;
+
+			if (token &&
+			    READ_ONCE(token->state) == BNXT_HWRM_DEFERRED) {
+				__hwrm_release_token(bp, token);
+				token = NULL;
+			}
+
+			len = le16_to_cpu(READ_ONCE(ctx->resp->resp_len));
+			if (len) {
+				__le16 resp_seq = READ_ONCE(ctx->resp->seq_id);
+
+				if (resp_seq == ctx->req->seq_id)
+					break;
+				if (resp_seq != seen_out_of_seq) {
+					netdev_warn(bp->dev, "Discarding out of seq response: 0x%x for msg {0x%x 0x%x}\n",
+						    le16_to_cpu(resp_seq),
+						    le16_to_cpu(ctx->req->req_type),
+						    le16_to_cpu(ctx->req->seq_id));
+					seen_out_of_seq = resp_seq;
+				}
+			}
+
+			/* on first few passes, just barely sleep */
+			if (i < HWRM_SHORT_TIMEOUT_COUNTER) {
+				usleep_range(HWRM_SHORT_MIN_TIMEOUT,
+					     HWRM_SHORT_MAX_TIMEOUT);
+			} else {
+				if (HWRM_WAIT_MUST_ABORT(bp, ctx))
+					goto timeout_abort;
+				usleep_range(HWRM_MIN_TIMEOUT,
+					     HWRM_MAX_TIMEOUT);
+			}
+		}
+
+		if (i >= tmo_count) {
+timeout_abort:
+			if (!(ctx->flags & BNXT_HWRM_CTX_SILENT))
+				netdev_err(bp->dev, "Error (timeout: %u) msg {0x%x 0x%x} len:%d\n",
+					   hwrm_total_timeout(i),
+					   le16_to_cpu(ctx->req->req_type),
+					   le16_to_cpu(ctx->req->seq_id), len);
+			goto exit;
+		}
+
+		/* Last byte of resp contains valid bit */
+		valid = ((u8 *)ctx->resp) + len - 1;
+		for (j = 0; j < HWRM_VALID_BIT_DELAY_USEC; j++) {
+			/* make sure we read from updated DMA memory */
+			dma_rmb();
+			if (*valid)
+				break;
+			usleep_range(1, 5);
+		}
+
+		if (j >= HWRM_VALID_BIT_DELAY_USEC) {
+			if (!(ctx->flags & BNXT_HWRM_CTX_SILENT))
+				netdev_err(bp->dev, "Error (timeout: %u) msg {0x%x 0x%x} len:%d v:%d\n",
+					   hwrm_total_timeout(i),
+					   le16_to_cpu(ctx->req->req_type),
+					   le16_to_cpu(ctx->req->seq_id), len,
+					   *valid);
+			goto exit;
+		}
+	}
+
+	/* Zero valid bit for compatibility.  Valid bit in an older spec
+	 * may become a new field in a newer spec.  We must make sure that
+	 * a new field not implemented by old spec will read zero.
+	 */
+	*valid = 0;
+	rc = le16_to_cpu(ctx->resp->error_code);
+	if (rc && !(ctx->flags & BNXT_HWRM_CTX_SILENT)) {
+		netdev_err(bp->dev, "hwrm req_type 0x%x seq id 0x%x error 0x%x\n",
+			   le16_to_cpu(ctx->resp->req_type),
+			   le16_to_cpu(ctx->resp->seq_id), rc);
+	}
+	rc = __hwrm_to_stderr(rc);
+exit:
+	if (token)
+		__hwrm_release_token(bp, token);
+	if (ctx->flags & BNXT_HWRM_INTERNAL_CTX_OWNED)
+		ctx->flags |= BNXT_HWRM_INTERNAL_RESP_DIRTY;
+	else
+		__hwrm_ctx_drop(bp, ctx);
+	return rc;
+}
+
+/**
+ * hwrm_req_send() - Execute an HWRM command.
+ * @bp: The driver context.
+ * @req: A pointer to the request to send. The DMA resources associated with
+ *	the request will be released (ie. the request will be consumed) unless
+ *	ownership of the request has been assumed by the caller via a call to
+ *	hwrm_req_hold().
+ *
+ * Send an HWRM request to the device and wait for a response. The request is
+ * consumed if it is not owned by the caller. This function will block until
+ * the request has either completed or times out due to an error.
+ *
+ * Return: A result code.
+ *
+ * The result is zero on success, otherwise the negative error code indicates
+ * one of the following errors:
+ *	E2BIG: The request was too large.
+ *	EBUSY: The firmware is in a fatal state or the request timed out
+ *	EACCESS: HWRM access denied.
+ *	ENOSPC: HWRM resource allocation error.
+ *	EINVAL: Request parameters are invalid.
+ *	ENOMEM: HWRM has no buffers.
+ *	EAGAIN: HWRM busy or reset in progress.
+ *	EOPNOTSUPP: Invalid request type.
+ *	EIO: Any other error.
+ * Error handling is orthogonal to request ownership. An unowned request will
+ * still be consumed on error. If the caller owns the request, then the caller
+ * is responsible for releasing the resources. Otherwise, hwrm_req_send() will
+ * always consume the request.
+ */
+int hwrm_req_send(struct bnxt *bp, void *req)
+{
+	struct bnxt_hwrm_ctx *ctx = __hwrm_ctx(bp, req);
+
+	if (!ctx)
+		return -EINVAL;
+
+	return __hwrm_send(bp, ctx);
+}
+
+/**
+ * hwrm_req_send_silent() - A silent version of hwrm_req_send().
+ * @bp: The driver context.
+ * @req: The request to send without logging.
+ *
+ * The same as hwrm_req_send(), except that the request is silenced using
+ * hwrm_req_silence() prior the call. This version of the function is
+ * provided solely to preserve the legacy API’s flavor for this functionality.
+ *
+ * Return: A result code, see hwrm_req_send().
+ */
+int hwrm_req_send_silent(struct bnxt *bp, void *req)
+{
+	hwrm_req_flags(bp, req, BNXT_HWRM_CTX_SILENT);
+	return hwrm_req_send(bp, req);
+}
+
+/**
+ * hwrm_req_dma_slice() - Allocate a slice of DMA mapped memory.
+ * @bp: The driver context.
+ * @req: The request for which indirect data will be associated.
+ * @size: The size of the allocation.
+ * @dma: The bus address associated with the allocation. The HWRM API has no
+ *	knowledge about the type of the request and so cannot infer how the
+ *	caller intends to use the indirect data. Thus, the caller is
+ *	responsible for configuring the request object appropriately to
+ *	point to the associated indirect memory. Note, DMA handle has the
+ *	same definition as it does in dma_alloc_coherent(), the caller is
+ *	responsible for endian conversions via cpu_to_le64() before assigning
+ *	this address.
+ *
+ * Allocates DMA mapped memory for indirect data related to a request. The
+ * lifetime of the DMA resources will be bound to that of the request (ie.
+ * they will be automatically released when the request is either consumed by
+ * hwrm_req_send() or dropped by hwrm_req_drop()). Small allocations are
+ * efficiently suballocated out of the request buffer space, hence the name
+ * slice, while larger requests are satisfied via an underlying call to
+ * dma_alloc_coherent(). Multiple suballocations are supported, however, only
+ * one externally mapped region is.
+ *
+ * Return: The kernel virtual address of the DMA mapping.
+ */
+void *
+hwrm_req_dma_slice(struct bnxt *bp, void *req, u32 size, dma_addr_t *dma_handle)
+{
+	struct bnxt_hwrm_ctx *ctx = __hwrm_ctx(bp, req);
+	u8 *end = ((u8 *)req) + BNXT_HWRM_DMA_SIZE;
+	struct input *input = req;
+	u8 *addr, *req_addr = req;
+	u32 max_offset, offset;
+
+	if (!ctx)
+		return NULL;
+
+	max_offset = BNXT_HWRM_DMA_SIZE - ctx->allocated;
+	offset = max_offset - size;
+	offset = ALIGN_DOWN(offset, BNXT_HWRM_DMA_ALIGN);
+	addr = req_addr + offset;
+
+	if (addr < req_addr + max_offset && req_addr + ctx->req_len <= addr) {
+		ctx->allocated = end - addr;
+		*dma_handle = ctx->dma_handle + offset;
+		return addr;
+	}
+
+	/* could not suballocate from ctx buffer, try create a new mapping */
+	if (ctx->slice_addr) {
+		/* if one exists, can only be due to software bug, be loud */
+		netdev_err(bp->dev, "HWRM refusing to reallocate DMA slice, req_type = %u\n",
+			   (u32)le16_to_cpu(input->req_type));
+		dump_stack();
+		return NULL;
+	}
+
+	addr = dma_alloc_coherent(&bp->pdev->dev, size, dma_handle, ctx->gfp);
+
+	if (!addr)
+		return NULL;
+
+	ctx->slice_addr = addr;
+	ctx->slice_size = size;
+	ctx->slice_handle = *dma_handle;
+
+	return addr;
+}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
new file mode 100644
index 000000000000..4d17f0d5363b
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
@@ -0,0 +1,145 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2020 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef BNXT_HWRM_H
+#define BNXT_HWRM_H
+
+#include "bnxt_hsi.h"
+
+enum bnxt_hwrm_ctx_flags {
+	/* Update the HWRM_API_FLAGS right below for any new non-internal bit added here */
+	BNXT_HWRM_INTERNAL_CTX_OWNED	= BIT(0), /* caller owns the context */
+	BNXT_HWRM_INTERNAL_RESP_DIRTY	= BIT(1), /* response contains data */
+	BNXT_HWRM_CTX_SILENT		= BIT(2), /* squelch firmware errors */
+	BNXT_HWRM_FULL_WAIT		= BIT(3), /* wait for full timeout of HWRM command */
+};
+
+#define HWRM_API_FLAGS (BNXT_HWRM_CTX_SILENT | BNXT_HWRM_FULL_WAIT)
+
+struct bnxt_hwrm_ctx {
+	u64 sentinel;
+	dma_addr_t dma_handle;
+	struct output *resp;
+	struct input *req;
+	dma_addr_t slice_handle;
+	void *slice_addr;
+	u32 slice_size;
+	u32 req_len;
+	enum bnxt_hwrm_ctx_flags flags;
+	unsigned int timeout;
+	u32 allocated;
+	gfp_t gfp;
+};
+
+enum bnxt_hwrm_wait_state {
+	BNXT_HWRM_PENDING,
+	BNXT_HWRM_DEFERRED,
+	BNXT_HWRM_COMPLETE,
+	BNXT_HWRM_CANCELLED,
+};
+
+enum bnxt_hwrm_chnl { BNXT_HWRM_CHNL_CHIMP, BNXT_HWRM_CHNL_KONG };
+
+struct bnxt_hwrm_wait_token {
+	struct rcu_head rcu;
+	struct hlist_node node;
+	enum bnxt_hwrm_wait_state state;
+	enum bnxt_hwrm_chnl dst;
+	u16 seq_id;
+};
+
+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		40000
+#define SHORT_HWRM_CMD_TIMEOUT		20
+#define HWRM_CMD_TIMEOUT		(bp->hwrm_cmd_timeout)
+#define HWRM_RESET_TIMEOUT		((HWRM_CMD_TIMEOUT) * 4)
+#define HWRM_COREDUMP_TIMEOUT		((HWRM_CMD_TIMEOUT) * 12)
+#define BNXT_HWRM_TARGET		0xffff
+#define BNXT_HWRM_NO_CMPL_RING		-1
+#define BNXT_HWRM_REQ_MAX_SIZE		128
+#define BNXT_HWRM_DMA_SIZE		(2 * PAGE_SIZE) /* space for req+resp */
+#define BNXT_HWRM_RESP_RESERVED		PAGE_SIZE
+#define BNXT_HWRM_RESP_OFFSET		(BNXT_HWRM_DMA_SIZE -		\
+					 BNXT_HWRM_RESP_RESERVED)
+#define BNXT_HWRM_CTX_OFFSET		(BNXT_HWRM_RESP_OFFSET -	\
+					 sizeof(struct bnxt_hwrm_ctx))
+#define BNXT_HWRM_DMA_ALIGN		16
+#define BNXT_HWRM_SENTINEL		0xb6e1f68a12e9a7eb /* arbitrary value */
+#define BNXT_HWRM_REQS_PER_PAGE		(BNXT_PAGE_SIZE /	\
+					 BNXT_HWRM_REQ_MAX_SIZE)
+#define HWRM_SHORT_MIN_TIMEOUT		3
+#define HWRM_SHORT_MAX_TIMEOUT		10
+#define HWRM_SHORT_TIMEOUT_COUNTER	5
+
+#define HWRM_MIN_TIMEOUT		25
+#define HWRM_MAX_TIMEOUT		40
+
+#define HWRM_WAIT_MUST_ABORT(bp, ctx)					\
+	(le16_to_cpu((ctx)->req->req_type) != HWRM_VER_GET &&		\
+	 !bnxt_is_fw_healthy(bp))
+
+static inline unsigned int hwrm_total_timeout(unsigned int n)
+{
+	return n <= HWRM_SHORT_TIMEOUT_COUNTER ? n * HWRM_SHORT_MIN_TIMEOUT :
+		HWRM_SHORT_TIMEOUT_COUNTER * HWRM_SHORT_MIN_TIMEOUT +
+		(n - HWRM_SHORT_TIMEOUT_COUNTER) * HWRM_MIN_TIMEOUT;
+}
+
+
+#define HWRM_VALID_BIT_DELAY_USEC	150
+
+static inline bool bnxt_cfa_hwrm_message(u16 req_type)
+{
+	switch (req_type) {
+	case HWRM_CFA_ENCAP_RECORD_ALLOC:
+	case HWRM_CFA_ENCAP_RECORD_FREE:
+	case HWRM_CFA_DECAP_FILTER_ALLOC:
+	case HWRM_CFA_DECAP_FILTER_FREE:
+	case HWRM_CFA_EM_FLOW_ALLOC:
+	case HWRM_CFA_EM_FLOW_FREE:
+	case HWRM_CFA_EM_FLOW_CFG:
+	case HWRM_CFA_FLOW_ALLOC:
+	case HWRM_CFA_FLOW_FREE:
+	case HWRM_CFA_FLOW_INFO:
+	case HWRM_CFA_FLOW_FLUSH:
+	case HWRM_CFA_FLOW_STATS:
+	case HWRM_CFA_METER_PROFILE_ALLOC:
+	case HWRM_CFA_METER_PROFILE_FREE:
+	case HWRM_CFA_METER_PROFILE_CFG:
+	case HWRM_CFA_METER_INSTANCE_ALLOC:
+	case HWRM_CFA_METER_INSTANCE_FREE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline bool bnxt_kong_hwrm_message(struct bnxt *bp, struct input *req)
+{
+	return (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL &&
+		(bnxt_cfa_hwrm_message(le16_to_cpu(req->req_type)) ||
+		 le16_to_cpu(req->target_id) == HWRM_TARGET_ID_KONG));
+}
+
+int __hwrm_req_init(struct bnxt *bp, void **req, u16 req_type, u32 req_len);
+#define hwrm_req_init(bp, req, req_type) \
+	__hwrm_req_init((bp), (void **)&(req), (req_type), sizeof(*(req)))
+void *hwrm_req_hold(struct bnxt *bp, void *req);
+void hwrm_req_drop(struct bnxt *bp, void *req);
+void hwrm_req_flags(struct bnxt *bp, void *req, enum bnxt_hwrm_ctx_flags flags);
+void hwrm_req_timeout(struct bnxt *bp, void *req, unsigned int timeout);
+int hwrm_req_send(struct bnxt *bp, void *req);
+int hwrm_req_send_silent(struct bnxt *bp, void *req);
+int hwrm_req_replace(struct bnxt *bp, void *req, void *new_req, u32 len);
+void hwrm_req_alloc_flags(struct bnxt *bp, void *req, gfp_t flags);
+void *hwrm_req_dma_slice(struct bnxt *bp, void *req, u32 size, dma_addr_t *dma);
+#endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 81f40ab748f1..f0aa480799ca 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -18,6 +18,7 @@
 #include <linux/ptp_classify.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
+#include "bnxt_hwrm.h"
 #include "bnxt_ptp.h"
 
 int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off)
@@ -56,16 +57,19 @@ static int bnxt_ptp_settime(struct ptp_clock_info *ptp_info,
 }
 
 /* Caller holds ptp_lock */
-static u64 bnxt_refclk_read(struct bnxt *bp, struct ptp_system_timestamp *sts)
+static int bnxt_refclk_read(struct bnxt *bp, struct ptp_system_timestamp *sts,
+			    u64 *ns)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
-	u64 ns;
+
+	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
+		return -EIO;
 
 	ptp_read_system_prets(sts);
-	ns = readl(bp->bar0 + ptp->refclk_mapped_regs[0]);
+	*ns = readl(bp->bar0 + ptp->refclk_mapped_regs[0]);
 	ptp_read_system_postts(sts);
-	ns |= (u64)readl(bp->bar0 + ptp->refclk_mapped_regs[1]) << 32;
-	return ns;
+	*ns |= (u64)readl(bp->bar0 + ptp->refclk_mapped_regs[1]) << 32;
+	return 0;
 }
 
 static void bnxt_ptp_get_current_time(struct bnxt *bp)
@@ -76,30 +80,34 @@ static void bnxt_ptp_get_current_time(struct bnxt *bp)
 		return;
 	spin_lock_bh(&ptp->ptp_lock);
 	WRITE_ONCE(ptp->old_time, ptp->current_time);
-	ptp->current_time = bnxt_refclk_read(bp, NULL);
+	bnxt_refclk_read(bp, NULL, &ptp->current_time);
 	spin_unlock_bh(&ptp->ptp_lock);
 }
 
 static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts)
 {
-	struct hwrm_port_ts_query_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_port_ts_query_input req = {0};
+	struct hwrm_port_ts_query_output *resp;
+	struct hwrm_port_ts_query_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_TS_QUERY, -1, -1);
-	req.flags = cpu_to_le32(flags);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_TS_QUERY);
+	if (rc)
+		return rc;
+
+	req->flags = cpu_to_le32(flags);
 	if ((flags & PORT_TS_QUERY_REQ_FLAGS_PATH) ==
 	    PORT_TS_QUERY_REQ_FLAGS_PATH_TX) {
-		req.enables = cpu_to_le16(BNXT_PTP_QTS_TX_ENABLES);
-		req.ptp_seq_id = cpu_to_le32(bp->ptp_cfg->tx_seqid);
-		req.ptp_hdr_offset = cpu_to_le16(bp->ptp_cfg->tx_hdr_off);
-		req.ts_req_timeout = cpu_to_le16(BNXT_PTP_QTS_TIMEOUT);
+		req->enables = cpu_to_le16(BNXT_PTP_QTS_TX_ENABLES);
+		req->ptp_seq_id = cpu_to_le32(bp->ptp_cfg->tx_seqid);
+		req->ptp_hdr_offset = cpu_to_le16(bp->ptp_cfg->tx_hdr_off);
+		req->ts_req_timeout = cpu_to_le16(BNXT_PTP_QTS_TIMEOUT);
 	}
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+
+	rc = hwrm_req_send(bp, req);
 	if (!rc)
 		*ts = le64_to_cpu(resp->ptp_msg_ts);
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -110,9 +118,14 @@ static int bnxt_ptp_gettimex(struct ptp_clock_info *ptp_info,
 	struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
 						ptp_info);
 	u64 ns, cycles;
+	int rc;
 
 	spin_lock_bh(&ptp->ptp_lock);
-	cycles = bnxt_refclk_read(ptp->bp, sts);
+	rc = bnxt_refclk_read(ptp->bp, sts, &cycles);
+	if (rc) {
+		spin_unlock_bh(&ptp->ptp_lock);
+		return rc;
+	}
 	ns = timecounter_cyc2time(&ptp->tc, cycles);
 	spin_unlock_bh(&ptp->ptp_lock);
 	*ts = ns_to_timespec64(ns);
@@ -135,33 +148,246 @@ static int bnxt_ptp_adjfreq(struct ptp_clock_info *ptp_info, s32 ppb)
 {
 	struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
 						ptp_info);
-	struct hwrm_port_mac_cfg_input req = {0};
+	struct hwrm_port_mac_cfg_input *req;
 	struct bnxt *bp = ptp->bp;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_MAC_CFG, -1, -1);
-	req.ptp_freq_adj_ppb = cpu_to_le32(ppb);
-	req.enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_PORT_MAC_CFG);
+	if (rc)
+		return rc;
+
+	req->ptp_freq_adj_ppb = cpu_to_le32(ppb);
+	req->enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB);
+	rc = hwrm_req_send(ptp->bp, req);
 	if (rc)
 		netdev_err(ptp->bp->dev,
 			   "ptp adjfreq failed. rc = %d\n", rc);
 	return rc;
 }
 
-static int bnxt_ptp_enable(struct ptp_clock_info *ptp,
+void bnxt_ptp_pps_event(struct bnxt *bp, u32 data1, u32 data2)
+{
+	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+	struct ptp_clock_event event;
+	u64 ns, pps_ts;
+
+	pps_ts = EVENT_PPS_TS(data2, data1);
+	spin_lock_bh(&ptp->ptp_lock);
+	ns = timecounter_cyc2time(&ptp->tc, pps_ts);
+	spin_unlock_bh(&ptp->ptp_lock);
+
+	switch (EVENT_DATA2_PPS_EVENT_TYPE(data2)) {
+	case ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_INTERNAL:
+		event.pps_times.ts_real = ns_to_timespec64(ns);
+		event.type = PTP_CLOCK_PPSUSR;
+		event.index = EVENT_DATA2_PPS_PIN_NUM(data2);
+		break;
+	case ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_EXTERNAL:
+		event.timestamp = ns;
+		event.type = PTP_CLOCK_EXTTS;
+		event.index = EVENT_DATA2_PPS_PIN_NUM(data2);
+		break;
+	}
+
+	ptp_clock_event(bp->ptp_cfg->ptp_clock, &event);
+}
+
+static int bnxt_ptp_cfg_pin(struct bnxt *bp, u8 pin, u8 usage)
+{
+	struct hwrm_func_ptp_pin_cfg_input *req;
+	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+	u8 state = usage != BNXT_PPS_PIN_NONE;
+	u8 *pin_state, *pin_usg;
+	u32 enables;
+	int rc;
+
+	if (!TSIO_PIN_VALID(pin)) {
+		netdev_err(ptp->bp->dev, "1PPS: Invalid pin. Check pin-function configuration\n");
+		return -EOPNOTSUPP;
+	}
+
+	rc = hwrm_req_init(ptp->bp, req, HWRM_FUNC_PTP_PIN_CFG);
+	if (rc)
+		return rc;
+
+	enables = (FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN0_STATE |
+		   FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN0_USAGE) << (pin * 2);
+	req->enables = cpu_to_le32(enables);
+
+	pin_state = &req->pin0_state;
+	pin_usg = &req->pin0_usage;
+
+	*(pin_state + (pin * 2)) = state;
+	*(pin_usg + (pin * 2)) = usage;
+
+	rc = hwrm_req_send(ptp->bp, req);
+	if (rc)
+		return rc;
+
+	ptp->pps_info.pins[pin].usage = usage;
+	ptp->pps_info.pins[pin].state = state;
+
+	return 0;
+}
+
+static int bnxt_ptp_cfg_event(struct bnxt *bp, u8 event)
+{
+	struct hwrm_func_ptp_cfg_input *req;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_PTP_CFG);
+	if (rc)
+		return rc;
+
+	req->enables = cpu_to_le16(FUNC_PTP_CFG_REQ_ENABLES_PTP_PPS_EVENT);
+	req->ptp_pps_event = event;
+	return hwrm_req_send(bp, req);
+}
+
+void bnxt_ptp_reapply_pps(struct bnxt *bp)
+{
+	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+	struct bnxt_pps *pps;
+	u32 pin = 0;
+	int rc;
+
+	if (!ptp || !(bp->fw_cap & BNXT_FW_CAP_PTP_PPS) ||
+	    !(ptp->ptp_info.pin_config))
+		return;
+	pps = &ptp->pps_info;
+	for (pin = 0; pin < BNXT_MAX_TSIO_PINS; pin++) {
+		if (pps->pins[pin].state) {
+			rc = bnxt_ptp_cfg_pin(bp, pin, pps->pins[pin].usage);
+			if (!rc && pps->pins[pin].event)
+				rc = bnxt_ptp_cfg_event(bp,
+							pps->pins[pin].event);
+			if (rc)
+				netdev_err(bp->dev, "1PPS: Failed to configure pin%d\n",
+					   pin);
+		}
+	}
+}
+
+static int bnxt_get_target_cycles(struct bnxt_ptp_cfg *ptp, u64 target_ns,
+				  u64 *cycles_delta)
+{
+	u64 cycles_now;
+	u64 nsec_now, nsec_delta;
+	int rc;
+
+	spin_lock_bh(&ptp->ptp_lock);
+	rc = bnxt_refclk_read(ptp->bp, NULL, &cycles_now);
+	if (rc) {
+		spin_unlock_bh(&ptp->ptp_lock);
+		return rc;
+	}
+	nsec_now = timecounter_cyc2time(&ptp->tc, cycles_now);
+	spin_unlock_bh(&ptp->ptp_lock);
+
+	nsec_delta = target_ns - nsec_now;
+	*cycles_delta = div64_u64(nsec_delta << ptp->cc.shift, ptp->cc.mult);
+	return 0;
+}
+
+static int bnxt_ptp_perout_cfg(struct bnxt_ptp_cfg *ptp,
+			       struct ptp_clock_request *rq)
+{
+	struct hwrm_func_ptp_cfg_input *req;
+	struct bnxt *bp = ptp->bp;
+	struct timespec64 ts;
+	u64 target_ns, delta;
+	u16 enables;
+	int rc;
+
+	ts.tv_sec = rq->perout.start.sec;
+	ts.tv_nsec = rq->perout.start.nsec;
+	target_ns = timespec64_to_ns(&ts);
+
+	rc = bnxt_get_target_cycles(ptp, target_ns, &delta);
+	if (rc)
+		return rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_PTP_CFG);
+	if (rc)
+		return rc;
+
+	enables = FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PERIOD |
+		  FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_UP |
+		  FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PHASE;
+	req->enables = cpu_to_le16(enables);
+	req->ptp_pps_event = 0;
+	req->ptp_freq_adj_dll_source = 0;
+	req->ptp_freq_adj_dll_phase = 0;
+	req->ptp_freq_adj_ext_period = cpu_to_le32(NSEC_PER_SEC);
+	req->ptp_freq_adj_ext_up = 0;
+	req->ptp_freq_adj_ext_phase_lower = cpu_to_le32(delta);
+
+	return hwrm_req_send(bp, req);
+}
+
+static int bnxt_ptp_enable(struct ptp_clock_info *ptp_info,
 			   struct ptp_clock_request *rq, int on)
 {
-	return -EOPNOTSUPP;
+	struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
+						ptp_info);
+	struct bnxt *bp = ptp->bp;
+	u8 pin_id;
+	int rc;
+
+	switch (rq->type) {
+	case PTP_CLK_REQ_EXTTS:
+		/* Configure an External PPS IN */
+		pin_id = ptp_find_pin(ptp->ptp_clock, PTP_PF_EXTTS,
+				      rq->extts.index);
+		if (!on)
+			break;
+		rc = bnxt_ptp_cfg_pin(bp, pin_id, BNXT_PPS_PIN_PPS_IN);
+		if (rc)
+			return rc;
+		rc = bnxt_ptp_cfg_event(bp, BNXT_PPS_EVENT_EXTERNAL);
+		if (!rc)
+			ptp->pps_info.pins[pin_id].event = BNXT_PPS_EVENT_EXTERNAL;
+		return rc;
+	case PTP_CLK_REQ_PEROUT:
+		/* Configure a Periodic PPS OUT */
+		pin_id = ptp_find_pin(ptp->ptp_clock, PTP_PF_PEROUT,
+				      rq->perout.index);
+		if (!on)
+			break;
+
+		rc = bnxt_ptp_cfg_pin(bp, pin_id, BNXT_PPS_PIN_PPS_OUT);
+		if (!rc)
+			rc = bnxt_ptp_perout_cfg(ptp, rq);
+
+		return rc;
+	case PTP_CLK_REQ_PPS:
+		/* Configure PHC PPS IN */
+		rc = bnxt_ptp_cfg_pin(bp, 0, BNXT_PPS_PIN_PPS_IN);
+		if (rc)
+			return rc;
+		rc = bnxt_ptp_cfg_event(bp, BNXT_PPS_EVENT_INTERNAL);
+		if (!rc)
+			ptp->pps_info.pins[0].event = BNXT_PPS_EVENT_INTERNAL;
+		return rc;
+	default:
+		netdev_err(ptp->bp->dev, "Unrecognized PIN function\n");
+		return -EOPNOTSUPP;
+	}
+
+	return bnxt_ptp_cfg_pin(bp, pin_id, BNXT_PPS_PIN_NONE);
 }
 
 static int bnxt_hwrm_ptp_cfg(struct bnxt *bp)
 {
-	struct hwrm_port_mac_cfg_input req = {0};
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+	struct hwrm_port_mac_cfg_input *req;
 	u32 flags = 0;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_PORT_MAC_CFG);
+	if (rc)
+		return rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_MAC_CFG, -1, -1);
 	if (ptp->rx_filter)
 		flags |= PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_ENABLE;
 	else
@@ -170,11 +396,11 @@ static int bnxt_hwrm_ptp_cfg(struct bnxt *bp)
 		flags |= PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_ENABLE;
 	else
 		flags |= PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_DISABLE;
-	req.flags = cpu_to_le32(flags);
-	req.enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_RX_TS_CAPTURE_PTP_MSG_TYPE);
-	req.rx_ts_capture_ptp_msg_type = cpu_to_le16(ptp->rxctl);
+	req->flags = cpu_to_le32(flags);
+	req->enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_RX_TS_CAPTURE_PTP_MSG_TYPE);
+	req->rx_ts_capture_ptp_msg_type = cpu_to_le16(ptp->rxctl);
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
 int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
@@ -311,8 +537,10 @@ static void bnxt_unmap_ptp_regs(struct bnxt *bp)
 static u64 bnxt_cc_read(const struct cyclecounter *cc)
 {
 	struct bnxt_ptp_cfg *ptp = container_of(cc, struct bnxt_ptp_cfg, cc);
+	u64 ns = 0;
 
-	return bnxt_refclk_read(ptp->bp, NULL);
+	bnxt_refclk_read(ptp->bp, NULL, &ns);
+	return ns;
 }
 
 static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
@@ -410,6 +638,87 @@ static const struct ptp_clock_info bnxt_ptp_caps = {
 	.enable		= bnxt_ptp_enable,
 };
 
+static int bnxt_ptp_verify(struct ptp_clock_info *ptp_info, unsigned int pin,
+			   enum ptp_pin_function func, unsigned int chan)
+{
+	struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
+						ptp_info);
+	/* Allow only PPS pin function configuration */
+	if (ptp->pps_info.pins[pin].usage <= BNXT_PPS_PIN_PPS_OUT &&
+	    func != PTP_PF_PHYSYNC)
+		return 0;
+	else
+		return -EOPNOTSUPP;
+}
+
+static int bnxt_ptp_pps_init(struct bnxt *bp)
+{
+	struct hwrm_func_ptp_pin_qcfg_output *resp;
+	struct hwrm_func_ptp_pin_qcfg_input *req;
+	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+	struct ptp_clock_info *ptp_info;
+	struct bnxt_pps *pps_info;
+	u8 *pin_usg;
+	u32 i, rc;
+
+	/* Query current/default PIN CFG */
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_PTP_PIN_QCFG);
+	if (rc)
+		return rc;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
+	if (rc || !resp->num_pins) {
+		hwrm_req_drop(bp, req);
+		return -EOPNOTSUPP;
+	}
+
+	ptp_info = &ptp->ptp_info;
+	pps_info = &ptp->pps_info;
+	pps_info->num_pins = resp->num_pins;
+	ptp_info->n_pins = pps_info->num_pins;
+	ptp_info->pin_config = kcalloc(ptp_info->n_pins,
+				       sizeof(*ptp_info->pin_config),
+				       GFP_KERNEL);
+	if (!ptp_info->pin_config) {
+		hwrm_req_drop(bp, req);
+		return -ENOMEM;
+	}
+
+	/* Report the TSIO capability to kernel */
+	pin_usg = &resp->pin0_usage;
+	for (i = 0; i < pps_info->num_pins; i++, pin_usg++) {
+		snprintf(ptp_info->pin_config[i].name,
+			 sizeof(ptp_info->pin_config[i].name), "bnxt_pps%d", i);
+		ptp_info->pin_config[i].index = i;
+		ptp_info->pin_config[i].chan = i;
+		if (*pin_usg == BNXT_PPS_PIN_PPS_IN)
+			ptp_info->pin_config[i].func = PTP_PF_EXTTS;
+		else if (*pin_usg == BNXT_PPS_PIN_PPS_OUT)
+			ptp_info->pin_config[i].func = PTP_PF_PEROUT;
+		else
+			ptp_info->pin_config[i].func = PTP_PF_NONE;
+
+		pps_info->pins[i].usage = *pin_usg;
+	}
+	hwrm_req_drop(bp, req);
+
+	/* Only 1 each of ext_ts and per_out pins is available in HW */
+	ptp_info->n_ext_ts = 1;
+	ptp_info->n_per_out = 1;
+	ptp_info->pps = 1;
+	ptp_info->verify = bnxt_ptp_verify;
+
+	return 0;
+}
+
+static bool bnxt_pps_config_ok(struct bnxt *bp)
+{
+	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+
+	return !(bp->fw_cap & BNXT_FW_CAP_PTP_PPS) == !ptp->ptp_info.pin_config;
+}
+
 int bnxt_ptp_init(struct bnxt *bp)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
@@ -422,6 +731,15 @@ int bnxt_ptp_init(struct bnxt *bp)
 	if (rc)
 		return rc;
 
+	if (ptp->ptp_clock && bnxt_pps_config_ok(bp))
+		return 0;
+
+	if (ptp->ptp_clock) {
+		ptp_clock_unregister(ptp->ptp_clock);
+		ptp->ptp_clock = NULL;
+		kfree(ptp->ptp_info.pin_config);
+		ptp->ptp_info.pin_config = NULL;
+	}
 	atomic_set(&ptp->tx_avail, BNXT_MAX_TX_TS);
 	spin_lock_init(&ptp->ptp_lock);
 
@@ -435,6 +753,10 @@ int bnxt_ptp_init(struct bnxt *bp)
 	timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real()));
 
 	ptp->ptp_info = bnxt_ptp_caps;
+	if ((bp->fw_cap & BNXT_FW_CAP_PTP_PPS)) {
+		if (bnxt_ptp_pps_init(bp))
+			netdev_err(bp->dev, "1pps not initialized, continuing without 1pps support\n");
+	}
 	ptp->ptp_clock = ptp_clock_register(&ptp->ptp_info, &bp->pdev->dev);
 	if (IS_ERR(ptp->ptp_clock)) {
 		int err = PTR_ERR(ptp->ptp_clock);
@@ -445,7 +767,7 @@ int bnxt_ptp_init(struct bnxt *bp)
 	}
 	if (bp->flags & BNXT_FLAG_CHIP_P5) {
 		spin_lock_bh(&ptp->ptp_lock);
-		ptp->current_time = bnxt_refclk_read(bp, NULL);
+		bnxt_refclk_read(bp, NULL, &ptp->current_time);
 		WRITE_ONCE(ptp->old_time, ptp->current_time);
 		spin_unlock_bh(&ptp->ptp_lock);
 		ptp_schedule_worker(ptp->ptp_clock, 0);
@@ -464,6 +786,9 @@ void bnxt_ptp_clear(struct bnxt *bp)
 		ptp_clock_unregister(ptp->ptp_clock);
 
 	ptp->ptp_clock = NULL;
+	kfree(ptp->ptp_info.pin_config);
+	ptp->ptp_info.pin_config = NULL;
+
 	if (ptp->tx_skb) {
 		dev_kfree_skb_any(ptp->tx_skb);
 		ptp->tx_skb = NULL;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index 524f1c272054..fa5f05708e6d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -22,11 +22,62 @@
 				 PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT | \
 				 PORT_TS_QUERY_REQ_ENABLES_PTP_HDR_OFFSET)
 
+struct pps_pin {
+	u8 event;
+	u8 usage;
+	u8 state;
+};
+
+#define TSIO_PIN_VALID(pin) ((pin) < (BNXT_MAX_TSIO_PINS))
+
+#define EVENT_DATA2_PPS_EVENT_TYPE(data2)				\
+	((data2) & ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE)
+
+#define EVENT_DATA2_PPS_PIN_NUM(data2)					\
+	(((data2) &							\
+	  ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PIN_NUMBER_MASK) >>\
+	 ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PIN_NUMBER_SFT)
+
+#define BNXT_DATA2_UPPER_MSK						\
+	ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PPS_TIMESTAMP_UPPER_MASK
+
+#define BNXT_DATA2_UPPER_SFT						\
+	(32 -								\
+	 ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PPS_TIMESTAMP_UPPER_SFT)
+
+#define BNXT_DATA1_LOWER_MSK						\
+	ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA1_PPS_TIMESTAMP_LOWER_MASK
+
+#define BNXT_DATA1_LOWER_SFT						\
+	  ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA1_PPS_TIMESTAMP_LOWER_SFT
+
+#define EVENT_PPS_TS(data2, data1)					\
+	(((u64)((data2) & BNXT_DATA2_UPPER_MSK) << BNXT_DATA2_UPPER_SFT) |\
+	 (((data1) & BNXT_DATA1_LOWER_MSK) >> BNXT_DATA1_LOWER_SFT))
+
+#define BNXT_PPS_PIN_DISABLE	0
+#define BNXT_PPS_PIN_ENABLE	1
+#define BNXT_PPS_PIN_NONE	0
+#define BNXT_PPS_PIN_PPS_IN	1
+#define BNXT_PPS_PIN_PPS_OUT	2
+#define BNXT_PPS_PIN_SYNC_IN	3
+#define BNXT_PPS_PIN_SYNC_OUT	4
+
+#define BNXT_PPS_EVENT_INTERNAL	1
+#define BNXT_PPS_EVENT_EXTERNAL	2
+
+struct bnxt_pps {
+	u8 num_pins;
+#define BNXT_MAX_TSIO_PINS	4
+	struct pps_pin pins[BNXT_MAX_TSIO_PINS];
+};
+
 struct bnxt_ptp_cfg {
 	struct ptp_clock_info	ptp_info;
 	struct ptp_clock	*ptp_clock;
 	struct cyclecounter	cc;
 	struct timecounter	tc;
+	struct bnxt_pps		pps_info;
 	/* serialize timecounter access */
 	spinlock_t		ptp_lock;
 	struct sk_buff		*tx_skb;
@@ -77,6 +128,8 @@ do {						\
 #endif
 
 int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off);
+void bnxt_ptp_pps_event(struct bnxt *bp, u32 data1, u32 data2);
+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);
 int bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 7fa881e1cd80..70d8ca3039dc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -17,6 +17,7 @@
 #include <linux/etherdevice.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
+#include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
 #include "bnxt_sriov.h"
 #include "bnxt_vfr.h"
@@ -26,21 +27,26 @@
 static int bnxt_hwrm_fwd_async_event_cmpl(struct bnxt *bp,
 					  struct bnxt_vf_info *vf, u16 event_id)
 {
-	struct hwrm_fwd_async_event_cmpl_input req = {0};
+	struct hwrm_fwd_async_event_cmpl_input *req;
 	struct hwrm_async_event_cmpl *async_cmpl;
 	int rc = 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FWD_ASYNC_EVENT_CMPL, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_FWD_ASYNC_EVENT_CMPL);
+	if (rc)
+		goto exit;
+
 	if (vf)
-		req.encap_async_event_target_id = cpu_to_le16(vf->fw_fid);
+		req->encap_async_event_target_id = cpu_to_le16(vf->fw_fid);
 	else
 		/* broadcast this async event to all VFs */
-		req.encap_async_event_target_id = cpu_to_le16(0xffff);
-	async_cmpl = (struct hwrm_async_event_cmpl *)req.encap_async_event_cmpl;
+		req->encap_async_event_target_id = cpu_to_le16(0xffff);
+	async_cmpl =
+		(struct hwrm_async_event_cmpl *)req->encap_async_event_cmpl;
 	async_cmpl->type = cpu_to_le16(ASYNC_EVENT_CMPL_TYPE_HWRM_ASYNC_EVENT);
 	async_cmpl->event_id = cpu_to_le16(event_id);
 
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_send(bp, req);
+exit:
 	if (rc)
 		netdev_err(bp->dev, "hwrm_fwd_async_event_cmpl failed. rc:%d\n",
 			   rc);
@@ -62,10 +68,10 @@ static int bnxt_vf_ndo_prep(struct bnxt *bp, int vf_id)
 
 int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 {
-	struct hwrm_func_cfg_input req = {0};
 	struct bnxt *bp = netdev_priv(dev);
-	struct bnxt_vf_info *vf;
+	struct hwrm_func_cfg_input *req;
 	bool old_setting = false;
+	struct bnxt_vf_info *vf;
 	u32 func_flags;
 	int rc;
 
@@ -89,36 +95,38 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 	/*TODO: if the driver supports VLAN filter on guest VLAN,
 	 * the spoof check should also include vlan anti-spoofing
 	 */
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
-	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(func_flags);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_CFG);
 	if (!rc) {
-		if (setting)
-			vf->flags |= BNXT_VF_SPOOFCHK;
-		else
-			vf->flags &= ~BNXT_VF_SPOOFCHK;
+		req->fid = cpu_to_le16(vf->fw_fid);
+		req->flags = cpu_to_le32(func_flags);
+		rc = hwrm_req_send(bp, req);
+		if (!rc) {
+			if (setting)
+				vf->flags |= BNXT_VF_SPOOFCHK;
+			else
+				vf->flags &= ~BNXT_VF_SPOOFCHK;
+		}
 	}
 	return rc;
 }
 
 static int bnxt_hwrm_func_qcfg_flags(struct bnxt *bp, struct bnxt_vf_info *vf)
 {
-	struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_func_qcfg_input req = {0};
+	struct hwrm_func_qcfg_output *resp;
+	struct hwrm_func_qcfg_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1);
-	req.fid = cpu_to_le16(BNXT_PF(bp) ? vf->fw_fid : 0xffff);
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc) {
-		mutex_unlock(&bp->hwrm_cmd_lock);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_QCFG);
+	if (rc)
 		return rc;
-	}
-	vf->func_qcfg_flags = le16_to_cpu(resp->flags);
-	mutex_unlock(&bp->hwrm_cmd_lock);
-	return 0;
+
+	req->fid = cpu_to_le16(BNXT_PF(bp) ? vf->fw_fid : 0xffff);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
+	if (!rc)
+		vf->func_qcfg_flags = le16_to_cpu(resp->flags);
+	hwrm_req_drop(bp, req);
+	return rc;
 }
 
 bool bnxt_is_trusted_vf(struct bnxt *bp, struct bnxt_vf_info *vf)
@@ -132,18 +140,22 @@ bool bnxt_is_trusted_vf(struct bnxt *bp, struct bnxt_vf_info *vf)
 
 static int bnxt_hwrm_set_trusted_vf(struct bnxt *bp, struct bnxt_vf_info *vf)
 {
-	struct hwrm_func_cfg_input req = {0};
+	struct hwrm_func_cfg_input *req;
+	int rc;
 
 	if (!(bp->fw_cap & BNXT_FW_CAP_TRUSTED_VF))
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
-	req.fid = cpu_to_le16(vf->fw_fid);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_CFG);
+	if (rc)
+		return rc;
+
+	req->fid = cpu_to_le16(vf->fw_fid);
 	if (vf->flags & BNXT_VF_TRUST)
-		req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE);
+		req->flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE);
 	else
-		req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		req->flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE);
+	return hwrm_req_send(bp, req);
 }
 
 int bnxt_set_vf_trust(struct net_device *dev, int vf_id, bool trusted)
@@ -203,8 +215,8 @@ int bnxt_get_vf_config(struct net_device *dev, int vf_id,
 
 int bnxt_set_vf_mac(struct net_device *dev, int vf_id, u8 *mac)
 {
-	struct hwrm_func_cfg_input req = {0};
 	struct bnxt *bp = netdev_priv(dev);
+	struct hwrm_func_cfg_input *req;
 	struct bnxt_vf_info *vf;
 	int rc;
 
@@ -220,19 +232,23 @@ int bnxt_set_vf_mac(struct net_device *dev, int vf_id, u8 *mac)
 	}
 	vf = &bp->pf.vf[vf_id];
 
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_CFG);
+	if (rc)
+		return rc;
+
 	memcpy(vf->mac_addr, mac, ETH_ALEN);
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
-	req.fid = cpu_to_le16(vf->fw_fid);
-	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
-	memcpy(req.dflt_mac_addr, mac, ETH_ALEN);
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+
+	req->fid = cpu_to_le16(vf->fw_fid);
+	req->enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
+	memcpy(req->dflt_mac_addr, mac, ETH_ALEN);
+	return hwrm_req_send(bp, req);
 }
 
 int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos,
 		     __be16 vlan_proto)
 {
-	struct hwrm_func_cfg_input req = {0};
 	struct bnxt *bp = netdev_priv(dev);
+	struct hwrm_func_cfg_input *req;
 	struct bnxt_vf_info *vf;
 	u16 vlan_tag;
 	int rc;
@@ -258,21 +274,23 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos,
 	if (vlan_tag == vf->vlan)
 		return 0;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
-	req.fid = cpu_to_le16(vf->fw_fid);
-	req.dflt_vlan = cpu_to_le16(vlan_tag);
-	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc)
-		vf->vlan = vlan_tag;
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_CFG);
+	if (!rc) {
+		req->fid = cpu_to_le16(vf->fw_fid);
+		req->dflt_vlan = cpu_to_le16(vlan_tag);
+		req->enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN);
+		rc = hwrm_req_send(bp, req);
+		if (!rc)
+			vf->vlan = vlan_tag;
+	}
 	return rc;
 }
 
 int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate,
 		   int max_tx_rate)
 {
-	struct hwrm_func_cfg_input req = {0};
 	struct bnxt *bp = netdev_priv(dev);
+	struct hwrm_func_cfg_input *req;
 	struct bnxt_vf_info *vf;
 	u32 pf_link_speed;
 	int rc;
@@ -296,16 +314,18 @@ int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate,
 	}
 	if (min_tx_rate == vf->min_tx_rate && max_tx_rate == vf->max_tx_rate)
 		return 0;
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
-	req.fid = cpu_to_le16(vf->fw_fid);
-	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW);
-	req.max_bw = cpu_to_le32(max_tx_rate);
-	req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MIN_BW);
-	req.min_bw = cpu_to_le32(min_tx_rate);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_CFG);
 	if (!rc) {
-		vf->min_tx_rate = min_tx_rate;
-		vf->max_tx_rate = max_tx_rate;
+		req->fid = cpu_to_le16(vf->fw_fid);
+		req->enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW |
+					   FUNC_CFG_REQ_ENABLES_MIN_BW);
+		req->max_bw = cpu_to_le32(max_tx_rate);
+		req->min_bw = cpu_to_le32(min_tx_rate);
+		rc = hwrm_req_send(bp, req);
+		if (!rc) {
+			vf->min_tx_rate = min_tx_rate;
+			vf->max_tx_rate = max_tx_rate;
+		}
 	}
 	return rc;
 }
@@ -358,21 +378,22 @@ static int bnxt_set_vf_attr(struct bnxt *bp, int num_vfs)
 
 static int bnxt_hwrm_func_vf_resource_free(struct bnxt *bp, int num_vfs)
 {
-	int i, rc = 0;
+	struct hwrm_func_vf_resc_free_input *req;
 	struct bnxt_pf_info *pf = &bp->pf;
-	struct hwrm_func_vf_resc_free_input req = {0};
+	int i, rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESC_FREE, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_VF_RESC_FREE);
+	if (rc)
+		return rc;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
+	hwrm_req_hold(bp, req);
 	for (i = pf->first_vf_id; i < pf->first_vf_id + num_vfs; i++) {
-		req.vf_id = cpu_to_le16(i);
-		rc = _hwrm_send_message(bp, &req, sizeof(req),
-					HWRM_CMD_TIMEOUT);
+		req->vf_id = cpu_to_le16(i);
+		rc = hwrm_req_send(bp, req);
 		if (rc)
 			break;
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -446,51 +467,55 @@ static int bnxt_alloc_vf_resources(struct bnxt *bp, int num_vfs)
 
 static int bnxt_hwrm_func_buf_rgtr(struct bnxt *bp)
 {
-	struct hwrm_func_buf_rgtr_input req = {0};
+	struct hwrm_func_buf_rgtr_input *req;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_BUF_RGTR, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_BUF_RGTR);
+	if (rc)
+		return rc;
 
-	req.req_buf_num_pages = cpu_to_le16(bp->pf.hwrm_cmd_req_pages);
-	req.req_buf_page_size = cpu_to_le16(BNXT_PAGE_SHIFT);
-	req.req_buf_len = cpu_to_le16(BNXT_HWRM_REQ_MAX_SIZE);
-	req.req_buf_page_addr0 = cpu_to_le64(bp->pf.hwrm_cmd_req_dma_addr[0]);
-	req.req_buf_page_addr1 = cpu_to_le64(bp->pf.hwrm_cmd_req_dma_addr[1]);
-	req.req_buf_page_addr2 = cpu_to_le64(bp->pf.hwrm_cmd_req_dma_addr[2]);
-	req.req_buf_page_addr3 = cpu_to_le64(bp->pf.hwrm_cmd_req_dma_addr[3]);
+	req->req_buf_num_pages = cpu_to_le16(bp->pf.hwrm_cmd_req_pages);
+	req->req_buf_page_size = cpu_to_le16(BNXT_PAGE_SHIFT);
+	req->req_buf_len = cpu_to_le16(BNXT_HWRM_REQ_MAX_SIZE);
+	req->req_buf_page_addr0 = cpu_to_le64(bp->pf.hwrm_cmd_req_dma_addr[0]);
+	req->req_buf_page_addr1 = cpu_to_le64(bp->pf.hwrm_cmd_req_dma_addr[1]);
+	req->req_buf_page_addr2 = cpu_to_le64(bp->pf.hwrm_cmd_req_dma_addr[2]);
+	req->req_buf_page_addr3 = cpu_to_le64(bp->pf.hwrm_cmd_req_dma_addr[3]);
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
-/* Caller holds bp->hwrm_cmd_lock mutex lock */
-static void __bnxt_set_vf_params(struct bnxt *bp, int vf_id)
+static int __bnxt_set_vf_params(struct bnxt *bp, int vf_id)
 {
-	struct hwrm_func_cfg_input req = {0};
+	struct hwrm_func_cfg_input *req;
 	struct bnxt_vf_info *vf;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_CFG);
+	if (rc)
+		return rc;
 
 	vf = &bp->pf.vf[vf_id];
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
-	req.fid = cpu_to_le16(vf->fw_fid);
+	req->fid = cpu_to_le16(vf->fw_fid);
 
 	if (is_valid_ether_addr(vf->mac_addr)) {
-		req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
-		memcpy(req.dflt_mac_addr, vf->mac_addr, ETH_ALEN);
+		req->enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
+		memcpy(req->dflt_mac_addr, vf->mac_addr, ETH_ALEN);
 	}
 	if (vf->vlan) {
-		req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN);
-		req.dflt_vlan = cpu_to_le16(vf->vlan);
+		req->enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN);
+		req->dflt_vlan = cpu_to_le16(vf->vlan);
 	}
 	if (vf->max_tx_rate) {
-		req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW);
-		req.max_bw = cpu_to_le32(vf->max_tx_rate);
-#ifdef HAVE_IFLA_TX_RATE
-		req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MIN_BW);
-		req.min_bw = cpu_to_le32(vf->min_tx_rate);
-#endif
+		req->enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW |
+					    FUNC_CFG_REQ_ENABLES_MIN_BW);
+		req->max_bw = cpu_to_le32(vf->max_tx_rate);
+		req->min_bw = cpu_to_le32(vf->min_tx_rate);
 	}
 	if (vf->flags & BNXT_VF_TRUST)
-		req.flags |= cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE);
+		req->flags |= cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE);
 
-	_hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return hwrm_req_send(bp, req);
 }
 
 /* Only called by PF to reserve resources for VFs, returns actual number of
@@ -498,7 +523,7 @@ static void __bnxt_set_vf_params(struct bnxt *bp, int vf_id)
  */
 static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 {
-	struct hwrm_func_vf_resource_cfg_input req = {0};
+	struct hwrm_func_vf_resource_cfg_input *req;
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 	u16 vf_tx_rings, vf_rx_rings, vf_cp_rings;
 	u16 vf_stat_ctx, vf_vnics, vf_ring_grps;
@@ -507,7 +532,9 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 	u16 vf_msix = 0;
 	u16 vf_rss;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESOURCE_CFG, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_VF_RESOURCE_CFG);
+	if (rc)
+		return rc;
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5) {
 		vf_msix = hw_resc->max_nqs - bnxt_nq_rings_in_use(bp);
@@ -526,21 +553,21 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 	vf_vnics = min_t(u16, vf_vnics, vf_rx_rings);
 	vf_rss = hw_resc->max_rsscos_ctxs - bp->rsscos_nr_ctxs;
 
-	req.min_rsscos_ctx = cpu_to_le16(BNXT_VF_MIN_RSS_CTX);
+	req->min_rsscos_ctx = cpu_to_le16(BNXT_VF_MIN_RSS_CTX);
 	if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC) {
 		min = 0;
-		req.min_rsscos_ctx = cpu_to_le16(min);
+		req->min_rsscos_ctx = cpu_to_le16(min);
 	}
 	if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL ||
 	    pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC) {
-		req.min_cmpl_rings = cpu_to_le16(min);
-		req.min_tx_rings = cpu_to_le16(min);
-		req.min_rx_rings = cpu_to_le16(min);
-		req.min_l2_ctxs = cpu_to_le16(min);
-		req.min_vnics = cpu_to_le16(min);
-		req.min_stat_ctx = cpu_to_le16(min);
+		req->min_cmpl_rings = cpu_to_le16(min);
+		req->min_tx_rings = cpu_to_le16(min);
+		req->min_rx_rings = cpu_to_le16(min);
+		req->min_l2_ctxs = cpu_to_le16(min);
+		req->min_vnics = cpu_to_le16(min);
+		req->min_stat_ctx = cpu_to_le16(min);
 		if (!(bp->flags & BNXT_FLAG_CHIP_P5))
-			req.min_hw_ring_grps = cpu_to_le16(min);
+			req->min_hw_ring_grps = cpu_to_le16(min);
 	} else {
 		vf_cp_rings /= num_vfs;
 		vf_tx_rings /= num_vfs;
@@ -550,56 +577,57 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 		vf_ring_grps /= num_vfs;
 		vf_rss /= num_vfs;
 
-		req.min_cmpl_rings = cpu_to_le16(vf_cp_rings);
-		req.min_tx_rings = cpu_to_le16(vf_tx_rings);
-		req.min_rx_rings = cpu_to_le16(vf_rx_rings);
-		req.min_l2_ctxs = cpu_to_le16(BNXT_VF_MAX_L2_CTX);
-		req.min_vnics = cpu_to_le16(vf_vnics);
-		req.min_stat_ctx = cpu_to_le16(vf_stat_ctx);
-		req.min_hw_ring_grps = cpu_to_le16(vf_ring_grps);
-		req.min_rsscos_ctx = cpu_to_le16(vf_rss);
+		req->min_cmpl_rings = cpu_to_le16(vf_cp_rings);
+		req->min_tx_rings = cpu_to_le16(vf_tx_rings);
+		req->min_rx_rings = cpu_to_le16(vf_rx_rings);
+		req->min_l2_ctxs = cpu_to_le16(BNXT_VF_MAX_L2_CTX);
+		req->min_vnics = cpu_to_le16(vf_vnics);
+		req->min_stat_ctx = cpu_to_le16(vf_stat_ctx);
+		req->min_hw_ring_grps = cpu_to_le16(vf_ring_grps);
+		req->min_rsscos_ctx = cpu_to_le16(vf_rss);
 	}
-	req.max_cmpl_rings = cpu_to_le16(vf_cp_rings);
-	req.max_tx_rings = cpu_to_le16(vf_tx_rings);
-	req.max_rx_rings = cpu_to_le16(vf_rx_rings);
-	req.max_l2_ctxs = cpu_to_le16(BNXT_VF_MAX_L2_CTX);
-	req.max_vnics = cpu_to_le16(vf_vnics);
-	req.max_stat_ctx = cpu_to_le16(vf_stat_ctx);
-	req.max_hw_ring_grps = cpu_to_le16(vf_ring_grps);
-	req.max_rsscos_ctx = cpu_to_le16(vf_rss);
+	req->max_cmpl_rings = cpu_to_le16(vf_cp_rings);
+	req->max_tx_rings = cpu_to_le16(vf_tx_rings);
+	req->max_rx_rings = cpu_to_le16(vf_rx_rings);
+	req->max_l2_ctxs = cpu_to_le16(BNXT_VF_MAX_L2_CTX);
+	req->max_vnics = cpu_to_le16(vf_vnics);
+	req->max_stat_ctx = cpu_to_le16(vf_stat_ctx);
+	req->max_hw_ring_grps = cpu_to_le16(vf_ring_grps);
+	req->max_rsscos_ctx = cpu_to_le16(vf_rss);
 	if (bp->flags & BNXT_FLAG_CHIP_P5)
-		req.max_msix = cpu_to_le16(vf_msix / num_vfs);
+		req->max_msix = cpu_to_le16(vf_msix / num_vfs);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
+	hwrm_req_hold(bp, req);
 	for (i = 0; i < num_vfs; i++) {
 		if (reset)
 			__bnxt_set_vf_params(bp, i);
 
-		req.vf_id = cpu_to_le16(pf->first_vf_id + i);
-		rc = _hwrm_send_message(bp, &req, sizeof(req),
-					HWRM_CMD_TIMEOUT);
+		req->vf_id = cpu_to_le16(pf->first_vf_id + i);
+		rc = hwrm_req_send(bp, req);
 		if (rc)
 			break;
 		pf->active_vfs = i + 1;
 		pf->vf[i].fw_fid = pf->first_vf_id + i;
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+
 	if (pf->active_vfs) {
 		u16 n = pf->active_vfs;
 
-		hw_resc->max_tx_rings -= le16_to_cpu(req.min_tx_rings) * n;
-		hw_resc->max_rx_rings -= le16_to_cpu(req.min_rx_rings) * n;
-		hw_resc->max_hw_ring_grps -= le16_to_cpu(req.min_hw_ring_grps) *
-					     n;
-		hw_resc->max_cp_rings -= le16_to_cpu(req.min_cmpl_rings) * n;
-		hw_resc->max_rsscos_ctxs -= le16_to_cpu(req.min_rsscos_ctx) * n;
-		hw_resc->max_stat_ctxs -= le16_to_cpu(req.min_stat_ctx) * n;
-		hw_resc->max_vnics -= le16_to_cpu(req.min_vnics) * n;
+		hw_resc->max_tx_rings -= le16_to_cpu(req->min_tx_rings) * n;
+		hw_resc->max_rx_rings -= le16_to_cpu(req->min_rx_rings) * n;
+		hw_resc->max_hw_ring_grps -=
+			le16_to_cpu(req->min_hw_ring_grps) * n;
+		hw_resc->max_cp_rings -= le16_to_cpu(req->min_cmpl_rings) * n;
+		hw_resc->max_rsscos_ctxs -=
+			le16_to_cpu(req->min_rsscos_ctx) * n;
+		hw_resc->max_stat_ctxs -= le16_to_cpu(req->min_stat_ctx) * n;
+		hw_resc->max_vnics -= le16_to_cpu(req->min_vnics) * n;
 		if (bp->flags & BNXT_FLAG_CHIP_P5)
 			hw_resc->max_irqs -= vf_msix * n;
 
 		rc = pf->active_vfs;
 	}
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -608,15 +636,18 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
  */
 static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 {
-	u32 rc = 0, mtu, i;
 	u16 vf_tx_rings, vf_rx_rings, vf_cp_rings, vf_stat_ctx, vf_vnics;
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
-	struct hwrm_func_cfg_input req = {0};
 	struct bnxt_pf_info *pf = &bp->pf;
+	struct hwrm_func_cfg_input *req;
 	int total_vf_tx_rings = 0;
 	u16 vf_ring_grps;
+	u32 mtu, i;
+	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_CFG);
+	if (rc)
+		return rc;
 
 	/* Remaining rings are distributed equally amongs VF's for now */
 	vf_cp_rings = bnxt_get_avail_cp_rings_for_en(bp) / num_vfs;
@@ -632,50 +663,49 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 	vf_vnics = (hw_resc->max_vnics - bp->nr_vnics) / num_vfs;
 	vf_vnics = min_t(u16, vf_vnics, vf_rx_rings);
 
-	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_ADMIN_MTU |
-				  FUNC_CFG_REQ_ENABLES_MRU |
-				  FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS |
-				  FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS |
-				  FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-				  FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS |
-				  FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS |
-				  FUNC_CFG_REQ_ENABLES_NUM_L2_CTXS |
-				  FUNC_CFG_REQ_ENABLES_NUM_VNICS |
-				  FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS);
+	req->enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_ADMIN_MTU |
+				   FUNC_CFG_REQ_ENABLES_MRU |
+				   FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS |
+				   FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS |
+				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
+				   FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS |
+				   FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS |
+				   FUNC_CFG_REQ_ENABLES_NUM_L2_CTXS |
+				   FUNC_CFG_REQ_ENABLES_NUM_VNICS |
+				   FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS);
 
 	mtu = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
-	req.mru = cpu_to_le16(mtu);
-	req.admin_mtu = cpu_to_le16(mtu);
+	req->mru = cpu_to_le16(mtu);
+	req->admin_mtu = cpu_to_le16(mtu);
 
-	req.num_rsscos_ctxs = cpu_to_le16(1);
-	req.num_cmpl_rings = cpu_to_le16(vf_cp_rings);
-	req.num_tx_rings = cpu_to_le16(vf_tx_rings);
-	req.num_rx_rings = cpu_to_le16(vf_rx_rings);
-	req.num_hw_ring_grps = cpu_to_le16(vf_ring_grps);
-	req.num_l2_ctxs = cpu_to_le16(4);
+	req->num_rsscos_ctxs = cpu_to_le16(1);
+	req->num_cmpl_rings = cpu_to_le16(vf_cp_rings);
+	req->num_tx_rings = cpu_to_le16(vf_tx_rings);
+	req->num_rx_rings = cpu_to_le16(vf_rx_rings);
+	req->num_hw_ring_grps = cpu_to_le16(vf_ring_grps);
+	req->num_l2_ctxs = cpu_to_le16(4);
 
-	req.num_vnics = cpu_to_le16(vf_vnics);
+	req->num_vnics = cpu_to_le16(vf_vnics);
 	/* FIXME spec currently uses 1 bit for stats ctx */
-	req.num_stat_ctxs = cpu_to_le16(vf_stat_ctx);
+	req->num_stat_ctxs = cpu_to_le16(vf_stat_ctx);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
+	hwrm_req_hold(bp, req);
 	for (i = 0; i < num_vfs; i++) {
 		int vf_tx_rsvd = vf_tx_rings;
 
-		req.fid = cpu_to_le16(pf->first_vf_id + i);
-		rc = _hwrm_send_message(bp, &req, sizeof(req),
-					HWRM_CMD_TIMEOUT);
+		req->fid = cpu_to_le16(pf->first_vf_id + i);
+		rc = hwrm_req_send(bp, req);
 		if (rc)
 			break;
 		pf->active_vfs = i + 1;
-		pf->vf[i].fw_fid = le16_to_cpu(req.fid);
+		pf->vf[i].fw_fid = le16_to_cpu(req->fid);
 		rc = __bnxt_hwrm_get_tx_rings(bp, pf->vf[i].fw_fid,
 					      &vf_tx_rsvd);
 		if (rc)
 			break;
 		total_vf_tx_rings += vf_tx_rsvd;
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	if (pf->active_vfs) {
 		hw_resc->max_tx_rings -= total_vf_tx_rings;
 		hw_resc->max_rx_rings -= vf_rx_rings * num_vfs;
@@ -893,23 +923,24 @@ static int bnxt_hwrm_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf,
 			      void *encap_resp, __le64 encap_resp_addr,
 			      __le16 encap_resp_cpr, u32 msg_size)
 {
-	int rc = 0;
-	struct hwrm_fwd_resp_input req = {0};
+	struct hwrm_fwd_resp_input *req;
+	int rc;
 
 	if (BNXT_FWD_RESP_SIZE_ERR(msg_size))
 		return -EINVAL;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FWD_RESP, -1, -1);
-
-	/* Set the new target id */
-	req.target_id = cpu_to_le16(vf->fw_fid);
-	req.encap_resp_target_id = cpu_to_le16(vf->fw_fid);
-	req.encap_resp_len = cpu_to_le16(msg_size);
-	req.encap_resp_addr = encap_resp_addr;
-	req.encap_resp_cmpl_ring = encap_resp_cpr;
-	memcpy(req.encap_resp, encap_resp, msg_size);
-
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_FWD_RESP);
+	if (!rc) {
+		/* Set the new target id */
+		req->target_id = cpu_to_le16(vf->fw_fid);
+		req->encap_resp_target_id = cpu_to_le16(vf->fw_fid);
+		req->encap_resp_len = cpu_to_le16(msg_size);
+		req->encap_resp_addr = encap_resp_addr;
+		req->encap_resp_cmpl_ring = encap_resp_cpr;
+		memcpy(req->encap_resp, encap_resp, msg_size);
+
+		rc = hwrm_req_send(bp, req);
+	}
 	if (rc)
 		netdev_err(bp->dev, "hwrm_fwd_resp failed. rc:%d\n", rc);
 	return rc;
@@ -918,19 +949,21 @@ static int bnxt_hwrm_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf,
 static int bnxt_hwrm_fwd_err_resp(struct bnxt *bp, struct bnxt_vf_info *vf,
 				  u32 msg_size)
 {
-	int rc = 0;
-	struct hwrm_reject_fwd_resp_input req = {0};
+	struct hwrm_reject_fwd_resp_input *req;
+	int rc;
 
 	if (BNXT_REJ_FWD_RESP_SIZE_ERR(msg_size))
 		return -EINVAL;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_REJECT_FWD_RESP, -1, -1);
-	/* Set the new target id */
-	req.target_id = cpu_to_le16(vf->fw_fid);
-	req.encap_resp_target_id = cpu_to_le16(vf->fw_fid);
-	memcpy(req.encap_request, vf->hwrm_cmd_req_addr, msg_size);
+	rc = hwrm_req_init(bp, req, HWRM_REJECT_FWD_RESP);
+	if (!rc) {
+		/* Set the new target id */
+		req->target_id = cpu_to_le16(vf->fw_fid);
+		req->encap_resp_target_id = cpu_to_le16(vf->fw_fid);
+		memcpy(req->encap_request, vf->hwrm_cmd_req_addr, msg_size);
 
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		rc = hwrm_req_send(bp, req);
+	}
 	if (rc)
 		netdev_err(bp->dev, "hwrm_fwd_err_resp failed. rc:%d\n", rc);
 	return rc;
@@ -939,19 +972,21 @@ static int bnxt_hwrm_fwd_err_resp(struct bnxt *bp, struct bnxt_vf_info *vf,
 static int bnxt_hwrm_exec_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf,
 				   u32 msg_size)
 {
-	int rc = 0;
-	struct hwrm_exec_fwd_resp_input req = {0};
+	struct hwrm_exec_fwd_resp_input *req;
+	int rc;
 
 	if (BNXT_EXEC_FWD_RESP_SIZE_ERR(msg_size))
 		return -EINVAL;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_EXEC_FWD_RESP, -1, -1);
-	/* Set the new target id */
-	req.target_id = cpu_to_le16(vf->fw_fid);
-	req.encap_resp_target_id = cpu_to_le16(vf->fw_fid);
-	memcpy(req.encap_request, vf->hwrm_cmd_req_addr, msg_size);
+	rc = hwrm_req_init(bp, req, HWRM_EXEC_FWD_RESP);
+	if (!rc) {
+		/* Set the new target id */
+		req->target_id = cpu_to_le16(vf->fw_fid);
+		req->encap_resp_target_id = cpu_to_le16(vf->fw_fid);
+		memcpy(req->encap_request, vf->hwrm_cmd_req_addr, msg_size);
 
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		rc = hwrm_req_send(bp, req);
+	}
 	if (rc)
 		netdev_err(bp->dev, "hwrm_exec_fw_resp failed. rc:%d\n", rc);
 	return rc;
@@ -1031,10 +1066,10 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf)
 
 		phy_qcfg_req =
 		(struct hwrm_port_phy_qcfg_input *)vf->hwrm_cmd_req_addr;
-		mutex_lock(&bp->hwrm_cmd_lock);
+		mutex_lock(&bp->link_lock);
 		memcpy(&phy_qcfg_resp, &bp->link_info.phy_qcfg_resp,
 		       sizeof(phy_qcfg_resp));
-		mutex_unlock(&bp->hwrm_cmd_lock);
+		mutex_unlock(&bp->link_lock);
 		phy_qcfg_resp.resp_len = cpu_to_le16(sizeof(phy_qcfg_resp));
 		phy_qcfg_resp.seq_id = phy_qcfg_req->seq_id;
 		phy_qcfg_resp.valid = 1;
@@ -1118,7 +1153,7 @@ void bnxt_hwrm_exec_fwd_req(struct bnxt *bp)
 
 int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict)
 {
-	struct hwrm_func_vf_cfg_input req = {0};
+	struct hwrm_func_vf_cfg_input *req;
 	int rc = 0;
 
 	if (!BNXT_VF(bp))
@@ -1129,10 +1164,16 @@ int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict)
 			rc = -EADDRNOTAVAIL;
 		goto mac_done;
 	}
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_CFG, -1, -1);
-	req.enables = cpu_to_le32(FUNC_VF_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
-	memcpy(req.dflt_mac_addr, mac, ETH_ALEN);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_VF_CFG);
+	if (rc)
+		goto mac_done;
+
+	req->enables = cpu_to_le32(FUNC_VF_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
+	memcpy(req->dflt_mac_addr, mac, ETH_ALEN);
+	if (!strict)
+		hwrm_req_flags(bp, req, BNXT_HWRM_CTX_SILENT);
+	rc = hwrm_req_send(bp, req);
 mac_done:
 	if (rc && strict) {
 		rc = -EADDRNOTAVAIL;
@@ -1145,15 +1186,17 @@ mac_done:
 
 void bnxt_update_vf_mac(struct bnxt *bp)
 {
-	struct hwrm_func_qcaps_input req = {0};
-	struct hwrm_func_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_func_qcaps_output *resp;
+	struct hwrm_func_qcaps_input *req;
 	bool inform_pf = false;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCAPS, -1, -1);
-	req.fid = cpu_to_le16(0xffff);
+	if (hwrm_req_init(bp, req, HWRM_FUNC_QCAPS))
+		return;
+
+	req->fid = cpu_to_le16(0xffff);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	if (_hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT))
+	resp = hwrm_req_hold(bp, req);
+	if (hwrm_req_send(bp, req))
 		goto update_vf_mac_exit;
 
 	/* Store MAC address from the firmware.  There are 2 cases:
@@ -1176,7 +1219,7 @@ void bnxt_update_vf_mac(struct bnxt *bp)
 	if (is_valid_ether_addr(bp->vf.mac_addr))
 		memcpy(bp->dev->dev_addr, bp->vf.mac_addr, ETH_ALEN);
 update_vf_mac_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	if (inform_pf)
 		bnxt_approve_mac(bp, bp->dev->dev_addr, false);
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 5e4429b14b8c..46fae1acbeed 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -22,6 +22,7 @@
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
+#include "bnxt_hwrm.h"
 #include "bnxt_sriov.h"
 #include "bnxt_tc.h"
 #include "bnxt_vfr.h"
@@ -502,16 +503,18 @@ static int bnxt_tc_parse_flow(struct bnxt *bp,
 static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp,
 				   struct bnxt_tc_flow_node *flow_node)
 {
-	struct hwrm_cfa_flow_free_input req = { 0 };
+	struct hwrm_cfa_flow_free_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_FREE, -1, -1);
-	if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE)
-		req.ext_flow_handle = flow_node->ext_flow_handle;
-	else
-		req.flow_handle = flow_node->flow_handle;
+	rc = hwrm_req_init(bp, req, HWRM_CFA_FLOW_FREE);
+	if (!rc) {
+		if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE)
+			req->ext_flow_handle = flow_node->ext_flow_handle;
+		else
+			req->flow_handle = flow_node->flow_handle;
 
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		rc = hwrm_req_send(bp, req);
+	}
 	if (rc)
 		netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc);
 
@@ -587,20 +590,22 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 	struct bnxt_tc_actions *actions = &flow->actions;
 	struct bnxt_tc_l3_key *l3_mask = &flow->l3_mask;
 	struct bnxt_tc_l3_key *l3_key = &flow->l3_key;
-	struct hwrm_cfa_flow_alloc_input req = { 0 };
 	struct hwrm_cfa_flow_alloc_output *resp;
+	struct hwrm_cfa_flow_alloc_input *req;
 	u16 flow_flags = 0, action_flags = 0;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_ALLOC, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_FLOW_ALLOC);
+	if (rc)
+		return rc;
 
-	req.src_fid = cpu_to_le16(flow->src_fid);
-	req.ref_flow_handle = ref_flow_handle;
+	req->src_fid = cpu_to_le16(flow->src_fid);
+	req->ref_flow_handle = ref_flow_handle;
 
 	if (actions->flags & BNXT_TC_ACTION_FLAG_L2_REWRITE) {
-		memcpy(req.l2_rewrite_dmac, actions->l2_rewrite_dmac,
+		memcpy(req->l2_rewrite_dmac, actions->l2_rewrite_dmac,
 		       ETH_ALEN);
-		memcpy(req.l2_rewrite_smac, actions->l2_rewrite_smac,
+		memcpy(req->l2_rewrite_smac, actions->l2_rewrite_smac,
 		       ETH_ALEN);
 		action_flags |=
 			CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE;
@@ -615,71 +620,71 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 				action_flags |=
 					CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC;
 				/* L3 source rewrite */
-				req.nat_ip_address[0] =
+				req->nat_ip_address[0] =
 					actions->nat.l3.ipv4.saddr.s_addr;
 				/* L4 source port */
 				if (actions->nat.l4.ports.sport)
-					req.nat_port =
+					req->nat_port =
 						actions->nat.l4.ports.sport;
 			} else {
 				action_flags |=
 					CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST;
 				/* L3 destination rewrite */
-				req.nat_ip_address[0] =
+				req->nat_ip_address[0] =
 					actions->nat.l3.ipv4.daddr.s_addr;
 				/* L4 destination port */
 				if (actions->nat.l4.ports.dport)
-					req.nat_port =
+					req->nat_port =
 						actions->nat.l4.ports.dport;
 			}
 			netdev_dbg(bp->dev,
-				   "req.nat_ip_address: %pI4 src_xlate: %d req.nat_port: %x\n",
-				   req.nat_ip_address, actions->nat.src_xlate,
-				   req.nat_port);
+				   "req->nat_ip_address: %pI4 src_xlate: %d req->nat_port: %x\n",
+				   req->nat_ip_address, actions->nat.src_xlate,
+				   req->nat_port);
 		} else {
 			if (actions->nat.src_xlate) {
 				action_flags |=
 					CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC;
 				/* L3 source rewrite */
-				memcpy(req.nat_ip_address,
+				memcpy(req->nat_ip_address,
 				       actions->nat.l3.ipv6.saddr.s6_addr32,
-				       sizeof(req.nat_ip_address));
+				       sizeof(req->nat_ip_address));
 				/* L4 source port */
 				if (actions->nat.l4.ports.sport)
-					req.nat_port =
+					req->nat_port =
 						actions->nat.l4.ports.sport;
 			} else {
 				action_flags |=
 					CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST;
 				/* L3 destination rewrite */
-				memcpy(req.nat_ip_address,
+				memcpy(req->nat_ip_address,
 				       actions->nat.l3.ipv6.daddr.s6_addr32,
-				       sizeof(req.nat_ip_address));
+				       sizeof(req->nat_ip_address));
 				/* L4 destination port */
 				if (actions->nat.l4.ports.dport)
-					req.nat_port =
+					req->nat_port =
 						actions->nat.l4.ports.dport;
 			}
 			netdev_dbg(bp->dev,
-				   "req.nat_ip_address: %pI6 src_xlate: %d req.nat_port: %x\n",
-				   req.nat_ip_address, actions->nat.src_xlate,
-				   req.nat_port);
+				   "req->nat_ip_address: %pI6 src_xlate: %d req->nat_port: %x\n",
+				   req->nat_ip_address, actions->nat.src_xlate,
+				   req->nat_port);
 		}
 	}
 
 	if (actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP ||
 	    actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP) {
-		req.tunnel_handle = tunnel_handle;
+		req->tunnel_handle = tunnel_handle;
 		flow_flags |= CFA_FLOW_ALLOC_REQ_FLAGS_TUNNEL;
 		action_flags |= CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL;
 	}
 
-	req.ethertype = flow->l2_key.ether_type;
-	req.ip_proto = flow->l4_key.ip_proto;
+	req->ethertype = flow->l2_key.ether_type;
+	req->ip_proto = flow->l4_key.ip_proto;
 
 	if (flow->flags & BNXT_TC_FLOW_FLAGS_ETH_ADDRS) {
-		memcpy(req.dmac, flow->l2_key.dmac, ETH_ALEN);
-		memcpy(req.smac, flow->l2_key.smac, ETH_ALEN);
+		memcpy(req->dmac, flow->l2_key.dmac, ETH_ALEN);
+		memcpy(req->smac, flow->l2_key.smac, ETH_ALEN);
 	}
 
 	if (flow->l2_key.num_vlans > 0) {
@@ -688,7 +693,7 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 		 * in outer_vlan_tci when num_vlans is 1 (which is
 		 * always the case in TC.)
 		 */
-		req.outer_vlan_tci = flow->l2_key.inner_vlan_tci;
+		req->outer_vlan_tci = flow->l2_key.inner_vlan_tci;
 	}
 
 	/* If all IP and L4 fields are wildcarded then this is an L2 flow */
@@ -701,68 +706,67 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 				CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6;
 
 		if (flow->flags & BNXT_TC_FLOW_FLAGS_IPV4_ADDRS) {
-			req.ip_dst[0] = l3_key->ipv4.daddr.s_addr;
-			req.ip_dst_mask_len =
+			req->ip_dst[0] = l3_key->ipv4.daddr.s_addr;
+			req->ip_dst_mask_len =
 				inet_mask_len(l3_mask->ipv4.daddr.s_addr);
-			req.ip_src[0] = l3_key->ipv4.saddr.s_addr;
-			req.ip_src_mask_len =
+			req->ip_src[0] = l3_key->ipv4.saddr.s_addr;
+			req->ip_src_mask_len =
 				inet_mask_len(l3_mask->ipv4.saddr.s_addr);
 		} else if (flow->flags & BNXT_TC_FLOW_FLAGS_IPV6_ADDRS) {
-			memcpy(req.ip_dst, l3_key->ipv6.daddr.s6_addr32,
-			       sizeof(req.ip_dst));
-			req.ip_dst_mask_len =
+			memcpy(req->ip_dst, l3_key->ipv6.daddr.s6_addr32,
+			       sizeof(req->ip_dst));
+			req->ip_dst_mask_len =
 					ipv6_mask_len(&l3_mask->ipv6.daddr);
-			memcpy(req.ip_src, l3_key->ipv6.saddr.s6_addr32,
-			       sizeof(req.ip_src));
-			req.ip_src_mask_len =
+			memcpy(req->ip_src, l3_key->ipv6.saddr.s6_addr32,
+			       sizeof(req->ip_src));
+			req->ip_src_mask_len =
 					ipv6_mask_len(&l3_mask->ipv6.saddr);
 		}
 	}
 
 	if (flow->flags & BNXT_TC_FLOW_FLAGS_PORTS) {
-		req.l4_src_port = flow->l4_key.ports.sport;
-		req.l4_src_port_mask = flow->l4_mask.ports.sport;
-		req.l4_dst_port = flow->l4_key.ports.dport;
-		req.l4_dst_port_mask = flow->l4_mask.ports.dport;
+		req->l4_src_port = flow->l4_key.ports.sport;
+		req->l4_src_port_mask = flow->l4_mask.ports.sport;
+		req->l4_dst_port = flow->l4_key.ports.dport;
+		req->l4_dst_port_mask = flow->l4_mask.ports.dport;
 	} else if (flow->flags & BNXT_TC_FLOW_FLAGS_ICMP) {
 		/* l4 ports serve as type/code when ip_proto is ICMP */
-		req.l4_src_port = htons(flow->l4_key.icmp.type);
-		req.l4_src_port_mask = htons(flow->l4_mask.icmp.type);
-		req.l4_dst_port = htons(flow->l4_key.icmp.code);
-		req.l4_dst_port_mask = htons(flow->l4_mask.icmp.code);
+		req->l4_src_port = htons(flow->l4_key.icmp.type);
+		req->l4_src_port_mask = htons(flow->l4_mask.icmp.type);
+		req->l4_dst_port = htons(flow->l4_key.icmp.code);
+		req->l4_dst_port_mask = htons(flow->l4_mask.icmp.code);
 	}
-	req.flags = cpu_to_le16(flow_flags);
+	req->flags = cpu_to_le16(flow_flags);
 
 	if (actions->flags & BNXT_TC_ACTION_FLAG_DROP) {
 		action_flags |= CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP;
 	} else {
 		if (actions->flags & BNXT_TC_ACTION_FLAG_FWD) {
 			action_flags |= CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD;
-			req.dst_fid = cpu_to_le16(actions->dst_fid);
+			req->dst_fid = cpu_to_le16(actions->dst_fid);
 		}
 		if (actions->flags & BNXT_TC_ACTION_FLAG_PUSH_VLAN) {
 			action_flags |=
 			    CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE;
-			req.l2_rewrite_vlan_tpid = actions->push_vlan_tpid;
-			req.l2_rewrite_vlan_tci = actions->push_vlan_tci;
-			memcpy(&req.l2_rewrite_dmac, &req.dmac, ETH_ALEN);
-			memcpy(&req.l2_rewrite_smac, &req.smac, ETH_ALEN);
+			req->l2_rewrite_vlan_tpid = actions->push_vlan_tpid;
+			req->l2_rewrite_vlan_tci = actions->push_vlan_tci;
+			memcpy(&req->l2_rewrite_dmac, &req->dmac, ETH_ALEN);
+			memcpy(&req->l2_rewrite_smac, &req->smac, ETH_ALEN);
 		}
 		if (actions->flags & BNXT_TC_ACTION_FLAG_POP_VLAN) {
 			action_flags |=
 			    CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE;
 			/* Rewrite config with tpid = 0 implies vlan pop */
-			req.l2_rewrite_vlan_tpid = 0;
-			memcpy(&req.l2_rewrite_dmac, &req.dmac, ETH_ALEN);
-			memcpy(&req.l2_rewrite_smac, &req.smac, ETH_ALEN);
+			req->l2_rewrite_vlan_tpid = 0;
+			memcpy(&req->l2_rewrite_dmac, &req->dmac, ETH_ALEN);
+			memcpy(&req->l2_rewrite_smac, &req->smac, ETH_ALEN);
 		}
 	}
-	req.action_flags = cpu_to_le16(action_flags);
+	req->action_flags = cpu_to_le16(action_flags);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
 	if (!rc) {
-		resp = bnxt_get_hwrm_resp_addr(bp, &req);
 		/* CFA_FLOW_ALLOC response interpretation:
 		 *		    fw with	     fw with
 		 *		    16-bit	     64-bit
@@ -778,7 +782,7 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 			flow_node->flow_id = resp->flow_id;
 		}
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
@@ -788,67 +792,69 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp,
 				       __le32 ref_decap_handle,
 				       __le32 *decap_filter_handle)
 {
-	struct hwrm_cfa_decap_filter_alloc_input req = { 0 };
 	struct hwrm_cfa_decap_filter_alloc_output *resp;
 	struct ip_tunnel_key *tun_key = &flow->tun_key;
+	struct hwrm_cfa_decap_filter_alloc_input *req;
 	u32 enables = 0;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_DECAP_FILTER_ALLOC, -1, -1);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_DECAP_FILTER_ALLOC);
+	if (rc)
+		goto exit;
 
-	req.flags = cpu_to_le32(CFA_DECAP_FILTER_ALLOC_REQ_FLAGS_OVS_TUNNEL);
+	req->flags = cpu_to_le32(CFA_DECAP_FILTER_ALLOC_REQ_FLAGS_OVS_TUNNEL);
 	enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE |
 		   CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL;
-	req.tunnel_type = CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN;
-	req.ip_protocol = CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP;
+	req->tunnel_type = CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN;
+	req->ip_protocol = CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP;
 
 	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_ID) {
 		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_ID;
 		/* tunnel_id is wrongly defined in hsi defn. as __le32 */
-		req.tunnel_id = tunnel_id_to_key32(tun_key->tun_id);
+		req->tunnel_id = tunnel_id_to_key32(tun_key->tun_id);
 	}
 
 	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_ETH_ADDRS) {
 		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR;
-		ether_addr_copy(req.dst_macaddr, l2_info->dmac);
+		ether_addr_copy(req->dst_macaddr, l2_info->dmac);
 	}
 	if (l2_info->num_vlans) {
 		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_IVLAN_VID;
-		req.t_ivlan_vid = l2_info->inner_vlan_tci;
+		req->t_ivlan_vid = l2_info->inner_vlan_tci;
 	}
 
 	enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE;
-	req.ethertype = htons(ETH_P_IP);
+	req->ethertype = htons(ETH_P_IP);
 
 	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS) {
 		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR |
 			   CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR |
 			   CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE;
-		req.ip_addr_type = CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4;
-		req.dst_ipaddr[0] = tun_key->u.ipv4.dst;
-		req.src_ipaddr[0] = tun_key->u.ipv4.src;
+		req->ip_addr_type =
+			CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4;
+		req->dst_ipaddr[0] = tun_key->u.ipv4.dst;
+		req->src_ipaddr[0] = tun_key->u.ipv4.src;
 	}
 
 	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_PORTS) {
 		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_PORT;
-		req.dst_port = tun_key->tp_dst;
+		req->dst_port = tun_key->tp_dst;
 	}
 
 	/* Eventhough the decap_handle returned by hwrm_cfa_decap_filter_alloc
 	 * is defined as __le32, l2_ctxt_ref_id is defined in HSI as __le16.
 	 */
-	req.l2_ctxt_ref_id = (__force __le16)ref_decap_handle;
-	req.enables = cpu_to_le32(enables);
+	req->l2_ctxt_ref_id = (__force __le16)ref_decap_handle;
+	req->enables = cpu_to_le32(enables);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc) {
-		resp = bnxt_get_hwrm_resp_addr(bp, &req);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
+	if (!rc)
 		*decap_filter_handle = resp->decap_filter_id;
-	} else {
+	hwrm_req_drop(bp, req);
+exit:
+	if (rc)
 		netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc);
-	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
 
 	return rc;
 }
@@ -856,13 +862,14 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp,
 static int hwrm_cfa_decap_filter_free(struct bnxt *bp,
 				      __le32 decap_filter_handle)
 {
-	struct hwrm_cfa_decap_filter_free_input req = { 0 };
+	struct hwrm_cfa_decap_filter_free_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_DECAP_FILTER_FREE, -1, -1);
-	req.decap_filter_id = decap_filter_handle;
-
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_DECAP_FILTER_FREE);
+	if (!rc) {
+		req->decap_filter_id = decap_filter_handle;
+		rc = hwrm_req_send(bp, req);
+	}
 	if (rc)
 		netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc);
 
@@ -874,18 +881,18 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp,
 				       struct bnxt_tc_l2_key *l2_info,
 				       __le32 *encap_record_handle)
 {
-	struct hwrm_cfa_encap_record_alloc_input req = { 0 };
 	struct hwrm_cfa_encap_record_alloc_output *resp;
-	struct hwrm_cfa_encap_data_vxlan *encap =
-			(struct hwrm_cfa_encap_data_vxlan *)&req.encap_data;
-	struct hwrm_vxlan_ipv4_hdr *encap_ipv4 =
-				(struct hwrm_vxlan_ipv4_hdr *)encap->l3;
+	struct hwrm_cfa_encap_record_alloc_input *req;
+	struct hwrm_cfa_encap_data_vxlan *encap;
+	struct hwrm_vxlan_ipv4_hdr *encap_ipv4;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_ENCAP_RECORD_ALLOC, -1, -1);
-
-	req.encap_type = CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN;
+	rc = hwrm_req_init(bp, req, HWRM_CFA_ENCAP_RECORD_ALLOC);
+	if (rc)
+		goto exit;
 
+	encap = (struct hwrm_cfa_encap_data_vxlan *)&req->encap_data;
+	req->encap_type = CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN;
 	ether_addr_copy(encap->dst_mac_addr, l2_info->dmac);
 	ether_addr_copy(encap->src_mac_addr, l2_info->smac);
 	if (l2_info->num_vlans) {
@@ -894,6 +901,7 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp,
 		encap->ovlan_tpid = l2_info->inner_vlan_tpid;
 	}
 
+	encap_ipv4 = (struct hwrm_vxlan_ipv4_hdr *)encap->l3;
 	encap_ipv4->ver_hlen = 4 << VXLAN_IPV4_HDR_VER_HLEN_VERSION_SFT;
 	encap_ipv4->ver_hlen |= 5 << VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_SFT;
 	encap_ipv4->ttl = encap_key->ttl;
@@ -905,15 +913,14 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp,
 	encap->dst_port = encap_key->tp_dst;
 	encap->vni = tunnel_id_to_key32(encap_key->tun_id);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc) {
-		resp = bnxt_get_hwrm_resp_addr(bp, &req);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
+	if (!rc)
 		*encap_record_handle = resp->encap_record_id;
-	} else {
+	hwrm_req_drop(bp, req);
+exit:
+	if (rc)
 		netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc);
-	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
 
 	return rc;
 }
@@ -921,13 +928,14 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp,
 static int hwrm_cfa_encap_record_free(struct bnxt *bp,
 				      __le32 encap_record_handle)
 {
-	struct hwrm_cfa_encap_record_free_input req = { 0 };
+	struct hwrm_cfa_encap_record_free_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_ENCAP_RECORD_FREE, -1, -1);
-	req.encap_record_id = encap_record_handle;
-
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_ENCAP_RECORD_FREE);
+	if (!rc) {
+		req->encap_record_id = encap_record_handle;
+		rc = hwrm_req_send(bp, req);
+	}
 	if (rc)
 		netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc);
 
@@ -1673,14 +1681,20 @@ static int
 bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
 			     struct bnxt_tc_stats_batch stats_batch[])
 {
-	struct hwrm_cfa_flow_stats_input req = { 0 };
 	struct hwrm_cfa_flow_stats_output *resp;
-	__le16 *req_flow_handles = &req.flow_handle_0;
-	__le32 *req_flow_ids = &req.flow_id_0;
+	struct hwrm_cfa_flow_stats_input *req;
+	__le16 *req_flow_handles;
+	__le32 *req_flow_ids;
 	int rc, i;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_STATS, -1, -1);
-	req.num_flows = cpu_to_le16(num_flows);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_FLOW_STATS);
+	if (rc)
+		goto exit;
+
+	req_flow_handles = &req->flow_handle_0;
+	req_flow_ids = &req->flow_id_0;
+
+	req->num_flows = cpu_to_le16(num_flows);
 	for (i = 0; i < num_flows; i++) {
 		struct bnxt_tc_flow_node *flow_node = stats_batch[i].flow_node;
 
@@ -1688,13 +1702,12 @@ bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
 					&req_flow_handles[i], &req_flow_ids[i]);
 	}
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc) {
 		__le64 *resp_packets;
 		__le64 *resp_bytes;
 
-		resp = bnxt_get_hwrm_resp_addr(bp, &req);
 		resp_packets = &resp->packet_0;
 		resp_bytes = &resp->byte_0;
 
@@ -1704,10 +1717,11 @@ bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
 			stats_batch[i].hw_stats.bytes =
 						le64_to_cpu(resp_bytes[i]);
 		}
-	} else {
-		netdev_info(bp->dev, "error rc=%d\n", rc);
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
+exit:
+	if (rc)
+		netdev_info(bp->dev, "error rc=%d\n", rc);
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 187ff643ad2a..fde0c3e8ac57 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -22,6 +22,7 @@
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
+#include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
 
 static int bnxt_register_dev(struct bnxt_en_dev *edev, int ulp_id,
@@ -237,27 +238,33 @@ static int bnxt_send_msg(struct bnxt_en_dev *edev, int ulp_id,
 {
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
+	struct output *resp;
 	struct input *req;
+	u32 resp_len;
 	int rc;
 
 	if (ulp_id != BNXT_ROCE_ULP && bp->fw_reset_state)
 		return -EBUSY;
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	req = fw_msg->msg;
-	req->resp_addr = cpu_to_le64(bp->hwrm_cmd_resp_dma_addr);
-	rc = _hwrm_send_message(bp, fw_msg->msg, fw_msg->msg_len,
-				fw_msg->timeout);
-	if (!rc) {
-		struct output *resp = bp->hwrm_cmd_resp_addr;
-		u32 len = le16_to_cpu(resp->resp_len);
+	rc = hwrm_req_init(bp, req, 0 /* don't care */);
+	if (rc)
+		return rc;
 
-		if (fw_msg->resp_max_len < len)
-			len = fw_msg->resp_max_len;
+	rc = hwrm_req_replace(bp, req, fw_msg->msg, fw_msg->msg_len);
+	if (rc)
+		return rc;
 
-		memcpy(fw_msg->resp, resp, len);
+	hwrm_req_timeout(bp, req, fw_msg->timeout);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
+	resp_len = le16_to_cpu(resp->resp_len);
+	if (resp_len) {
+		if (fw_msg->resp_max_len < resp_len)
+			resp_len = fw_msg->resp_max_len;
+
+		memcpy(fw_msg->resp, resp, resp_len);
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index dd66302343a2..9401936b74fa 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -15,6 +15,7 @@
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
+#include "bnxt_hwrm.h"
 #include "bnxt_vfr.h"
 #include "bnxt_devlink.h"
 #include "bnxt_tc.h"
@@ -27,38 +28,40 @@
 static int hwrm_cfa_vfr_alloc(struct bnxt *bp, u16 vf_idx,
 			      u16 *tx_cfa_action, u16 *rx_cfa_code)
 {
-	struct hwrm_cfa_vfr_alloc_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_cfa_vfr_alloc_input req = { 0 };
+	struct hwrm_cfa_vfr_alloc_output *resp;
+	struct hwrm_cfa_vfr_alloc_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_VFR_ALLOC, -1, -1);
-	req.vf_id = cpu_to_le16(vf_idx);
-	sprintf(req.vfr_name, "vfr%d", vf_idx);
-
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_VFR_ALLOC);
 	if (!rc) {
-		*tx_cfa_action = le16_to_cpu(resp->tx_cfa_action);
-		*rx_cfa_code = le16_to_cpu(resp->rx_cfa_code);
-		netdev_dbg(bp->dev, "tx_cfa_action=0x%x, rx_cfa_code=0x%x",
-			   *tx_cfa_action, *rx_cfa_code);
-	} else {
-		netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc);
+		req->vf_id = cpu_to_le16(vf_idx);
+		sprintf(req->vfr_name, "vfr%d", vf_idx);
+
+		resp = hwrm_req_hold(bp, req);
+		rc = hwrm_req_send(bp, req);
+		if (!rc) {
+			*tx_cfa_action = le16_to_cpu(resp->tx_cfa_action);
+			*rx_cfa_code = le16_to_cpu(resp->rx_cfa_code);
+			netdev_dbg(bp->dev, "tx_cfa_action=0x%x, rx_cfa_code=0x%x",
+				   *tx_cfa_action, *rx_cfa_code);
+		}
+		hwrm_req_drop(bp, req);
 	}
-
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	if (rc)
+		netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc);
 	return rc;
 }
 
 static int hwrm_cfa_vfr_free(struct bnxt *bp, u16 vf_idx)
 {
-	struct hwrm_cfa_vfr_free_input req = { 0 };
+	struct hwrm_cfa_vfr_free_input *req;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_VFR_FREE, -1, -1);
-	sprintf(req.vfr_name, "vfr%d", vf_idx);
-
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_req_init(bp, req, HWRM_CFA_VFR_FREE);
+	if (!rc) {
+		sprintf(req->vfr_name, "vfr%d", vf_idx);
+		rc = hwrm_req_send(bp, req);
+	}
 	if (rc)
 		netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc);
 	return rc;
@@ -67,17 +70,18 @@ static int hwrm_cfa_vfr_free(struct bnxt *bp, u16 vf_idx)
 static int bnxt_hwrm_vfr_qcfg(struct bnxt *bp, struct bnxt_vf_rep *vf_rep,
 			      u16 *max_mtu)
 {
-	struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_func_qcfg_input req = {0};
+	struct hwrm_func_qcfg_output *resp;
+	struct hwrm_func_qcfg_input *req;
 	u16 mtu;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1);
-	req.fid = cpu_to_le16(bp->pf.vf[vf_rep->vf_idx].fw_fid);
-
-	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_QCFG);
+	if (rc)
+		return rc;
 
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	req->fid = cpu_to_le16(bp->pf.vf[vf_rep->vf_idx].fw_fid);
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
 	if (!rc) {
 		mtu = le16_to_cpu(resp->max_mtu_configured);
 		if (!mtu)
@@ -85,7 +89,7 @@ static int bnxt_hwrm_vfr_qcfg(struct bnxt *bp, struct bnxt_vf_rep *vf_rep,
 		else
 			*max_mtu = mtu;
 	}
-	mutex_unlock(&bp->hwrm_cmd_lock);
+	hwrm_req_drop(bp, req);
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index bee6e091a997..c8083df5e0ab 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -87,7 +87,7 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 			dma_unmap_single(&pdev->dev,
 					 dma_unmap_addr(tx_buf, mapping),
 					 dma_unmap_len(tx_buf, len),
-					 PCI_DMA_TODEVICE);
+					 DMA_TO_DEVICE);
 			xdp_return_frame(tx_buf->xdpf);
 			tx_buf->action = 0;
 			tx_buf->xdpf = NULL;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index db74241935ab..23c7595d2a1d 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -828,7 +828,9 @@ static void bcmgenet_set_msglevel(struct net_device *dev, u32 level)
 }
 
 static int bcmgenet_get_coalesce(struct net_device *dev,
-				 struct ethtool_coalesce *ec)
+				 struct ethtool_coalesce *ec,
+				 struct kernel_ethtool_coalesce *kernel_coal,
+				 struct netlink_ext_ack *extack)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct bcmgenet_rx_ring *ring;
@@ -890,7 +892,9 @@ static void bcmgenet_set_ring_rx_coalesce(struct bcmgenet_rx_ring *ring,
 }
 
 static int bcmgenet_set_coalesce(struct net_device *dev,
-				 struct ethtool_coalesce *ec)
+				 struct ethtool_coalesce *ec,
+				 struct kernel_ethtool_coalesce *kernel_coal,
+				 struct netlink_ext_ack *extack)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	unsigned int i;
@@ -3659,7 +3663,7 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_tx_timeout		= bcmgenet_timeout,
 	.ndo_set_rx_mode	= bcmgenet_set_rx_mode,
 	.ndo_set_mac_address	= bcmgenet_set_mac_addr,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_set_features	= bcmgenet_set_features,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= bcmgenet_poll_controller,
@@ -3972,8 +3976,6 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	 */
 	dev->needed_headroom += 64;
 
-	netdev_boot_setup_check(dev);
-
 	priv->dev = dev;
 	priv->pdev = pdev;
 
diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c
index 5b4568c2ad1c..f38f40eb966e 100644
--- a/drivers/net/ethernet/broadcom/sb1250-mac.c
+++ b/drivers/net/ethernet/broadcom/sb1250-mac.c
@@ -2136,7 +2136,7 @@ static const struct net_device_ops sbmac_netdev_ops = {
 	.ndo_start_xmit		= sbmac_start_tx,
 	.ndo_set_rx_mode	= sbmac_set_rx_mode,
 	.ndo_tx_timeout		= sbmac_tx_timeout,
-	.ndo_do_ioctl		= sbmac_mii_ioctl,
+	.ndo_eth_ioctl		= sbmac_mii_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index b0e49643f483..8a238e349e02 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6564,10 +6564,8 @@ static void tg3_tx(struct tg3_napi *tnapi)
 			skb_tstamp_tx(skb, &timestamp);
 		}
 
-		pci_unmap_single(tp->pdev,
-				 dma_unmap_addr(ri, mapping),
-				 skb_headlen(skb),
-				 PCI_DMA_TODEVICE);
+		dma_unmap_single(&tp->pdev->dev, dma_unmap_addr(ri, mapping),
+				 skb_headlen(skb), DMA_TO_DEVICE);
 
 		ri->skb = NULL;
 
@@ -6584,10 +6582,10 @@ static void tg3_tx(struct tg3_napi *tnapi)
 			if (unlikely(ri->skb != NULL || sw_idx == hw_idx))
 				tx_bug = 1;
 
-			pci_unmap_page(tp->pdev,
+			dma_unmap_page(&tp->pdev->dev,
 				       dma_unmap_addr(ri, mapping),
 				       skb_frag_size(&skb_shinfo(skb)->frags[i]),
-				       PCI_DMA_TODEVICE);
+				       DMA_TO_DEVICE);
 
 			while (ri->fragmented) {
 				ri->fragmented = false;
@@ -6646,8 +6644,8 @@ static void tg3_rx_data_free(struct tg3 *tp, struct ring_info *ri, u32 map_sz)
 	if (!ri->data)
 		return;
 
-	pci_unmap_single(tp->pdev, dma_unmap_addr(ri, mapping),
-			 map_sz, PCI_DMA_FROMDEVICE);
+	dma_unmap_single(&tp->pdev->dev, dma_unmap_addr(ri, mapping), map_sz,
+			 DMA_FROM_DEVICE);
 	tg3_frag_free(skb_size <= PAGE_SIZE, ri->data);
 	ri->data = NULL;
 }
@@ -6711,11 +6709,9 @@ static int tg3_alloc_rx_data(struct tg3 *tp, struct tg3_rx_prodring_set *tpr,
 	if (!data)
 		return -ENOMEM;
 
-	mapping = pci_map_single(tp->pdev,
-				 data + TG3_RX_OFFSET(tp),
-				 data_size,
-				 PCI_DMA_FROMDEVICE);
-	if (unlikely(pci_dma_mapping_error(tp->pdev, mapping))) {
+	mapping = dma_map_single(&tp->pdev->dev, data + TG3_RX_OFFSET(tp),
+				 data_size, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(&tp->pdev->dev, mapping))) {
 		tg3_frag_free(skb_size <= PAGE_SIZE, data);
 		return -EIO;
 	}
@@ -6882,8 +6878,8 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 			if (skb_size < 0)
 				goto drop_it;
 
-			pci_unmap_single(tp->pdev, dma_addr, skb_size,
-					 PCI_DMA_FROMDEVICE);
+			dma_unmap_single(&tp->pdev->dev, dma_addr, skb_size,
+					 DMA_FROM_DEVICE);
 
 			/* Ensure that the update to the data happens
 			 * after the usage of the old DMA mapping.
@@ -6908,11 +6904,13 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 				goto drop_it_no_recycle;
 
 			skb_reserve(skb, TG3_RAW_IP_ALIGN);
-			pci_dma_sync_single_for_cpu(tp->pdev, dma_addr, len, PCI_DMA_FROMDEVICE);
+			dma_sync_single_for_cpu(&tp->pdev->dev, dma_addr, len,
+						DMA_FROM_DEVICE);
 			memcpy(skb->data,
 			       data + TG3_RX_OFFSET(tp),
 			       len);
-			pci_dma_sync_single_for_device(tp->pdev, dma_addr, len, PCI_DMA_FROMDEVICE);
+			dma_sync_single_for_device(&tp->pdev->dev, dma_addr,
+						   len, DMA_FROM_DEVICE);
 		}
 
 		skb_put(skb, len);
@@ -7762,10 +7760,8 @@ static void tg3_tx_skb_unmap(struct tg3_napi *tnapi, u32 entry, int last)
 	skb = txb->skb;
 	txb->skb = NULL;
 
-	pci_unmap_single(tnapi->tp->pdev,
-			 dma_unmap_addr(txb, mapping),
-			 skb_headlen(skb),
-			 PCI_DMA_TODEVICE);
+	dma_unmap_single(&tnapi->tp->pdev->dev, dma_unmap_addr(txb, mapping),
+			 skb_headlen(skb), DMA_TO_DEVICE);
 
 	while (txb->fragmented) {
 		txb->fragmented = false;
@@ -7779,9 +7775,9 @@ static void tg3_tx_skb_unmap(struct tg3_napi *tnapi, u32 entry, int last)
 		entry = NEXT_TX(entry);
 		txb = &tnapi->tx_buffers[entry];
 
-		pci_unmap_page(tnapi->tp->pdev,
+		dma_unmap_page(&tnapi->tp->pdev->dev,
 			       dma_unmap_addr(txb, mapping),
-			       skb_frag_size(frag), PCI_DMA_TODEVICE);
+			       skb_frag_size(frag), DMA_TO_DEVICE);
 
 		while (txb->fragmented) {
 			txb->fragmented = false;
@@ -7816,10 +7812,10 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi,
 		ret = -1;
 	} else {
 		/* New SKB is guaranteed to be linear. */
-		new_addr = pci_map_single(tp->pdev, new_skb->data, new_skb->len,
-					  PCI_DMA_TODEVICE);
+		new_addr = dma_map_single(&tp->pdev->dev, new_skb->data,
+					  new_skb->len, DMA_TO_DEVICE);
 		/* Make sure the mapping succeeded */
-		if (pci_dma_mapping_error(tp->pdev, new_addr)) {
+		if (dma_mapping_error(&tp->pdev->dev, new_addr)) {
 			dev_kfree_skb_any(new_skb);
 			ret = -1;
 		} else {
@@ -8043,8 +8039,9 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	len = skb_headlen(skb);
 
-	mapping = pci_map_single(tp->pdev, skb->data, len, PCI_DMA_TODEVICE);
-	if (pci_dma_mapping_error(tp->pdev, mapping))
+	mapping = dma_map_single(&tp->pdev->dev, skb->data, len,
+				 DMA_TO_DEVICE);
+	if (dma_mapping_error(&tp->pdev->dev, mapping))
 		goto drop;
 
 
@@ -13499,8 +13496,8 @@ static int tg3_run_loopback(struct tg3 *tp, u32 pktsz, bool tso_loopback)
 	for (i = data_off; i < tx_len; i++)
 		tx_data[i] = (u8) (i & 0xff);
 
-	map = pci_map_single(tp->pdev, skb->data, tx_len, PCI_DMA_TODEVICE);
-	if (pci_dma_mapping_error(tp->pdev, map)) {
+	map = dma_map_single(&tp->pdev->dev, skb->data, tx_len, DMA_TO_DEVICE);
+	if (dma_mapping_error(&tp->pdev->dev, map)) {
 		dev_kfree_skb(skb);
 		return -EIO;
 	}
@@ -13598,8 +13595,8 @@ static int tg3_run_loopback(struct tg3 *tp, u32 pktsz, bool tso_loopback)
 		} else
 			goto out;
 
-		pci_dma_sync_single_for_cpu(tp->pdev, map, rx_len,
-					    PCI_DMA_FROMDEVICE);
+		dma_sync_single_for_cpu(&tp->pdev->dev, map, rx_len,
+					DMA_FROM_DEVICE);
 
 		rx_data += TG3_RX_OFFSET(tp);
 		for (i = data_off; i < rx_len; i++, val++) {
@@ -14040,7 +14037,10 @@ static int tg3_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return -EOPNOTSUPP;
 }
 
-static int tg3_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
+static int tg3_get_coalesce(struct net_device *dev,
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct tg3 *tp = netdev_priv(dev);
 
@@ -14048,7 +14048,10 @@ static int tg3_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 	return 0;
 }
 
-static int tg3_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
+static int tg3_set_coalesce(struct net_device *dev,
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	u32 max_rxcoal_tick_int = 0, max_txcoal_tick_int = 0;
@@ -14290,7 +14293,7 @@ static const struct net_device_ops tg3_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= tg3_set_rx_mode,
 	.ndo_set_mac_address	= tg3_set_mac_addr,
-	.ndo_do_ioctl		= tg3_ioctl,
+	.ndo_eth_ioctl		= tg3_ioctl,
 	.ndo_tx_timeout		= tg3_tx_timeout,
 	.ndo_change_mtu		= tg3_change_mtu,
 	.ndo_fix_features	= tg3_fix_features,
@@ -17755,11 +17758,11 @@ static int tg3_init_one(struct pci_dev *pdev,
 
 	/* Configure DMA attributes. */
 	if (dma_mask > DMA_BIT_MASK(32)) {
-		err = pci_set_dma_mask(pdev, dma_mask);
+		err = dma_set_mask(&pdev->dev, dma_mask);
 		if (!err) {
 			features |= NETIF_F_HIGHDMA;
-			err = pci_set_consistent_dma_mask(pdev,
-							  persist_dma_mask);
+			err = dma_set_coherent_mask(&pdev->dev,
+						    persist_dma_mask);
 			if (err < 0) {
 				dev_err(&pdev->dev, "Unable to obtain 64 bit "
 					"DMA for consistent allocations\n");
@@ -17768,7 +17771,7 @@ static int tg3_init_one(struct pci_dev *pdev,
 		}
 	}
 	if (err || dma_mask == DMA_BIT_MASK(32)) {
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
 			dev_err(&pdev->dev,
 				"No usable DMA configuration, aborting\n");
diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
index 265c2fa6bbe0..391b85f25141 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
@@ -307,8 +307,10 @@ bnad_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wolinfo)
 	wolinfo->wolopts = 0;
 }
 
-static int
-bnad_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *coalesce)
+static int bnad_get_coalesce(struct net_device *netdev,
+			     struct ethtool_coalesce *coalesce,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct bnad *bnad = netdev_priv(netdev);
 	unsigned long flags;
@@ -328,8 +330,10 @@ bnad_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *coalesce)
 	return 0;
 }
 
-static int
-bnad_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *coalesce)
+static int bnad_set_coalesce(struct net_device *netdev,
+			     struct ethtool_coalesce *coalesce,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct bnad *bnad = netdev_priv(netdev);
 	unsigned long flags;
diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig
index e432a68ac520..5b2a461dfd28 100644
--- a/drivers/net/ethernet/cadence/Kconfig
+++ b/drivers/net/ethernet/cadence/Kconfig
@@ -22,6 +22,7 @@ if NET_VENDOR_CADENCE
 config MACB
 	tristate "Cadence MACB/GEM support"
 	depends on HAS_DMA && COMMON_CLK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select PHYLINK
 	select CRC32
 	help
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 7d2fe13a52f8..d13fb1d31821 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3664,7 +3664,7 @@ static const struct net_device_ops macb_netdev_ops = {
 	.ndo_start_xmit		= macb_start_xmit,
 	.ndo_set_rx_mode	= macb_set_rx_mode,
 	.ndo_get_stats		= macb_get_stats,
-	.ndo_do_ioctl		= macb_ioctl,
+	.ndo_eth_ioctl		= macb_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= macb_change_mtu,
 	.ndo_set_mac_address	= eth_mac_addr,
@@ -4323,7 +4323,7 @@ static const struct net_device_ops at91ether_netdev_ops = {
 	.ndo_get_stats		= macb_get_stats,
 	.ndo_set_rx_mode	= macb_set_rx_mode,
 	.ndo_set_mac_address	= eth_mac_addr,
-	.ndo_do_ioctl		= macb_ioctl,
+	.ndo_eth_ioctl		= macb_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= at91ether_poll_controller,
@@ -4533,6 +4533,14 @@ static const struct macb_config sama5d2_config = {
 	.usrio = &macb_default_usrio,
 };
 
+static const struct macb_config sama5d29_config = {
+	.caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII | MACB_CAPS_GEM_HAS_PTP,
+	.dma_burst_length = 16,
+	.clk_init = macb_clk_init,
+	.init = macb_init,
+	.usrio = &macb_default_usrio,
+};
+
 static const struct macb_config sama5d3_config = {
 	.caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE
 	      | MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII | MACB_CAPS_JUMBO,
@@ -4610,6 +4618,7 @@ static const struct of_device_id macb_dt_ids[] = {
 	{ .compatible = "cdns,gem", .data = &pc302gem_config },
 	{ .compatible = "cdns,sam9x60-macb", .data = &at91sam9260_config },
 	{ .compatible = "atmel,sama5d2-gem", .data = &sama5d2_config },
+	{ .compatible = "atmel,sama5d29-gem", .data = &sama5d29_config },
 	{ .compatible = "atmel,sama5d3-gem", .data = &sama5d3_config },
 	{ .compatible = "atmel,sama5d3-macb", .data = &sama5d3macb_config },
 	{ .compatible = "atmel,sama5d4-gem", .data = &sama5d4_config },
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 4875cdae622e..1c76c95b0b27 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -66,7 +66,7 @@ config LIQUIDIO
 	tristate "Cavium LiquidIO support"
 	depends on 64BIT && PCI
 	depends on PCI
-	imply PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select FW_LOADER
 	select LIBCRC32C
 	select NET_DEVLINK
@@ -91,7 +91,7 @@ config OCTEON_MGMT_ETHERNET
 config LIQUIDIO_VF
 	tristate "Cavium LiquidIO VF support"
 	depends on 64BIT && PCI_MSI
-	imply PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  This driver supports Cavium LiquidIO Intelligent Server Adapter
 	  based on CN23XX chips.
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 66f2c553370c..2b9747867d4c 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -2108,7 +2108,9 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
 }
 
 static int lio_get_intr_coalesce(struct net_device *netdev,
-				 struct ethtool_coalesce *intr_coal)
+				 struct ethtool_coalesce *intr_coal,
+				 struct kernel_ethtool_coalesce *kernel_coal,
+				 struct netlink_ext_ack *extack)
 {
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
@@ -2412,7 +2414,9 @@ oct_cfg_tx_intrcnt(struct lio *lio,
 }
 
 static int lio_set_intr_coalesce(struct net_device *netdev,
-				 struct ethtool_coalesce *intr_coal)
+				 struct ethtool_coalesce *intr_coal,
+				 struct kernel_ethtool_coalesce *kernel_coal,
+				 struct netlink_ext_ack *extack)
 {
 	struct lio *lio = GET_LIO(netdev);
 	int ret;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 591229b96257..2907e13b9df6 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -1457,7 +1457,7 @@ static void free_netsgbuf(void *buf)
 	while (frags--) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
 
-		pci_unmap_page((lio->oct_dev)->pci_dev,
+		dma_unmap_page(&lio->oct_dev->pci_dev->dev,
 			       g->sg[(i >> 2)].ptr[(i & 3)],
 			       skb_frag_size(frag), DMA_TO_DEVICE);
 		i++;
@@ -1500,7 +1500,7 @@ static void free_netsgbuf_with_resp(void *buf)
 	while (frags--) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
 
-		pci_unmap_page((lio->oct_dev)->pci_dev,
+		dma_unmap_page(&lio->oct_dev->pci_dev->dev,
 			       g->sg[(i >> 2)].ptr[(i & 3)],
 			       skb_frag_size(frag), DMA_TO_DEVICE);
 		i++;
@@ -3223,7 +3223,7 @@ static const struct net_device_ops lionetdevops = {
 	.ndo_vlan_rx_add_vid    = liquidio_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = liquidio_vlan_rx_kill_vid,
 	.ndo_change_mtu		= liquidio_change_mtu,
-	.ndo_do_ioctl		= liquidio_ioctl,
+	.ndo_eth_ioctl		= liquidio_ioctl,
 	.ndo_fix_features	= liquidio_fix_features,
 	.ndo_set_features	= liquidio_set_features,
 	.ndo_set_vf_mac		= liquidio_set_vf_mac,
@@ -3750,7 +3750,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 	}
 
 	devlink = devlink_alloc(&liquidio_devlink_ops,
-				sizeof(struct lio_devlink_priv));
+				sizeof(struct lio_devlink_priv),
+				&octeon_dev->pci_dev->dev);
 	if (!devlink) {
 		dev_err(&octeon_dev->pci_dev->dev, "devlink alloc failed\n");
 		goto setup_nic_dev_free;
@@ -3759,7 +3760,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 	lio_devlink = devlink_priv(devlink);
 	lio_devlink->oct = octeon_dev;
 
-	if (devlink_register(devlink, &octeon_dev->pci_dev->dev)) {
+	if (devlink_register(devlink)) {
 		devlink_free(devlink);
 		dev_err(&octeon_dev->pci_dev->dev,
 			"devlink registration failed\n");
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index ffddb3126a32..c6fe0f2a4d0e 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -843,7 +843,7 @@ static void free_netsgbuf(void *buf)
 	while (frags--) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
 
-		pci_unmap_page((lio->oct_dev)->pci_dev,
+		dma_unmap_page(&lio->oct_dev->pci_dev->dev,
 			       g->sg[(i >> 2)].ptr[(i & 3)],
 			       skb_frag_size(frag), DMA_TO_DEVICE);
 		i++;
@@ -887,7 +887,7 @@ static void free_netsgbuf_with_resp(void *buf)
 	while (frags--) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
 
-		pci_unmap_page((lio->oct_dev)->pci_dev,
+		dma_unmap_page(&lio->oct_dev->pci_dev->dev,
 			       g->sg[(i >> 2)].ptr[(i & 3)],
 			       skb_frag_size(frag), DMA_TO_DEVICE);
 		i++;
@@ -1889,7 +1889,7 @@ static const struct net_device_ops lionetdevops = {
 	.ndo_vlan_rx_add_vid    = liquidio_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = liquidio_vlan_rx_kill_vid,
 	.ndo_change_mtu		= liquidio_change_mtu,
-	.ndo_do_ioctl		= liquidio_ioctl,
+	.ndo_eth_ioctl		= liquidio_ioctl,
 	.ndo_fix_features	= liquidio_fix_features,
 	.ndo_set_features	= liquidio_set_features,
 };
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 48ff6fb0eed9..30463a6d1f8c 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -1373,7 +1373,7 @@ static const struct net_device_ops octeon_mgmt_ops = {
 	.ndo_start_xmit =		octeon_mgmt_xmit,
 	.ndo_set_rx_mode =		octeon_mgmt_set_rx_filtering,
 	.ndo_set_mac_address =		octeon_mgmt_set_mac_address,
-	.ndo_do_ioctl =			octeon_mgmt_ioctl,
+	.ndo_eth_ioctl =			octeon_mgmt_ioctl,
 	.ndo_change_mtu =		octeon_mgmt_change_mtu,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller =		octeon_mgmt_poll_controller,
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 9361f964bb9b..691e1475d55e 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -1322,18 +1322,12 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_disable_device;
 	}
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(48));
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48));
 	if (err) {
 		dev_err(dev, "Unable to get usable DMA configuration\n");
 		goto err_release_regions;
 	}
 
-	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48));
-	if (err) {
-		dev_err(dev, "Unable to get 48-bit DMA for consistent allocations\n");
-		goto err_release_regions;
-	}
-
 	/* MAP PF's configuration registers */
 	nic->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0);
 	if (!nic->reg_base) {
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index 2f218fbfed06..7f2882109b16 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -456,7 +456,9 @@ static void nicvf_get_regs(struct net_device *dev,
 }
 
 static int nicvf_get_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *cmd)
+			      struct ethtool_coalesce *cmd,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct nicvf *nic = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index e2b290135fd9..d1667b759522 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -2096,7 +2096,7 @@ static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_fix_features       = nicvf_fix_features,
 	.ndo_set_features       = nicvf_set_features,
 	.ndo_bpf		= nicvf_xdp,
-	.ndo_do_ioctl           = nicvf_ioctl,
+	.ndo_eth_ioctl           = nicvf_ioctl,
 	.ndo_set_rx_mode        = nicvf_set_rx_mode,
 };
 
@@ -2130,18 +2130,12 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_disable_device;
 	}
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(48));
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48));
 	if (err) {
 		dev_err(dev, "Unable to get usable DMA configuration\n");
 		goto err_release_regions;
 	}
 
-	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48));
-	if (err) {
-		dev_err(dev, "unable to get 48-bit DMA for consistent allocations\n");
-		goto err_release_regions;
-	}
-
 	qcount = netif_get_num_default_rss_queues();
 
 	/* Restrict multiqset support only for host bound VFs */
diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig
index 8ba0e08e5e64..c931ec8cac40 100644
--- a/drivers/net/ethernet/chelsio/Kconfig
+++ b/drivers/net/ethernet/chelsio/Kconfig
@@ -69,6 +69,7 @@ config CHELSIO_T3
 config CHELSIO_T4
 	tristate "Chelsio Communications T4/T5/T6 Ethernet support"
 	depends on PCI && (IPV6 || IPV6=n) && (TLS || TLS=n)
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select FW_LOADER
 	select MDIO
 	select ZLIB_DEFLATE
diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index 512da98019c6..73c016166f06 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -748,7 +748,9 @@ static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e)
 	return 0;
 }
 
-static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
+static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c,
+			struct kernel_ethtool_coalesce *kernel_coal,
+			struct netlink_ext_ack *extack)
 {
 	struct adapter *adapter = dev->ml_priv;
 
@@ -759,7 +761,9 @@ static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
 	return 0;
 }
 
-static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
+static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c,
+			struct kernel_ethtool_coalesce *kernel_coal,
+			struct netlink_ext_ack *extack)
 {
 	struct adapter *adapter = dev->ml_priv;
 
@@ -924,7 +928,7 @@ static const struct net_device_ops cxgb_netdev_ops = {
 	.ndo_get_stats		= t1_get_stats,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= t1_set_rxmode,
-	.ndo_do_ioctl		= t1_ioctl,
+	.ndo_eth_ioctl		= t1_ioctl,
 	.ndo_change_mtu		= t1_change_mtu,
 	.ndo_set_mac_address	= t1_set_mac_addr,
 	.ndo_fix_features	= t1_fix_features,
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 57f210c53afc..38e47703f9ab 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -1996,7 +1996,9 @@ static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e)
 	return 0;
 }
 
-static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
+static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c,
+			struct kernel_ethtool_coalesce *kernel_coal,
+			struct netlink_ext_ack *extack)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
@@ -2017,7 +2019,9 @@ static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
 	return 0;
 }
 
-static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
+static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c,
+			struct kernel_ethtool_coalesce *kernel_coal,
+			struct netlink_ext_ack *extack)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
@@ -2135,13 +2139,18 @@ static int in_range(int val, int lo, int hi)
 	return val < 0 || (val <= hi && val >= lo);
 }
 
-static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
+static int cxgb_siocdevprivate(struct net_device *dev,
+			       struct ifreq *ifreq,
+			       void __user *useraddr,
+			       int cmd)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
-	u32 cmd;
 	int ret;
 
+	if (cmd != SIOCCHIOCTL)
+		return -EOPNOTSUPP;
+
 	if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
 		return -EFAULT;
 
@@ -2546,8 +2555,6 @@ static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
 		fallthrough;
 	case SIOCGMIIPHY:
 		return mdio_mii_ioctl(&pi->phy.mdio, data, cmd);
-	case SIOCCHIOCTL:
-		return cxgb_extension_ioctl(dev, req->ifr_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -3181,7 +3188,8 @@ static const struct net_device_ops cxgb_netdev_ops = {
 	.ndo_get_stats		= cxgb_get_stats,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= cxgb_set_rxmode,
-	.ndo_do_ioctl		= cxgb_ioctl,
+	.ndo_eth_ioctl		= cxgb_ioctl,
+	.ndo_siocdevprivate	= cxgb_siocdevprivate,
 	.ndo_change_mtu		= cxgb_change_mtu,
 	.ndo_set_mac_address	= cxgb_set_mac_addr,
 	.ndo_fix_features	= cxgb_fix_features,
@@ -3231,15 +3239,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto out_disable_device;
 	}
 
-	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+	if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
 		pci_using_dac = 1;
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-		if (err) {
-			dev_err(&pdev->dev, "unable to obtain 64-bit DMA for "
-			       "coherent allocations\n");
-			goto out_release_regions;
-		}
-	} else if ((err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) != 0) {
+	} else if ((err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) != 0) {
 		dev_err(&pdev->dev, "no usable DMA configuration\n");
 		goto out_release_regions;
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index cb5c79c43bc9..e21a2e691382 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -244,8 +244,8 @@ static inline void unmap_skb(struct sk_buff *skb, struct sge_txq *q,
 	frag_idx = d->fragidx;
 
 	if (frag_idx == 0 && skb_headlen(skb)) {
-		pci_unmap_single(pdev, be64_to_cpu(sgp->addr[0]),
-				 skb_headlen(skb), PCI_DMA_TODEVICE);
+		dma_unmap_single(&pdev->dev, be64_to_cpu(sgp->addr[0]),
+				 skb_headlen(skb), DMA_TO_DEVICE);
 		j = 1;
 	}
 
@@ -253,9 +253,9 @@ static inline void unmap_skb(struct sk_buff *skb, struct sge_txq *q,
 	nfrags = skb_shinfo(skb)->nr_frags;
 
 	while (frag_idx < nfrags && curflit < WR_FLITS) {
-		pci_unmap_page(pdev, be64_to_cpu(sgp->addr[j]),
+		dma_unmap_page(&pdev->dev, be64_to_cpu(sgp->addr[j]),
 			       skb_frag_size(&skb_shinfo(skb)->frags[frag_idx]),
-			       PCI_DMA_TODEVICE);
+			       DMA_TO_DEVICE);
 		j ^= 1;
 		if (j == 0) {
 			sgp++;
@@ -355,15 +355,14 @@ static void clear_rx_desc(struct pci_dev *pdev, const struct sge_fl *q,
 	if (q->use_pages && d->pg_chunk.page) {
 		(*d->pg_chunk.p_cnt)--;
 		if (!*d->pg_chunk.p_cnt)
-			pci_unmap_page(pdev,
-				       d->pg_chunk.mapping,
-				       q->alloc_size, PCI_DMA_FROMDEVICE);
+			dma_unmap_page(&pdev->dev, d->pg_chunk.mapping,
+				       q->alloc_size, DMA_FROM_DEVICE);
 
 		put_page(d->pg_chunk.page);
 		d->pg_chunk.page = NULL;
 	} else {
-		pci_unmap_single(pdev, dma_unmap_addr(d, dma_addr),
-				 q->buf_size, PCI_DMA_FROMDEVICE);
+		dma_unmap_single(&pdev->dev, dma_unmap_addr(d, dma_addr),
+				 q->buf_size, DMA_FROM_DEVICE);
 		kfree_skb(d->skb);
 		d->skb = NULL;
 	}
@@ -414,8 +413,8 @@ static inline int add_one_rx_buf(void *va, unsigned int len,
 {
 	dma_addr_t mapping;
 
-	mapping = pci_map_single(pdev, va, len, PCI_DMA_FROMDEVICE);
-	if (unlikely(pci_dma_mapping_error(pdev, mapping)))
+	mapping = dma_map_single(&pdev->dev, va, len, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(&pdev->dev, mapping)))
 		return -ENOMEM;
 
 	dma_unmap_addr_set(sd, dma_addr, mapping);
@@ -453,9 +452,9 @@ static int alloc_pg_chunk(struct adapter *adapter, struct sge_fl *q,
 		q->pg_chunk.p_cnt = q->pg_chunk.va + (PAGE_SIZE << order) -
 				    SGE_PG_RSVD;
 		q->pg_chunk.offset = 0;
-		mapping = pci_map_page(adapter->pdev, q->pg_chunk.page,
-				       0, q->alloc_size, PCI_DMA_FROMDEVICE);
-		if (unlikely(pci_dma_mapping_error(adapter->pdev, mapping))) {
+		mapping = dma_map_page(&adapter->pdev->dev, q->pg_chunk.page,
+				       0, q->alloc_size, DMA_FROM_DEVICE);
+		if (unlikely(dma_mapping_error(&adapter->pdev->dev, mapping))) {
 			__free_pages(q->pg_chunk.page, order);
 			q->pg_chunk.page = NULL;
 			return -EIO;
@@ -522,9 +521,9 @@ nomem:				q->alloc_failed++;
 			dma_unmap_addr_set(sd, dma_addr, mapping);
 
 			add_one_rx_chunk(mapping, d, q->gen);
-			pci_dma_sync_single_for_device(adap->pdev, mapping,
-						q->buf_size - SGE_PG_RSVD,
-						PCI_DMA_FROMDEVICE);
+			dma_sync_single_for_device(&adap->pdev->dev, mapping,
+						   q->buf_size - SGE_PG_RSVD,
+						   DMA_FROM_DEVICE);
 		} else {
 			void *buf_start;
 
@@ -793,13 +792,13 @@ static struct sk_buff *get_packet(struct adapter *adap, struct sge_fl *fl,
 		skb = alloc_skb(len, GFP_ATOMIC);
 		if (likely(skb != NULL)) {
 			__skb_put(skb, len);
-			pci_dma_sync_single_for_cpu(adap->pdev,
-					    dma_unmap_addr(sd, dma_addr), len,
-					    PCI_DMA_FROMDEVICE);
+			dma_sync_single_for_cpu(&adap->pdev->dev,
+						dma_unmap_addr(sd, dma_addr),
+						len, DMA_FROM_DEVICE);
 			memcpy(skb->data, sd->skb->data, len);
-			pci_dma_sync_single_for_device(adap->pdev,
-					    dma_unmap_addr(sd, dma_addr), len,
-					    PCI_DMA_FROMDEVICE);
+			dma_sync_single_for_device(&adap->pdev->dev,
+						   dma_unmap_addr(sd, dma_addr),
+						   len, DMA_FROM_DEVICE);
 		} else if (!drop_thres)
 			goto use_orig_buf;
 recycle:
@@ -813,8 +812,8 @@ recycle:
 		goto recycle;
 
 use_orig_buf:
-	pci_unmap_single(adap->pdev, dma_unmap_addr(sd, dma_addr),
-			 fl->buf_size, PCI_DMA_FROMDEVICE);
+	dma_unmap_single(&adap->pdev->dev, dma_unmap_addr(sd, dma_addr),
+			 fl->buf_size, DMA_FROM_DEVICE);
 	skb = sd->skb;
 	skb_put(skb, len);
 	__refill_fl(adap, fl);
@@ -854,12 +853,11 @@ static struct sk_buff *get_packet_pg(struct adapter *adap, struct sge_fl *fl,
 		newskb = alloc_skb(len, GFP_ATOMIC);
 		if (likely(newskb != NULL)) {
 			__skb_put(newskb, len);
-			pci_dma_sync_single_for_cpu(adap->pdev, dma_addr, len,
-					    PCI_DMA_FROMDEVICE);
+			dma_sync_single_for_cpu(&adap->pdev->dev, dma_addr,
+						len, DMA_FROM_DEVICE);
 			memcpy(newskb->data, sd->pg_chunk.va, len);
-			pci_dma_sync_single_for_device(adap->pdev, dma_addr,
-						       len,
-						       PCI_DMA_FROMDEVICE);
+			dma_sync_single_for_device(&adap->pdev->dev, dma_addr,
+						   len, DMA_FROM_DEVICE);
 		} else if (!drop_thres)
 			return NULL;
 recycle:
@@ -883,14 +881,12 @@ recycle:
 		goto recycle;
 	}
 
-	pci_dma_sync_single_for_cpu(adap->pdev, dma_addr, len,
-				    PCI_DMA_FROMDEVICE);
+	dma_sync_single_for_cpu(&adap->pdev->dev, dma_addr, len,
+				DMA_FROM_DEVICE);
 	(*sd->pg_chunk.p_cnt)--;
 	if (!*sd->pg_chunk.p_cnt && sd->pg_chunk.page != fl->pg_chunk.page)
-		pci_unmap_page(adap->pdev,
-			       sd->pg_chunk.mapping,
-			       fl->alloc_size,
-			       PCI_DMA_FROMDEVICE);
+		dma_unmap_page(&adap->pdev->dev, sd->pg_chunk.mapping,
+			       fl->alloc_size, DMA_FROM_DEVICE);
 	if (!skb) {
 		__skb_put(newskb, SGE_RX_PULL_LEN);
 		memcpy(newskb->data, sd->pg_chunk.va, SGE_RX_PULL_LEN);
@@ -968,9 +964,9 @@ static int map_skb(struct pci_dev *pdev, const struct sk_buff *skb,
 	const struct skb_shared_info *si;
 
 	if (skb_headlen(skb)) {
-		*addr = pci_map_single(pdev, skb->data, skb_headlen(skb),
-				       PCI_DMA_TODEVICE);
-		if (pci_dma_mapping_error(pdev, *addr))
+		*addr = dma_map_single(&pdev->dev, skb->data,
+				       skb_headlen(skb), DMA_TO_DEVICE);
+		if (dma_mapping_error(&pdev->dev, *addr))
 			goto out_err;
 		addr++;
 	}
@@ -981,7 +977,7 @@ static int map_skb(struct pci_dev *pdev, const struct sk_buff *skb,
 	for (fp = si->frags; fp < end; fp++) {
 		*addr = skb_frag_dma_map(&pdev->dev, fp, 0, skb_frag_size(fp),
 					 DMA_TO_DEVICE);
-		if (pci_dma_mapping_error(pdev, *addr))
+		if (dma_mapping_error(&pdev->dev, *addr))
 			goto unwind;
 		addr++;
 	}
@@ -992,7 +988,8 @@ unwind:
 		dma_unmap_page(&pdev->dev, *--addr, skb_frag_size(fp),
 			       DMA_TO_DEVICE);
 
-	pci_unmap_single(pdev, addr[-1], skb_headlen(skb), PCI_DMA_TODEVICE);
+	dma_unmap_single(&pdev->dev, addr[-1], skb_headlen(skb),
+			 DMA_TO_DEVICE);
 out_err:
 	return -ENOMEM;
 }
@@ -1592,13 +1589,14 @@ static void deferred_unmap_destructor(struct sk_buff *skb)
 	p = dui->addr;
 
 	if (skb_tail_pointer(skb) - skb_transport_header(skb))
-		pci_unmap_single(dui->pdev, *p++, skb_tail_pointer(skb) -
-				 skb_transport_header(skb), PCI_DMA_TODEVICE);
+		dma_unmap_single(&dui->pdev->dev, *p++,
+				 skb_tail_pointer(skb) - skb_transport_header(skb),
+				 DMA_TO_DEVICE);
 
 	si = skb_shinfo(skb);
 	for (i = 0; i < si->nr_frags; i++)
-		pci_unmap_page(dui->pdev, *p++, skb_frag_size(&si->frags[i]),
-			       PCI_DMA_TODEVICE);
+		dma_unmap_page(&dui->pdev->dev, *p++,
+			       skb_frag_size(&si->frags[i]), DMA_TO_DEVICE);
 }
 
 static void setup_deferred_unmapping(struct sk_buff *skb, struct pci_dev *pdev,
@@ -2153,17 +2151,14 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs,
 
 	fl->credits--;
 
-	pci_dma_sync_single_for_cpu(adap->pdev,
-				    dma_unmap_addr(sd, dma_addr),
-				    fl->buf_size - SGE_PG_RSVD,
-				    PCI_DMA_FROMDEVICE);
+	dma_sync_single_for_cpu(&adap->pdev->dev,
+				dma_unmap_addr(sd, dma_addr),
+				fl->buf_size - SGE_PG_RSVD, DMA_FROM_DEVICE);
 
 	(*sd->pg_chunk.p_cnt)--;
 	if (!*sd->pg_chunk.p_cnt && sd->pg_chunk.page != fl->pg_chunk.page)
-		pci_unmap_page(adap->pdev,
-			       sd->pg_chunk.mapping,
-			       fl->alloc_size,
-			       PCI_DMA_FROMDEVICE);
+		dma_unmap_page(&adap->pdev->dev, sd->pg_chunk.mapping,
+			       fl->alloc_size, DMA_FROM_DEVICE);
 
 	if (!skb) {
 		put_page(sd->pg_chunk.page);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 83ed10ac8660..5903bdb78916 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -1147,7 +1147,9 @@ static int set_dbqtimer_tickval(struct net_device *dev,
 }
 
 static int set_coalesce(struct net_device *dev,
-			struct ethtool_coalesce *coalesce)
+			struct ethtool_coalesce *coalesce,
+			struct kernel_ethtool_coalesce *kernel_coal,
+			struct netlink_ext_ack *extack)
 {
 	int ret;
 
@@ -1163,7 +1165,9 @@ static int set_coalesce(struct net_device *dev,
 				    coalesce->tx_coalesce_usecs);
 }
 
-static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
+static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c,
+			struct kernel_ethtool_coalesce *kernel_coal,
+			struct netlink_ext_ack *extack)
 {
 	const struct port_info *pi = netdev_priv(dev);
 	const struct adapter *adap = pi->adapter;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 6260b3bebd2b..786ceae34488 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -1441,7 +1441,7 @@ static int cxgb4_set_hash_filter(struct net_device *dev,
 	} else if (iconf & USE_ENC_IDX_F) {
 		if (f->fs.val.encap_vld) {
 			struct port_info *pi = netdev_priv(f->dev);
-			u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 };
+			static const u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 };
 
 			/* allocate MPS TCAM entry */
 			ret = t4_alloc_encap_mac_filt(adapter, pi->viid,
@@ -1688,7 +1688,7 @@ int __cxgb4_set_filter(struct net_device *dev, int ftid,
 	} else if (iconf & USE_ENC_IDX_F) {
 		if (f->fs.val.encap_vld) {
 			struct port_info *pi = netdev_priv(f->dev);
-			u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 };
+			static const u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 };
 
 			/* allocate MPS TCAM entry */
 			ret = t4_alloc_encap_mac_filt(adapter, pi->viid,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 710cb00ce3a3..0d9cda4ab303 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3872,7 +3872,7 @@ static const struct net_device_ops cxgb4_netdev_ops = {
 	.ndo_set_mac_address  = cxgb_set_mac_addr,
 	.ndo_set_features     = cxgb_set_features,
 	.ndo_validate_addr    = eth_validate_addr,
-	.ndo_do_ioctl         = cxgb_ioctl,
+	.ndo_eth_ioctl         = cxgb_ioctl,
 	.ndo_change_mtu       = cxgb_change_mtu,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller  = cxgb_netpoll,
@@ -4008,7 +4008,7 @@ static void adap_free_hma_mem(struct adapter *adapter)
 
 	if (adapter->hma.flags & HMA_DMA_MAPPED_FLAG) {
 		dma_unmap_sg(adapter->pdev_dev, adapter->hma.sgt->sgl,
-			     adapter->hma.sgt->nents, PCI_DMA_BIDIRECTIONAL);
+			     adapter->hma.sgt->nents, DMA_BIDIRECTIONAL);
 		adapter->hma.flags &= ~HMA_DMA_MAPPED_FLAG;
 	}
 
@@ -6163,8 +6163,7 @@ static void print_port_info(const struct net_device *dev)
 		--bufp;
 	sprintf(bufp, "BASE-%s", t4_get_port_type_description(pi->port_type));
 
-	netdev_info(dev, "%s: Chelsio %s (%s) %s\n",
-		    dev->name, adap->params.vpd.id, adap->name, buf);
+	netdev_info(dev, "Chelsio %s %s\n", adap->params.vpd.id, buf);
 }
 
 /*
@@ -6688,16 +6687,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return 0;
 	}
 
-	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+	if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
 		highdma = true;
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-		if (err) {
-			dev_err(&pdev->dev, "unable to obtain 64-bit DMA for "
-				"coherent allocations\n");
-			goto out_free_adapter;
-		}
 	} else {
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
 			dev_err(&pdev->dev, "no usable DMA configuration\n");
 			goto out_free_adapter;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 6a099cb34b12..fa5b596ff23a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -443,7 +443,7 @@ static void free_rx_bufs(struct adapter *adap, struct sge_fl *q, int n)
 		if (is_buf_mapped(d))
 			dma_unmap_page(adap->pdev_dev, get_buf_addr(d),
 				       get_buf_size(adap, d),
-				       PCI_DMA_FROMDEVICE);
+				       DMA_FROM_DEVICE);
 		put_page(d->page);
 		d->page = NULL;
 		if (++q->cidx == q->size)
@@ -469,7 +469,7 @@ static void unmap_rx_buf(struct adapter *adap, struct sge_fl *q)
 
 	if (is_buf_mapped(d))
 		dma_unmap_page(adap->pdev_dev, get_buf_addr(d),
-			       get_buf_size(adap, d), PCI_DMA_FROMDEVICE);
+			       get_buf_size(adap, d), DMA_FROM_DEVICE);
 	d->page = NULL;
 	if (++q->cidx == q->size)
 		q->cidx = 0;
@@ -566,7 +566,7 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n,
 
 		mapping = dma_map_page(adap->pdev_dev, pg, 0,
 				       PAGE_SIZE << s->fl_pg_order,
-				       PCI_DMA_FROMDEVICE);
+				       DMA_FROM_DEVICE);
 		if (unlikely(dma_mapping_error(adap->pdev_dev, mapping))) {
 			__free_pages(pg, s->fl_pg_order);
 			q->mapping_err++;
@@ -596,7 +596,7 @@ alloc_small_pages:
 		}
 
 		mapping = dma_map_page(adap->pdev_dev, pg, 0, PAGE_SIZE,
-				       PCI_DMA_FROMDEVICE);
+				       DMA_FROM_DEVICE);
 		if (unlikely(dma_mapping_error(adap->pdev_dev, mapping))) {
 			put_page(pg);
 			q->mapping_err++;
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 2820a0bb971b..49b76fd47daa 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -1647,7 +1647,9 @@ static int cxgb4vf_set_ringparam(struct net_device *dev,
  * interrupt holdoff timer to be read on all of the device's Queue Sets.
  */
 static int cxgb4vf_get_coalesce(struct net_device *dev,
-				struct ethtool_coalesce *coalesce)
+				struct ethtool_coalesce *coalesce,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	const struct port_info *pi = netdev_priv(dev);
 	const struct adapter *adapter = pi->adapter;
@@ -1667,7 +1669,9 @@ static int cxgb4vf_get_coalesce(struct net_device *dev,
  * the interrupt holdoff timer on any of the device's Queue Sets.
  */
 static int cxgb4vf_set_coalesce(struct net_device *dev,
-				struct ethtool_coalesce *coalesce)
+				struct ethtool_coalesce *coalesce,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	const struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
@@ -2837,7 +2841,7 @@ static const struct net_device_ops cxgb4vf_netdev_ops	= {
 	.ndo_set_rx_mode	= cxgb4vf_set_rxmode,
 	.ndo_set_mac_address	= cxgb4vf_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= cxgb4vf_do_ioctl,
+	.ndo_eth_ioctl		= cxgb4vf_do_ioctl,
 	.ndo_change_mtu		= cxgb4vf_change_mtu,
 	.ndo_fix_features	= cxgb4vf_fix_features,
 	.ndo_set_features	= cxgb4vf_set_features,
@@ -2917,17 +2921,11 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 	 * Set up our DMA mask: try for 64-bit address masking first and
 	 * fall back to 32-bit if we can't get 64 bits ...
 	 */
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (err == 0) {
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-		if (err) {
-			dev_err(&pdev->dev, "unable to obtain 64-bit DMA for"
-				" coherent allocations\n");
-			goto err_release_regions;
-		}
 		pci_using_dac = 1;
 	} else {
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
 		if (err != 0) {
 			dev_err(&pdev->dev, "no usable DMA configuration\n");
 			goto err_release_regions;
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 7bc80eeb2c21..0295b2406646 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -478,7 +478,7 @@ static void free_rx_bufs(struct adapter *adapter, struct sge_fl *fl, int n)
 		if (is_buf_mapped(sdesc))
 			dma_unmap_page(adapter->pdev_dev, get_buf_addr(sdesc),
 				       get_buf_size(adapter, sdesc),
-				       PCI_DMA_FROMDEVICE);
+				       DMA_FROM_DEVICE);
 		put_page(sdesc->page);
 		sdesc->page = NULL;
 		if (++fl->cidx == fl->size)
@@ -507,7 +507,7 @@ static void unmap_rx_buf(struct adapter *adapter, struct sge_fl *fl)
 	if (is_buf_mapped(sdesc))
 		dma_unmap_page(adapter->pdev_dev, get_buf_addr(sdesc),
 			       get_buf_size(adapter, sdesc),
-			       PCI_DMA_FROMDEVICE);
+			       DMA_FROM_DEVICE);
 	sdesc->page = NULL;
 	if (++fl->cidx == fl->size)
 		fl->cidx = 0;
@@ -644,7 +644,7 @@ static unsigned int refill_fl(struct adapter *adapter, struct sge_fl *fl,
 
 		dma_addr = dma_map_page(adapter->pdev_dev, page, 0,
 					PAGE_SIZE << s->fl_pg_order,
-					PCI_DMA_FROMDEVICE);
+					DMA_FROM_DEVICE);
 		if (unlikely(dma_mapping_error(adapter->pdev_dev, dma_addr))) {
 			/*
 			 * We've run out of DMA mapping space.  Free up the
@@ -682,7 +682,7 @@ alloc_small_pages:
 		poison_buf(page, PAGE_SIZE);
 
 		dma_addr = dma_map_page(adapter->pdev_dev, page, 0, PAGE_SIZE,
-				       PCI_DMA_FROMDEVICE);
+				       DMA_FROM_DEVICE);
 		if (unlikely(dma_mapping_error(adapter->pdev_dev, dma_addr))) {
 			put_page(page);
 			break;
diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig
index d8af9e64dd1e..dac1764ba740 100644
--- a/drivers/net/ethernet/cirrus/Kconfig
+++ b/drivers/net/ethernet/cirrus/Kconfig
@@ -6,7 +6,7 @@
 config NET_VENDOR_CIRRUS
 	bool "Cirrus devices"
 	default y
-	depends on ISA || EISA || ARM || MAC
+	depends on ISA || EISA || ARM || MAC || COMPILE_TEST
 	help
 	  If you have a network (Ethernet) card belonging to this class, say Y.
 
@@ -18,9 +18,16 @@ config NET_VENDOR_CIRRUS
 if NET_VENDOR_CIRRUS
 
 config CS89x0
-	tristate "CS89x0 support"
-	depends on ISA || EISA || ARM
+	tristate
+
+config CS89x0_ISA
+	tristate "CS89x0 ISA driver support"
+	depends on HAS_IOPORT_MAP
+	depends on ISA
 	depends on !PPC32
+	depends on CS89x0_PLATFORM=n
+	select NETDEV_LEGACY_INIT
+	select CS89x0
 	help
 	  Support for CS89x0 chipset based Ethernet cards. If you have a
 	  network (Ethernet) card of this type, say Y and read the file
@@ -30,15 +37,15 @@ config CS89x0
 	  will be called cs89x0.
 
 config CS89x0_PLATFORM
-	bool "CS89x0 platform driver support" if HAS_IOPORT_MAP
-	default !HAS_IOPORT_MAP
-	depends on CS89x0
+	tristate "CS89x0 platform driver support"
+	depends on ARM || COMPILE_TEST
+	select CS89x0
 	help
-	  Say Y to compile the cs89x0 driver as a platform driver. This
-	  makes this driver suitable for use on certain evaluation boards
-	  such as the iMX21ADS.
+	  Say Y to compile the cs89x0 platform driver. This makes this driver
+	  suitable for use on certain evaluation boards such as the iMX21ADS.
 
-	  If you are unsure, say N.
+	  To compile this driver as a module, choose M here. The module
+	  will be called cs89x0.
 
 config EP93XX_ETH
 	tristate "EP93xx Ethernet support"
diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c
index 33ace3307059..d0c4c8b7a15a 100644
--- a/drivers/net/ethernet/cirrus/cs89x0.c
+++ b/drivers/net/ethernet/cirrus/cs89x0.c
@@ -104,7 +104,7 @@ static char version[] __initdata =
  * them to system IRQ numbers. This mapping is card specific and is set to
  * the configuration of the Cirrus Eval board for this chip.
  */
-#ifndef CONFIG_CS89x0_PLATFORM
+#if IS_ENABLED(CONFIG_CS89x0_ISA)
 static unsigned int netcard_portlist[] __used __initdata = {
 	0x300, 0x320, 0x340, 0x360, 0x200, 0x220, 0x240,
 	0x260, 0x280, 0x2a0, 0x2c0, 0x2e0, 0
@@ -292,7 +292,7 @@ write_irq(struct net_device *dev, int chip_type, int irq)
 	int i;
 
 	if (chip_type == CS8900) {
-#ifndef CONFIG_CS89x0_PLATFORM
+#if IS_ENABLED(CONFIG_CS89x0_ISA)
 		/* Search the mapping table for the corresponding IRQ pin. */
 		for (i = 0; i != ARRAY_SIZE(cs8900_irq_map); i++)
 			if (cs8900_irq_map[i] == irq)
@@ -859,7 +859,7 @@ net_open(struct net_device *dev)
 			goto bad_out;
 		}
 	} else {
-#if !defined(CONFIG_CS89x0_PLATFORM)
+#if IS_ENABLED(CONFIG_CS89x0_ISA)
 		if (((1 << dev->irq) & lp->irq_map) == 0) {
 			pr_err("%s: IRQ %d is not in our map of allowable IRQs, which is %x\n",
 			       dev->name, dev->irq, lp->irq_map);
@@ -1523,7 +1523,7 @@ cs89x0_probe1(struct net_device *dev, void __iomem *ioaddr, int modular)
 			dev->irq = i;
 	} else {
 		i = lp->isa_config & INT_NO_MASK;
-#ifndef CONFIG_CS89x0_PLATFORM
+#if IS_ENABLED(CONFIG_CS89x0_ISA)
 		if (lp->chip_type == CS8900) {
 			/* Translate the IRQ using the IRQ mapping table. */
 			if (i >= ARRAY_SIZE(cs8900_irq_map))
@@ -1576,7 +1576,7 @@ out1:
 	return retval;
 }
 
-#ifndef CONFIG_CS89x0_PLATFORM
+#if IS_ENABLED(CONFIG_CS89x0_ISA)
 /*
  * This function converts the I/O port address used by the cs89x0_probe() and
  * init_module() functions to the I/O memory address used by the
@@ -1682,11 +1682,7 @@ out:
 	pr_warn("no cs8900 or cs8920 detected.  Be sure to disable PnP with SETUP\n");
 	return ERR_PTR(err);
 }
-#endif
-#endif
-
-#if defined(MODULE) && !defined(CONFIG_CS89x0_PLATFORM)
-
+#else
 static struct net_device *dev_cs89x0;
 
 /* Support the 'debug' module parm even if we're compiled for non-debug to
@@ -1757,9 +1753,9 @@ MODULE_LICENSE("GPL");
  * (hw or software util)
  */
 
-int __init init_module(void)
+static int __init cs89x0_isa_init_module(void)
 {
-	struct net_device *dev = alloc_etherdev(sizeof(struct net_local));
+	struct net_device *dev;
 	struct net_local *lp;
 	int ret = 0;
 
@@ -1768,6 +1764,7 @@ int __init init_module(void)
 #else
 	debug = 0;
 #endif
+	dev = alloc_etherdev(sizeof(struct net_local));
 	if (!dev)
 		return -ENOMEM;
 
@@ -1826,9 +1823,9 @@ out:
 	free_netdev(dev);
 	return ret;
 }
+module_init(cs89x0_isa_init_module);
 
-void __exit
-cleanup_module(void)
+static void __exit cs89x0_isa_cleanup_module(void)
 {
 	struct net_local *lp = netdev_priv(dev_cs89x0);
 
@@ -1838,9 +1835,11 @@ cleanup_module(void)
 	release_region(dev_cs89x0->base_addr, NETCARD_IO_EXTENT);
 	free_netdev(dev_cs89x0);
 }
-#endif /* MODULE && !CONFIG_CS89x0_PLATFORM */
+module_exit(cs89x0_isa_cleanup_module);
+#endif /* MODULE */
+#endif /* CONFIG_CS89x0_ISA */
 
-#ifdef CONFIG_CS89x0_PLATFORM
+#if IS_ENABLED(CONFIG_CS89x0_PLATFORM)
 static int __init cs89x0_platform_probe(struct platform_device *pdev)
 {
 	struct net_device *dev = alloc_etherdev(sizeof(struct net_local));
diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c
index 9f5e5ec69991..072fac5f5d24 100644
--- a/drivers/net/ethernet/cirrus/ep93xx_eth.c
+++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c
@@ -733,7 +733,7 @@ static const struct net_device_ops ep93xx_netdev_ops = {
 	.ndo_open		= ep93xx_open,
 	.ndo_stop		= ep93xx_close,
 	.ndo_start_xmit		= ep93xx_xmit,
-	.ndo_do_ioctl		= ep93xx_ioctl,
+	.ndo_eth_ioctl		= ep93xx_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 };
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index 1a9803f2073e..12ffc14fbecd 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -298,7 +298,9 @@ static void enic_set_msglevel(struct net_device *netdev, u32 value)
 }
 
 static int enic_get_coalesce(struct net_device *netdev,
-	struct ethtool_coalesce *ecmd)
+			     struct ethtool_coalesce *ecmd,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct enic *enic = netdev_priv(netdev);
 	struct enic_rx_coal *rxcoal = &enic->rx_coalesce_setting;
@@ -343,7 +345,9 @@ static int enic_coalesce_valid(struct enic *enic,
 }
 
 static int enic_set_coalesce(struct net_device *netdev,
-	struct ethtool_coalesce *ecmd)
+			     struct ethtool_coalesce *ecmd,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct enic *enic = netdev_priv(netdev);
 	u32 tx_coalesce_usecs;
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index c2ebb3388789..6e745ca4c433 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -2144,7 +2144,9 @@ static int gmac_set_ringparam(struct net_device *netdev,
 }
 
 static int gmac_get_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *ecmd)
+			     struct ethtool_coalesce *ecmd,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct gemini_ethernet_port *port = netdev_priv(netdev);
 
@@ -2156,7 +2158,9 @@ static int gmac_get_coalesce(struct net_device *netdev,
 }
 
 static int gmac_set_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *ecmd)
+			     struct ethtool_coalesce *ecmd,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct gemini_ethernet_port *port = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 2a8bf53c2f75..e842de6f6635 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1372,7 +1372,7 @@ static const struct net_device_ops dm9000_netdev_ops = {
 	.ndo_start_xmit		= dm9000_start_xmit,
 	.ndo_tx_timeout		= dm9000_timeout,
 	.ndo_set_rx_mode	= dm9000_hash_table,
-	.ndo_do_ioctl		= dm9000_ioctl,
+	.ndo_eth_ioctl		= dm9000_ioctl,
 	.ndo_set_features	= dm9000_set_features,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index b125d7faefdf..36ab4cbf2ad0 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -443,6 +443,7 @@
     =========================================================================
 */
 
+#include <linux/compat.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
@@ -902,7 +903,8 @@ static int     de4x5_close(struct net_device *dev);
 static struct  net_device_stats *de4x5_get_stats(struct net_device *dev);
 static void    de4x5_local_stats(struct net_device *dev, char *buf, int pkt_len);
 static void    set_multicast_list(struct net_device *dev);
-static int     de4x5_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
+static int     de4x5_siocdevprivate(struct net_device *dev, struct ifreq *rq,
+				    void __user *data, int cmd);
 
 /*
 ** Private functions
@@ -1084,7 +1086,7 @@ static const struct net_device_ops de4x5_netdev_ops = {
     .ndo_start_xmit	= de4x5_queue_pkt,
     .ndo_get_stats	= de4x5_get_stats,
     .ndo_set_rx_mode	= set_multicast_list,
-    .ndo_do_ioctl	= de4x5_ioctl,
+    .ndo_siocdevprivate	= de4x5_siocdevprivate,
     .ndo_set_mac_address= eth_mac_addr,
     .ndo_validate_addr	= eth_validate_addr,
 };
@@ -5357,7 +5359,7 @@ de4x5_dbg_rx(struct sk_buff *skb, int len)
 ** this function is only used for my testing.
 */
 static int
-de4x5_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+de4x5_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *data, int cmd)
 {
     struct de4x5_private *lp = netdev_priv(dev);
     struct de4x5_ioctl *ioc = (struct de4x5_ioctl *) &rq->ifr_ifru;
@@ -5371,6 +5373,9 @@ de4x5_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
     } tmp;
     u_long flags = 0;
 
+    if (cmd != SIOCDEVPRIVATE || in_compat_syscall())
+	return -EOPNOTSUPP;
+
     switch(ioc->cmd) {
     case DE4X5_GET_HWADDR:           /* Get the hardware address */
 	ioc->len = ETH_ALEN;
diff --git a/drivers/net/ethernet/dec/tulip/media.c b/drivers/net/ethernet/dec/tulip/media.c
index 011604787b8e..55d6fc99f40b 100644
--- a/drivers/net/ethernet/dec/tulip/media.c
+++ b/drivers/net/ethernet/dec/tulip/media.c
@@ -362,7 +362,7 @@ void tulip_select_media(struct net_device *dev, int startup)
 			iowrite32(0x33, ioaddr + CSR12);
 			new_csr6 = 0x01860000;
 			/* Trigger autonegotiation. */
-			iowrite32(startup ? 0x0201F868 : 0x0001F868, ioaddr + 0xB8);
+			iowrite32(0x0001F868, ioaddr + 0xB8);
 		} else {
 			iowrite32(0x32, ioaddr + CSR12);
 			new_csr6 = 0x00420000;
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index c1dcd6ca1457..fcedd733bacb 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -1271,7 +1271,7 @@ static const struct net_device_ops tulip_netdev_ops = {
 	.ndo_tx_timeout		= tulip_tx_timeout,
 	.ndo_stop		= tulip_close,
 	.ndo_get_stats		= tulip_get_stats,
-	.ndo_do_ioctl 		= private_ioctl,
+	.ndo_eth_ioctl		= private_ioctl,
 	.ndo_set_rx_mode	= set_rx_mode,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index 1876f15dd827..85b99099c6b9 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -341,7 +341,7 @@ static const struct net_device_ops netdev_ops = {
 	.ndo_start_xmit		= start_tx,
 	.ndo_get_stats		= get_stats,
 	.ndo_set_rx_mode	= set_rx_mode,
-	.ndo_do_ioctl		= netdev_ioctl,
+	.ndo_eth_ioctl		= netdev_ioctl,
 	.ndo_tx_timeout		= tx_timeout,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index 734acb834c98..202ecb132053 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -95,7 +95,7 @@ static const struct net_device_ops netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_set_rx_mode	= set_multicast,
-	.ndo_do_ioctl		= rio_ioctl,
+	.ndo_eth_ioctl		= rio_ioctl,
 	.ndo_tx_timeout		= rio_tx_timeout,
 };
 
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index ee0ca712dd1c..c36d186dffed 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -479,7 +479,7 @@ static const struct net_device_ops netdev_ops = {
 	.ndo_start_xmit		= start_tx,
 	.ndo_get_stats 		= get_stats,
 	.ndo_set_rx_mode	= set_rx_mode,
-	.ndo_do_ioctl 		= netdev_ioctl,
+	.ndo_eth_ioctl		= netdev_ioctl,
 	.ndo_tx_timeout		= tx_timeout,
 	.ndo_change_mtu		= change_mtu,
 	.ndo_set_mac_address 	= sundance_set_mac_addr,
diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c
index 48c6eb142dcc..6c51cf991dad 100644
--- a/drivers/net/ethernet/dnet.c
+++ b/drivers/net/ethernet/dnet.c
@@ -742,7 +742,7 @@ static const struct net_device_ops dnet_netdev_ops = {
 	.ndo_stop		= dnet_close,
 	.ndo_get_stats		= dnet_get_stats,
 	.ndo_start_xmit		= dnet_start_xmit,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c
index 7c992172933b..b2d4fb3feb74 100644
--- a/drivers/net/ethernet/ec_bhf.c
+++ b/drivers/net/ethernet/ec_bhf.c
@@ -488,15 +488,7 @@ static int ec_bhf_probe(struct pci_dev *dev, const struct pci_device_id *id)
 
 	pci_set_master(dev);
 
-	err = pci_set_dma_mask(dev, DMA_BIT_MASK(32));
-	if (err) {
-		dev_err(&dev->dev,
-			"Required dma mask not supported, failed to initialize device\n");
-		err = -EIO;
-		goto err_disable_dev;
-	}
-
-	err = pci_set_consistent_dma_mask(dev, DMA_BIT_MASK(32));
+	err = dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32));
 	if (err) {
 		dev_err(&dev->dev,
 			"Required dma mask not supported, failed to initialize device\n");
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 99cc1c46fb30..f9955308b93d 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -315,7 +315,9 @@ static int be_read_dump_data(struct be_adapter *adapter, u32 dump_len,
 }
 
 static int be_get_coalesce(struct net_device *netdev,
-			   struct ethtool_coalesce *et)
+			   struct ethtool_coalesce *et,
+			   struct kernel_ethtool_coalesce *kernel_coal,
+			   struct netlink_ext_ack *extack)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	struct be_aic_obj *aic = &adapter->aic_obj[0];
@@ -338,7 +340,9 @@ static int be_get_coalesce(struct net_device *netdev,
  * eqd cmd is issued in the worker thread.
  */
 static int be_set_coalesce(struct net_device *netdev,
-			   struct ethtool_coalesce *et)
+			   struct ethtool_coalesce *et,
+			   struct kernel_ethtool_coalesce *kernel_coal,
+			   struct netlink_ext_ack *extack)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	struct be_aic_obj *aic = &adapter->aic_obj[0];
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index e1b43b07755b..ed1ed48e7483 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1009,7 +1009,7 @@ static const struct ethtool_ops ethoc_ethtool_ops = {
 static const struct net_device_ops ethoc_netdev_ops = {
 	.ndo_open = ethoc_open,
 	.ndo_stop = ethoc_stop,
-	.ndo_do_ioctl = ethoc_ioctl,
+	.ndo_eth_ioctl = ethoc_ioctl,
 	.ndo_set_mac_address = ethoc_set_mac_address,
 	.ndo_set_rx_mode = ethoc_set_multicast_list,
 	.ndo_change_mtu = ethoc_change_mtu,
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 11dbbfd38770..ff76e401a014 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1616,7 +1616,7 @@ static const struct net_device_ops ftgmac100_netdev_ops = {
 	.ndo_start_xmit		= ftgmac100_hard_start_xmit,
 	.ndo_set_mac_address	= ftgmac100_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= phy_do_ioctl,
+	.ndo_eth_ioctl		= phy_do_ioctl,
 	.ndo_tx_timeout		= ftgmac100_tx_timeout,
 	.ndo_set_rx_mode	= ftgmac100_set_rx_mode,
 	.ndo_set_features	= ftgmac100_set_features,
diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c
index 5a1a8f2ea63c..8a341e2d5833 100644
--- a/drivers/net/ethernet/faraday/ftmac100.c
+++ b/drivers/net/ethernet/faraday/ftmac100.c
@@ -1043,7 +1043,7 @@ static const struct net_device_ops ftmac100_netdev_ops = {
 	.ndo_start_xmit		= ftmac100_hard_start_xmit,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= ftmac100_do_ioctl,
+	.ndo_eth_ioctl		= ftmac100_do_ioctl,
 };
 
 /******************************************************************************
diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index 0f141c14d72d..25c91b3c5fd3 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -463,7 +463,7 @@ static const struct net_device_ops netdev_ops = {
 	.ndo_start_xmit		= start_tx,
 	.ndo_get_stats 		= get_stats,
 	.ndo_set_rx_mode	= set_rx_mode,
-	.ndo_do_ioctl		= mii_ioctl,
+	.ndo_eth_ioctl		= mii_ioctl,
 	.ndo_tx_timeout		= fealnx_tx_timeout,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index 2d1abdd58fab..e04e1c5cb013 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -25,10 +25,10 @@ config FEC
 	depends on (M523x || M527x || M5272 || M528x || M520x || M532x || \
 		   ARCH_MXC || SOC_IMX28 || COMPILE_TEST)
 	default ARCH_MXC || SOC_IMX28 if ARM
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select CRC32
 	select PHYLIB
 	imply NET_SELFTESTS
-	imply PTP_1588_CLOCK
 	help
 	  Say Y here if you want to use the built-in 10/100 Fast ethernet
 	  controller on some Motorola ColdFire and Freescale i.MX processors.
diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig b/drivers/net/ethernet/freescale/dpaa/Kconfig
index 626ec58a0afc..0e1439fd00bd 100644
--- a/drivers/net/ethernet/freescale/dpaa/Kconfig
+++ b/drivers/net/ethernet/freescale/dpaa/Kconfig
@@ -4,7 +4,6 @@ menuconfig FSL_DPAA_ETH
 	depends on FSL_DPAA && FSL_FMAN
 	select PHYLIB
 	select FIXED_PHY
-	select FSL_FMAN_MAC
 	help
 	  Data Path Acceleration Architecture Ethernet driver,
 	  supporting the Freescale QorIQ chips.
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index e6826561cf11..685d2d8a3b36 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -3157,7 +3157,7 @@ static const struct net_device_ops dpaa_ops = {
 	.ndo_set_mac_address = dpaa_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_set_rx_mode = dpaa_set_rx_mode,
-	.ndo_do_ioctl = dpaa_ioctl,
+	.ndo_eth_ioctl = dpaa_ioctl,
 	.ndo_setup_tc = dpaa_setup_tc,
 	.ndo_change_mtu = dpaa_change_mtu,
 	.ndo_bpf = dpaa_xdp,
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
index 1268996b7030..763d2c7b5fb1 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
@@ -513,7 +513,9 @@ static int dpaa_get_ts_info(struct net_device *net_dev,
 }
 
 static int dpaa_get_coalesce(struct net_device *dev,
-			     struct ethtool_coalesce *c)
+			     struct ethtool_coalesce *c,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct qman_portal *portal;
 	u32 period;
@@ -530,7 +532,9 @@ static int dpaa_get_coalesce(struct net_device *dev,
 }
 
 static int dpaa_set_coalesce(struct net_device *dev,
-			     struct ethtool_coalesce *c)
+			     struct ethtool_coalesce *c,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	const cpumask_t *cpus = qman_affine_cpus();
 	bool needs_revert[NR_CPUS] = {false};
diff --git a/drivers/net/ethernet/freescale/dpaa2/Makefile b/drivers/net/ethernet/freescale/dpaa2/Makefile
index c2ef74052ef8..3d9842af7f10 100644
--- a/drivers/net/ethernet/freescale/dpaa2/Makefile
+++ b/drivers/net/ethernet/freescale/dpaa2/Makefile
@@ -11,7 +11,7 @@ fsl-dpaa2-eth-objs	:= dpaa2-eth.o dpaa2-ethtool.o dpni.o dpaa2-mac.o dpmac.o dpa
 fsl-dpaa2-eth-${CONFIG_FSL_DPAA2_ETH_DCB} += dpaa2-eth-dcb.o
 fsl-dpaa2-eth-${CONFIG_DEBUG_FS} += dpaa2-eth-debugfs.o
 fsl-dpaa2-ptp-objs	:= dpaa2-ptp.o dprtc.o
-fsl-dpaa2-switch-objs	:= dpaa2-switch.o dpaa2-switch-ethtool.o dpsw.o dpaa2-switch-flower.o
+fsl-dpaa2-switch-objs	:= dpaa2-switch.o dpaa2-switch-ethtool.o dpsw.o dpaa2-switch-flower.o dpaa2-mac.o dpmac.o
 
 # Needed by the tracing framework
 CFLAGS_dpaa2-eth.o := -I$(src)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c
index 833696245565..605a39f892b9 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c
@@ -68,7 +68,7 @@ dpaa2_eth_dl_trap_item_lookup(struct dpaa2_eth_priv *priv, u16 trap_id)
 struct dpaa2_eth_trap_item *dpaa2_eth_dl_get_trap(struct dpaa2_eth_priv *priv,
 						  struct dpaa2_fapr *fapr)
 {
-	struct dpaa2_faf_error_bit {
+	static const struct dpaa2_faf_error_bit {
 		int position;
 		enum devlink_trap_generic_id trap_id;
 	} faf_bits[] = {
@@ -196,7 +196,8 @@ int dpaa2_eth_dl_register(struct dpaa2_eth_priv *priv)
 	struct dpaa2_eth_devlink_priv *dl_priv;
 	int err;
 
-	priv->devlink = devlink_alloc(&dpaa2_eth_devlink_ops, sizeof(*dl_priv));
+	priv->devlink =
+		devlink_alloc(&dpaa2_eth_devlink_ops, sizeof(*dl_priv), dev);
 	if (!priv->devlink) {
 		dev_err(dev, "devlink_alloc failed\n");
 		return -ENOMEM;
@@ -204,7 +205,7 @@ int dpaa2_eth_dl_register(struct dpaa2_eth_priv *priv)
 	dl_priv = devlink_priv(priv->devlink);
 	dl_priv->dpaa2_priv = priv;
 
-	err = devlink_register(priv->devlink, dev);
+	err = devlink_register(priv->devlink);
 	if (err) {
 		dev_err(dev, "devlink_register() = %d\n", err);
 		goto devlink_free;
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 973352393bd4..7065c71ed7b8 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2594,7 +2594,7 @@ static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_get_stats64 = dpaa2_eth_get_stats,
 	.ndo_set_rx_mode = dpaa2_eth_set_rx_mode,
 	.ndo_set_features = dpaa2_eth_set_features,
-	.ndo_do_ioctl = dpaa2_eth_ioctl,
+	.ndo_eth_ioctl = dpaa2_eth_ioctl,
 	.ndo_change_mtu = dpaa2_eth_change_mtu,
 	.ndo_bpf = dpaa2_eth_xdp,
 	.ndo_xdp_xmit = dpaa2_eth_xdp_xmit,
@@ -4138,7 +4138,7 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv)
 	int err;
 
 	dpni_dev = to_fsl_mc_device(priv->net_dev->dev.parent);
-	dpmac_dev = fsl_mc_get_endpoint(dpni_dev);
+	dpmac_dev = fsl_mc_get_endpoint(dpni_dev, 0);
 
 	if (PTR_ERR(dpmac_dev) == -EPROBE_DEFER)
 		return PTR_ERR(dpmac_dev);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index ad5e374eeccf..2da5f881f630 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -72,12 +72,12 @@ static void dpaa2_eth_get_drvinfo(struct net_device *net_dev,
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 
-	strlcpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
+	strscpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
 
 	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
 		 "%u.%u", priv->dpni_ver_major, priv->dpni_ver_minor);
 
-	strlcpy(drvinfo->bus_info, dev_name(net_dev->dev.parent->parent),
+	strscpy(drvinfo->bus_info, dev_name(net_dev->dev.parent->parent),
 		sizeof(drvinfo->bus_info));
 }
 
@@ -191,11 +191,11 @@ static void dpaa2_eth_get_strings(struct net_device *netdev, u32 stringset,
 	switch (stringset) {
 	case ETH_SS_STATS:
 		for (i = 0; i < DPAA2_ETH_NUM_STATS; i++) {
-			strlcpy(p, dpaa2_ethtool_stats[i], ETH_GSTRING_LEN);
+			strscpy(p, dpaa2_ethtool_stats[i], ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
 		for (i = 0; i < DPAA2_ETH_NUM_EXTRA_STATS; i++) {
-			strlcpy(p, dpaa2_ethtool_extras[i], ETH_GSTRING_LEN);
+			strscpy(p, dpaa2_ethtool_extras[i], ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
 		if (dpaa2_eth_has_mac(priv))
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-ethtool.c
index 70e04321c420..720c9230cab5 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-ethtool.c
@@ -15,18 +15,18 @@ static struct {
 	enum dpsw_counter id;
 	char name[ETH_GSTRING_LEN];
 } dpaa2_switch_ethtool_counters[] =  {
-	{DPSW_CNT_ING_FRAME,		"rx frames"},
-	{DPSW_CNT_ING_BYTE,		"rx bytes"},
-	{DPSW_CNT_ING_FLTR_FRAME,	"rx filtered frames"},
-	{DPSW_CNT_ING_FRAME_DISCARD,	"rx discarded frames"},
-	{DPSW_CNT_ING_BCAST_FRAME,	"rx b-cast frames"},
-	{DPSW_CNT_ING_BCAST_BYTES,	"rx b-cast bytes"},
-	{DPSW_CNT_ING_MCAST_FRAME,	"rx m-cast frames"},
-	{DPSW_CNT_ING_MCAST_BYTE,	"rx m-cast bytes"},
-	{DPSW_CNT_EGR_FRAME,		"tx frames"},
-	{DPSW_CNT_EGR_BYTE,		"tx bytes"},
-	{DPSW_CNT_EGR_FRAME_DISCARD,	"tx discarded frames"},
-	{DPSW_CNT_ING_NO_BUFF_DISCARD,	"rx discarded no buffer frames"},
+	{DPSW_CNT_ING_FRAME,		"[hw] rx frames"},
+	{DPSW_CNT_ING_BYTE,		"[hw] rx bytes"},
+	{DPSW_CNT_ING_FLTR_FRAME,	"[hw] rx filtered frames"},
+	{DPSW_CNT_ING_FRAME_DISCARD,	"[hw] rx discarded frames"},
+	{DPSW_CNT_ING_BCAST_FRAME,	"[hw] rx bcast frames"},
+	{DPSW_CNT_ING_BCAST_BYTES,	"[hw] rx bcast bytes"},
+	{DPSW_CNT_ING_MCAST_FRAME,	"[hw] rx mcast frames"},
+	{DPSW_CNT_ING_MCAST_BYTE,	"[hw] rx mcast bytes"},
+	{DPSW_CNT_EGR_FRAME,		"[hw] tx frames"},
+	{DPSW_CNT_EGR_BYTE,		"[hw] tx bytes"},
+	{DPSW_CNT_EGR_FRAME_DISCARD,	"[hw] tx discarded frames"},
+	{DPSW_CNT_ING_NO_BUFF_DISCARD,	"[hw] rx nobuffer discards"},
 };
 
 #define DPAA2_SWITCH_NUM_COUNTERS	ARRAY_SIZE(dpaa2_switch_ethtool_counters)
@@ -62,6 +62,10 @@ dpaa2_switch_get_link_ksettings(struct net_device *netdev,
 	struct dpsw_link_state state = {0};
 	int err = 0;
 
+	if (dpaa2_switch_port_is_type_phy(port_priv))
+		return phylink_ethtool_ksettings_get(port_priv->mac->phylink,
+						     link_ksettings);
+
 	err = dpsw_if_get_link_state(port_priv->ethsw_data->mc_io, 0,
 				     port_priv->ethsw_data->dpsw_handle,
 				     port_priv->idx,
@@ -95,6 +99,10 @@ dpaa2_switch_set_link_ksettings(struct net_device *netdev,
 	bool if_running;
 	int err = 0, ret;
 
+	if (dpaa2_switch_port_is_type_phy(port_priv))
+		return phylink_ethtool_ksettings_set(port_priv->mac->phylink,
+						     link_ksettings);
+
 	/* Interface needs to be down to change link settings */
 	if_running = netif_running(netdev);
 	if (if_running) {
@@ -134,11 +142,17 @@ dpaa2_switch_set_link_ksettings(struct net_device *netdev,
 	return err;
 }
 
-static int dpaa2_switch_ethtool_get_sset_count(struct net_device *dev, int sset)
+static int
+dpaa2_switch_ethtool_get_sset_count(struct net_device *netdev, int sset)
 {
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	int num_ss_stats = DPAA2_SWITCH_NUM_COUNTERS;
+
 	switch (sset) {
 	case ETH_SS_STATS:
-		return DPAA2_SWITCH_NUM_COUNTERS;
+		if (port_priv->mac)
+			num_ss_stats += dpaa2_mac_get_sset_count();
+		return num_ss_stats;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -147,14 +161,19 @@ static int dpaa2_switch_ethtool_get_sset_count(struct net_device *dev, int sset)
 static void dpaa2_switch_ethtool_get_strings(struct net_device *netdev,
 					     u32 stringset, u8 *data)
 {
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	u8 *p = data;
 	int i;
 
 	switch (stringset) {
 	case ETH_SS_STATS:
-		for (i = 0; i < DPAA2_SWITCH_NUM_COUNTERS; i++)
-			memcpy(data + i * ETH_GSTRING_LEN,
-			       dpaa2_switch_ethtool_counters[i].name,
+		for (i = 0; i < DPAA2_SWITCH_NUM_COUNTERS; i++) {
+			memcpy(p, dpaa2_switch_ethtool_counters[i].name,
 			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+		if (port_priv->mac)
+			dpaa2_mac_get_strings(p);
 		break;
 	}
 }
@@ -176,6 +195,9 @@ static void dpaa2_switch_ethtool_get_stats(struct net_device *netdev,
 			netdev_err(netdev, "dpsw_if_get_counter[%s] err %d\n",
 				   dpaa2_switch_ethtool_counters[i].name, err);
 	}
+
+	if (port_priv->mac)
+		dpaa2_mac_get_ethtool_stats(port_priv->mac, data + i);
 }
 
 const struct ethtool_ops dpaa2_switch_port_ethtool_ops = {
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
index f9451ec5f2cb..d6eefbbf163f 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
@@ -111,11 +111,11 @@ static int dpaa2_switch_flower_parse_key(struct flow_cls_offload *cls,
 	return 0;
 }
 
-int dpaa2_switch_acl_entry_add(struct dpaa2_switch_acl_tbl *acl_tbl,
+int dpaa2_switch_acl_entry_add(struct dpaa2_switch_filter_block *filter_block,
 			       struct dpaa2_switch_acl_entry *entry)
 {
 	struct dpsw_acl_entry_cfg *acl_entry_cfg = &entry->cfg;
-	struct ethsw_core *ethsw = acl_tbl->ethsw;
+	struct ethsw_core *ethsw = filter_block->ethsw;
 	struct dpsw_acl_key *acl_key = &entry->key;
 	struct device *dev = ethsw->dev;
 	u8 *cmd_buff;
@@ -136,7 +136,7 @@ int dpaa2_switch_acl_entry_add(struct dpaa2_switch_acl_tbl *acl_tbl,
 	}
 
 	err = dpsw_acl_add_entry(ethsw->mc_io, 0, ethsw->dpsw_handle,
-				 acl_tbl->id, acl_entry_cfg);
+				 filter_block->acl_id, acl_entry_cfg);
 
 	dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff),
 			 DMA_TO_DEVICE);
@@ -150,12 +150,13 @@ int dpaa2_switch_acl_entry_add(struct dpaa2_switch_acl_tbl *acl_tbl,
 	return 0;
 }
 
-static int dpaa2_switch_acl_entry_remove(struct dpaa2_switch_acl_tbl *acl_tbl,
-					 struct dpaa2_switch_acl_entry *entry)
+static int
+dpaa2_switch_acl_entry_remove(struct dpaa2_switch_filter_block *block,
+			      struct dpaa2_switch_acl_entry *entry)
 {
 	struct dpsw_acl_entry_cfg *acl_entry_cfg = &entry->cfg;
 	struct dpsw_acl_key *acl_key = &entry->key;
-	struct ethsw_core *ethsw = acl_tbl->ethsw;
+	struct ethsw_core *ethsw = block->ethsw;
 	struct device *dev = ethsw->dev;
 	u8 *cmd_buff;
 	int err;
@@ -175,7 +176,7 @@ static int dpaa2_switch_acl_entry_remove(struct dpaa2_switch_acl_tbl *acl_tbl,
 	}
 
 	err = dpsw_acl_remove_entry(ethsw->mc_io, 0, ethsw->dpsw_handle,
-				    acl_tbl->id, acl_entry_cfg);
+				    block->acl_id, acl_entry_cfg);
 
 	dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff),
 			 DMA_TO_DEVICE);
@@ -190,19 +191,19 @@ static int dpaa2_switch_acl_entry_remove(struct dpaa2_switch_acl_tbl *acl_tbl,
 }
 
 static int
-dpaa2_switch_acl_entry_add_to_list(struct dpaa2_switch_acl_tbl *acl_tbl,
+dpaa2_switch_acl_entry_add_to_list(struct dpaa2_switch_filter_block *block,
 				   struct dpaa2_switch_acl_entry *entry)
 {
 	struct dpaa2_switch_acl_entry *tmp;
 	struct list_head *pos, *n;
 	int index = 0;
 
-	if (list_empty(&acl_tbl->entries)) {
-		list_add(&entry->list, &acl_tbl->entries);
+	if (list_empty(&block->acl_entries)) {
+		list_add(&entry->list, &block->acl_entries);
 		return index;
 	}
 
-	list_for_each_safe(pos, n, &acl_tbl->entries) {
+	list_for_each_safe(pos, n, &block->acl_entries) {
 		tmp = list_entry(pos, struct dpaa2_switch_acl_entry, list);
 		if (entry->prio < tmp->prio)
 			break;
@@ -213,13 +214,13 @@ dpaa2_switch_acl_entry_add_to_list(struct dpaa2_switch_acl_tbl *acl_tbl,
 }
 
 static struct dpaa2_switch_acl_entry*
-dpaa2_switch_acl_entry_get_by_index(struct dpaa2_switch_acl_tbl *acl_tbl,
+dpaa2_switch_acl_entry_get_by_index(struct dpaa2_switch_filter_block *block,
 				    int index)
 {
 	struct dpaa2_switch_acl_entry *tmp;
 	int i = 0;
 
-	list_for_each_entry(tmp, &acl_tbl->entries, list) {
+	list_for_each_entry(tmp, &block->acl_entries, list) {
 		if (i == index)
 			return tmp;
 		++i;
@@ -229,37 +230,38 @@ dpaa2_switch_acl_entry_get_by_index(struct dpaa2_switch_acl_tbl *acl_tbl,
 }
 
 static int
-dpaa2_switch_acl_entry_set_precedence(struct dpaa2_switch_acl_tbl *acl_tbl,
+dpaa2_switch_acl_entry_set_precedence(struct dpaa2_switch_filter_block *block,
 				      struct dpaa2_switch_acl_entry *entry,
 				      int precedence)
 {
 	int err;
 
-	err = dpaa2_switch_acl_entry_remove(acl_tbl, entry);
+	err = dpaa2_switch_acl_entry_remove(block, entry);
 	if (err)
 		return err;
 
 	entry->cfg.precedence = precedence;
-	return dpaa2_switch_acl_entry_add(acl_tbl, entry);
+	return dpaa2_switch_acl_entry_add(block, entry);
 }
 
-static int dpaa2_switch_acl_tbl_add_entry(struct dpaa2_switch_acl_tbl *acl_tbl,
-					  struct dpaa2_switch_acl_entry *entry)
+static int
+dpaa2_switch_acl_tbl_add_entry(struct dpaa2_switch_filter_block *block,
+			       struct dpaa2_switch_acl_entry *entry)
 {
 	struct dpaa2_switch_acl_entry *tmp;
 	int index, i, precedence, err;
 
 	/* Add the new ACL entry to the linked list and get its index */
-	index = dpaa2_switch_acl_entry_add_to_list(acl_tbl, entry);
+	index = dpaa2_switch_acl_entry_add_to_list(block, entry);
 
 	/* Move up in priority the ACL entries to make space
 	 * for the new filter.
 	 */
-	precedence = DPAA2_ETHSW_PORT_MAX_ACL_ENTRIES - acl_tbl->num_rules - 1;
+	precedence = DPAA2_ETHSW_PORT_MAX_ACL_ENTRIES - block->num_acl_rules - 1;
 	for (i = 0; i < index; i++) {
-		tmp = dpaa2_switch_acl_entry_get_by_index(acl_tbl, i);
+		tmp = dpaa2_switch_acl_entry_get_by_index(block, i);
 
-		err = dpaa2_switch_acl_entry_set_precedence(acl_tbl, tmp,
+		err = dpaa2_switch_acl_entry_set_precedence(block, tmp,
 							    precedence);
 		if (err)
 			return err;
@@ -269,19 +271,19 @@ static int dpaa2_switch_acl_tbl_add_entry(struct dpaa2_switch_acl_tbl *acl_tbl,
 
 	/* Add the new entry to hardware */
 	entry->cfg.precedence = precedence;
-	err = dpaa2_switch_acl_entry_add(acl_tbl, entry);
-	acl_tbl->num_rules++;
+	err = dpaa2_switch_acl_entry_add(block, entry);
+	block->num_acl_rules++;
 
 	return err;
 }
 
 static struct dpaa2_switch_acl_entry *
-dpaa2_switch_acl_tbl_find_entry_by_cookie(struct dpaa2_switch_acl_tbl *acl_tbl,
+dpaa2_switch_acl_tbl_find_entry_by_cookie(struct dpaa2_switch_filter_block *block,
 					  unsigned long cookie)
 {
 	struct dpaa2_switch_acl_entry *tmp, *n;
 
-	list_for_each_entry_safe(tmp, n, &acl_tbl->entries, list) {
+	list_for_each_entry_safe(tmp, n, &block->acl_entries, list) {
 		if (tmp->cookie == cookie)
 			return tmp;
 	}
@@ -289,13 +291,13 @@ dpaa2_switch_acl_tbl_find_entry_by_cookie(struct dpaa2_switch_acl_tbl *acl_tbl,
 }
 
 static int
-dpaa2_switch_acl_entry_get_index(struct dpaa2_switch_acl_tbl *acl_tbl,
+dpaa2_switch_acl_entry_get_index(struct dpaa2_switch_filter_block *block,
 				 struct dpaa2_switch_acl_entry *entry)
 {
 	struct dpaa2_switch_acl_entry *tmp, *n;
 	int index = 0;
 
-	list_for_each_entry_safe(tmp, n, &acl_tbl->entries, list) {
+	list_for_each_entry_safe(tmp, n, &block->acl_entries, list) {
 		if (tmp->cookie == entry->cookie)
 			return index;
 		index++;
@@ -303,21 +305,34 @@ dpaa2_switch_acl_entry_get_index(struct dpaa2_switch_acl_tbl *acl_tbl,
 	return -ENOENT;
 }
 
+static struct dpaa2_switch_mirror_entry *
+dpaa2_switch_mirror_find_entry_by_cookie(struct dpaa2_switch_filter_block *block,
+					 unsigned long cookie)
+{
+	struct dpaa2_switch_mirror_entry *tmp, *n;
+
+	list_for_each_entry_safe(tmp, n, &block->mirror_entries, list) {
+		if (tmp->cookie == cookie)
+			return tmp;
+	}
+	return NULL;
+}
+
 static int
-dpaa2_switch_acl_tbl_remove_entry(struct dpaa2_switch_acl_tbl *acl_tbl,
+dpaa2_switch_acl_tbl_remove_entry(struct dpaa2_switch_filter_block *block,
 				  struct dpaa2_switch_acl_entry *entry)
 {
 	struct dpaa2_switch_acl_entry *tmp;
 	int index, i, precedence, err;
 
-	index = dpaa2_switch_acl_entry_get_index(acl_tbl, entry);
+	index = dpaa2_switch_acl_entry_get_index(block, entry);
 
 	/* Remove from hardware the ACL entry */
-	err = dpaa2_switch_acl_entry_remove(acl_tbl, entry);
+	err = dpaa2_switch_acl_entry_remove(block, entry);
 	if (err)
 		return err;
 
-	acl_tbl->num_rules--;
+	block->num_acl_rules--;
 
 	/* Remove it from the list also */
 	list_del(&entry->list);
@@ -325,8 +340,8 @@ dpaa2_switch_acl_tbl_remove_entry(struct dpaa2_switch_acl_tbl *acl_tbl,
 	/* Move down in priority the entries over the deleted one */
 	precedence = entry->cfg.precedence;
 	for (i = index - 1; i >= 0; i--) {
-		tmp = dpaa2_switch_acl_entry_get_by_index(acl_tbl, i);
-		err = dpaa2_switch_acl_entry_set_precedence(acl_tbl, tmp,
+		tmp = dpaa2_switch_acl_entry_get_by_index(block, i);
+		err = dpaa2_switch_acl_entry_set_precedence(block, tmp,
 							    precedence);
 		if (err)
 			return err;
@@ -339,10 +354,10 @@ dpaa2_switch_acl_tbl_remove_entry(struct dpaa2_switch_acl_tbl *acl_tbl,
 	return 0;
 }
 
-static int dpaa2_switch_tc_parse_action(struct ethsw_core *ethsw,
-					struct flow_action_entry *cls_act,
-					struct dpsw_acl_result *dpsw_act,
-					struct netlink_ext_ack *extack)
+static int dpaa2_switch_tc_parse_action_acl(struct ethsw_core *ethsw,
+					    struct flow_action_entry *cls_act,
+					    struct dpsw_acl_result *dpsw_act,
+					    struct netlink_ext_ack *extack)
 {
 	int err = 0;
 
@@ -374,22 +389,110 @@ out:
 	return err;
 }
 
-int dpaa2_switch_cls_flower_replace(struct dpaa2_switch_acl_tbl *acl_tbl,
+static int
+dpaa2_switch_block_add_mirror(struct dpaa2_switch_filter_block *block,
+			      struct dpaa2_switch_mirror_entry *entry,
+			      u16 to, struct netlink_ext_ack *extack)
+{
+	unsigned long block_ports = block->ports;
+	struct ethsw_core *ethsw = block->ethsw;
+	struct ethsw_port_priv *port_priv;
+	unsigned long ports_added = 0;
+	u16 vlan = entry->cfg.vlan_id;
+	bool mirror_port_enabled;
+	int err, port;
+
+	/* Setup the mirroring port */
+	mirror_port_enabled = (ethsw->mirror_port != ethsw->sw_attr.num_ifs);
+	if (!mirror_port_enabled) {
+		err = dpsw_set_reflection_if(ethsw->mc_io, 0,
+					     ethsw->dpsw_handle, to);
+		if (err)
+			return err;
+		ethsw->mirror_port = to;
+	}
+
+	/* Setup the same egress mirroring configuration on all the switch
+	 * ports that share the same filter block.
+	 */
+	for_each_set_bit(port, &block_ports, ethsw->sw_attr.num_ifs) {
+		port_priv = ethsw->ports[port];
+
+		/* We cannot add a per VLAN mirroring rule if the VLAN in
+		 * question is not installed on the switch port.
+		 */
+		if (entry->cfg.filter == DPSW_REFLECTION_FILTER_INGRESS_VLAN &&
+		    !(port_priv->vlans[vlan] & ETHSW_VLAN_MEMBER)) {
+			NL_SET_ERR_MSG(extack,
+				       "VLAN must be installed on the switch port");
+			err = -EINVAL;
+			goto err_remove_filters;
+		}
+
+		err = dpsw_if_add_reflection(ethsw->mc_io, 0,
+					     ethsw->dpsw_handle,
+					     port, &entry->cfg);
+		if (err)
+			goto err_remove_filters;
+
+		ports_added |= BIT(port);
+	}
+
+	list_add(&entry->list, &block->mirror_entries);
+
+	return 0;
+
+err_remove_filters:
+	for_each_set_bit(port, &ports_added, ethsw->sw_attr.num_ifs) {
+		dpsw_if_remove_reflection(ethsw->mc_io, 0, ethsw->dpsw_handle,
+					  port, &entry->cfg);
+	}
+
+	if (!mirror_port_enabled)
+		ethsw->mirror_port = ethsw->sw_attr.num_ifs;
+
+	return err;
+}
+
+static int
+dpaa2_switch_block_remove_mirror(struct dpaa2_switch_filter_block *block,
+				 struct dpaa2_switch_mirror_entry *entry)
+{
+	struct dpsw_reflection_cfg *cfg = &entry->cfg;
+	unsigned long block_ports = block->ports;
+	struct ethsw_core *ethsw = block->ethsw;
+	int port;
+
+	/* Remove this mirroring configuration from all the ports belonging to
+	 * the filter block.
+	 */
+	for_each_set_bit(port, &block_ports, ethsw->sw_attr.num_ifs)
+		dpsw_if_remove_reflection(ethsw->mc_io, 0, ethsw->dpsw_handle,
+					  port, cfg);
+
+	/* Also remove it from the list of mirror filters */
+	list_del(&entry->list);
+	kfree(entry);
+
+	/* If this was the last mirror filter, then unset the mirror port */
+	if (list_empty(&block->mirror_entries))
+		ethsw->mirror_port =  ethsw->sw_attr.num_ifs;
+
+	return 0;
+}
+
+static int
+dpaa2_switch_cls_flower_replace_acl(struct dpaa2_switch_filter_block *block,
 				    struct flow_cls_offload *cls)
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
 	struct netlink_ext_ack *extack = cls->common.extack;
-	struct ethsw_core *ethsw = acl_tbl->ethsw;
 	struct dpaa2_switch_acl_entry *acl_entry;
+	struct ethsw_core *ethsw = block->ethsw;
 	struct flow_action_entry *act;
 	int err;
 
-	if (!flow_offload_has_one_action(&rule->action)) {
-		NL_SET_ERR_MSG(extack, "Only singular actions are supported");
-		return -EOPNOTSUPP;
-	}
-
-	if (dpaa2_switch_acl_tbl_is_full(acl_tbl)) {
+	if (dpaa2_switch_acl_tbl_is_full(block)) {
 		NL_SET_ERR_MSG(extack, "Maximum filter capacity reached");
 		return -ENOMEM;
 	}
@@ -403,15 +506,15 @@ int dpaa2_switch_cls_flower_replace(struct dpaa2_switch_acl_tbl *acl_tbl,
 		goto free_acl_entry;
 
 	act = &rule->action.entries[0];
-	err = dpaa2_switch_tc_parse_action(ethsw, act,
-					   &acl_entry->cfg.result, extack);
+	err = dpaa2_switch_tc_parse_action_acl(ethsw, act,
+					       &acl_entry->cfg.result, extack);
 	if (err)
 		goto free_acl_entry;
 
 	acl_entry->prio = cls->common.prio;
 	acl_entry->cookie = cls->cookie;
 
-	err = dpaa2_switch_acl_tbl_add_entry(acl_tbl, acl_entry);
+	err = dpaa2_switch_acl_tbl_add_entry(block, acl_entry);
 	if (err)
 		goto free_acl_entry;
 
@@ -423,33 +526,171 @@ free_acl_entry:
 	return err;
 }
 
-int dpaa2_switch_cls_flower_destroy(struct dpaa2_switch_acl_tbl *acl_tbl,
-				    struct flow_cls_offload *cls)
+static int dpaa2_switch_flower_parse_mirror_key(struct flow_cls_offload *cls,
+						u16 *vlan)
 {
-	struct dpaa2_switch_acl_entry *entry;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
+	struct flow_dissector *dissector = rule->match.dissector;
+	struct netlink_ext_ack *extack = cls->common.extack;
+
+	if (dissector->used_keys &
+	    ~(BIT(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT(FLOW_DISSECTOR_KEY_VLAN))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Mirroring is supported only per VLAN");
+		return -EOPNOTSUPP;
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
+
+		flow_rule_match_vlan(rule, &match);
 
-	entry = dpaa2_switch_acl_tbl_find_entry_by_cookie(acl_tbl, cls->cookie);
-	if (!entry)
-		return 0;
+		if (match.mask->vlan_priority != 0 ||
+		    match.mask->vlan_dei != 0) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Only matching on VLAN ID supported");
+			return -EOPNOTSUPP;
+		}
 
-	return dpaa2_switch_acl_tbl_remove_entry(acl_tbl, entry);
+		if (match.mask->vlan_id != 0xFFF) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Masked matching not supported");
+			return -EOPNOTSUPP;
+		}
+
+		*vlan = (u16)match.key->vlan_id;
+	}
+
+	return 0;
 }
 
-int dpaa2_switch_cls_matchall_replace(struct dpaa2_switch_acl_tbl *acl_tbl,
-				      struct tc_cls_matchall_offload *cls)
+static int
+dpaa2_switch_cls_flower_replace_mirror(struct dpaa2_switch_filter_block *block,
+				       struct flow_cls_offload *cls)
 {
 	struct netlink_ext_ack *extack = cls->common.extack;
-	struct ethsw_core *ethsw = acl_tbl->ethsw;
-	struct dpaa2_switch_acl_entry *acl_entry;
-	struct flow_action_entry *act;
+	struct dpaa2_switch_mirror_entry *mirror_entry;
+	struct ethsw_core *ethsw = block->ethsw;
+	struct dpaa2_switch_mirror_entry *tmp;
+	struct flow_action_entry *cls_act;
+	struct list_head *pos, *n;
+	bool mirror_port_enabled;
+	u16 if_id, vlan;
 	int err;
 
-	if (!flow_offload_has_one_action(&cls->rule->action)) {
+	mirror_port_enabled = (ethsw->mirror_port != ethsw->sw_attr.num_ifs);
+	cls_act = &cls->rule->action.entries[0];
+
+	/* Offload rules only when the destination is a DPAA2 switch port */
+	if (!dpaa2_switch_port_dev_check(cls_act->dev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Destination not a DPAA2 switch port");
+		return -EOPNOTSUPP;
+	}
+	if_id = dpaa2_switch_get_index(ethsw, cls_act->dev);
+
+	/* We have a single mirror port but can configure egress mirroring on
+	 * all the other switch ports. We need to allow mirroring rules only
+	 * when the destination port is the same.
+	 */
+	if (mirror_port_enabled && ethsw->mirror_port != if_id) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Multiple mirror ports not supported");
+		return -EBUSY;
+	}
+
+	/* Parse the key */
+	err = dpaa2_switch_flower_parse_mirror_key(cls, &vlan);
+	if (err)
+		return err;
+
+	/* Make sure that we don't already have a mirror rule with the same
+	 * configuration.
+	 */
+	list_for_each_safe(pos, n, &block->mirror_entries) {
+		tmp = list_entry(pos, struct dpaa2_switch_mirror_entry, list);
+
+		if (tmp->cfg.filter == DPSW_REFLECTION_FILTER_INGRESS_VLAN &&
+		    tmp->cfg.vlan_id == vlan) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "VLAN mirror filter already installed");
+			return -EBUSY;
+		}
+	}
+
+	mirror_entry = kzalloc(sizeof(*mirror_entry), GFP_KERNEL);
+	if (!mirror_entry)
+		return -ENOMEM;
+
+	mirror_entry->cfg.filter = DPSW_REFLECTION_FILTER_INGRESS_VLAN;
+	mirror_entry->cfg.vlan_id = vlan;
+	mirror_entry->cookie = cls->cookie;
+
+	return dpaa2_switch_block_add_mirror(block, mirror_entry, if_id,
+					     extack);
+}
+
+int dpaa2_switch_cls_flower_replace(struct dpaa2_switch_filter_block *block,
+				    struct flow_cls_offload *cls)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
+	struct netlink_ext_ack *extack = cls->common.extack;
+	struct flow_action_entry *act;
+
+	if (!flow_offload_has_one_action(&rule->action)) {
 		NL_SET_ERR_MSG(extack, "Only singular actions are supported");
 		return -EOPNOTSUPP;
 	}
 
-	if (dpaa2_switch_acl_tbl_is_full(acl_tbl)) {
+	act = &rule->action.entries[0];
+	switch (act->id) {
+	case FLOW_ACTION_REDIRECT:
+	case FLOW_ACTION_TRAP:
+	case FLOW_ACTION_DROP:
+		return dpaa2_switch_cls_flower_replace_acl(block, cls);
+	case FLOW_ACTION_MIRRED:
+		return dpaa2_switch_cls_flower_replace_mirror(block, cls);
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "Action not supported");
+		return -EOPNOTSUPP;
+	}
+}
+
+int dpaa2_switch_cls_flower_destroy(struct dpaa2_switch_filter_block *block,
+				    struct flow_cls_offload *cls)
+{
+	struct dpaa2_switch_mirror_entry *mirror_entry;
+	struct dpaa2_switch_acl_entry *acl_entry;
+
+	/* If this filter is a an ACL one, remove it */
+	acl_entry = dpaa2_switch_acl_tbl_find_entry_by_cookie(block,
+							      cls->cookie);
+	if (acl_entry)
+		return dpaa2_switch_acl_tbl_remove_entry(block, acl_entry);
+
+	/* If not, then it has to be a mirror */
+	mirror_entry = dpaa2_switch_mirror_find_entry_by_cookie(block,
+								cls->cookie);
+	if (mirror_entry)
+		return dpaa2_switch_block_remove_mirror(block,
+							mirror_entry);
+
+	return 0;
+}
+
+static int
+dpaa2_switch_cls_matchall_replace_acl(struct dpaa2_switch_filter_block *block,
+				      struct tc_cls_matchall_offload *cls)
+{
+	struct netlink_ext_ack *extack = cls->common.extack;
+	struct ethsw_core *ethsw = block->ethsw;
+	struct dpaa2_switch_acl_entry *acl_entry;
+	struct flow_action_entry *act;
+	int err;
+
+	if (dpaa2_switch_acl_tbl_is_full(block)) {
 		NL_SET_ERR_MSG(extack, "Maximum filter capacity reached");
 		return -ENOMEM;
 	}
@@ -459,15 +700,15 @@ int dpaa2_switch_cls_matchall_replace(struct dpaa2_switch_acl_tbl *acl_tbl,
 		return -ENOMEM;
 
 	act = &cls->rule->action.entries[0];
-	err = dpaa2_switch_tc_parse_action(ethsw, act,
-					   &acl_entry->cfg.result, extack);
+	err = dpaa2_switch_tc_parse_action_acl(ethsw, act,
+					       &acl_entry->cfg.result, extack);
 	if (err)
 		goto free_acl_entry;
 
 	acl_entry->prio = cls->common.prio;
 	acl_entry->cookie = cls->cookie;
 
-	err = dpaa2_switch_acl_tbl_add_entry(acl_tbl, acl_entry);
+	err = dpaa2_switch_acl_tbl_add_entry(block, acl_entry);
 	if (err)
 		goto free_acl_entry;
 
@@ -479,14 +720,159 @@ free_acl_entry:
 	return err;
 }
 
-int dpaa2_switch_cls_matchall_destroy(struct dpaa2_switch_acl_tbl *acl_tbl,
+static int
+dpaa2_switch_cls_matchall_replace_mirror(struct dpaa2_switch_filter_block *block,
+					 struct tc_cls_matchall_offload *cls)
+{
+	struct netlink_ext_ack *extack = cls->common.extack;
+	struct dpaa2_switch_mirror_entry *mirror_entry;
+	struct ethsw_core *ethsw = block->ethsw;
+	struct dpaa2_switch_mirror_entry *tmp;
+	struct flow_action_entry *cls_act;
+	struct list_head *pos, *n;
+	bool mirror_port_enabled;
+	u16 if_id;
+
+	mirror_port_enabled = (ethsw->mirror_port != ethsw->sw_attr.num_ifs);
+	cls_act = &cls->rule->action.entries[0];
+
+	/* Offload rules only when the destination is a DPAA2 switch port */
+	if (!dpaa2_switch_port_dev_check(cls_act->dev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Destination not a DPAA2 switch port");
+		return -EOPNOTSUPP;
+	}
+	if_id = dpaa2_switch_get_index(ethsw, cls_act->dev);
+
+	/* We have a single mirror port but can configure egress mirroring on
+	 * all the other switch ports. We need to allow mirroring rules only
+	 * when the destination port is the same.
+	 */
+	if (mirror_port_enabled && ethsw->mirror_port != if_id) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Multiple mirror ports not supported");
+		return -EBUSY;
+	}
+
+	/* Make sure that we don't already have a mirror rule with the same
+	 * configuration. One matchall rule per block is the maximum.
+	 */
+	list_for_each_safe(pos, n, &block->mirror_entries) {
+		tmp = list_entry(pos, struct dpaa2_switch_mirror_entry, list);
+
+		if (tmp->cfg.filter == DPSW_REFLECTION_FILTER_INGRESS_ALL) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Matchall mirror filter already installed");
+			return -EBUSY;
+		}
+	}
+
+	mirror_entry = kzalloc(sizeof(*mirror_entry), GFP_KERNEL);
+	if (!mirror_entry)
+		return -ENOMEM;
+
+	mirror_entry->cfg.filter = DPSW_REFLECTION_FILTER_INGRESS_ALL;
+	mirror_entry->cookie = cls->cookie;
+
+	return dpaa2_switch_block_add_mirror(block, mirror_entry, if_id,
+					     extack);
+}
+
+int dpaa2_switch_cls_matchall_replace(struct dpaa2_switch_filter_block *block,
+				      struct tc_cls_matchall_offload *cls)
+{
+	struct netlink_ext_ack *extack = cls->common.extack;
+	struct flow_action_entry *act;
+
+	if (!flow_offload_has_one_action(&cls->rule->action)) {
+		NL_SET_ERR_MSG(extack, "Only singular actions are supported");
+		return -EOPNOTSUPP;
+	}
+
+	act = &cls->rule->action.entries[0];
+	switch (act->id) {
+	case FLOW_ACTION_REDIRECT:
+	case FLOW_ACTION_TRAP:
+	case FLOW_ACTION_DROP:
+		return dpaa2_switch_cls_matchall_replace_acl(block, cls);
+	case FLOW_ACTION_MIRRED:
+		return dpaa2_switch_cls_matchall_replace_mirror(block, cls);
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "Action not supported");
+		return -EOPNOTSUPP;
+	}
+}
+
+int dpaa2_switch_block_offload_mirror(struct dpaa2_switch_filter_block *block,
+				      struct ethsw_port_priv *port_priv)
+{
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct dpaa2_switch_mirror_entry *tmp;
+	int err;
+
+	list_for_each_entry(tmp, &block->mirror_entries, list) {
+		err = dpsw_if_add_reflection(ethsw->mc_io, 0,
+					     ethsw->dpsw_handle,
+					     port_priv->idx, &tmp->cfg);
+		if (err)
+			goto unwind_add;
+	}
+
+	return 0;
+
+unwind_add:
+	list_for_each_entry(tmp, &block->mirror_entries, list)
+		dpsw_if_remove_reflection(ethsw->mc_io, 0,
+					  ethsw->dpsw_handle,
+					  port_priv->idx, &tmp->cfg);
+
+	return err;
+}
+
+int dpaa2_switch_block_unoffload_mirror(struct dpaa2_switch_filter_block *block,
+					struct ethsw_port_priv *port_priv)
+{
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct dpaa2_switch_mirror_entry *tmp;
+	int err;
+
+	list_for_each_entry(tmp, &block->mirror_entries, list) {
+		err = dpsw_if_remove_reflection(ethsw->mc_io, 0,
+						ethsw->dpsw_handle,
+						port_priv->idx, &tmp->cfg);
+		if (err)
+			goto unwind_remove;
+	}
+
+	return 0;
+
+unwind_remove:
+	list_for_each_entry(tmp, &block->mirror_entries, list)
+		dpsw_if_add_reflection(ethsw->mc_io, 0, ethsw->dpsw_handle,
+				       port_priv->idx, &tmp->cfg);
+
+	return err;
+}
+
+int dpaa2_switch_cls_matchall_destroy(struct dpaa2_switch_filter_block *block,
 				      struct tc_cls_matchall_offload *cls)
 {
-	struct dpaa2_switch_acl_entry *entry;
+	struct dpaa2_switch_mirror_entry *mirror_entry;
+	struct dpaa2_switch_acl_entry *acl_entry;
+
+	/* If this filter is a an ACL one, remove it */
+	acl_entry = dpaa2_switch_acl_tbl_find_entry_by_cookie(block,
+							      cls->cookie);
+	if (acl_entry)
+		return dpaa2_switch_acl_tbl_remove_entry(block,
+							 acl_entry);
 
-	entry = dpaa2_switch_acl_tbl_find_entry_by_cookie(acl_tbl, cls->cookie);
-	if (!entry)
-		return 0;
+	/* If not, then it has to be a mirror */
+	mirror_entry = dpaa2_switch_mirror_find_entry_by_cookie(block,
+								cls->cookie);
+	if (mirror_entry)
+		return dpaa2_switch_block_remove_mirror(block,
+							mirror_entry);
 
-	return  dpaa2_switch_acl_tbl_remove_entry(acl_tbl, entry);
+	return 0;
 }
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index 98cc0133c343..175f15c46842 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -41,14 +41,14 @@ static struct dpaa2_switch_fdb *dpaa2_switch_fdb_get_unused(struct ethsw_core *e
 	return NULL;
 }
 
-static struct dpaa2_switch_acl_tbl *
-dpaa2_switch_acl_tbl_get_unused(struct ethsw_core *ethsw)
+static struct dpaa2_switch_filter_block *
+dpaa2_switch_filter_block_get_unused(struct ethsw_core *ethsw)
 {
 	int i;
 
 	for (i = 0; i < ethsw->sw_attr.num_ifs; i++)
-		if (!ethsw->acls[i].in_use)
-			return &ethsw->acls[i];
+		if (!ethsw->filter_blocks[i].in_use)
+			return &ethsw->filter_blocks[i];
 	return NULL;
 }
 
@@ -594,12 +594,18 @@ static int dpaa2_switch_port_change_mtu(struct net_device *netdev, int mtu)
 	return 0;
 }
 
-static int dpaa2_switch_port_carrier_state_sync(struct net_device *netdev)
+static int dpaa2_switch_port_link_state_update(struct net_device *netdev)
 {
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
 	struct dpsw_link_state state;
 	int err;
 
+	/* When we manage the MAC/PHY using phylink there is no need
+	 * to manually update the netif_carrier.
+	 */
+	if (dpaa2_switch_port_is_type_phy(port_priv))
+		return 0;
+
 	/* Interrupts are received even though no one issued an 'ifconfig up'
 	 * on the switch interface. Ignore these link state update interrupts
 	 */
@@ -677,12 +683,14 @@ static int dpaa2_switch_port_open(struct net_device *netdev)
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
 	int err;
 
-	/* Explicitly set carrier off, otherwise
-	 * netif_carrier_ok() will return true and cause 'ip link show'
-	 * to report the LOWER_UP flag, even though the link
-	 * notification wasn't even received.
-	 */
-	netif_carrier_off(netdev);
+	if (!dpaa2_switch_port_is_type_phy(port_priv)) {
+		/* Explicitly set carrier off, otherwise
+		 * netif_carrier_ok() will return true and cause 'ip link show'
+		 * to report the LOWER_UP flag, even though the link
+		 * notification wasn't even received.
+		 */
+		netif_carrier_off(netdev);
+	}
 
 	err = dpsw_if_enable(port_priv->ethsw_data->mc_io, 0,
 			     port_priv->ethsw_data->dpsw_handle,
@@ -692,23 +700,12 @@ static int dpaa2_switch_port_open(struct net_device *netdev)
 		return err;
 	}
 
-	/* sync carrier state */
-	err = dpaa2_switch_port_carrier_state_sync(netdev);
-	if (err) {
-		netdev_err(netdev,
-			   "dpaa2_switch_port_carrier_state_sync err %d\n", err);
-		goto err_carrier_sync;
-	}
-
 	dpaa2_switch_enable_ctrl_if_napi(ethsw);
 
-	return 0;
+	if (dpaa2_switch_port_is_type_phy(port_priv))
+		phylink_start(port_priv->mac->phylink);
 
-err_carrier_sync:
-	dpsw_if_disable(port_priv->ethsw_data->mc_io, 0,
-			port_priv->ethsw_data->dpsw_handle,
-			port_priv->idx);
-	return err;
+	return 0;
 }
 
 static int dpaa2_switch_port_stop(struct net_device *netdev)
@@ -717,6 +714,13 @@ static int dpaa2_switch_port_stop(struct net_device *netdev)
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
 	int err;
 
+	if (dpaa2_switch_port_is_type_phy(port_priv)) {
+		phylink_stop(port_priv->mac->phylink);
+	} else {
+		netif_tx_stop_all_queues(netdev);
+		netif_carrier_off(netdev);
+	}
+
 	err = dpsw_if_disable(port_priv->ethsw_data->mc_io, 0,
 			      port_priv->ethsw_data->dpsw_handle,
 			      port_priv->idx);
@@ -1127,28 +1131,28 @@ err_exit:
 }
 
 static int
-dpaa2_switch_setup_tc_cls_flower(struct dpaa2_switch_acl_tbl *acl_tbl,
+dpaa2_switch_setup_tc_cls_flower(struct dpaa2_switch_filter_block *filter_block,
 				 struct flow_cls_offload *f)
 {
 	switch (f->command) {
 	case FLOW_CLS_REPLACE:
-		return dpaa2_switch_cls_flower_replace(acl_tbl, f);
+		return dpaa2_switch_cls_flower_replace(filter_block, f);
 	case FLOW_CLS_DESTROY:
-		return dpaa2_switch_cls_flower_destroy(acl_tbl, f);
+		return dpaa2_switch_cls_flower_destroy(filter_block, f);
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 
 static int
-dpaa2_switch_setup_tc_cls_matchall(struct dpaa2_switch_acl_tbl *acl_tbl,
+dpaa2_switch_setup_tc_cls_matchall(struct dpaa2_switch_filter_block *block,
 				   struct tc_cls_matchall_offload *f)
 {
 	switch (f->command) {
 	case TC_CLSMATCHALL_REPLACE:
-		return dpaa2_switch_cls_matchall_replace(acl_tbl, f);
+		return dpaa2_switch_cls_matchall_replace(block, f);
 	case TC_CLSMATCHALL_DESTROY:
-		return dpaa2_switch_cls_matchall_destroy(acl_tbl, f);
+		return dpaa2_switch_cls_matchall_destroy(block, f);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1170,106 +1174,122 @@ static int dpaa2_switch_port_setup_tc_block_cb_ig(enum tc_setup_type type,
 
 static LIST_HEAD(dpaa2_switch_block_cb_list);
 
-static int dpaa2_switch_port_acl_tbl_bind(struct ethsw_port_priv *port_priv,
-					  struct dpaa2_switch_acl_tbl *acl_tbl)
+static int
+dpaa2_switch_port_acl_tbl_bind(struct ethsw_port_priv *port_priv,
+			       struct dpaa2_switch_filter_block *block)
 {
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
 	struct net_device *netdev = port_priv->netdev;
 	struct dpsw_acl_if_cfg acl_if_cfg;
 	int err;
 
-	if (port_priv->acl_tbl)
+	if (port_priv->filter_block)
 		return -EINVAL;
 
 	acl_if_cfg.if_id[0] = port_priv->idx;
 	acl_if_cfg.num_ifs = 1;
 	err = dpsw_acl_add_if(ethsw->mc_io, 0, ethsw->dpsw_handle,
-			      acl_tbl->id, &acl_if_cfg);
+			      block->acl_id, &acl_if_cfg);
 	if (err) {
 		netdev_err(netdev, "dpsw_acl_add_if err %d\n", err);
 		return err;
 	}
 
-	acl_tbl->ports |= BIT(port_priv->idx);
-	port_priv->acl_tbl = acl_tbl;
+	block->ports |= BIT(port_priv->idx);
+	port_priv->filter_block = block;
 
 	return 0;
 }
 
 static int
 dpaa2_switch_port_acl_tbl_unbind(struct ethsw_port_priv *port_priv,
-				 struct dpaa2_switch_acl_tbl *acl_tbl)
+				 struct dpaa2_switch_filter_block *block)
 {
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
 	struct net_device *netdev = port_priv->netdev;
 	struct dpsw_acl_if_cfg acl_if_cfg;
 	int err;
 
-	if (port_priv->acl_tbl != acl_tbl)
+	if (port_priv->filter_block != block)
 		return -EINVAL;
 
 	acl_if_cfg.if_id[0] = port_priv->idx;
 	acl_if_cfg.num_ifs = 1;
 	err = dpsw_acl_remove_if(ethsw->mc_io, 0, ethsw->dpsw_handle,
-				 acl_tbl->id, &acl_if_cfg);
+				 block->acl_id, &acl_if_cfg);
 	if (err) {
 		netdev_err(netdev, "dpsw_acl_add_if err %d\n", err);
 		return err;
 	}
 
-	acl_tbl->ports &= ~BIT(port_priv->idx);
-	port_priv->acl_tbl = NULL;
+	block->ports &= ~BIT(port_priv->idx);
+	port_priv->filter_block = NULL;
 	return 0;
 }
 
 static int dpaa2_switch_port_block_bind(struct ethsw_port_priv *port_priv,
-					struct dpaa2_switch_acl_tbl *acl_tbl)
+					struct dpaa2_switch_filter_block *block)
 {
-	struct dpaa2_switch_acl_tbl *old_acl_tbl = port_priv->acl_tbl;
+	struct dpaa2_switch_filter_block *old_block = port_priv->filter_block;
 	int err;
 
+	/* Offload all the mirror entries found in the block on this new port
+	 * joining it.
+	 */
+	err = dpaa2_switch_block_offload_mirror(block, port_priv);
+	if (err)
+		return err;
+
 	/* If the port is already bound to this ACL table then do nothing. This
 	 * can happen when this port is the first one to join a tc block
 	 */
-	if (port_priv->acl_tbl == acl_tbl)
+	if (port_priv->filter_block == block)
 		return 0;
 
-	err = dpaa2_switch_port_acl_tbl_unbind(port_priv, old_acl_tbl);
+	err = dpaa2_switch_port_acl_tbl_unbind(port_priv, old_block);
 	if (err)
 		return err;
 
 	/* Mark the previous ACL table as being unused if this was the last
 	 * port that was using it.
 	 */
-	if (old_acl_tbl->ports == 0)
-		old_acl_tbl->in_use = false;
+	if (old_block->ports == 0)
+		old_block->in_use = false;
 
-	return dpaa2_switch_port_acl_tbl_bind(port_priv, acl_tbl);
+	return dpaa2_switch_port_acl_tbl_bind(port_priv, block);
 }
 
-static int dpaa2_switch_port_block_unbind(struct ethsw_port_priv *port_priv,
-					  struct dpaa2_switch_acl_tbl *acl_tbl)
+static int
+dpaa2_switch_port_block_unbind(struct ethsw_port_priv *port_priv,
+			       struct dpaa2_switch_filter_block *block)
 {
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
-	struct dpaa2_switch_acl_tbl *new_acl_tbl;
+	struct dpaa2_switch_filter_block *new_block;
 	int err;
 
+	/* Unoffload all the mirror entries found in the block from the
+	 * port leaving it.
+	 */
+	err = dpaa2_switch_block_unoffload_mirror(block, port_priv);
+	if (err)
+		return err;
+
 	/* We are the last port that leaves a block (an ACL table).
 	 * We'll continue to use this table.
 	 */
-	if (acl_tbl->ports == BIT(port_priv->idx))
+	if (block->ports == BIT(port_priv->idx))
 		return 0;
 
-	err = dpaa2_switch_port_acl_tbl_unbind(port_priv, acl_tbl);
+	err = dpaa2_switch_port_acl_tbl_unbind(port_priv, block);
 	if (err)
 		return err;
 
-	if (acl_tbl->ports == 0)
-		acl_tbl->in_use = false;
+	if (block->ports == 0)
+		block->in_use = false;
 
-	new_acl_tbl = dpaa2_switch_acl_tbl_get_unused(ethsw);
-	new_acl_tbl->in_use = true;
-	return dpaa2_switch_port_acl_tbl_bind(port_priv, new_acl_tbl);
+	new_block = dpaa2_switch_filter_block_get_unused(ethsw);
+	new_block->in_use = true;
+	return dpaa2_switch_port_acl_tbl_bind(port_priv, new_block);
 }
 
 static int dpaa2_switch_setup_tc_block_bind(struct net_device *netdev,
@@ -1277,7 +1297,7 @@ static int dpaa2_switch_setup_tc_block_bind(struct net_device *netdev,
 {
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
-	struct dpaa2_switch_acl_tbl *acl_tbl;
+	struct dpaa2_switch_filter_block *filter_block;
 	struct flow_block_cb *block_cb;
 	bool register_block = false;
 	int err;
@@ -1287,24 +1307,24 @@ static int dpaa2_switch_setup_tc_block_bind(struct net_device *netdev,
 					ethsw);
 
 	if (!block_cb) {
-		/* If the ACL table is not already known, then this port must
-		 * be the first to join it. In this case, we can just continue
-		 * to use our private table
+		/* If the filter block is not already known, then this port
+		 * must be the first to join it. In this case, we can just
+		 * continue to use our private table
 		 */
-		acl_tbl = port_priv->acl_tbl;
+		filter_block = port_priv->filter_block;
 
 		block_cb = flow_block_cb_alloc(dpaa2_switch_port_setup_tc_block_cb_ig,
-					       ethsw, acl_tbl, NULL);
+					       ethsw, filter_block, NULL);
 		if (IS_ERR(block_cb))
 			return PTR_ERR(block_cb);
 
 		register_block = true;
 	} else {
-		acl_tbl = flow_block_cb_priv(block_cb);
+		filter_block = flow_block_cb_priv(block_cb);
 	}
 
 	flow_block_cb_incref(block_cb);
-	err = dpaa2_switch_port_block_bind(port_priv, acl_tbl);
+	err = dpaa2_switch_port_block_bind(port_priv, filter_block);
 	if (err)
 		goto err_block_bind;
 
@@ -1327,7 +1347,7 @@ static void dpaa2_switch_setup_tc_block_unbind(struct net_device *netdev,
 {
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
-	struct dpaa2_switch_acl_tbl *acl_tbl;
+	struct dpaa2_switch_filter_block *filter_block;
 	struct flow_block_cb *block_cb;
 	int err;
 
@@ -1337,8 +1357,8 @@ static void dpaa2_switch_setup_tc_block_unbind(struct net_device *netdev,
 	if (!block_cb)
 		return;
 
-	acl_tbl = flow_block_cb_priv(block_cb);
-	err = dpaa2_switch_port_block_unbind(port_priv, acl_tbl);
+	filter_block = flow_block_cb_priv(block_cb);
+	err = dpaa2_switch_port_block_unbind(port_priv, filter_block);
 	if (!err && !flow_block_cb_decref(block_cb)) {
 		flow_block_cb_remove(block_cb, f);
 		list_del(&block_cb->driver_list);
@@ -1403,41 +1423,105 @@ bool dpaa2_switch_port_dev_check(const struct net_device *netdev)
 	return netdev->netdev_ops == &dpaa2_switch_port_ops;
 }
 
-static void dpaa2_switch_links_state_update(struct ethsw_core *ethsw)
+static int dpaa2_switch_port_connect_mac(struct ethsw_port_priv *port_priv)
 {
-	int i;
+	struct fsl_mc_device *dpsw_port_dev, *dpmac_dev;
+	struct dpaa2_mac *mac;
+	int err;
 
-	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
-		dpaa2_switch_port_carrier_state_sync(ethsw->ports[i]->netdev);
-		dpaa2_switch_port_set_mac_addr(ethsw->ports[i]);
+	dpsw_port_dev = to_fsl_mc_device(port_priv->netdev->dev.parent);
+	dpmac_dev = fsl_mc_get_endpoint(dpsw_port_dev, port_priv->idx);
+
+	if (PTR_ERR(dpmac_dev) == -EPROBE_DEFER)
+		return PTR_ERR(dpmac_dev);
+
+	if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type)
+		return 0;
+
+	mac = kzalloc(sizeof(*mac), GFP_KERNEL);
+	if (!mac)
+		return -ENOMEM;
+
+	mac->mc_dev = dpmac_dev;
+	mac->mc_io = port_priv->ethsw_data->mc_io;
+	mac->net_dev = port_priv->netdev;
+
+	err = dpaa2_mac_open(mac);
+	if (err)
+		goto err_free_mac;
+	port_priv->mac = mac;
+
+	if (dpaa2_switch_port_is_type_phy(port_priv)) {
+		err = dpaa2_mac_connect(mac);
+		if (err) {
+			netdev_err(port_priv->netdev,
+				   "Error connecting to the MAC endpoint %pe\n",
+				   ERR_PTR(err));
+			goto err_close_mac;
+		}
 	}
+
+	return 0;
+
+err_close_mac:
+	dpaa2_mac_close(mac);
+	port_priv->mac = NULL;
+err_free_mac:
+	kfree(mac);
+	return err;
+}
+
+static void dpaa2_switch_port_disconnect_mac(struct ethsw_port_priv *port_priv)
+{
+	if (dpaa2_switch_port_is_type_phy(port_priv))
+		dpaa2_mac_disconnect(port_priv->mac);
+
+	if (!dpaa2_switch_port_has_mac(port_priv))
+		return;
+
+	dpaa2_mac_close(port_priv->mac);
+	kfree(port_priv->mac);
+	port_priv->mac = NULL;
 }
 
 static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg)
 {
 	struct device *dev = (struct device *)arg;
 	struct ethsw_core *ethsw = dev_get_drvdata(dev);
-
-	/* Mask the events and the if_id reserved bits to be cleared on read */
-	u32 status = DPSW_IRQ_EVENT_LINK_CHANGED | 0xFFFF0000;
-	int err;
+	struct ethsw_port_priv *port_priv;
+	u32 status = ~0;
+	int err, if_id;
 
 	err = dpsw_get_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle,
 				  DPSW_IRQ_INDEX_IF, &status);
 	if (err) {
 		dev_err(dev, "Can't get irq status (err %d)\n", err);
-
-		err = dpsw_clear_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle,
-					    DPSW_IRQ_INDEX_IF, 0xFFFFFFFF);
-		if (err)
-			dev_err(dev, "Can't clear irq status (err %d)\n", err);
 		goto out;
 	}
 
-	if (status & DPSW_IRQ_EVENT_LINK_CHANGED)
-		dpaa2_switch_links_state_update(ethsw);
+	if_id = (status & 0xFFFF0000) >> 16;
+	port_priv = ethsw->ports[if_id];
+
+	if (status & DPSW_IRQ_EVENT_LINK_CHANGED) {
+		dpaa2_switch_port_link_state_update(port_priv->netdev);
+		dpaa2_switch_port_set_mac_addr(port_priv);
+	}
+
+	if (status & DPSW_IRQ_EVENT_ENDPOINT_CHANGED) {
+		rtnl_lock();
+		if (dpaa2_switch_port_has_mac(port_priv))
+			dpaa2_switch_port_disconnect_mac(port_priv);
+		else
+			dpaa2_switch_port_connect_mac(port_priv);
+		rtnl_unlock();
+	}
 
 out:
+	err = dpsw_clear_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle,
+				    DPSW_IRQ_INDEX_IF, status);
+	if (err)
+		dev_err(dev, "Can't clear irq status (err %d)\n", err);
+
 	return IRQ_HANDLED;
 }
 
@@ -1889,8 +1973,12 @@ static int dpaa2_switch_port_attr_set_event(struct net_device *netdev,
 	return notifier_from_errno(err);
 }
 
+static struct notifier_block dpaa2_switch_port_switchdev_nb;
+static struct notifier_block dpaa2_switch_port_switchdev_blocking_nb;
+
 static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
-					 struct net_device *upper_dev)
+					 struct net_device *upper_dev,
+					 struct netlink_ext_ack *extack)
 {
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
@@ -1906,8 +1994,8 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 
 		other_port_priv = netdev_priv(other_dev);
 		if (other_port_priv->ethsw_data != port_priv->ethsw_data) {
-			netdev_err(netdev,
-				   "Interface from a different DPSW is in the bridge already!\n");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Interface from a different DPSW is in the bridge already");
 			return -EINVAL;
 		}
 	}
@@ -1929,8 +2017,16 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 	if (err)
 		goto err_egress_flood;
 
+	err = switchdev_bridge_port_offload(netdev, netdev, NULL,
+					    &dpaa2_switch_port_switchdev_nb,
+					    &dpaa2_switch_port_switchdev_blocking_nb,
+					    false, extack);
+	if (err)
+		goto err_switchdev_offload;
+
 	return 0;
 
+err_switchdev_offload:
 err_egress_flood:
 	dpaa2_switch_port_set_fdb(port_priv, NULL);
 	return err;
@@ -1956,6 +2052,13 @@ static int dpaa2_switch_port_restore_rxvlan(struct net_device *vdev, int vid, vo
 	return dpaa2_switch_port_vlan_add(arg, vlan_proto, vid);
 }
 
+static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev)
+{
+	switchdev_bridge_port_unoffload(netdev, NULL,
+					&dpaa2_switch_port_switchdev_nb,
+					&dpaa2_switch_port_switchdev_blocking_nb);
+}
+
 static int dpaa2_switch_port_bridge_leave(struct net_device *netdev)
 {
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
@@ -2029,6 +2132,28 @@ static int dpaa2_switch_prevent_bridging_with_8021q_upper(struct net_device *net
 	return 0;
 }
 
+static int
+dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev,
+					  struct net_device *upper_dev,
+					  struct netlink_ext_ack *extack)
+{
+	int err;
+
+	if (!br_vlan_enabled(upper_dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot join a VLAN-unaware bridge");
+		return -EOPNOTSUPP;
+	}
+
+	err = dpaa2_switch_prevent_bridging_with_8021q_upper(netdev);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot join a bridge while VLAN uppers are present");
+		return 0;
+	}
+
+	return 0;
+}
+
 static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb,
 					     unsigned long event, void *ptr)
 {
@@ -2049,25 +2174,23 @@ static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb,
 		if (!netif_is_bridge_master(upper_dev))
 			break;
 
-		if (!br_vlan_enabled(upper_dev)) {
-			NL_SET_ERR_MSG_MOD(extack, "Cannot join a VLAN-unaware bridge");
-			err = -EOPNOTSUPP;
+		err = dpaa2_switch_prechangeupper_sanity_checks(netdev,
+								upper_dev,
+								extack);
+		if (err)
 			goto out;
-		}
 
-		err = dpaa2_switch_prevent_bridging_with_8021q_upper(netdev);
-		if (err) {
-			NL_SET_ERR_MSG_MOD(extack,
-					   "Cannot join a bridge while VLAN uppers are present");
-			goto out;
-		}
+		if (!info->linking)
+			dpaa2_switch_port_pre_bridge_leave(netdev);
 
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
 		if (netif_is_bridge_master(upper_dev)) {
 			if (info->linking)
-				err = dpaa2_switch_port_bridge_join(netdev, upper_dev);
+				err = dpaa2_switch_port_bridge_join(netdev,
+								    upper_dev,
+								    extack);
 			else
 				err = dpaa2_switch_port_bridge_leave(netdev);
 		}
@@ -2802,6 +2925,18 @@ err_free_dpbp:
 	return err;
 }
 
+static void dpaa2_switch_remove_port(struct ethsw_core *ethsw,
+				     u16 port_idx)
+{
+	struct ethsw_port_priv *port_priv = ethsw->ports[port_idx];
+
+	rtnl_lock();
+	dpaa2_switch_port_disconnect_mac(port_priv);
+	rtnl_unlock();
+	free_netdev(port_priv->netdev);
+	ethsw->ports[port_idx] = NULL;
+}
+
 static int dpaa2_switch_init(struct fsl_mc_device *sw_dev)
 {
 	struct device *dev = &sw_dev->dev;
@@ -2952,7 +3087,7 @@ static int dpaa2_switch_port_trap_mac_addr(struct ethsw_port_priv *port_priv,
 	acl_entry.cfg.precedence = 0;
 	acl_entry.cfg.result.action = DPSW_ACL_ACTION_REDIRECT_TO_CTRL_IF;
 
-	return dpaa2_switch_acl_entry_add(port_priv->acl_tbl, &acl_entry);
+	return dpaa2_switch_acl_entry_add(port_priv->filter_block, &acl_entry);
 }
 
 static int dpaa2_switch_port_init(struct ethsw_port_priv *port_priv, u16 port)
@@ -2965,7 +3100,7 @@ static int dpaa2_switch_port_init(struct ethsw_port_priv *port_priv, u16 port)
 	};
 	struct net_device *netdev = port_priv->netdev;
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
-	struct dpaa2_switch_acl_tbl *acl_tbl;
+	struct dpaa2_switch_filter_block *filter_block;
 	struct dpsw_fdb_cfg fdb_cfg = {0};
 	struct dpsw_if_attr dpsw_if_attr;
 	struct dpaa2_switch_fdb *fdb;
@@ -3020,14 +3155,15 @@ static int dpaa2_switch_port_init(struct ethsw_port_priv *port_priv, u16 port)
 		return err;
 	}
 
-	acl_tbl = dpaa2_switch_acl_tbl_get_unused(ethsw);
-	acl_tbl->ethsw = ethsw;
-	acl_tbl->id = acl_tbl_id;
-	acl_tbl->in_use = true;
-	acl_tbl->num_rules = 0;
-	INIT_LIST_HEAD(&acl_tbl->entries);
+	filter_block = dpaa2_switch_filter_block_get_unused(ethsw);
+	filter_block->ethsw = ethsw;
+	filter_block->acl_id = acl_tbl_id;
+	filter_block->in_use = true;
+	filter_block->num_acl_rules = 0;
+	INIT_LIST_HEAD(&filter_block->acl_entries);
+	INIT_LIST_HEAD(&filter_block->mirror_entries);
 
-	err = dpaa2_switch_port_acl_tbl_bind(port_priv, acl_tbl);
+	err = dpaa2_switch_port_acl_tbl_bind(port_priv, filter_block);
 	if (err)
 		return err;
 
@@ -3079,11 +3215,11 @@ static int dpaa2_switch_remove(struct fsl_mc_device *sw_dev)
 	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
 		port_priv = ethsw->ports[i];
 		unregister_netdev(port_priv->netdev);
-		free_netdev(port_priv->netdev);
+		dpaa2_switch_remove_port(ethsw, i);
 	}
 
 	kfree(ethsw->fdbs);
-	kfree(ethsw->acls);
+	kfree(ethsw->filter_blocks);
 	kfree(ethsw->ports);
 
 	dpaa2_switch_teardown(sw_dev);
@@ -3156,6 +3292,10 @@ static int dpaa2_switch_probe_port(struct ethsw_core *ethsw,
 		goto err_port_probe;
 	port_priv->learn_ena = false;
 
+	err = dpaa2_switch_port_connect_mac(port_priv);
+	if (err)
+		goto err_port_probe;
+
 	return 0;
 
 err_port_probe:
@@ -3209,9 +3349,10 @@ static int dpaa2_switch_probe(struct fsl_mc_device *sw_dev)
 		goto err_free_ports;
 	}
 
-	ethsw->acls = kcalloc(ethsw->sw_attr.num_ifs, sizeof(*ethsw->acls),
-			      GFP_KERNEL);
-	if (!ethsw->acls) {
+	ethsw->filter_blocks = kcalloc(ethsw->sw_attr.num_ifs,
+				       sizeof(*ethsw->filter_blocks),
+				       GFP_KERNEL);
+	if (!ethsw->filter_blocks) {
 		err = -ENOMEM;
 		goto err_free_fdbs;
 	}
@@ -3231,17 +3372,16 @@ static int dpaa2_switch_probe(struct fsl_mc_device *sw_dev)
 			       &ethsw->fq[i].napi, dpaa2_switch_poll,
 			       NAPI_POLL_WEIGHT);
 
-	err = dpsw_enable(ethsw->mc_io, 0, ethsw->dpsw_handle);
-	if (err) {
-		dev_err(ethsw->dev, "dpsw_enable err %d\n", err);
-		goto err_free_netdev;
-	}
-
 	/* Setup IRQs */
 	err = dpaa2_switch_setup_irqs(sw_dev);
 	if (err)
 		goto err_stop;
 
+	/* By convention, if the mirror port is equal to the number of switch
+	 * interfaces, then mirroring of any kind is disabled.
+	 */
+	ethsw->mirror_port =  ethsw->sw_attr.num_ifs;
+
 	/* Register the netdev only when the entire setup is done and the
 	 * switch port interfaces are ready to receive traffic
 	 */
@@ -3263,8 +3403,8 @@ err_stop:
 	dpsw_disable(ethsw->mc_io, 0, ethsw->dpsw_handle);
 err_free_netdev:
 	for (i--; i >= 0; i--)
-		free_netdev(ethsw->ports[i]->netdev);
-	kfree(ethsw->acls);
+		dpaa2_switch_remove_port(ethsw, i);
+	kfree(ethsw->filter_blocks);
 err_free_fdbs:
 	kfree(ethsw->fdbs);
 err_free_ports:
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h
index bdef71f234cb..0002dca4d417 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h
@@ -21,6 +21,7 @@
 #include <net/pkt_cls.h>
 #include <soc/fsl/dpaa2-io.h>
 
+#include "dpaa2-mac.h"
 #include "dpsw.h"
 
 /* Number of IRQs supported */
@@ -113,20 +114,29 @@ struct dpaa2_switch_acl_entry {
 	struct dpsw_acl_key	key;
 };
 
-struct dpaa2_switch_acl_tbl {
-	struct list_head	entries;
+struct dpaa2_switch_mirror_entry {
+	struct list_head	list;
+	struct dpsw_reflection_cfg cfg;
+	unsigned long		cookie;
+	u16 if_id;
+};
+
+struct dpaa2_switch_filter_block {
 	struct ethsw_core	*ethsw;
 	u64			ports;
-
-	u16			id;
-	u8			num_rules;
 	bool			in_use;
+
+	struct list_head	acl_entries;
+	u16			acl_id;
+	u8			num_acl_rules;
+
+	struct list_head	mirror_entries;
 };
 
 static inline bool
-dpaa2_switch_acl_tbl_is_full(struct dpaa2_switch_acl_tbl *acl_tbl)
+dpaa2_switch_acl_tbl_is_full(struct dpaa2_switch_filter_block *filter_block)
 {
-	if ((acl_tbl->num_rules + DPAA2_ETHSW_PORT_DEFAULT_TRAPS) >=
+	if ((filter_block->num_acl_rules + DPAA2_ETHSW_PORT_DEFAULT_TRAPS) >=
 	    DPAA2_ETHSW_PORT_MAX_ACL_ENTRIES)
 		return true;
 	return false;
@@ -149,7 +159,8 @@ struct ethsw_port_priv {
 	bool			ucast_flood;
 	bool			learn_ena;
 
-	struct dpaa2_switch_acl_tbl *acl_tbl;
+	struct dpaa2_switch_filter_block *filter_block;
+	struct dpaa2_mac	*mac;
 };
 
 /* Switch data */
@@ -175,7 +186,8 @@ struct ethsw_core {
 	int				napi_users;
 
 	struct dpaa2_switch_fdb		*fdbs;
-	struct dpaa2_switch_acl_tbl	*acls;
+	struct dpaa2_switch_filter_block *filter_blocks;
+	u16				mirror_port;
 };
 
 static inline int dpaa2_switch_get_index(struct ethsw_core *ethsw,
@@ -215,6 +227,22 @@ static inline bool dpaa2_switch_supports_cpu_traffic(struct ethsw_core *ethsw)
 	return true;
 }
 
+static inline bool
+dpaa2_switch_port_is_type_phy(struct ethsw_port_priv *port_priv)
+{
+	if (port_priv->mac &&
+	    (port_priv->mac->attr.link_type == DPMAC_LINK_TYPE_PHY ||
+	     port_priv->mac->attr.link_type == DPMAC_LINK_TYPE_BACKPLANE))
+		return true;
+
+	return false;
+}
+
+static inline bool dpaa2_switch_port_has_mac(struct ethsw_port_priv *port_priv)
+{
+	return port_priv->mac ? true : false;
+}
+
 bool dpaa2_switch_port_dev_check(const struct net_device *netdev);
 
 int dpaa2_switch_port_vlans_add(struct net_device *netdev,
@@ -229,18 +257,24 @@ typedef int dpaa2_switch_fdb_cb_t(struct ethsw_port_priv *port_priv,
 
 /* TC offload */
 
-int dpaa2_switch_cls_flower_replace(struct dpaa2_switch_acl_tbl *acl_tbl,
+int dpaa2_switch_cls_flower_replace(struct dpaa2_switch_filter_block *block,
 				    struct flow_cls_offload *cls);
 
-int dpaa2_switch_cls_flower_destroy(struct dpaa2_switch_acl_tbl *acl_tbl,
+int dpaa2_switch_cls_flower_destroy(struct dpaa2_switch_filter_block *block,
 				    struct flow_cls_offload *cls);
 
-int dpaa2_switch_cls_matchall_replace(struct dpaa2_switch_acl_tbl *acl_tbl,
+int dpaa2_switch_cls_matchall_replace(struct dpaa2_switch_filter_block *block,
 				      struct tc_cls_matchall_offload *cls);
 
-int dpaa2_switch_cls_matchall_destroy(struct dpaa2_switch_acl_tbl *acl_tbl,
+int dpaa2_switch_cls_matchall_destroy(struct dpaa2_switch_filter_block *block,
 				      struct tc_cls_matchall_offload *cls);
 
-int dpaa2_switch_acl_entry_add(struct dpaa2_switch_acl_tbl *acl_tbl,
+int dpaa2_switch_acl_entry_add(struct dpaa2_switch_filter_block *block,
 			       struct dpaa2_switch_acl_entry *entry);
+
+int dpaa2_switch_block_offload_mirror(struct dpaa2_switch_filter_block *block,
+				      struct ethsw_port_priv *port_priv);
+
+int dpaa2_switch_block_unoffload_mirror(struct dpaa2_switch_filter_block *block,
+					struct ethsw_port_priv *port_priv);
 #endif	/* __ETHSW_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h
index cb13e740f72b..397d55f2bd99 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h
@@ -39,11 +39,16 @@
 #define DPSW_CMDID_GET_IRQ_STATUS           DPSW_CMD_ID(0x016)
 #define DPSW_CMDID_CLEAR_IRQ_STATUS         DPSW_CMD_ID(0x017)
 
+#define DPSW_CMDID_SET_REFLECTION_IF        DPSW_CMD_ID(0x022)
+
 #define DPSW_CMDID_IF_SET_TCI               DPSW_CMD_ID(0x030)
 #define DPSW_CMDID_IF_SET_STP               DPSW_CMD_ID(0x031)
 
 #define DPSW_CMDID_IF_GET_COUNTER           DPSW_CMD_V2(0x034)
 
+#define DPSW_CMDID_IF_ADD_REFLECTION        DPSW_CMD_ID(0x037)
+#define DPSW_CMDID_IF_REMOVE_REFLECTION     DPSW_CMD_ID(0x038)
+
 #define DPSW_CMDID_IF_ENABLE                DPSW_CMD_ID(0x03D)
 #define DPSW_CMDID_IF_DISABLE               DPSW_CMD_ID(0x03E)
 
@@ -533,5 +538,19 @@ struct dpsw_cmd_acl_entry {
 	__le64 pad2[4];
 	__le64 key_iova;
 };
+
+struct dpsw_cmd_set_reflection_if {
+	__le16 if_id;
+};
+
+#define DPSW_FILTER_SHIFT	0
+#define DPSW_FILTER_SIZE	2
+
+struct dpsw_cmd_if_reflection {
+	__le16 if_id;
+	__le16 vlan_id;
+	/* only 2 bits from the LSB */
+	u8 filter;
+};
 #pragma pack(pop)
 #endif /* __FSL_DPSW_CMD_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpsw.c b/drivers/net/ethernet/freescale/dpaa2/dpsw.c
index 6352d6d1ecba..ab921d75deb2 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpsw.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpsw.c
@@ -1579,3 +1579,83 @@ int dpsw_acl_remove_entry(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
 	/* send command to mc*/
 	return mc_send_command(mc_io, &cmd);
 }
+
+/**
+ * dpsw_set_reflection_if() - Set target interface for traffic mirrored
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPSW object
+ * @if_id:	Interface Id
+ *
+ * Only one mirroring destination is allowed per switch
+ *
+ * Return:	Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_set_reflection_if(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+			   u16 if_id)
+{
+	struct dpsw_cmd_set_reflection_if *cmd_params;
+	struct fsl_mc_command cmd = { 0 };
+
+	cmd.header = mc_encode_cmd_header(DPSW_CMDID_SET_REFLECTION_IF,
+					  cmd_flags,
+					  token);
+	cmd_params = (struct dpsw_cmd_set_reflection_if *)cmd.params;
+	cmd_params->if_id = cpu_to_le16(if_id);
+
+	return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_if_add_reflection() - Setup mirroring rule
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPSW object
+ * @if_id:	Interface Identifier
+ * @cfg:	Reflection configuration
+ *
+ * Return:	Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_if_add_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+			   u16 if_id, const struct dpsw_reflection_cfg *cfg)
+{
+	struct dpsw_cmd_if_reflection *cmd_params;
+	struct fsl_mc_command cmd = { 0 };
+
+	cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_ADD_REFLECTION,
+					  cmd_flags,
+					  token);
+	cmd_params = (struct dpsw_cmd_if_reflection *)cmd.params;
+	cmd_params->if_id = cpu_to_le16(if_id);
+	cmd_params->vlan_id = cpu_to_le16(cfg->vlan_id);
+	dpsw_set_field(cmd_params->filter, FILTER, cfg->filter);
+
+	return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_if_remove_reflection() - Remove mirroring rule
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPSW object
+ * @if_id:	Interface Identifier
+ * @cfg:	Reflection configuration
+ *
+ * Return:	Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_if_remove_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+			      u16 if_id, const struct dpsw_reflection_cfg *cfg)
+{
+	struct dpsw_cmd_if_reflection *cmd_params;
+	struct fsl_mc_command cmd = { 0 };
+
+	cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_REMOVE_REFLECTION,
+					  cmd_flags,
+					  token);
+	cmd_params = (struct dpsw_cmd_if_reflection *)cmd.params;
+	cmd_params->if_id = cpu_to_le16(if_id);
+	cmd_params->vlan_id = cpu_to_le16(cfg->vlan_id);
+	dpsw_set_field(cmd_params->filter, FILTER, cfg->filter);
+
+	return mc_send_command(mc_io, &cmd);
+}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpsw.h b/drivers/net/ethernet/freescale/dpaa2/dpsw.h
index 5ef221a25b02..b90bd363f47a 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpsw.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpsw.h
@@ -99,6 +99,11 @@ int dpsw_reset(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token);
 #define DPSW_IRQ_EVENT_LINK_CHANGED	0x0001
 
 /**
+ * DPSW_IRQ_EVENT_ENDPOINT_CHANGED - Indicates a change in endpoint
+ */
+#define DPSW_IRQ_EVENT_ENDPOINT_CHANGED	0x0002
+
+/**
  * struct dpsw_irq_cfg - IRQ configuration
  * @addr:	Address that must be written to signal a message-based interrupt
  * @val:	Value to write into irq_addr address
@@ -752,4 +757,35 @@ int dpsw_acl_add_entry(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
 
 int dpsw_acl_remove_entry(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
 			  u16 acl_id, const struct dpsw_acl_entry_cfg *cfg);
+
+/**
+ * enum dpsw_reflection_filter - Filter type for frames to be reflected
+ * @DPSW_REFLECTION_FILTER_INGRESS_ALL: Reflect all frames
+ * @DPSW_REFLECTION_FILTER_INGRESS_VLAN: Reflect only frames that belong to
+ *	the particular VLAN defined by vid parameter
+ *
+ */
+enum dpsw_reflection_filter {
+	DPSW_REFLECTION_FILTER_INGRESS_ALL = 0,
+	DPSW_REFLECTION_FILTER_INGRESS_VLAN = 1
+};
+
+/**
+ * struct dpsw_reflection_cfg - Structure representing the mirroring config
+ * @filter: Filter type for frames to be mirrored
+ * @vlan_id: VLAN ID to mirror; valid only when the type is DPSW_INGRESS_VLAN
+ */
+struct dpsw_reflection_cfg {
+	enum dpsw_reflection_filter filter;
+	u16 vlan_id;
+};
+
+int dpsw_set_reflection_if(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+			   u16 if_id);
+
+int dpsw_if_add_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+			   u16 if_id, const struct dpsw_reflection_cfg *cfg);
+
+int dpsw_if_remove_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+			      u16 if_id, const struct dpsw_reflection_cfg *cfg);
 #endif /* __FSL_DPSW_H */
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index ebccaf02411c..9690e36e9e85 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -585,7 +585,9 @@ static void enetc_get_ringparam(struct net_device *ndev,
 }
 
 static int enetc_get_coalesce(struct net_device *ndev,
-			      struct ethtool_coalesce *ic)
+			      struct ethtool_coalesce *ic,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	struct enetc_int_vector *v = priv->int_vector[0];
@@ -602,7 +604,9 @@ static int enetc_get_coalesce(struct net_device *ndev,
 }
 
 static int enetc_set_coalesce(struct net_device *ndev,
-			      struct ethtool_coalesce *ic)
+			      struct ethtool_coalesce *ic,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	u32 rx_ictt, tx_ictt;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index c84f6c226743..60d94e0a07d6 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -735,7 +735,7 @@ static const struct net_device_ops enetc_ndev_ops = {
 	.ndo_set_vf_vlan	= enetc_pf_set_vf_vlan,
 	.ndo_set_vf_spoofchk	= enetc_pf_set_vf_spoofchk,
 	.ndo_set_features	= enetc_pf_set_features,
-	.ndo_do_ioctl		= enetc_ioctl,
+	.ndo_eth_ioctl		= enetc_ioctl,
 	.ndo_setup_tc		= enetc_setup_tc,
 	.ndo_bpf		= enetc_setup_bpf,
 	.ndo_xdp_xmit		= enetc_xdp_xmit,
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
index 03090ba7e226..1a9d1e8b772c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
@@ -99,7 +99,7 @@ static const struct net_device_ops enetc_ndev_ops = {
 	.ndo_get_stats		= enetc_get_stats,
 	.ndo_set_mac_address	= enetc_vf_set_mac_addr,
 	.ndo_set_features	= enetc_vf_set_features,
-	.ndo_do_ioctl		= enetc_ioctl,
+	.ndo_eth_ioctl		= enetc_ioctl,
 	.ndo_setup_tc		= enetc_setup_tc,
 };
 
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 2e002e4b4b4a..7b4961daa254 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -77,6 +77,8 @@
 #define FEC_R_DES_ACTIVE_2	0x1e8 /* Rx descriptor active for ring 2 */
 #define FEC_X_DES_ACTIVE_2	0x1ec /* Tx descriptor active for ring 2 */
 #define FEC_QOS_SCHEME		0x1f0 /* Set multi queues Qos scheme */
+#define FEC_LPI_SLEEP		0x1f4 /* Set IEEE802.3az LPI Sleep Ts time */
+#define FEC_LPI_WAKE		0x1f8 /* Set IEEE802.3az LPI Wake Tw time */
 #define FEC_MIIGSK_CFGR		0x300 /* MIIGSK Configuration reg */
 #define FEC_MIIGSK_ENR		0x308 /* MIIGSK Enable reg */
 
@@ -187,6 +189,8 @@
 #define FEC_RXIC0		0xfff
 #define FEC_RXIC1		0xfff
 #define FEC_RXIC2		0xfff
+#define FEC_LPI_SLEEP		0xfff
+#define FEC_LPI_WAKE		0xfff
 #endif /* CONFIG_M5272 */
 
 
@@ -379,6 +383,9 @@ struct bufdesc_ex {
 #define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF)
 #define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF))
 
+#define FEC_ENET_TXC_DLY	((uint)0x00010000)
+#define FEC_ENET_RXC_DLY	((uint)0x00020000)
+
 /* ENET interrupt coalescing macro define */
 #define FEC_ITR_CLK_SEL		(0x1 << 30)
 #define FEC_ITR_EN		(0x1 << 31)
@@ -472,6 +479,22 @@ struct bufdesc_ex {
  */
 #define FEC_QUIRK_HAS_MULTI_QUEUES	(1 << 19)
 
+/* i.MX8MQ ENET IP version add new feature to support IEEE 802.3az EEE
+ * standard. For the transmission, MAC supply two user registers to set
+ * Sleep (TS) and Wake (TW) time.
+ */
+#define FEC_QUIRK_HAS_EEE		(1 << 20)
+
+/* i.MX8QM ENET IP version add new feture to generate delayed TXC/RXC
+ * as an alternative option to make sure it works well with various PHYs.
+ * For the implementation of delayed clock, ENET takes synchronized 250MHz
+ * clocks to generate 2ns delay.
+ */
+#define FEC_QUIRK_DELAYED_CLKS_SUPPORT	(1 << 21)
+
+/* i.MX8MQ SoC integration mix wakeup interrupt signal into "int2" interrupt line. */
+#define FEC_QUIRK_WAKEUP_FROM_INT2	(1 << 22)
+
 struct bufdesc_prop {
 	int qid;
 	/* Address of Rx and Tx buffers */
@@ -528,6 +551,7 @@ struct fec_enet_private {
 	struct clk *clk_ref;
 	struct clk *clk_enet_out;
 	struct clk *clk_ptp;
+	struct clk *clk_2x_txclk;
 
 	bool ptp_clk_on;
 	struct mutex ptp_clk_mutex;
@@ -550,6 +574,8 @@ struct fec_enet_private {
 	uint	phy_speed;
 	phy_interface_t	phy_interface;
 	struct device_node *phy_node;
+	bool	rgmii_txc_dly;
+	bool	rgmii_rxc_dly;
 	int	link;
 	int	full_duplex;
 	int	speed;
@@ -557,6 +583,7 @@ struct fec_enet_private {
 	bool	bufdesc_ex;
 	int	pause_flag;
 	int	wol_flag;
+	int	wake_irq;
 	u32	quirks;
 
 	struct	napi_struct napi;
@@ -589,6 +616,10 @@ struct fec_enet_private {
 	unsigned int tx_time_itr;
 	unsigned int itr_clk_rate;
 
+	/* tx lpi eee mode */
+	struct ethtool_eee eee;
+	unsigned int clk_ref_rate;
+
 	u32 rx_copybreak;
 
 	/* ptp clock period in ns*/
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 7e4c4980ced7..80bd5c629fa0 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -135,6 +135,26 @@ static const struct fec_devinfo fec_imx6ul_info = {
 		  FEC_QUIRK_HAS_COALESCE | FEC_QUIRK_CLEAR_SETUP_MII,
 };
 
+static const struct fec_devinfo fec_imx8mq_info = {
+	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
+		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
+		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
+		  FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
+		  FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE |
+		  FEC_QUIRK_CLEAR_SETUP_MII | FEC_QUIRK_HAS_MULTI_QUEUES |
+		  FEC_QUIRK_HAS_EEE | FEC_QUIRK_WAKEUP_FROM_INT2,
+};
+
+static const struct fec_devinfo fec_imx8qm_info = {
+	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
+		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
+		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
+		  FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
+		  FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE |
+		  FEC_QUIRK_CLEAR_SETUP_MII | FEC_QUIRK_HAS_MULTI_QUEUES |
+		  FEC_QUIRK_DELAYED_CLKS_SUPPORT,
+};
+
 static struct platform_device_id fec_devtype[] = {
 	{
 		/* keep it for coldfire */
@@ -162,6 +182,12 @@ static struct platform_device_id fec_devtype[] = {
 		.name = "imx6ul-fec",
 		.driver_data = (kernel_ulong_t)&fec_imx6ul_info,
 	}, {
+		.name = "imx8mq-fec",
+		.driver_data = (kernel_ulong_t)&fec_imx8mq_info,
+	}, {
+		.name = "imx8qm-fec",
+		.driver_data = (kernel_ulong_t)&fec_imx8qm_info,
+	}, {
 		/* sentinel */
 	}
 };
@@ -175,6 +201,8 @@ enum imx_fec_type {
 	MVF600_FEC,
 	IMX6SX_FEC,
 	IMX6UL_FEC,
+	IMX8MQ_FEC,
+	IMX8QM_FEC,
 };
 
 static const struct of_device_id fec_dt_ids[] = {
@@ -185,6 +213,8 @@ static const struct of_device_id fec_dt_ids[] = {
 	{ .compatible = "fsl,mvf600-fec", .data = &fec_devtype[MVF600_FEC], },
 	{ .compatible = "fsl,imx6sx-fec", .data = &fec_devtype[IMX6SX_FEC], },
 	{ .compatible = "fsl,imx6ul-fec", .data = &fec_devtype[IMX6UL_FEC], },
+	{ .compatible = "fsl,imx8mq-fec", .data = &fec_devtype[IMX8MQ_FEC], },
+	{ .compatible = "fsl,imx8qm-fec", .data = &fec_devtype[IMX8QM_FEC], },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, fec_dt_ids);
@@ -1107,6 +1137,13 @@ fec_restart(struct net_device *ndev)
 	if (fep->bufdesc_ex)
 		ecntl |= (1 << 4);
 
+	if (fep->quirks & FEC_QUIRK_DELAYED_CLKS_SUPPORT &&
+	    fep->rgmii_txc_dly)
+		ecntl |= FEC_ENET_TXC_DLY;
+	if (fep->quirks & FEC_QUIRK_DELAYED_CLKS_SUPPORT &&
+	    fep->rgmii_rxc_dly)
+		ecntl |= FEC_ENET_RXC_DLY;
+
 #ifndef CONFIG_M5272
 	/* Enable the MIB statistic event counters */
 	writel(0 << 31, fep->hwp + FEC_MIB_CTRLSTAT);
@@ -1970,6 +2007,10 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 		if (ret)
 			goto failed_clk_ref;
 
+		ret = clk_prepare_enable(fep->clk_2x_txclk);
+		if (ret)
+			goto failed_clk_2x_txclk;
+
 		fec_enet_phy_reset_after_clk_enable(ndev);
 	} else {
 		clk_disable_unprepare(fep->clk_enet_out);
@@ -1980,10 +2021,14 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 			mutex_unlock(&fep->ptp_clk_mutex);
 		}
 		clk_disable_unprepare(fep->clk_ref);
+		clk_disable_unprepare(fep->clk_2x_txclk);
 	}
 
 	return 0;
 
+failed_clk_2x_txclk:
+	if (fep->clk_ref)
+		clk_disable_unprepare(fep->clk_ref);
 failed_clk_ref:
 	if (fep->clk_ptp) {
 		mutex_lock(&fep->ptp_clk_mutex);
@@ -1997,6 +2042,34 @@ failed_clk_ptp:
 	return ret;
 }
 
+static int fec_enet_parse_rgmii_delay(struct fec_enet_private *fep,
+				      struct device_node *np)
+{
+	u32 rgmii_tx_delay, rgmii_rx_delay;
+
+	/* For rgmii tx internal delay, valid values are 0ps and 2000ps */
+	if (!of_property_read_u32(np, "tx-internal-delay-ps", &rgmii_tx_delay)) {
+		if (rgmii_tx_delay != 0 && rgmii_tx_delay != 2000) {
+			dev_err(&fep->pdev->dev, "The only allowed RGMII TX delay values are: 0ps, 2000ps");
+			return -EINVAL;
+		} else if (rgmii_tx_delay == 2000) {
+			fep->rgmii_txc_dly = true;
+		}
+	}
+
+	/* For rgmii rx internal delay, valid values are 0ps and 2000ps */
+	if (!of_property_read_u32(np, "rx-internal-delay-ps", &rgmii_rx_delay)) {
+		if (rgmii_rx_delay != 0 && rgmii_rx_delay != 2000) {
+			dev_err(&fep->pdev->dev, "The only allowed RGMII RX delay values are: 0ps, 2000ps");
+			return -EINVAL;
+		} else if (rgmii_rx_delay == 2000) {
+			fep->rgmii_rxc_dly = true;
+		}
+	}
+
+	return 0;
+}
+
 static int fec_enet_mii_probe(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
@@ -2581,8 +2654,10 @@ static void fec_enet_itr_coal_set(struct net_device *ndev)
 	}
 }
 
-static int
-fec_enet_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
+static int fec_enet_get_coalesce(struct net_device *ndev,
+				 struct ethtool_coalesce *ec,
+				 struct kernel_ethtool_coalesce *kernel_coal,
+				 struct netlink_ext_ack *extack)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
@@ -2598,8 +2673,10 @@ fec_enet_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
 	return 0;
 }
 
-static int
-fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
+static int fec_enet_set_coalesce(struct net_device *ndev,
+				 struct ethtool_coalesce *ec,
+				 struct kernel_ethtool_coalesce *kernel_coal,
+				 struct netlink_ext_ack *extack)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	struct device *dev = &fep->pdev->dev;
@@ -2651,7 +2728,7 @@ static void fec_enet_itr_coal_init(struct net_device *ndev)
 	ec.tx_coalesce_usecs = FEC_ITR_ICTT_DEFAULT;
 	ec.tx_max_coalesced_frames = FEC_ITR_ICFT_DEFAULT;
 
-	fec_enet_set_coalesce(ndev, &ec);
+	fec_enet_set_coalesce(ndev, &ec, NULL, NULL);
 }
 
 static int fec_enet_get_tunable(struct net_device *netdev,
@@ -2692,6 +2769,92 @@ static int fec_enet_set_tunable(struct net_device *netdev,
 	return ret;
 }
 
+/* LPI Sleep Ts count base on tx clk (clk_ref).
+ * The lpi sleep cnt value = X us / (cycle_ns).
+ */
+static int fec_enet_us_to_tx_cycle(struct net_device *ndev, int us)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	return us * (fep->clk_ref_rate / 1000) / 1000;
+}
+
+static int fec_enet_eee_mode_set(struct net_device *ndev, bool enable)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct ethtool_eee *p = &fep->eee;
+	unsigned int sleep_cycle, wake_cycle;
+	int ret = 0;
+
+	if (enable) {
+		ret = phy_init_eee(ndev->phydev, 0);
+		if (ret)
+			return ret;
+
+		sleep_cycle = fec_enet_us_to_tx_cycle(ndev, p->tx_lpi_timer);
+		wake_cycle = sleep_cycle;
+	} else {
+		sleep_cycle = 0;
+		wake_cycle = 0;
+	}
+
+	p->tx_lpi_enabled = enable;
+	p->eee_enabled = enable;
+	p->eee_active = enable;
+
+	writel(sleep_cycle, fep->hwp + FEC_LPI_SLEEP);
+	writel(wake_cycle, fep->hwp + FEC_LPI_WAKE);
+
+	return 0;
+}
+
+static int
+fec_enet_get_eee(struct net_device *ndev, struct ethtool_eee *edata)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct ethtool_eee *p = &fep->eee;
+
+	if (!(fep->quirks & FEC_QUIRK_HAS_EEE))
+		return -EOPNOTSUPP;
+
+	if (!netif_running(ndev))
+		return -ENETDOWN;
+
+	edata->eee_enabled = p->eee_enabled;
+	edata->eee_active = p->eee_active;
+	edata->tx_lpi_timer = p->tx_lpi_timer;
+	edata->tx_lpi_enabled = p->tx_lpi_enabled;
+
+	return phy_ethtool_get_eee(ndev->phydev, edata);
+}
+
+static int
+fec_enet_set_eee(struct net_device *ndev, struct ethtool_eee *edata)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct ethtool_eee *p = &fep->eee;
+	int ret = 0;
+
+	if (!(fep->quirks & FEC_QUIRK_HAS_EEE))
+		return -EOPNOTSUPP;
+
+	if (!netif_running(ndev))
+		return -ENETDOWN;
+
+	p->tx_lpi_timer = edata->tx_lpi_timer;
+
+	if (!edata->eee_enabled || !edata->tx_lpi_enabled ||
+	    !edata->tx_lpi_timer)
+		ret = fec_enet_eee_mode_set(ndev, false);
+	else
+		ret = fec_enet_eee_mode_set(ndev, true);
+
+	if (ret)
+		return ret;
+
+	return phy_ethtool_set_eee(ndev->phydev, edata);
+}
+
 static void
 fec_enet_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
 {
@@ -2719,12 +2882,12 @@ fec_enet_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
 	device_set_wakeup_enable(&ndev->dev, wol->wolopts & WAKE_MAGIC);
 	if (device_may_wakeup(&ndev->dev)) {
 		fep->wol_flag |= FEC_WOL_FLAG_ENABLE;
-		if (fep->irq[0] > 0)
-			enable_irq_wake(fep->irq[0]);
+		if (fep->wake_irq > 0)
+			enable_irq_wake(fep->wake_irq);
 	} else {
 		fep->wol_flag &= (~FEC_WOL_FLAG_ENABLE);
-		if (fep->irq[0] > 0)
-			disable_irq_wake(fep->irq[0]);
+		if (fep->wake_irq > 0)
+			disable_irq_wake(fep->wake_irq);
 	}
 
 	return 0;
@@ -2752,6 +2915,8 @@ static const struct ethtool_ops fec_enet_ethtool_ops = {
 	.set_tunable		= fec_enet_set_tunable,
 	.get_wol		= fec_enet_get_wol,
 	.set_wol		= fec_enet_set_wol,
+	.get_eee		= fec_enet_get_eee,
+	.set_eee		= fec_enet_set_eee,
 	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 	.self_test		= net_selftest,
@@ -3280,7 +3445,7 @@ static const struct net_device_ops fec_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_tx_timeout		= fec_timeout,
 	.ndo_set_mac_address	= fec_set_mac_address,
-	.ndo_do_ioctl		= fec_enet_ioctl,
+	.ndo_eth_ioctl		= fec_enet_ioctl,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= fec_poll_controller,
 #endif
@@ -3535,6 +3700,17 @@ static int fec_enet_get_irq_cnt(struct platform_device *pdev)
 	return irq_cnt;
 }
 
+static void fec_enet_get_wakeup_irq(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	if (fep->quirks & FEC_QUIRK_WAKEUP_FROM_INT2)
+		fep->wake_irq = fep->irq[2];
+	else
+		fep->wake_irq = fep->irq[0];
+}
+
 static int fec_enet_init_stop_mode(struct fec_enet_private *fep,
 				   struct device_node *np)
 {
@@ -3666,6 +3842,10 @@ fec_probe(struct platform_device *pdev)
 		fep->phy_interface = interface;
 	}
 
+	ret = fec_enet_parse_rgmii_delay(fep, np);
+	if (ret)
+		goto failed_rgmii_delay;
+
 	fep->clk_ipg = devm_clk_get(&pdev->dev, "ipg");
 	if (IS_ERR(fep->clk_ipg)) {
 		ret = PTR_ERR(fep->clk_ipg);
@@ -3692,6 +3872,14 @@ fec_probe(struct platform_device *pdev)
 	fep->clk_ref = devm_clk_get(&pdev->dev, "enet_clk_ref");
 	if (IS_ERR(fep->clk_ref))
 		fep->clk_ref = NULL;
+	fep->clk_ref_rate = clk_get_rate(fep->clk_ref);
+
+	/* clk_2x_txclk is optional, depends on board */
+	if (fep->rgmii_txc_dly || fep->rgmii_rxc_dly) {
+		fep->clk_2x_txclk = devm_clk_get(&pdev->dev, "enet_2x_txclk");
+		if (IS_ERR(fep->clk_2x_txclk))
+			fep->clk_2x_txclk = NULL;
+	}
 
 	fep->bufdesc_ex = fep->quirks & FEC_QUIRK_HAS_BUFDESC_EX;
 	fep->clk_ptp = devm_clk_get(&pdev->dev, "ptp");
@@ -3762,6 +3950,9 @@ fec_probe(struct platform_device *pdev)
 		fep->irq[i] = irq;
 	}
 
+	/* Decide which interrupt line is wakeup capable */
+	fec_enet_get_wakeup_irq(pdev);
+
 	ret = fec_enet_mii_init(pdev);
 	if (ret)
 		goto failed_mii_init;
@@ -3809,6 +4000,7 @@ failed_clk_ahb:
 failed_clk_ipg:
 	fec_enet_clk_enable(ndev, false);
 failed_clk:
+failed_rgmii_delay:
 	if (of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 	of_node_put(phy_node);
diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c
index 02c47658a215..73ff359a15f1 100644
--- a/drivers/net/ethernet/freescale/fec_mpc52xx.c
+++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c
@@ -792,7 +792,7 @@ static const struct net_device_ops mpc52xx_fec_netdev_ops = {
 	.ndo_set_rx_mode = mpc52xx_fec_set_multicast_list,
 	.ndo_set_mac_address = mpc52xx_fec_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
-	.ndo_do_ioctl = phy_do_ioctl,
+	.ndo_eth_ioctl = phy_do_ioctl,
 	.ndo_tx_timeout = mpc52xx_fec_tx_timeout,
 	.ndo_get_stats = mpc52xx_fec_get_stats,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 6ee325ad35c5..2db6e38a772e 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -900,7 +900,7 @@ static const struct net_device_ops fs_enet_netdev_ops = {
 	.ndo_start_xmit		= fs_enet_start_xmit,
 	.ndo_tx_timeout		= fs_timeout,
 	.ndo_set_rx_mode	= fs_set_multicast_list,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 9646483137c4..af6ad94bf24a 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -3184,7 +3184,7 @@ 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_do_ioctl = gfar_ioctl,
+	.ndo_eth_ioctl = gfar_ioctl,
 	.ndo_get_stats64 = gfar_get_stats64,
 	.ndo_change_carrier = fixed_phy_change_carrier,
 	.ndo_set_mac_address = gfar_set_mac_addr,
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index cc7d4f93da54..7b32ed29bf4c 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -243,7 +243,9 @@ static unsigned int gfar_ticks2usecs(struct gfar_private *priv,
 /* Get the coalescing parameters, and put them in the cvals
  * structure.  */
 static int gfar_gcoalesce(struct net_device *dev,
-			  struct ethtool_coalesce *cvals)
+			  struct ethtool_coalesce *cvals,
+			  struct kernel_ethtool_coalesce *kernel_coal,
+			  struct netlink_ext_ack *extack)
 {
 	struct gfar_private *priv = netdev_priv(dev);
 	struct gfar_priv_rx_q *rx_queue = NULL;
@@ -280,7 +282,9 @@ static int gfar_gcoalesce(struct net_device *dev,
  * in order for coalescing to be active
  */
 static int gfar_scoalesce(struct net_device *dev,
-			  struct ethtool_coalesce *cvals)
+			  struct ethtool_coalesce *cvals,
+			  struct kernel_ethtool_coalesce *kernel_coal,
+			  struct netlink_ext_ack *extack)
 {
 	struct gfar_private *priv = netdev_priv(dev);
 	int i, err = 0;
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 0acfafb73db1..3eb288d10b0c 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -3516,7 +3516,7 @@ static const struct net_device_ops ucc_geth_netdev_ops = {
 	.ndo_set_mac_address	= ucc_geth_set_mac_addr,
 	.ndo_set_rx_mode	= ucc_geth_set_multi,
 	.ndo_tx_timeout		= ucc_geth_timeout,
-	.ndo_do_ioctl		= ucc_geth_ioctl,
+	.ndo_eth_ioctl		= ucc_geth_ioctl,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= ucc_netpoll,
 #endif
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index 5bb56b454541..f089d33dd48e 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -322,7 +322,8 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv,
 	tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
 
 	// Check if next command will overflow the buffer.
-	if (((priv->adminq_prod_cnt + 1) & priv->adminq_mask) == tail) {
+	if (((priv->adminq_prod_cnt + 1) & priv->adminq_mask) ==
+	    (tail & priv->adminq_mask)) {
 		int err;
 
 		// Flush existing commands to make room.
@@ -332,7 +333,8 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv,
 
 		// Retry.
 		tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
-		if (((priv->adminq_prod_cnt + 1) & priv->adminq_mask) == tail) {
+		if (((priv->adminq_prod_cnt + 1) & priv->adminq_mask) ==
+		    (tail & priv->adminq_mask)) {
 			// This should never happen. We just flushed the
 			// command queue so there should be enough space.
 			return -ENOMEM;
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index bb062b02fb85..3312e1d93c3b 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -90,6 +90,8 @@ config HNS_ENET
 config HNS3
 	tristate "Hisilicon Network Subsystem Support HNS3 (Framework)"
 	depends on PCI
+	select NET_DEVLINK
+	select PAGE_POOL
 	help
 	  This selects the framework support for Hisilicon Network Subsystem 3.
 	  This layer facilitates clients like ENET, RoCE and user-space ethernet
@@ -102,7 +104,7 @@ config HNS3_HCLGE
 	tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support"
 	default m
 	depends on PCI_MSI
-	imply PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  This selects the HNS3_HCLGE network acceleration engine & its hardware
 	  compatibility layer. The engine would be used in Hisilicon hip08 family of
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index e53512f6878a..37b605fed32c 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -796,7 +796,9 @@ static void hip04_tx_timeout_task(struct work_struct *work)
 }
 
 static int hip04_get_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct hip04_priv *priv = netdev_priv(netdev);
 
@@ -807,7 +809,9 @@ static int hip04_get_coalesce(struct net_device *netdev,
 }
 
 static int hip04_set_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct hip04_priv *priv = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c
index 3c4db4a6b431..22bf914f2dbd 100644
--- a/drivers/net/ethernet/hisilicon/hisi_femac.c
+++ b/drivers/net/ethernet/hisilicon/hisi_femac.c
@@ -685,7 +685,7 @@ static const struct net_device_ops hisi_femac_netdev_ops = {
 	.ndo_open		= hisi_femac_net_open,
 	.ndo_stop		= hisi_femac_net_close,
 	.ndo_start_xmit		= hisi_femac_net_xmit,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_set_mac_address	= hisi_femac_set_mac_address,
 	.ndo_set_rx_mode	= hisi_femac_net_set_rx_mode,
 };
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index ad534f9e41ab..343c605c4be8 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1945,7 +1945,7 @@ static const struct net_device_ops hns_nic_netdev_ops = {
 	.ndo_tx_timeout = hns_nic_net_timeout,
 	.ndo_set_mac_address = hns_nic_net_set_mac_address,
 	.ndo_change_mtu = hns_nic_change_mtu,
-	.ndo_do_ioctl = phy_do_ioctl_running,
+	.ndo_eth_ioctl = phy_do_ioctl_running,
 	.ndo_set_features = hns_nic_set_features,
 	.ndo_fix_features = hns_nic_fix_features,
 	.ndo_get_stats64 = hns_nic_get_stats64,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 7e62dcff2426..ab7390225942 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -730,11 +730,15 @@ static int hns_set_pauseparam(struct net_device *net_dev,
  * hns_get_coalesce - get coalesce info.
  * @net_dev: net device
  * @ec: coalesce info.
+ * @kernel_coal: ethtool CQE mode setting structure
+ * @extack: extack for reporting error messages
  *
  * Return 0 on success, negative on failure.
  */
 static int hns_get_coalesce(struct net_device *net_dev,
-			    struct ethtool_coalesce *ec)
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct hns_nic_priv *priv = netdev_priv(net_dev);
 	struct hnae_ae_ops *ops;
@@ -774,11 +778,15 @@ static int hns_get_coalesce(struct net_device *net_dev,
  * hns_set_coalesce - set coalesce info.
  * @net_dev: net device
  * @ec: coalesce info.
+ * @kernel_coal: ethtool CQE mode setting structure
+ * @extack: extack for reporting error messages
  *
  * Return 0 on success, negative on failure.
  */
 static int hns_set_coalesce(struct net_device *net_dev,
-			    struct ethtool_coalesce *ec)
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct hns_nic_priv *priv = netdev_priv(net_dev);
 	struct hnae_ae_ops *ops;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index aa86a81c8f4a..c2bd2584201f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -9,7 +9,7 @@
 
 enum HCLGE_MBX_OPCODE {
 	HCLGE_MBX_RESET = 0x01,		/* (VF -> PF) assert reset */
-	HCLGE_MBX_ASSERTING_RESET,	/* (PF -> VF) PF is asserting reset*/
+	HCLGE_MBX_ASSERTING_RESET,	/* (PF -> VF) PF is asserting reset */
 	HCLGE_MBX_SET_UNICAST,		/* (VF -> PF) set UC addr */
 	HCLGE_MBX_SET_MULTICAST,	/* (VF -> PF) set MC addr */
 	HCLGE_MBX_SET_VLAN,		/* (VF -> PF) set VLAN */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index e0b7c3c44e7b..546a60530384 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -65,7 +65,7 @@
 #define HNAE3_UNIC_CLIENT_INITED_B		0x4
 #define HNAE3_ROCE_CLIENT_INITED_B		0x5
 
-#define HNAE3_DEV_SUPPORT_ROCE_DCB_BITS (BIT(HNAE3_DEV_SUPPORT_DCB_B) |\
+#define HNAE3_DEV_SUPPORT_ROCE_DCB_BITS (BIT(HNAE3_DEV_SUPPORT_DCB_B) | \
 		BIT(HNAE3_DEV_SUPPORT_ROCE_B))
 
 #define hnae3_dev_roce_supported(hdev) \
@@ -718,6 +718,8 @@ struct hnae3_ae_ops {
 			    u32 nsec, u32 sec);
 	int (*get_ts_info)(struct hnae3_handle *handle,
 			   struct ethtool_ts_info *info);
+	int (*get_link_diagnosis_info)(struct hnae3_handle *handle,
+				       u32 *status_code);
 };
 
 struct hnae3_dcb_ops {
@@ -772,6 +774,7 @@ struct hnae3_knic_private_info {
 
 	u16 int_rl_setting;
 	enum pkt_hash_types rss_type;
+	void __iomem *io_base;
 };
 
 struct hnae3_roce_private_info {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 80461ab0ce9e..2b66c59f5eaf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -38,9 +38,8 @@ static struct hns3_dbg_dentry_info hns3_dbg_dentry[] = {
 	},
 };
 
-static int hns3_dbg_bd_file_init(struct hnae3_handle *handle, unsigned int cmd);
-static int hns3_dbg_common_file_init(struct hnae3_handle *handle,
-				     unsigned int cmd);
+static int hns3_dbg_bd_file_init(struct hnae3_handle *handle, u32 cmd);
+static int hns3_dbg_common_file_init(struct hnae3_handle *handle, u32 cmd);
 
 static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
 	{
@@ -696,7 +695,7 @@ static int hns3_dbg_queue_map(struct hnae3_handle *h, char *buf, int len)
 		sprintf(result[j++], "%u", i);
 		sprintf(result[j++], "%u",
 			h->ae_algo->ops->get_global_queue_id(h, i));
-		sprintf(result[j++], "%u",
+		sprintf(result[j++], "%d",
 			priv->ring[i].tqp_vector->vector_irq);
 		hns3_dbg_fill_content(content, sizeof(content), queue_map_items,
 				      (const char **)result,
@@ -798,10 +797,10 @@ static const struct hns3_dbg_item tx_bd_info_items[] = {
 	{ "T_CS_VLAN_TSO", 2 },
 	{ "OT_VLAN_TAG", 3 },
 	{ "TV", 2 },
-	{ "OLT_VLAN_LEN", 2},
-	{ "PAYLEN_OL4CS", 2},
-	{ "BD_FE_SC_VLD", 2},
-	{ "MSS_HW_CSUM", 0},
+	{ "OLT_VLAN_LEN", 2 },
+	{ "PAYLEN_OL4CS", 2 },
+	{ "BD_FE_SC_VLD", 2 },
+	{ "MSS_HW_CSUM", 0 },
 };
 
 static void hns3_dump_tx_bd_info(struct hns3_nic_priv *priv,
@@ -868,7 +867,7 @@ 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);
-	static const char * const str[] = {"no", "yes"};
+	const char * const str[] = {"no", "yes"};
 	unsigned long *caps = ae_dev->caps;
 	u32 i, state;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index cdb5f14fb6bc..22af3d6ce178 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -63,7 +63,7 @@ MODULE_PARM_DESC(tx_sgl, "Minimum number of frags when using dma_map_sg() to opt
 
 #define HNS3_SGL_SIZE(nfrag)	(sizeof(struct scatterlist) * (nfrag) +	\
 				 sizeof(struct sg_table))
-#define HNS3_MAX_SGL_SIZE	ALIGN(HNS3_SGL_SIZE(HNS3_MAX_TSO_BD_NUM),\
+#define HNS3_MAX_SGL_SIZE	ALIGN(HNS3_SGL_SIZE(HNS3_MAX_TSO_BD_NUM), \
 				      dma_get_cache_alignment())
 
 #define DEFAULT_MSG_LEVEL (NETIF_MSG_PROBE | NETIF_MSG_LINK | \
@@ -100,7 +100,7 @@ static const struct pci_device_id hns3_pci_tbl[] = {
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_RDMA_DCB_PFC_VF),
 	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
 	/* required last entry */
-	{0, }
+	{0,}
 };
 MODULE_DEVICE_TABLE(pci, hns3_pci_tbl);
 
@@ -971,8 +971,7 @@ static u32 hns3_tx_spare_space(struct hns3_enet_ring *ring)
 	/* The free tx buffer is divided into two part, so pick the
 	 * larger one.
 	 */
-	return (ntc > (tx_spare->len - ntu) ? ntc :
-			(tx_spare->len - ntu)) - 1;
+	return max(ntc, tx_spare->len - ntu) - 1;
 }
 
 static void hns3_tx_spare_update(struct hns3_enet_ring *ring)
@@ -2852,7 +2851,7 @@ static const struct net_device_ops hns3_nic_netdev_ops = {
 	.ndo_start_xmit		= hns3_nic_net_xmit,
 	.ndo_tx_timeout		= hns3_nic_net_timeout,
 	.ndo_set_mac_address	= hns3_nic_net_set_mac_address,
-	.ndo_do_ioctl		= hns3_nic_do_ioctl,
+	.ndo_eth_ioctl		= hns3_nic_do_ioctl,
 	.ndo_change_mtu		= hns3_nic_change_mtu,
 	.ndo_set_features	= hns3_nic_set_features,
 	.ndo_features_check	= hns3_features_check,
@@ -3127,11 +3126,6 @@ static void hns3_set_default_feature(struct net_device *netdev)
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
-	netdev->hw_enc_features |= NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
-		NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
-		NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
-		NETIF_F_SCTP_CRC | NETIF_F_TSO_MANGLEID | NETIF_F_FRAGLIST;
-
 	netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
 
 	netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
@@ -3141,62 +3135,37 @@ static void hns3_set_default_feature(struct net_device *netdev)
 		NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
 		NETIF_F_SCTP_CRC | NETIF_F_FRAGLIST;
 
-	netdev->vlan_features |= NETIF_F_RXCSUM |
-		NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO |
-		NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
-		NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
-		NETIF_F_SCTP_CRC | NETIF_F_FRAGLIST;
-
-	netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX |
-		NETIF_F_HW_VLAN_CTAG_RX |
-		NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
-		NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
-		NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
-		NETIF_F_SCTP_CRC | NETIF_F_FRAGLIST;
-
 	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
-		netdev->hw_features |= NETIF_F_GRO_HW;
 		netdev->features |= NETIF_F_GRO_HW;
 
-		if (!(h->flags & HNAE3_SUPPORT_VF)) {
-			netdev->hw_features |= NETIF_F_NTUPLE;
+		if (!(h->flags & HNAE3_SUPPORT_VF))
 			netdev->features |= NETIF_F_NTUPLE;
-		}
 	}
 
-	if (test_bit(HNAE3_DEV_SUPPORT_UDP_GSO_B, ae_dev->caps)) {
-		netdev->hw_features |= NETIF_F_GSO_UDP_L4;
+	if (test_bit(HNAE3_DEV_SUPPORT_UDP_GSO_B, ae_dev->caps))
 		netdev->features |= NETIF_F_GSO_UDP_L4;
-		netdev->vlan_features |= NETIF_F_GSO_UDP_L4;
-		netdev->hw_enc_features |= NETIF_F_GSO_UDP_L4;
-	}
 
-	if (test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps)) {
-		netdev->hw_features |= NETIF_F_HW_CSUM;
+	if (test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps))
 		netdev->features |= NETIF_F_HW_CSUM;
-		netdev->vlan_features |= NETIF_F_HW_CSUM;
-		netdev->hw_enc_features |= NETIF_F_HW_CSUM;
-	} else {
-		netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	else
 		netdev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
-		netdev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
-		netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
-	}
 
-	if (test_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, ae_dev->caps)) {
-		netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+	if (test_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, ae_dev->caps))
 		netdev->features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
-		netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
-		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
-	}
 
-	if (test_bit(HNAE3_DEV_SUPPORT_FD_FORWARD_TC_B, ae_dev->caps)) {
-		netdev->hw_features |= NETIF_F_HW_TC;
+	if (test_bit(HNAE3_DEV_SUPPORT_FD_FORWARD_TC_B, ae_dev->caps))
 		netdev->features |= NETIF_F_HW_TC;
-	}
 
-	if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps))
-		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+	netdev->hw_features |= netdev->features;
+	if (!test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps))
+		netdev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	netdev->vlan_features |= netdev->features &
+		~(NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_TX |
+		  NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_GRO_HW | NETIF_F_NTUPLE |
+		  NETIF_F_HW_TC);
+
+	netdev->hw_enc_features |= netdev->vlan_features | NETIF_F_TSO_MANGLEID;
 }
 
 static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
@@ -3205,6 +3174,21 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
 	unsigned int order = hns3_page_order(ring);
 	struct page *p;
 
+	if (ring->page_pool) {
+		p = page_pool_dev_alloc_frag(ring->page_pool,
+					     &cb->page_offset,
+					     hns3_buf_size(ring));
+		if (unlikely(!p))
+			return -ENOMEM;
+
+		cb->priv = p;
+		cb->buf = page_address(p);
+		cb->dma = page_pool_get_dma_addr(p);
+		cb->type = DESC_TYPE_PP_FRAG;
+		cb->reuse_flag = 0;
+		return 0;
+	}
+
 	p = dev_alloc_pages(order);
 	if (!p)
 		return -ENOMEM;
@@ -3227,8 +3211,13 @@ static void hns3_free_buffer(struct hns3_enet_ring *ring,
 	if (cb->type & (DESC_TYPE_SKB | DESC_TYPE_BOUNCE_HEAD |
 			DESC_TYPE_BOUNCE_ALL | DESC_TYPE_SGL_SKB))
 		napi_consume_skb(cb->priv, budget);
-	else if (!HNAE3_IS_TX_RING(ring) && cb->pagecnt_bias)
-		__page_frag_cache_drain(cb->priv, cb->pagecnt_bias);
+	else if (!HNAE3_IS_TX_RING(ring)) {
+		if (cb->type & DESC_TYPE_PAGE && cb->pagecnt_bias)
+			__page_frag_cache_drain(cb->priv, cb->pagecnt_bias);
+		else if (cb->type & DESC_TYPE_PP_FRAG)
+			page_pool_put_full_page(ring->page_pool, cb->priv,
+						false);
+	}
 	memset(cb, 0, sizeof(*cb));
 }
 
@@ -3315,7 +3304,7 @@ static int hns3_alloc_and_map_buffer(struct hns3_enet_ring *ring,
 	int ret;
 
 	ret = hns3_alloc_buffer(ring, cb);
-	if (ret)
+	if (ret || ring->page_pool)
 		goto out;
 
 	ret = hns3_map_buffer(ring, cb);
@@ -3337,7 +3326,8 @@ static int hns3_alloc_and_attach_buffer(struct hns3_enet_ring *ring, int i)
 	if (ret)
 		return ret;
 
-	ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma);
+	ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma +
+					 ring->desc_cb[i].page_offset);
 
 	return 0;
 }
@@ -3367,7 +3357,8 @@ static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i,
 {
 	hns3_unmap_buffer(ring, &ring->desc_cb[i]);
 	ring->desc_cb[i] = *res_cb;
-	ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma);
+	ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma +
+					 ring->desc_cb[i].page_offset);
 	ring->desc[i].rx.bd_base_info = 0;
 }
 
@@ -3539,6 +3530,12 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 	u32 frag_size = size - pull_len;
 	bool reused;
 
+	if (ring->page_pool) {
+		skb_add_rx_frag(skb, i, desc_cb->priv, frag_offset,
+				frag_size, truesize);
+		return;
+	}
+
 	/* Avoid re-using remote or pfmem page */
 	if (unlikely(!dev_page_is_reusable(desc_cb->priv)))
 		goto out;
@@ -3856,6 +3853,9 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
 		/* We can reuse buffer as-is, just make sure it is reusable */
 		if (dev_page_is_reusable(desc_cb->priv))
 			desc_cb->reuse_flag = 1;
+		else if (desc_cb->type & DESC_TYPE_PP_FRAG)
+			page_pool_put_full_page(ring->page_pool, desc_cb->priv,
+						false);
 		else /* This page cannot be reused so discard it */
 			__page_frag_cache_drain(desc_cb->priv,
 						desc_cb->pagecnt_bias);
@@ -3863,6 +3863,10 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
 		hns3_rx_ring_move_fw(ring);
 		return 0;
 	}
+
+	if (ring->page_pool)
+		skb_mark_for_recycle(skb);
+
 	u64_stats_update_begin(&ring->syncp);
 	ring->stats.seg_pkt_cnt++;
 	u64_stats_update_end(&ring->syncp);
@@ -3901,6 +3905,10 @@ static int hns3_add_frag(struct hns3_enet_ring *ring)
 					    "alloc rx fraglist skb fail\n");
 				return -ENXIO;
 			}
+
+			if (ring->page_pool)
+				skb_mark_for_recycle(new_skb);
+
 			ring->frag_num = 0;
 
 			if (ring->tail_skb) {
@@ -4434,9 +4442,7 @@ static void hns3_tx_dim_work(struct work_struct *work)
 static void hns3_nic_init_dim(struct hns3_enet_tqp_vector *tqp_vector)
 {
 	INIT_WORK(&tqp_vector->rx_group.dim.work, hns3_rx_dim_work);
-	tqp_vector->rx_group.dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 	INIT_WORK(&tqp_vector->tx_group.dim.work, hns3_tx_dim_work);
-	tqp_vector->tx_group.dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 }
 
 static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv)
@@ -4705,6 +4711,29 @@ static void hns3_put_ring_config(struct hns3_nic_priv *priv)
 	priv->ring = NULL;
 }
 
+static void hns3_alloc_page_pool(struct hns3_enet_ring *ring)
+{
+	struct page_pool_params pp_params = {
+		.flags = PP_FLAG_DMA_MAP | PP_FLAG_PAGE_FRAG |
+				PP_FLAG_DMA_SYNC_DEV,
+		.order = hns3_page_order(ring),
+		.pool_size = ring->desc_num * hns3_buf_size(ring) /
+				(PAGE_SIZE << hns3_page_order(ring)),
+		.nid = dev_to_node(ring_to_dev(ring)),
+		.dev = ring_to_dev(ring),
+		.dma_dir = DMA_FROM_DEVICE,
+		.offset = 0,
+		.max_len = PAGE_SIZE << hns3_page_order(ring),
+	};
+
+	ring->page_pool = page_pool_create(&pp_params);
+	if (IS_ERR(ring->page_pool)) {
+		dev_warn(ring_to_dev(ring), "page pool creation failed: %ld\n",
+			 PTR_ERR(ring->page_pool));
+		ring->page_pool = NULL;
+	}
+}
+
 static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring)
 {
 	int ret;
@@ -4724,6 +4753,8 @@ static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring)
 		goto out_with_desc_cb;
 
 	if (!HNAE3_IS_TX_RING(ring)) {
+		hns3_alloc_page_pool(ring);
+
 		ret = hns3_alloc_ring_buffers(ring);
 		if (ret)
 			goto out_with_desc;
@@ -4764,6 +4795,11 @@ void hns3_fini_ring(struct hns3_enet_ring *ring)
 		devm_kfree(ring_to_dev(ring), tx_spare);
 		ring->tx_spare = NULL;
 	}
+
+	if (!HNAE3_IS_TX_RING(ring) && ring->page_pool) {
+		page_pool_destroy(ring->page_pool);
+		ring->page_pool = NULL;
+	}
 }
 
 static int hns3_buf_size2type(u32 buf_size)
@@ -4954,6 +4990,66 @@ static void hns3_info_show(struct hns3_nic_priv *priv)
 	dev_info(priv->dev, "Max mtu size: %u\n", priv->netdev->max_mtu);
 }
 
+static void hns3_set_cq_period_mode(struct hns3_nic_priv *priv,
+				    enum dim_cq_period_mode mode, bool is_tx)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev);
+	struct hnae3_handle *handle = priv->ae_handle;
+	int i;
+
+	if (is_tx) {
+		priv->tx_cqe_mode = mode;
+
+		for (i = 0; i < priv->vector_num; i++)
+			priv->tqp_vector[i].tx_group.dim.mode = mode;
+	} else {
+		priv->rx_cqe_mode = mode;
+
+		for (i = 0; i < priv->vector_num; i++)
+			priv->tqp_vector[i].rx_group.dim.mode = mode;
+	}
+
+	/* only device version above V3(include V3), GL can switch CQ/EQ
+	 * period mode.
+	 */
+	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) {
+		u32 new_mode;
+		u64 reg;
+
+		new_mode = (mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE) ?
+			HNS3_CQ_MODE_CQE : HNS3_CQ_MODE_EQE;
+		reg = is_tx ? HNS3_GL1_CQ_MODE_REG : HNS3_GL0_CQ_MODE_REG;
+
+		writel(new_mode, handle->kinfo.io_base + reg);
+	}
+}
+
+void hns3_cq_period_mode_init(struct hns3_nic_priv *priv,
+			      enum dim_cq_period_mode tx_mode,
+			      enum dim_cq_period_mode rx_mode)
+{
+	hns3_set_cq_period_mode(priv, tx_mode, true);
+	hns3_set_cq_period_mode(priv, rx_mode, false);
+}
+
+static void hns3_state_init(struct hnae3_handle *handle)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
+	struct net_device *netdev = handle->kinfo.netdev;
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
+
+	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
+		set_bit(HNAE3_PFLAG_LIMIT_PROMISC, &handle->supported_pflags);
+
+	if (test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps))
+		set_bit(HNS3_NIC_STATE_HW_TX_CSUM_ENABLE, &priv->state);
+
+	if (hnae3_ae_dev_rxd_adv_layout_supported(ae_dev))
+		set_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state);
+}
+
 static int hns3_client_init(struct hnae3_handle *handle)
 {
 	struct pci_dev *pdev = handle->pdev;
@@ -5021,6 +5117,9 @@ static int hns3_client_init(struct hnae3_handle *handle)
 		goto out_init_ring;
 	}
 
+	hns3_cq_period_mode_init(priv, DIM_CQ_PERIOD_MODE_START_FROM_EQE,
+				 DIM_CQ_PERIOD_MODE_START_FROM_EQE);
+
 	ret = hns3_init_phy(netdev);
 	if (ret)
 		goto out_init_phy;
@@ -5054,16 +5153,7 @@ static int hns3_client_init(struct hnae3_handle *handle)
 
 	netdev->max_mtu = HNS3_MAX_MTU(ae_dev->dev_specs.max_frm_size);
 
-	if (test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps))
-		set_bit(HNS3_NIC_STATE_HW_TX_CSUM_ENABLE, &priv->state);
-
-	if (hnae3_ae_dev_rxd_adv_layout_supported(ae_dev))
-		set_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state);
-
-	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
-
-	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
-		set_bit(HNAE3_PFLAG_LIMIT_PROMISC, &handle->supported_pflags);
+	hns3_state_init(handle);
 
 	ret = register_netdev(netdev);
 	if (ret) {
@@ -5353,6 +5443,8 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
 	if (ret)
 		goto err_uninit_vector;
 
+	hns3_cq_period_mode_init(priv, priv->tx_cqe_mode, priv->rx_cqe_mode);
+
 	/* the device can work without cpu rmap, only aRFS needs it */
 	ret = hns3_set_rx_cpu_rmap(netdev);
 	if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 15af3d93857b..6162d9f88e37 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -6,6 +6,7 @@
 
 #include <linux/dim.h>
 #include <linux/if_vlan.h>
+#include <net/page_pool.h>
 
 #include "hnae3.h"
 
@@ -201,6 +202,12 @@ enum hns3_nic_state {
 
 #define HNS3_RING_EN_B				0
 
+#define HNS3_GL0_CQ_MODE_REG			0x20d00
+#define HNS3_GL1_CQ_MODE_REG			0x20d04
+#define HNS3_GL2_CQ_MODE_REG			0x20d08
+#define HNS3_CQ_MODE_EQE			1U
+#define HNS3_CQ_MODE_CQE			0U
+
 enum hns3_pkt_l2t_type {
 	HNS3_L2_TYPE_UNICAST,
 	HNS3_L2_TYPE_MULTICAST,
@@ -307,6 +314,7 @@ enum hns3_desc_type {
 	DESC_TYPE_BOUNCE_ALL		= 1 << 3,
 	DESC_TYPE_BOUNCE_HEAD		= 1 << 4,
 	DESC_TYPE_SGL_SKB		= 1 << 5,
+	DESC_TYPE_PP_FRAG		= 1 << 6,
 };
 
 struct hns3_desc_cb {
@@ -340,7 +348,7 @@ enum hns3_pkt_l3type {
 	HNS3_L3_TYPE_LLDP,
 	HNS3_L3_TYPE_BPDU,
 	HNS3_L3_TYPE_MAC_PAUSE,
-	HNS3_L3_TYPE_PFC_PAUSE,/* 0x9*/
+	HNS3_L3_TYPE_PFC_PAUSE, /* 0x9 */
 
 	/* reserved for 0xA~0xB */
 
@@ -384,11 +392,11 @@ enum hns3_pkt_ol4type {
 };
 
 struct hns3_rx_ptype {
-	u32 ptype:8;
-	u32 csum_level:2;
-	u32 ip_summed:2;
-	u32 l3_type:4;
-	u32 valid:1;
+	u32 ptype : 8;
+	u32 csum_level : 2;
+	u32 ip_summed : 2;
+	u32 l3_type : 4;
+	u32 valid : 1;
 };
 
 struct ring_stats {
@@ -451,6 +459,7 @@ struct hns3_enet_ring {
 	struct hnae3_queue *tqp;
 	int queue_index;
 	struct device *dev; /* will be used for DMA mapping of descriptors */
+	struct page_pool *page_pool;
 
 	/* statistic */
 	struct ring_stats stats;
@@ -513,9 +522,9 @@ struct hns3_enet_coalesce {
 	u16 int_gl;
 	u16 int_ql;
 	u16 int_ql_max;
-	u8 adapt_enable:1;
-	u8 ql_enable:1;
-	u8 unit_1us:1;
+	u8 adapt_enable : 1;
+	u8 ql_enable : 1;
+	u8 unit_1us : 1;
 	enum hns3_flow_level_range flow_level;
 };
 
@@ -569,6 +578,8 @@ struct hns3_nic_priv {
 
 	unsigned long state;
 
+	enum dim_cq_period_mode tx_cqe_mode;
+	enum dim_cq_period_mode rx_cqe_mode;
 	struct hns3_enet_coalesce tx_coal;
 	struct hns3_enet_coalesce rx_coal;
 	u32 tx_copybreak;
@@ -593,6 +604,11 @@ struct hns3_hw_error_info {
 	const char *msg;
 };
 
+struct hns3_reset_type_map {
+	enum ethtool_reset_flags rst_flags;
+	enum hnae3_reset_type rst_type;
+};
+
 static inline int ring_space(struct hns3_enet_ring *ring)
 {
 	/* This smp_load_acquire() pairs with smp_store_release() in
@@ -702,4 +718,7 @@ void hns3_dbg_register_debugfs(const char *debugfs_dir_name);
 void hns3_dbg_unregister_debugfs(void);
 void hns3_shinfo_pack(struct skb_shared_info *shinfo, __u32 *size);
 u16 hns3_get_max_available_channels(struct hnae3_handle *h);
+void hns3_cq_period_mode_init(struct hns3_nic_priv *priv,
+			      enum dim_cq_period_mode tx_mode,
+			      enum dim_cq_period_mode rx_mode);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 82061ab6930f..7ea511d59e91 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -7,21 +7,7 @@
 #include <linux/sfp.h>
 
 #include "hns3_enet.h"
-
-struct hns3_stats {
-	char stats_string[ETH_GSTRING_LEN];
-	int stats_offset;
-};
-
-struct hns3_sfp_type {
-	u8 type;
-	u8 ext_type;
-};
-
-struct hns3_pflag_desc {
-	char name[ETH_GSTRING_LEN];
-	void (*handler)(struct net_device *netdev, bool enable);
-};
+#include "hns3_ethtool.h"
 
 /* tqp related stats */
 #define HNS3_TQP_STAT(_string, _member)	{			\
@@ -312,33 +298,8 @@ out:
 	return ret_val;
 }
 
-/**
- * hns3_self_test - self test
- * @ndev: net device
- * @eth_test: test cmd
- * @data: test result
- */
-static void hns3_self_test(struct net_device *ndev,
-			   struct ethtool_test *eth_test, u64 *data)
+static void hns3_set_selftest_param(struct hnae3_handle *h, int (*st_param)[2])
 {
-	struct hns3_nic_priv *priv = netdev_priv(ndev);
-	struct hnae3_handle *h = priv->ae_handle;
-	int st_param[HNS3_SELF_TEST_TYPE_NUM][2];
-	bool if_running = netif_running(ndev);
-	int test_index = 0;
-	u32 i;
-
-	if (hns3_nic_resetting(ndev)) {
-		netdev_err(ndev, "dev resetting!");
-		return;
-	}
-
-	/* Only do offline selftest, or pass by default */
-	if (eth_test->flags != ETH_TEST_FL_OFFLINE)
-		return;
-
-	netif_dbg(h, drv, ndev, "self test start");
-
 	st_param[HNAE3_LOOP_APP][0] = HNAE3_LOOP_APP;
 	st_param[HNAE3_LOOP_APP][1] =
 			h->flags & HNAE3_SUPPORT_APP_LOOPBACK;
@@ -355,6 +316,18 @@ static void hns3_self_test(struct net_device *ndev,
 	st_param[HNAE3_LOOP_PHY][0] = HNAE3_LOOP_PHY;
 	st_param[HNAE3_LOOP_PHY][1] =
 			h->flags & HNAE3_SUPPORT_PHY_LOOPBACK;
+}
+
+static void hns3_selftest_prepare(struct net_device *ndev,
+				  bool if_running, int (*st_param)[2])
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct hnae3_handle *h = priv->ae_handle;
+
+	if (netif_msg_ifdown(h))
+		netdev_info(ndev, "self test start\n");
+
+	hns3_set_selftest_param(h, st_param);
 
 	if (if_running)
 		ndev->netdev_ops->ndo_stop(ndev);
@@ -373,6 +346,35 @@ static void hns3_self_test(struct net_device *ndev,
 		h->ae_algo->ops->halt_autoneg(h, true);
 
 	set_bit(HNS3_NIC_STATE_TESTING, &priv->state);
+}
+
+static void hns3_selftest_restore(struct net_device *ndev, bool if_running)
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct hnae3_handle *h = priv->ae_handle;
+
+	clear_bit(HNS3_NIC_STATE_TESTING, &priv->state);
+
+	if (h->ae_algo->ops->halt_autoneg)
+		h->ae_algo->ops->halt_autoneg(h, false);
+
+#if IS_ENABLED(CONFIG_VLAN_8021Q)
+	if (h->ae_algo->ops->enable_vlan_filter)
+		h->ae_algo->ops->enable_vlan_filter(h, true);
+#endif
+
+	if (if_running)
+		ndev->netdev_ops->ndo_open(ndev);
+
+	if (netif_msg_ifdown(h))
+		netdev_info(ndev, "self test end\n");
+}
+
+static void hns3_do_selftest(struct net_device *ndev, int (*st_param)[2],
+			     struct ethtool_test *eth_test, u64 *data)
+{
+	int test_index = 0;
+	u32 i;
 
 	for (i = 0; i < HNS3_SELF_TEST_TYPE_NUM; i++) {
 		enum hnae3_loop loop_type = (enum hnae3_loop)st_param[i][0];
@@ -391,21 +393,32 @@ static void hns3_self_test(struct net_device *ndev,
 
 		test_index++;
 	}
+}
 
-	clear_bit(HNS3_NIC_STATE_TESTING, &priv->state);
-
-	if (h->ae_algo->ops->halt_autoneg)
-		h->ae_algo->ops->halt_autoneg(h, false);
+/**
+ * hns3_nic_self_test - self test
+ * @ndev: net device
+ * @eth_test: test cmd
+ * @data: test result
+ */
+static void hns3_self_test(struct net_device *ndev,
+			   struct ethtool_test *eth_test, u64 *data)
+{
+	int st_param[HNS3_SELF_TEST_TYPE_NUM][2];
+	bool if_running = netif_running(ndev);
 
-#if IS_ENABLED(CONFIG_VLAN_8021Q)
-	if (h->ae_algo->ops->enable_vlan_filter)
-		h->ae_algo->ops->enable_vlan_filter(h, true);
-#endif
+	if (hns3_nic_resetting(ndev)) {
+		netdev_err(ndev, "dev resetting!");
+		return;
+	}
 
-	if (if_running)
-		ndev->netdev_ops->ndo_open(ndev);
+	/* Only do offline selftest, or pass by default */
+	if (eth_test->flags != ETH_TEST_FL_OFFLINE)
+		return;
 
-	netif_dbg(h, drv, ndev, "self test end\n");
+	hns3_selftest_prepare(ndev, if_running, st_param);
+	hns3_do_selftest(ndev, st_param, eth_test, data);
+	hns3_selftest_restore(ndev, if_running);
 }
 
 static void hns3_update_limit_promisc_mode(struct net_device *netdev,
@@ -953,6 +966,60 @@ static int hns3_get_rxnfc(struct net_device *netdev,
 	}
 }
 
+static const struct hns3_reset_type_map hns3_reset_type[] = {
+	{ETH_RESET_MGMT, HNAE3_IMP_RESET},
+	{ETH_RESET_ALL, HNAE3_GLOBAL_RESET},
+	{ETH_RESET_DEDICATED, HNAE3_FUNC_RESET},
+};
+
+static const struct hns3_reset_type_map hns3vf_reset_type[] = {
+	{ETH_RESET_DEDICATED, HNAE3_VF_FUNC_RESET},
+};
+
+static int hns3_set_reset(struct net_device *netdev, u32 *flags)
+{
+	enum hnae3_reset_type rst_type = HNAE3_NONE_RESET;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	const struct hnae3_ae_ops *ops = h->ae_algo->ops;
+	const struct hns3_reset_type_map *rst_type_map;
+	u32 i, size;
+
+	if (ops->ae_dev_resetting && ops->ae_dev_resetting(h))
+		return -EBUSY;
+
+	if (!ops->set_default_reset_request || !ops->reset_event)
+		return -EOPNOTSUPP;
+
+	if (h->flags & HNAE3_SUPPORT_VF) {
+		rst_type_map = hns3vf_reset_type;
+		size = ARRAY_SIZE(hns3vf_reset_type);
+	} else {
+		rst_type_map = hns3_reset_type;
+		size = ARRAY_SIZE(hns3_reset_type);
+	}
+
+	for (i = 0; i < size; i++) {
+		if (rst_type_map[i].rst_flags == *flags) {
+			rst_type = rst_type_map[i].rst_type;
+			break;
+		}
+	}
+
+	if (rst_type == HNAE3_NONE_RESET ||
+	    (rst_type == HNAE3_IMP_RESET &&
+	     ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2))
+		return -EOPNOTSUPP;
+
+	netdev_info(netdev, "Setting reset type %d\n", rst_type);
+
+	ops->set_default_reset_request(ae_dev, rst_type);
+
+	ops->reset_event(h->pdev, h);
+
+	return 0;
+}
+
 static void hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv,
 					u32 tx_desc_num, u32 rx_desc_num)
 {
@@ -1139,7 +1206,9 @@ static void hns3_get_channels(struct net_device *netdev,
 }
 
 static int hns3_get_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *cmd)
+			     struct ethtool_coalesce *cmd,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hns3_enet_coalesce *tx_coal = &priv->tx_coal;
@@ -1161,6 +1230,11 @@ static int hns3_get_coalesce(struct net_device *netdev,
 	cmd->tx_max_coalesced_frames = tx_coal->int_ql;
 	cmd->rx_max_coalesced_frames = rx_coal->int_ql;
 
+	kernel_coal->use_cqe_mode_tx = (priv->tx_cqe_mode ==
+					DIM_CQ_PERIOD_MODE_START_FROM_CQE);
+	kernel_coal->use_cqe_mode_rx = (priv->rx_cqe_mode ==
+					DIM_CQ_PERIOD_MODE_START_FROM_CQE);
+
 	return 0;
 }
 
@@ -1321,13 +1395,17 @@ static void hns3_set_coalesce_per_queue(struct net_device *netdev,
 }
 
 static int hns3_set_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *cmd)
+			     struct ethtool_coalesce *cmd,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hns3_enet_coalesce *tx_coal = &priv->tx_coal;
 	struct hns3_enet_coalesce *rx_coal = &priv->rx_coal;
 	u16 queue_num = h->kinfo.num_tqps;
+	enum dim_cq_period_mode tx_mode;
+	enum dim_cq_period_mode rx_mode;
 	int ret;
 	int i;
 
@@ -1353,6 +1431,14 @@ static int hns3_set_coalesce(struct net_device *netdev,
 	for (i = 0; i < queue_num; i++)
 		hns3_set_coalesce_per_queue(netdev, cmd, i);
 
+	tx_mode = kernel_coal->use_cqe_mode_tx ?
+		  DIM_CQ_PERIOD_MODE_START_FROM_CQE :
+		  DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+	rx_mode = kernel_coal->use_cqe_mode_rx ?
+		  DIM_CQ_PERIOD_MODE_START_FROM_CQE :
+		  DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+	hns3_cq_period_mode_init(priv, tx_mode, rx_mode);
+
 	return 0;
 }
 
@@ -1658,7 +1744,8 @@ static int hns3_set_tunable(struct net_device *netdev,
 				 ETHTOOL_COALESCE_USE_ADAPTIVE |	\
 				 ETHTOOL_COALESCE_RX_USECS_HIGH |	\
 				 ETHTOOL_COALESCE_TX_USECS_HIGH |	\
-				 ETHTOOL_COALESCE_MAX_FRAMES)
+				 ETHTOOL_COALESCE_MAX_FRAMES |		\
+				 ETHTOOL_COALESCE_USE_CQE)
 
 static int hns3_get_ts_info(struct net_device *netdev,
 			    struct ethtool_ts_info *info)
@@ -1671,6 +1758,71 @@ static int hns3_get_ts_info(struct net_device *netdev,
 	return ethtool_op_get_ts_info(netdev, info);
 }
 
+static const struct hns3_ethtool_link_ext_state_mapping
+hns3_link_ext_state_map[] = {
+	{1, ETHTOOL_LINK_EXT_STATE_AUTONEG,
+		ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD},
+	{2, ETHTOOL_LINK_EXT_STATE_AUTONEG,
+		ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED},
+
+	{256, ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE,
+		ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_LINK_INHIBIT_TIMEOUT},
+	{257, ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE,
+		ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_LINK_PARTNER_DID_NOT_SET_RECEIVER_READY},
+	{512, ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE,
+		ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT},
+
+	{513, ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH,
+		ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK},
+	{514, ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH,
+		ETHTOOL_LINK_EXT_SUBSTATE_LLM_FC_FEC_IS_NOT_LOCKED},
+	{515, ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH,
+		ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED},
+
+	{768, ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY,
+		ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS},
+	{769, ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY,
+		ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_REFERENCE_CLOCK_LOST},
+	{770, ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY,
+		ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_ALOS},
+
+	{1024, ETHTOOL_LINK_EXT_STATE_NO_CABLE, 0},
+	{1025, ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE,
+		ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE},
+
+	{1026, ETHTOOL_LINK_EXT_STATE_EEPROM_ISSUE, 0},
+};
+
+static int hns3_get_link_ext_state(struct net_device *netdev,
+				   struct ethtool_link_ext_state_info *info)
+{
+	const struct hns3_ethtool_link_ext_state_mapping *map;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+	u32 status_code, i;
+	int ret;
+
+	if (netif_carrier_ok(netdev))
+		return -ENODATA;
+
+	if (!h->ae_algo->ops->get_link_diagnosis_info)
+		return -EOPNOTSUPP;
+
+	ret = h->ae_algo->ops->get_link_diagnosis_info(h, &status_code);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ARRAY_SIZE(hns3_link_ext_state_map); i++) {
+		map = &hns3_link_ext_state_map[i];
+		if (map->status_code == status_code) {
+			info->link_ext_state = map->link_ext_state;
+			info->__link_ext_substate = map->link_ext_substate;
+			return 0;
+		}
+	}
+
+	return -ENODATA;
+}
+
 static const struct ethtool_ops hns3vf_ethtool_ops = {
 	.supported_coalesce_params = HNS3_ETHTOOL_COALESCE,
 	.get_drvinfo = hns3_get_drvinfo,
@@ -1699,6 +1851,7 @@ static const struct ethtool_ops hns3vf_ethtool_ops = {
 	.set_priv_flags = hns3_set_priv_flags,
 	.get_tunable = hns3_get_tunable,
 	.set_tunable = hns3_set_tunable,
+	.reset = hns3_set_reset,
 };
 
 static const struct ethtool_ops hns3_ethtool_ops = {
@@ -1740,6 +1893,8 @@ static const struct ethtool_ops hns3_ethtool_ops = {
 	.get_ts_info = hns3_get_ts_info,
 	.get_tunable = hns3_get_tunable,
 	.set_tunable = hns3_set_tunable,
+	.reset = hns3_set_reset,
+	.get_link_ext_state = hns3_get_link_ext_state,
 };
 
 void hns3_ethtool_set_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.h b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.h
new file mode 100644
index 000000000000..822d6fcbc73b
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+// Copyright (c) 2021 Hisilicon Limited.
+
+#ifndef __HNS3_ETHTOOL_H
+#define __HNS3_ETHTOOL_H
+
+#include <linux/ethtool.h>
+#include <linux/netdevice.h>
+
+struct hns3_stats {
+	char stats_string[ETH_GSTRING_LEN];
+	int stats_offset;
+};
+
+struct hns3_sfp_type {
+	u8 type;
+	u8 ext_type;
+};
+
+struct hns3_pflag_desc {
+	char name[ETH_GSTRING_LEN];
+	void (*handler)(struct net_device *netdev, bool enable);
+};
+
+struct hns3_ethtool_link_ext_state_mapping {
+	u32 status_code;
+	enum ethtool_link_ext_state link_ext_state;
+	u8 link_ext_substate;
+};
+
+#endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
index a685392dbfe9..d1bf5c4c0abb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
@@ -7,6 +7,6 @@ ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
 ccflags-y += -I $(srctree)/$(src)
 
 obj-$(CONFIG_HNS3_HCLGE) += hclge.o
-hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o  hclge_debugfs.o hclge_ptp.o
+hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o  hclge_debugfs.o hclge_ptp.o hclge_devlink.o
 
 hclge-$(CONFIG_HNS3_DCB) += hclge_dcb.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index eb748aa35952..474c6d1664e7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -169,17 +169,19 @@ static bool hclge_is_special_opcode(u16 opcode)
 	/* these commands have several descriptors,
 	 * and use the first one to save opcode and return value
 	 */
-	u16 spec_opcode[] = {HCLGE_OPC_STATS_64_BIT,
-			     HCLGE_OPC_STATS_32_BIT,
-			     HCLGE_OPC_STATS_MAC,
-			     HCLGE_OPC_STATS_MAC_ALL,
-			     HCLGE_OPC_QUERY_32_BIT_REG,
-			     HCLGE_OPC_QUERY_64_BIT_REG,
-			     HCLGE_QUERY_CLEAR_MPF_RAS_INT,
-			     HCLGE_QUERY_CLEAR_PF_RAS_INT,
-			     HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT,
-			     HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT,
-			     HCLGE_QUERY_ALL_ERR_INFO};
+	static const u16 spec_opcode[] = {
+		HCLGE_OPC_STATS_64_BIT,
+		HCLGE_OPC_STATS_32_BIT,
+		HCLGE_OPC_STATS_MAC,
+		HCLGE_OPC_STATS_MAC_ALL,
+		HCLGE_OPC_QUERY_32_BIT_REG,
+		HCLGE_OPC_QUERY_64_BIT_REG,
+		HCLGE_QUERY_CLEAR_MPF_RAS_INT,
+		HCLGE_QUERY_CLEAR_PF_RAS_INT,
+		HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT,
+		HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT,
+		HCLGE_QUERY_ALL_ERR_INFO
+	};
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(spec_opcode); i++) {
@@ -360,41 +362,34 @@ static void hclge_set_default_capability(struct hclge_dev *hdev)
 	}
 }
 
+const struct hclge_caps_bit_map hclge_cmd_caps_bit_map0[] = {
+	{HCLGE_CAP_UDP_GSO_B, HNAE3_DEV_SUPPORT_UDP_GSO_B},
+	{HCLGE_CAP_PTP_B, HNAE3_DEV_SUPPORT_PTP_B},
+	{HCLGE_CAP_INT_QL_B, HNAE3_DEV_SUPPORT_INT_QL_B},
+	{HCLGE_CAP_TQP_TXRX_INDEP_B, HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B},
+	{HCLGE_CAP_HW_TX_CSUM_B, HNAE3_DEV_SUPPORT_HW_TX_CSUM_B},
+	{HCLGE_CAP_UDP_TUNNEL_CSUM_B, HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B},
+	{HCLGE_CAP_FD_FORWARD_TC_B, HNAE3_DEV_SUPPORT_FD_FORWARD_TC_B},
+	{HCLGE_CAP_FEC_B, HNAE3_DEV_SUPPORT_FEC_B},
+	{HCLGE_CAP_PAUSE_B, HNAE3_DEV_SUPPORT_PAUSE_B},
+	{HCLGE_CAP_PHY_IMP_B, HNAE3_DEV_SUPPORT_PHY_IMP_B},
+	{HCLGE_CAP_RAS_IMP_B, HNAE3_DEV_SUPPORT_RAS_IMP_B},
+	{HCLGE_CAP_RXD_ADV_LAYOUT_B, HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B},
+	{HCLGE_CAP_PORT_VLAN_BYPASS_B, HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B},
+	{HCLGE_CAP_PORT_VLAN_BYPASS_B, HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B},
+};
+
 static void hclge_parse_capability(struct hclge_dev *hdev,
 				   struct hclge_query_version_cmd *cmd)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
-	u32 caps;
+	u32 caps, i;
 
 	caps = __le32_to_cpu(cmd->caps[0]);
-	if (hnae3_get_bit(caps, HCLGE_CAP_UDP_GSO_B))
-		set_bit(HNAE3_DEV_SUPPORT_UDP_GSO_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGE_CAP_PTP_B))
-		set_bit(HNAE3_DEV_SUPPORT_PTP_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGE_CAP_INT_QL_B))
-		set_bit(HNAE3_DEV_SUPPORT_INT_QL_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGE_CAP_TQP_TXRX_INDEP_B))
-		set_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGE_CAP_HW_TX_CSUM_B))
-		set_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGE_CAP_UDP_TUNNEL_CSUM_B))
-		set_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGE_CAP_FD_FORWARD_TC_B))
-		set_bit(HNAE3_DEV_SUPPORT_FD_FORWARD_TC_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGE_CAP_FEC_B))
-		set_bit(HNAE3_DEV_SUPPORT_FEC_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGE_CAP_PAUSE_B))
-		set_bit(HNAE3_DEV_SUPPORT_PAUSE_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGE_CAP_PHY_IMP_B))
-		set_bit(HNAE3_DEV_SUPPORT_PHY_IMP_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGE_CAP_RAS_IMP_B))
-		set_bit(HNAE3_DEV_SUPPORT_RAS_IMP_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGE_CAP_RXD_ADV_LAYOUT_B))
-		set_bit(HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGE_CAP_PORT_VLAN_BYPASS_B)) {
-		set_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps);
-		set_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps);
-	}
+	for (i = 0; i < ARRAY_SIZE(hclge_cmd_caps_bit_map0); i++)
+		if (hnae3_get_bit(caps, hclge_cmd_caps_bit_map0[i].imp_bit))
+			set_bit(hclge_cmd_caps_bit_map0[i].local_bit,
+				ae_dev->caps);
 }
 
 static __le32 hclge_build_api_caps(void)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index ac70d49e205d..33244472e0d0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -320,6 +320,9 @@ enum hclge_opcode_type {
 	/* PHY command */
 	HCLGE_OPC_PHY_LINK_KSETTING	= 0x7025,
 	HCLGE_OPC_PHY_REG		= 0x7026,
+
+	/* Query link diagnosis info command */
+	HCLGE_OPC_QUERY_LINK_DIAGNOSIS	= 0x702A,
 };
 
 #define HCLGE_TQP_REG_OFFSET		0x80000
@@ -450,7 +453,7 @@ struct hclge_tc_thrd {
 };
 
 struct hclge_priv_buf {
-	struct hclge_waterline wl;	/* Waterline for low and high*/
+	struct hclge_waterline wl;	/* Waterline for low and high */
 	u32 buf_size;	/* TC private buffer size */
 	u32 tx_buf_size;
 	u32 enable;	/* Enable TC private buffer or not */
@@ -1014,16 +1017,6 @@ struct hclge_common_lb_cmd {
 
 #define HCLGE_TYPE_CRQ			0
 #define HCLGE_TYPE_CSQ			1
-#define HCLGE_NIC_CSQ_BASEADDR_L_REG	0x27000
-#define HCLGE_NIC_CSQ_BASEADDR_H_REG	0x27004
-#define HCLGE_NIC_CSQ_DEPTH_REG		0x27008
-#define HCLGE_NIC_CSQ_TAIL_REG		0x27010
-#define HCLGE_NIC_CSQ_HEAD_REG		0x27014
-#define HCLGE_NIC_CRQ_BASEADDR_L_REG	0x27018
-#define HCLGE_NIC_CRQ_BASEADDR_H_REG	0x2701c
-#define HCLGE_NIC_CRQ_DEPTH_REG		0x27020
-#define HCLGE_NIC_CRQ_TAIL_REG		0x27024
-#define HCLGE_NIC_CRQ_HEAD_REG		0x27028
 
 /* this bit indicates that the driver is ready for hardware reset */
 #define HCLGE_NIC_SW_RST_RDY_B		16
@@ -1198,6 +1191,19 @@ struct hclge_dev_specs_1_cmd {
 	u8 rsv1[18];
 };
 
+/* mac speed type defined in firmware command */
+enum HCLGE_FIRMWARE_MAC_SPEED {
+	HCLGE_FW_MAC_SPEED_1G,
+	HCLGE_FW_MAC_SPEED_10G,
+	HCLGE_FW_MAC_SPEED_25G,
+	HCLGE_FW_MAC_SPEED_40G,
+	HCLGE_FW_MAC_SPEED_50G,
+	HCLGE_FW_MAC_SPEED_100G,
+	HCLGE_FW_MAC_SPEED_10M,
+	HCLGE_FW_MAC_SPEED_100M,
+	HCLGE_FW_MAC_SPEED_200G,
+};
+
 #define HCLGE_PHY_LINK_SETTING_BD_NUM		2
 
 struct hclge_phy_link_ksetting_0_cmd {
@@ -1228,6 +1234,12 @@ struct hclge_phy_reg_cmd {
 	u8 rsv1[18];
 };
 
+/* capabilities bits map between imp firmware and local driver */
+struct hclge_caps_bit_map {
+	u16 imp_bit;
+	u16 local_bit;
+};
+
 int hclge_cmd_init(struct hclge_dev *hdev);
 static inline void hclge_write_reg(void __iomem *base, u32 reg, u32 value)
 {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index 39f56f245d84..4a619e5d3f35 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -104,26 +104,30 @@ static int hclge_dcb_common_validate(struct hclge_dev *hdev, u8 num_tc,
 	return 0;
 }
 
-static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
-			      u8 *tc, bool *changed)
+static u8 hclge_ets_tc_changed(struct hclge_dev *hdev, struct ieee_ets *ets,
+			       bool *changed)
 {
-	bool has_ets_tc = false;
-	u32 total_ets_bw = 0;
-	u8 max_tc = 0;
-	int ret;
+	u8 max_tc_id = 0;
 	u8 i;
 
 	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
 		if (ets->prio_tc[i] != hdev->tm_info.prio_tc[i])
 			*changed = true;
 
-		if (ets->prio_tc[i] > max_tc)
-			max_tc = ets->prio_tc[i];
+		if (ets->prio_tc[i] > max_tc_id)
+			max_tc_id = ets->prio_tc[i];
 	}
 
-	ret = hclge_dcb_common_validate(hdev, max_tc + 1, ets->prio_tc);
-	if (ret)
-		return ret;
+	/* return max tc number, max tc id need to plus 1 */
+	return max_tc_id + 1;
+}
+
+static int hclge_ets_sch_mode_validate(struct hclge_dev *hdev,
+				       struct ieee_ets *ets, bool *changed)
+{
+	bool has_ets_tc = false;
+	u32 total_ets_bw = 0;
+	u8 i;
 
 	for (i = 0; i < hdev->tc_max; i++) {
 		switch (ets->tc_tsa[i]) {
@@ -148,7 +152,26 @@ static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
 	if (has_ets_tc && total_ets_bw != BW_PERCENT)
 		return -EINVAL;
 
-	*tc = max_tc + 1;
+	return 0;
+}
+
+static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
+			      u8 *tc, bool *changed)
+{
+	u8 tc_num;
+	int ret;
+
+	tc_num = hclge_ets_tc_changed(hdev, ets, changed);
+
+	ret = hclge_dcb_common_validate(hdev, tc_num, ets->prio_tc);
+	if (ret)
+		return ret;
+
+	ret = hclge_ets_sch_mode_validate(hdev, ets, changed);
+	if (ret)
+		return ret;
+
+	*tc = tc_num;
 	if (*tc != hdev->tm_info.num_tc)
 		*changed = true;
 
@@ -234,9 +257,7 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
 		if (ret)
 			goto err_out;
 
-		ret = hclge_notify_init_up(hdev);
-		if (ret)
-			return ret;
+		return hclge_notify_init_up(hdev);
 	}
 
 	return hclge_tm_dwrr_cfg(hdev);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 288788186ecc..68ed1715ac52 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -926,26 +926,45 @@ static int hclge_dbg_dump_tm_nodes(struct hclge_dev *hdev, char *buf, int len)
 	return 0;
 }
 
+static const struct hclge_dbg_item tm_pri_items[] = {
+	{ "ID", 4 },
+	{ "MODE", 2 },
+	{ "DWRR", 2 },
+	{ "C_IR_B", 2 },
+	{ "C_IR_U", 2 },
+	{ "C_IR_S", 2 },
+	{ "C_BS_B", 2 },
+	{ "C_BS_S", 2 },
+	{ "C_FLAG", 2 },
+	{ "C_RATE(Mbps)", 2 },
+	{ "P_IR_B", 2 },
+	{ "P_IR_U", 2 },
+	{ "P_IR_S", 2 },
+	{ "P_BS_B", 2 },
+	{ "P_BS_S", 2 },
+	{ "P_FLAG", 2 },
+	{ "P_RATE(Mbps)", 0 }
+};
+
 static int hclge_dbg_dump_tm_pri(struct hclge_dev *hdev, char *buf, int len)
 {
-	struct hclge_tm_shaper_para c_shaper_para;
-	struct hclge_tm_shaper_para p_shaper_para;
-	u8 pri_num, sch_mode, weight;
-	char *sch_mode_str;
-	int pos = 0;
-	int ret;
-	u8 i;
+	char data_str[ARRAY_SIZE(tm_pri_items)][HCLGE_DBG_DATA_STR_LEN];
+	struct hclge_tm_shaper_para c_shaper_para, p_shaper_para;
+	char *result[ARRAY_SIZE(tm_pri_items)], *sch_mode_str;
+	char content[HCLGE_DBG_TM_INFO_LEN];
+	u8 pri_num, sch_mode, weight, i, j;
+	int pos, ret;
 
 	ret = hclge_tm_get_pri_num(hdev, &pri_num);
 	if (ret)
 		return ret;
 
-	pos += scnprintf(buf + pos, len - pos,
-			 "ID    MODE  DWRR  C_IR_B  C_IR_U  C_IR_S  C_BS_B  ");
-	pos += scnprintf(buf + pos, len - pos,
-			 "C_BS_S  C_FLAG  C_RATE(Mbps)  P_IR_B  P_IR_U  ");
-	pos += scnprintf(buf + pos, len - pos,
-			 "P_IR_S  P_BS_B  P_BS_S  P_FLAG  P_RATE(Mbps)\n");
+	for (i = 0; i < ARRAY_SIZE(tm_pri_items); i++)
+		result[i] = &data_str[i][0];
+
+	hclge_dbg_fill_content(content, sizeof(content), tm_pri_items,
+			       NULL, ARRAY_SIZE(tm_pri_items));
+	pos = scnprintf(buf, len, "%s", content);
 
 	for (i = 0; i < pri_num; i++) {
 		ret = hclge_tm_get_pri_sch_mode(hdev, i, &sch_mode);
@@ -971,21 +990,16 @@ static int hclge_dbg_dump_tm_pri(struct hclge_dev *hdev, char *buf, int len)
 		sch_mode_str = sch_mode & HCLGE_TM_TX_SCHD_DWRR_MSK ? "dwrr" :
 			       "sp";
 
-		pos += scnprintf(buf + pos, len - pos,
-				 "%04u  %4s  %3u   %3u     %3u     %3u     ",
-				 i, sch_mode_str, weight, c_shaper_para.ir_b,
-				 c_shaper_para.ir_u, c_shaper_para.ir_s);
-		pos += scnprintf(buf + pos, len - pos,
-				 "%3u     %3u       %1u     %6u        ",
-				 c_shaper_para.bs_b, c_shaper_para.bs_s,
-				 c_shaper_para.flag, c_shaper_para.rate);
-		pos += scnprintf(buf + pos, len - pos,
-				 "%3u     %3u     %3u     %3u     %3u       ",
-				 p_shaper_para.ir_b, p_shaper_para.ir_u,
-				 p_shaper_para.ir_s, p_shaper_para.bs_b,
-				 p_shaper_para.bs_s);
-		pos += scnprintf(buf + pos, len - pos, "%1u     %6u\n",
-				 p_shaper_para.flag, p_shaper_para.rate);
+		j = 0;
+		sprintf(result[j++], "%04u", i);
+		sprintf(result[j++], "%4s", sch_mode_str);
+		sprintf(result[j++], "%3u", weight);
+		hclge_dbg_fill_shaper_content(&c_shaper_para, result, &j);
+		hclge_dbg_fill_shaper_content(&p_shaper_para, result, &j);
+		hclge_dbg_fill_content(content, sizeof(content), tm_pri_items,
+				       (const char **)result,
+				       ARRAY_SIZE(tm_pri_items));
+		pos += scnprintf(buf + pos, len - pos, "%s", content);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c
new file mode 100644
index 000000000000..e4aad695abcc
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (c) 2021 Hisilicon Limited. */
+
+#include <net/devlink.h>
+
+#include "hclge_devlink.h"
+
+static int hclge_devlink_info_get(struct devlink *devlink,
+				  struct devlink_info_req *req,
+				  struct netlink_ext_ack *extack)
+{
+#define	HCLGE_DEVLINK_FW_STRING_LEN	32
+	struct hclge_devlink_priv *priv = devlink_priv(devlink);
+	char version_str[HCLGE_DEVLINK_FW_STRING_LEN];
+	struct hclge_dev *hdev = priv->hdev;
+	int ret;
+
+	ret = devlink_info_driver_name_put(req, KBUILD_MODNAME);
+	if (ret)
+		return ret;
+
+	snprintf(version_str, sizeof(version_str), "%lu.%lu.%lu.%lu",
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE3_MASK,
+				 HNAE3_FW_VERSION_BYTE3_SHIFT),
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE2_MASK,
+				 HNAE3_FW_VERSION_BYTE2_SHIFT),
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE1_MASK,
+				 HNAE3_FW_VERSION_BYTE1_SHIFT),
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE0_MASK,
+				 HNAE3_FW_VERSION_BYTE0_SHIFT));
+
+	return devlink_info_version_running_put(req,
+						DEVLINK_INFO_VERSION_GENERIC_FW,
+						version_str);
+}
+
+static int hclge_devlink_reload_down(struct devlink *devlink, bool netns_change,
+				     enum devlink_reload_action action,
+				     enum devlink_reload_limit limit,
+				     struct netlink_ext_ack *extack)
+{
+	struct hclge_devlink_priv *priv = devlink_priv(devlink);
+	struct hclge_dev *hdev = priv->hdev;
+	struct hnae3_handle *h = &hdev->vport->nic;
+	struct pci_dev *pdev = hdev->pdev;
+	int ret;
+
+	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) {
+		dev_err(&pdev->dev, "reset is handling\n");
+		return -EBUSY;
+	}
+
+	switch (action) {
+	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
+		rtnl_lock();
+		ret = hdev->nic_client->ops->reset_notify(h, HNAE3_DOWN_CLIENT);
+		if (ret) {
+			rtnl_unlock();
+			return ret;
+		}
+
+		ret = hdev->nic_client->ops->reset_notify(h,
+							  HNAE3_UNINIT_CLIENT);
+		rtnl_unlock();
+		return ret;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int hclge_devlink_reload_up(struct devlink *devlink,
+				   enum devlink_reload_action action,
+				   enum devlink_reload_limit limit,
+				   u32 *actions_performed,
+				   struct netlink_ext_ack *extack)
+{
+	struct hclge_devlink_priv *priv = devlink_priv(devlink);
+	struct hclge_dev *hdev = priv->hdev;
+	struct hnae3_handle *h = &hdev->vport->nic;
+	int ret;
+
+	*actions_performed = BIT(action);
+	switch (action) {
+	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
+		rtnl_lock();
+		ret = hdev->nic_client->ops->reset_notify(h, HNAE3_INIT_CLIENT);
+		if (ret) {
+			rtnl_unlock();
+			return ret;
+		}
+
+		ret = hdev->nic_client->ops->reset_notify(h, HNAE3_UP_CLIENT);
+		rtnl_unlock();
+		return ret;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct devlink_ops hclge_devlink_ops = {
+	.info_get = hclge_devlink_info_get,
+	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
+	.reload_down = hclge_devlink_reload_down,
+	.reload_up = hclge_devlink_reload_up,
+};
+
+int hclge_devlink_init(struct hclge_dev *hdev)
+{
+	struct pci_dev *pdev = hdev->pdev;
+	struct hclge_devlink_priv *priv;
+	struct devlink *devlink;
+	int ret;
+
+	devlink = devlink_alloc(&hclge_devlink_ops,
+				sizeof(struct hclge_devlink_priv), &pdev->dev);
+	if (!devlink)
+		return -ENOMEM;
+
+	priv = devlink_priv(devlink);
+	priv->hdev = hdev;
+	hdev->devlink = devlink;
+
+	ret = devlink_register(devlink);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register devlink, ret = %d\n",
+			ret);
+		goto out_reg_fail;
+	}
+
+	devlink_reload_enable(devlink);
+
+	return 0;
+
+out_reg_fail:
+	devlink_free(devlink);
+	return ret;
+}
+
+void hclge_devlink_uninit(struct hclge_dev *hdev)
+{
+	struct devlink *devlink = hdev->devlink;
+
+	devlink_reload_disable(devlink);
+
+	devlink_unregister(devlink);
+
+	devlink_free(devlink);
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.h
new file mode 100644
index 000000000000..918be04507a5
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2021 Hisilicon Limited. */
+
+#ifndef __HCLGE_DEVLINK_H
+#define __HCLGE_DEVLINK_H
+
+#include "hclge_main.h"
+
+struct hclge_devlink_priv {
+	struct hclge_dev *hdev;
+};
+
+int hclge_devlink_init(struct hclge_dev *hdev);
+void hclge_devlink_uninit(struct hclge_dev *hdev);
+#endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index ec9a7f8bc3fe..718c16d686fa 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -4,468 +4,895 @@
 #include "hclge_err.h"
 
 static const struct hclge_hw_error hclge_imp_tcm_ecc_int[] = {
-	{ .int_msk = BIT(1), .msg = "imp_itcm0_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(3), .msg = "imp_itcm1_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(5), .msg = "imp_itcm2_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(7), .msg = "imp_itcm3_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(9), .msg = "imp_dtcm0_mem0_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(11), .msg = "imp_dtcm0_mem1_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(13), .msg = "imp_dtcm1_mem0_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(15), .msg = "imp_dtcm1_mem1_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(17), .msg = "imp_itcm4_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(1),
+		.msg = "imp_itcm0_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "imp_itcm1_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "imp_itcm2_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(7),
+		.msg = "imp_itcm3_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(9),
+		.msg = "imp_dtcm0_mem0_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(11),
+		.msg = "imp_dtcm0_mem1_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(13),
+		.msg = "imp_dtcm1_mem0_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(15),
+		.msg = "imp_dtcm1_mem1_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(17),
+		.msg = "imp_itcm4_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_cmdq_nic_mem_ecc_int[] = {
-	{ .int_msk = BIT(1), .msg = "cmdq_nic_rx_depth_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(3), .msg = "cmdq_nic_tx_depth_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(5), .msg = "cmdq_nic_rx_tail_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(7), .msg = "cmdq_nic_tx_tail_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(9), .msg = "cmdq_nic_rx_head_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(11), .msg = "cmdq_nic_tx_head_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(13), .msg = "cmdq_nic_rx_addr_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(15), .msg = "cmdq_nic_tx_addr_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(17), .msg = "cmdq_rocee_rx_depth_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(19), .msg = "cmdq_rocee_tx_depth_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(21), .msg = "cmdq_rocee_rx_tail_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(23), .msg = "cmdq_rocee_tx_tail_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(25), .msg = "cmdq_rocee_rx_head_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(27), .msg = "cmdq_rocee_tx_head_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(29), .msg = "cmdq_rocee_rx_addr_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(31), .msg = "cmdq_rocee_tx_addr_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(1),
+		.msg = "cmdq_nic_rx_depth_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "cmdq_nic_tx_depth_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "cmdq_nic_rx_tail_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(7),
+		.msg = "cmdq_nic_tx_tail_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(9),
+		.msg = "cmdq_nic_rx_head_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(11),
+		.msg = "cmdq_nic_tx_head_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(13),
+		.msg = "cmdq_nic_rx_addr_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(15),
+		.msg = "cmdq_nic_tx_addr_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(17),
+		.msg = "cmdq_rocee_rx_depth_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(19),
+		.msg = "cmdq_rocee_tx_depth_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(21),
+		.msg = "cmdq_rocee_rx_tail_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(23),
+		.msg = "cmdq_rocee_tx_tail_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(25),
+		.msg = "cmdq_rocee_rx_head_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(27),
+		.msg = "cmdq_rocee_tx_head_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(29),
+		.msg = "cmdq_rocee_rx_addr_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(31),
+		.msg = "cmdq_rocee_tx_addr_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_tqp_int_ecc_int[] = {
-	{ .int_msk = BIT(6), .msg = "tqp_int_cfg_even_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(7), .msg = "tqp_int_cfg_odd_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(8), .msg = "tqp_int_ctrl_even_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(9), .msg = "tqp_int_ctrl_odd_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(10), .msg = "tx_que_scan_int_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(11), .msg = "rx_que_scan_int_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(6),
+		.msg = "tqp_int_cfg_even_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(7),
+		.msg = "tqp_int_cfg_odd_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(8),
+		.msg = "tqp_int_ctrl_even_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(9),
+		.msg = "tqp_int_ctrl_odd_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(10),
+		.msg = "tx_que_scan_int_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(11),
+		.msg = "rx_que_scan_int_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_msix_sram_ecc_int[] = {
-	{ .int_msk = BIT(1), .msg = "msix_nic_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(3), .msg = "msix_rocee_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(1),
+		.msg = "msix_nic_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "msix_rocee_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_igu_int[] = {
-	{ .int_msk = BIT(0), .msg = "igu_rx_buf0_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(2), .msg = "igu_rx_buf1_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "igu_rx_buf0_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(2),
+		.msg = "igu_rx_buf1_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_igu_egu_tnl_int[] = {
-	{ .int_msk = BIT(0), .msg = "rx_buf_overflow",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(1), .msg = "rx_stp_fifo_overflow",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(2), .msg = "rx_stp_fifo_underflow",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(3), .msg = "tx_buf_overflow",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(4), .msg = "tx_buf_underrun",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(5), .msg = "rx_stp_buf_overflow",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "rx_buf_overflow",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(1),
+		.msg = "rx_stp_fifo_overflow",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(2),
+		.msg = "rx_stp_fifo_underflow",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "tx_buf_overflow",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(4),
+		.msg = "tx_buf_underrun",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "rx_stp_buf_overflow",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_ncsi_err_int[] = {
-	{ .int_msk = BIT(1), .msg = "ncsi_tx_ecc_mbit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(1),
+		.msg = "ncsi_tx_ecc_mbit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st1[] = {
-	{ .int_msk = BIT(0), .msg = "vf_vlan_ad_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(1), .msg = "umv_mcast_group_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(2), .msg = "umv_key_mem0_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(3), .msg = "umv_key_mem1_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(4), .msg = "umv_key_mem2_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(5), .msg = "umv_key_mem3_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(6), .msg = "umv_ad_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(7), .msg = "rss_tc_mode_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(8), .msg = "rss_idt_mem0_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(9), .msg = "rss_idt_mem1_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(10), .msg = "rss_idt_mem2_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(11), .msg = "rss_idt_mem3_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(12), .msg = "rss_idt_mem4_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(13), .msg = "rss_idt_mem5_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(14), .msg = "rss_idt_mem6_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(15), .msg = "rss_idt_mem7_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(16), .msg = "rss_idt_mem8_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(17), .msg = "rss_idt_mem9_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(18), .msg = "rss_idt_mem10_ecc_m1bit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(19), .msg = "rss_idt_mem11_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(20), .msg = "rss_idt_mem12_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(21), .msg = "rss_idt_mem13_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(22), .msg = "rss_idt_mem14_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(23), .msg = "rss_idt_mem15_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(24), .msg = "port_vlan_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(25), .msg = "mcast_linear_table_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(26), .msg = "mcast_result_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(27), .msg = "flow_director_ad_mem0_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(28), .msg = "flow_director_ad_mem1_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(29), .msg = "rx_vlan_tag_memory_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(30), .msg = "Tx_UP_mapping_config_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "vf_vlan_ad_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(1),
+		.msg = "umv_mcast_group_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(2),
+		.msg = "umv_key_mem0_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "umv_key_mem1_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(4),
+		.msg = "umv_key_mem2_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "umv_key_mem3_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(6),
+		.msg = "umv_ad_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(7),
+		.msg = "rss_tc_mode_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(8),
+		.msg = "rss_idt_mem0_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(9),
+		.msg = "rss_idt_mem1_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(10),
+		.msg = "rss_idt_mem2_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(11),
+		.msg = "rss_idt_mem3_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(12),
+		.msg = "rss_idt_mem4_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(13),
+		.msg = "rss_idt_mem5_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(14),
+		.msg = "rss_idt_mem6_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(15),
+		.msg = "rss_idt_mem7_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(16),
+		.msg = "rss_idt_mem8_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(17),
+		.msg = "rss_idt_mem9_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(18),
+		.msg = "rss_idt_mem10_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(19),
+		.msg = "rss_idt_mem11_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(20),
+		.msg = "rss_idt_mem12_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(21),
+		.msg = "rss_idt_mem13_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(22),
+		.msg = "rss_idt_mem14_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(23),
+		.msg = "rss_idt_mem15_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(24),
+		.msg = "port_vlan_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(25),
+		.msg = "mcast_linear_table_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(26),
+		.msg = "mcast_result_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(27),
+		.msg = "flow_director_ad_mem0_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(28),
+		.msg = "flow_director_ad_mem1_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(29),
+		.msg = "rx_vlan_tag_memory_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(30),
+		.msg = "Tx_UP_mapping_config_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_ppp_pf_abnormal_int[] = {
-	{ .int_msk = BIT(0), .msg = "tx_vlan_tag_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(1), .msg = "rss_list_tc_unassigned_queue_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "tx_vlan_tag_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(1),
+		.msg = "rss_list_tc_unassigned_queue_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st3[] = {
-	{ .int_msk = BIT(0), .msg = "hfs_fifo_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(1), .msg = "rslt_descr_fifo_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(2), .msg = "tx_vlan_tag_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(3), .msg = "FD_CN0_memory_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(4), .msg = "FD_CN1_memory_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(5), .msg = "GRO_AD_memory_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "hfs_fifo_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(1),
+		.msg = "rslt_descr_fifo_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(2),
+		.msg = "tx_vlan_tag_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "FD_CN0_memory_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(4),
+		.msg = "FD_CN1_memory_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "GRO_AD_memory_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_tm_sch_rint[] = {
-	{ .int_msk = BIT(1), .msg = "tm_sch_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(2), .msg = "tm_sch_port_shap_sub_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(3), .msg = "tm_sch_port_shap_sub_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(4), .msg = "tm_sch_pg_pshap_sub_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(5), .msg = "tm_sch_pg_pshap_sub_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(6), .msg = "tm_sch_pg_cshap_sub_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(7), .msg = "tm_sch_pg_cshap_sub_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(8), .msg = "tm_sch_pri_pshap_sub_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(9), .msg = "tm_sch_pri_pshap_sub_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(10), .msg = "tm_sch_pri_cshap_sub_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(11), .msg = "tm_sch_pri_cshap_sub_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(12), .msg = "tm_sch_port_shap_offset_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(13), .msg = "tm_sch_port_shap_offset_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(14), .msg = "tm_sch_pg_pshap_offset_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(15), .msg = "tm_sch_pg_pshap_offset_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(16), .msg = "tm_sch_pg_cshap_offset_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(17), .msg = "tm_sch_pg_cshap_offset_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(18), .msg = "tm_sch_pri_pshap_offset_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(19), .msg = "tm_sch_pri_pshap_offset_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(20), .msg = "tm_sch_pri_cshap_offset_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(21), .msg = "tm_sch_pri_cshap_offset_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(22), .msg = "tm_sch_rq_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(23), .msg = "tm_sch_rq_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(24), .msg = "tm_sch_nq_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(25), .msg = "tm_sch_nq_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(26), .msg = "tm_sch_roce_up_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(27), .msg = "tm_sch_roce_up_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(28), .msg = "tm_sch_rcb_byte_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(29), .msg = "tm_sch_rcb_byte_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(30), .msg = "tm_sch_ssu_byte_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(31), .msg = "tm_sch_ssu_byte_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(1),
+		.msg = "tm_sch_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(2),
+		.msg = "tm_sch_port_shap_sub_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "tm_sch_port_shap_sub_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(4),
+		.msg = "tm_sch_pg_pshap_sub_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "tm_sch_pg_pshap_sub_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(6),
+		.msg = "tm_sch_pg_cshap_sub_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(7),
+		.msg = "tm_sch_pg_cshap_sub_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(8),
+		.msg = "tm_sch_pri_pshap_sub_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(9),
+		.msg = "tm_sch_pri_pshap_sub_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(10),
+		.msg = "tm_sch_pri_cshap_sub_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(11),
+		.msg = "tm_sch_pri_cshap_sub_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(12),
+		.msg = "tm_sch_port_shap_offset_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(13),
+		.msg = "tm_sch_port_shap_offset_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(14),
+		.msg = "tm_sch_pg_pshap_offset_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(15),
+		.msg = "tm_sch_pg_pshap_offset_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(16),
+		.msg = "tm_sch_pg_cshap_offset_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(17),
+		.msg = "tm_sch_pg_cshap_offset_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(18),
+		.msg = "tm_sch_pri_pshap_offset_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(19),
+		.msg = "tm_sch_pri_pshap_offset_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(20),
+		.msg = "tm_sch_pri_cshap_offset_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(21),
+		.msg = "tm_sch_pri_cshap_offset_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(22),
+		.msg = "tm_sch_rq_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(23),
+		.msg = "tm_sch_rq_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(24),
+		.msg = "tm_sch_nq_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(25),
+		.msg = "tm_sch_nq_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(26),
+		.msg = "tm_sch_roce_up_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(27),
+		.msg = "tm_sch_roce_up_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(28),
+		.msg = "tm_sch_rcb_byte_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(29),
+		.msg = "tm_sch_rcb_byte_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(30),
+		.msg = "tm_sch_ssu_byte_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(31),
+		.msg = "tm_sch_ssu_byte_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_qcn_fifo_rint[] = {
-	{ .int_msk = BIT(0), .msg = "qcn_shap_gp0_sch_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(1), .msg = "qcn_shap_gp0_sch_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(2), .msg = "qcn_shap_gp1_sch_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(3), .msg = "qcn_shap_gp1_sch_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(4), .msg = "qcn_shap_gp2_sch_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(5), .msg = "qcn_shap_gp2_sch_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(6), .msg = "qcn_shap_gp3_sch_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(7), .msg = "qcn_shap_gp3_sch_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(8), .msg = "qcn_shap_gp0_offset_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(9), .msg = "qcn_shap_gp0_offset_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(10), .msg = "qcn_shap_gp1_offset_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(11), .msg = "qcn_shap_gp1_offset_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(12), .msg = "qcn_shap_gp2_offset_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(13), .msg = "qcn_shap_gp2_offset_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(14), .msg = "qcn_shap_gp3_offset_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(15), .msg = "qcn_shap_gp3_offset_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(16), .msg = "qcn_byte_info_fifo_rd_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(17), .msg = "qcn_byte_info_fifo_wr_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "qcn_shap_gp0_sch_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(1),
+		.msg = "qcn_shap_gp0_sch_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(2),
+		.msg = "qcn_shap_gp1_sch_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "qcn_shap_gp1_sch_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(4),
+		.msg = "qcn_shap_gp2_sch_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "qcn_shap_gp2_sch_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(6),
+		.msg = "qcn_shap_gp3_sch_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(7),
+		.msg = "qcn_shap_gp3_sch_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(8),
+		.msg = "qcn_shap_gp0_offset_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(9),
+		.msg = "qcn_shap_gp0_offset_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(10),
+		.msg = "qcn_shap_gp1_offset_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(11),
+		.msg = "qcn_shap_gp1_offset_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(12),
+		.msg = "qcn_shap_gp2_offset_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(13),
+		.msg = "qcn_shap_gp2_offset_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(14),
+		.msg = "qcn_shap_gp3_offset_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(15),
+		.msg = "qcn_shap_gp3_offset_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(16),
+		.msg = "qcn_byte_info_fifo_rd_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(17),
+		.msg = "qcn_byte_info_fifo_wr_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_qcn_ecc_rint[] = {
-	{ .int_msk = BIT(1), .msg = "qcn_byte_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(3), .msg = "qcn_time_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(5), .msg = "qcn_fb_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(7), .msg = "qcn_link_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(9), .msg = "qcn_rate_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(11), .msg = "qcn_tmplt_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(13), .msg = "qcn_shap_cfg_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(15), .msg = "qcn_gp0_barrel_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(17), .msg = "qcn_gp1_barrel_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(19), .msg = "qcn_gp2_barrel_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(21), .msg = "qcn_gp3_barral_mem_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(1),
+		.msg = "qcn_byte_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "qcn_time_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "qcn_fb_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(7),
+		.msg = "qcn_link_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(9),
+		.msg = "qcn_rate_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(11),
+		.msg = "qcn_tmplt_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(13),
+		.msg = "qcn_shap_cfg_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(15),
+		.msg = "qcn_gp0_barrel_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(17),
+		.msg = "qcn_gp1_barrel_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(19),
+		.msg = "qcn_gp2_barrel_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(21),
+		.msg = "qcn_gp3_barral_mem_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_mac_afifo_tnl_int[] = {
-	{ .int_msk = BIT(0), .msg = "egu_cge_afifo_ecc_1bit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(1), .msg = "egu_cge_afifo_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(2), .msg = "egu_lge_afifo_ecc_1bit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(3), .msg = "egu_lge_afifo_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(4), .msg = "cge_igu_afifo_ecc_1bit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(5), .msg = "cge_igu_afifo_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(6), .msg = "lge_igu_afifo_ecc_1bit_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(7), .msg = "lge_igu_afifo_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(8), .msg = "cge_igu_afifo_overflow_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(9), .msg = "lge_igu_afifo_overflow_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(10), .msg = "egu_cge_afifo_underrun_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(11), .msg = "egu_lge_afifo_underrun_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(12), .msg = "egu_ge_afifo_underrun_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(13), .msg = "ge_igu_afifo_overflow_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "egu_cge_afifo_ecc_1bit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(1),
+		.msg = "egu_cge_afifo_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(2),
+		.msg = "egu_lge_afifo_ecc_1bit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "egu_lge_afifo_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(4),
+		.msg = "cge_igu_afifo_ecc_1bit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "cge_igu_afifo_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(6),
+		.msg = "lge_igu_afifo_ecc_1bit_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(7),
+		.msg = "lge_igu_afifo_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(8),
+		.msg = "cge_igu_afifo_overflow_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(9),
+		.msg = "lge_igu_afifo_overflow_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(10),
+		.msg = "egu_cge_afifo_underrun_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(11),
+		.msg = "egu_lge_afifo_underrun_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(12),
+		.msg = "egu_ge_afifo_underrun_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(13),
+		.msg = "ge_igu_afifo_overflow_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_ppu_mpf_abnormal_int_st2[] = {
-	{ .int_msk = BIT(13), .msg = "rpu_rx_pkt_bit32_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(14), .msg = "rpu_rx_pkt_bit33_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(15), .msg = "rpu_rx_pkt_bit34_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(16), .msg = "rpu_rx_pkt_bit35_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(17), .msg = "rcb_tx_ring_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(18), .msg = "rcb_rx_ring_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(19), .msg = "rcb_tx_fbd_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(20), .msg = "rcb_rx_ebd_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(21), .msg = "rcb_tso_info_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(22), .msg = "rcb_tx_int_info_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(23), .msg = "rcb_rx_int_info_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(24), .msg = "tpu_tx_pkt_0_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(25), .msg = "tpu_tx_pkt_1_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(26), .msg = "rd_bus_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(27), .msg = "wr_bus_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(28), .msg = "reg_search_miss",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(29), .msg = "rx_q_search_miss",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(30), .msg = "ooo_ecc_err_detect",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(31), .msg = "ooo_ecc_err_multpl",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(13),
+		.msg = "rpu_rx_pkt_bit32_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(14),
+		.msg = "rpu_rx_pkt_bit33_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(15),
+		.msg = "rpu_rx_pkt_bit34_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(16),
+		.msg = "rpu_rx_pkt_bit35_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(17),
+		.msg = "rcb_tx_ring_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(18),
+		.msg = "rcb_rx_ring_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(19),
+		.msg = "rcb_tx_fbd_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(20),
+		.msg = "rcb_rx_ebd_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(21),
+		.msg = "rcb_tso_info_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(22),
+		.msg = "rcb_tx_int_info_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(23),
+		.msg = "rcb_rx_int_info_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(24),
+		.msg = "tpu_tx_pkt_0_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(25),
+		.msg = "tpu_tx_pkt_1_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(26),
+		.msg = "rd_bus_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(27),
+		.msg = "wr_bus_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(28),
+		.msg = "reg_search_miss",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(29),
+		.msg = "rx_q_search_miss",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(30),
+		.msg = "ooo_ecc_err_detect",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(31),
+		.msg = "ooo_ecc_err_multpl",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_ppu_mpf_abnormal_int_st3[] = {
-	{ .int_msk = BIT(4), .msg = "gro_bd_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(5), .msg = "gro_context_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(6), .msg = "rx_stash_cfg_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(7), .msg = "axi_rd_fbd_ecc_mbit_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(4),
+		.msg = "gro_bd_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "gro_context_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(6),
+		.msg = "rx_stash_cfg_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(7),
+		.msg = "axi_rd_fbd_ecc_mbit_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_ppu_pf_abnormal_int[] = {
-	{ .int_msk = BIT(0), .msg = "over_8bd_no_fe",
-	  .reset_level = HNAE3_FUNC_RESET },
-	{ .int_msk = BIT(1), .msg = "tso_mss_cmp_min_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(2), .msg = "tso_mss_cmp_max_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(3), .msg = "tx_rd_fbd_poison",
-	  .reset_level = HNAE3_FUNC_RESET },
-	{ .int_msk = BIT(4), .msg = "rx_rd_ebd_poison",
-	  .reset_level = HNAE3_FUNC_RESET },
-	{ .int_msk = BIT(5), .msg = "buf_wait_timeout",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "over_8bd_no_fe",
+		.reset_level = HNAE3_FUNC_RESET
+	}, {
+		.int_msk = BIT(1),
+		.msg = "tso_mss_cmp_min_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(2),
+		.msg = "tso_mss_cmp_max_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "tx_rd_fbd_poison",
+		.reset_level = HNAE3_FUNC_RESET
+	}, {
+		.int_msk = BIT(4),
+		.msg = "rx_rd_ebd_poison",
+		.reset_level = HNAE3_FUNC_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "buf_wait_timeout",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_ssu_com_err_int[] = {
-	{ .int_msk = BIT(0), .msg = "buf_sum_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(1), .msg = "ppp_mb_num_err",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(2), .msg = "ppp_mbid_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(3), .msg = "ppp_rlt_mac_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(4), .msg = "ppp_rlt_host_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(5), .msg = "cks_edit_position_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(6), .msg = "cks_edit_condition_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(7), .msg = "vlan_edit_condition_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(8), .msg = "vlan_num_ot_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(9), .msg = "vlan_num_in_err",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "buf_sum_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(1),
+		.msg = "ppp_mb_num_err",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(2),
+		.msg = "ppp_mbid_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "ppp_rlt_mac_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(4),
+		.msg = "ppp_rlt_host_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "cks_edit_position_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(6),
+		.msg = "cks_edit_condition_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(7),
+		.msg = "vlan_edit_condition_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(8),
+		.msg = "vlan_num_ot_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(9),
+		.msg = "vlan_num_in_err",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 #define HCLGE_SSU_MEM_ECC_ERR(x) \
-	{ .int_msk = BIT(x), .msg = "ssu_mem" #x "_ecc_mbit_err", \
-	  .reset_level = HNAE3_GLOBAL_RESET }
+{ \
+	.int_msk = BIT(x), \
+	.msg = "ssu_mem" #x "_ecc_mbit_err", \
+	.reset_level = HNAE3_GLOBAL_RESET \
+}
 
 static const struct hclge_hw_error hclge_ssu_mem_ecc_err_int[] = {
 	HCLGE_SSU_MEM_ECC_ERR(0),
@@ -504,131 +931,269 @@ static const struct hclge_hw_error hclge_ssu_mem_ecc_err_int[] = {
 };
 
 static const struct hclge_hw_error hclge_ssu_port_based_err_int[] = {
-	{ .int_msk = BIT(0), .msg = "roc_pkt_without_key_port",
-	  .reset_level = HNAE3_FUNC_RESET },
-	{ .int_msk = BIT(1), .msg = "tpu_pkt_without_key_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(2), .msg = "igu_pkt_without_key_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(3), .msg = "roc_eof_mis_match_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(4), .msg = "tpu_eof_mis_match_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(5), .msg = "igu_eof_mis_match_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(6), .msg = "roc_sof_mis_match_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(7), .msg = "tpu_sof_mis_match_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(8), .msg = "igu_sof_mis_match_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(11), .msg = "ets_rd_int_rx_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(12), .msg = "ets_wr_int_rx_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(13), .msg = "ets_rd_int_tx_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(14), .msg = "ets_wr_int_tx_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "roc_pkt_without_key_port",
+		.reset_level = HNAE3_FUNC_RESET
+	}, {
+		.int_msk = BIT(1),
+		.msg = "tpu_pkt_without_key_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(2),
+		.msg = "igu_pkt_without_key_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "roc_eof_mis_match_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(4),
+		.msg = "tpu_eof_mis_match_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "igu_eof_mis_match_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(6),
+		.msg = "roc_sof_mis_match_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(7),
+		.msg = "tpu_sof_mis_match_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(8),
+		.msg = "igu_sof_mis_match_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(11),
+		.msg = "ets_rd_int_rx_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(12),
+		.msg = "ets_wr_int_rx_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(13),
+		.msg = "ets_rd_int_tx_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(14),
+		.msg = "ets_wr_int_tx_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_ssu_fifo_overflow_int[] = {
-	{ .int_msk = BIT(0), .msg = "ig_mac_inf_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(1), .msg = "ig_host_inf_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(2), .msg = "ig_roc_buf_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(3), .msg = "ig_host_data_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(4), .msg = "ig_host_key_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(5), .msg = "tx_qcn_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(6), .msg = "rx_qcn_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(7), .msg = "tx_pf_rd_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(8), .msg = "rx_pf_rd_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(9), .msg = "qm_eof_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(10), .msg = "mb_rlt_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(11), .msg = "dup_uncopy_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(12), .msg = "dup_cnt_rd_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(13), .msg = "dup_cnt_drop_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(14), .msg = "dup_cnt_wrb_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(15), .msg = "host_cmd_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(16), .msg = "mac_cmd_fifo_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(17), .msg = "host_cmd_bitmap_empty_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(18), .msg = "mac_cmd_bitmap_empty_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(19), .msg = "dup_bitmap_empty_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(20), .msg = "out_queue_bitmap_empty_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(21), .msg = "bank2_bitmap_empty_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(22), .msg = "bank1_bitmap_empty_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(23), .msg = "bank0_bitmap_empty_int",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "ig_mac_inf_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(1),
+		.msg = "ig_host_inf_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(2),
+		.msg = "ig_roc_buf_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "ig_host_data_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(4),
+		.msg = "ig_host_key_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(5),
+		.msg = "tx_qcn_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(6),
+		.msg = "rx_qcn_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(7),
+		.msg = "tx_pf_rd_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(8),
+		.msg = "rx_pf_rd_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(9),
+		.msg = "qm_eof_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(10),
+		.msg = "mb_rlt_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(11),
+		.msg = "dup_uncopy_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(12),
+		.msg = "dup_cnt_rd_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(13),
+		.msg = "dup_cnt_drop_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(14),
+		.msg = "dup_cnt_wrb_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(15),
+		.msg = "host_cmd_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(16),
+		.msg = "mac_cmd_fifo_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(17),
+		.msg = "host_cmd_bitmap_empty_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(18),
+		.msg = "mac_cmd_bitmap_empty_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(19),
+		.msg = "dup_bitmap_empty_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(20),
+		.msg = "out_queue_bitmap_empty_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(21),
+		.msg = "bank2_bitmap_empty_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(22),
+		.msg = "bank1_bitmap_empty_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(23),
+		.msg = "bank0_bitmap_empty_int",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_ssu_ets_tcg_int[] = {
-	{ .int_msk = BIT(0), .msg = "ets_rd_int_rx_tcg",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(1), .msg = "ets_wr_int_rx_tcg",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(2), .msg = "ets_rd_int_tx_tcg",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ .int_msk = BIT(3), .msg = "ets_wr_int_tx_tcg",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "ets_rd_int_rx_tcg",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(1),
+		.msg = "ets_wr_int_rx_tcg",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(2),
+		.msg = "ets_rd_int_tx_tcg",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		.int_msk = BIT(3),
+		.msg = "ets_wr_int_tx_tcg",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_ssu_port_based_pf_int[] = {
-	{ .int_msk = BIT(0), .msg = "roc_pkt_without_key_port",
-	  .reset_level = HNAE3_FUNC_RESET },
-	{ .int_msk = BIT(9), .msg = "low_water_line_err_port",
-	  .reset_level = HNAE3_NONE_RESET },
-	{ .int_msk = BIT(10), .msg = "hi_water_line_err_port",
-	  .reset_level = HNAE3_GLOBAL_RESET },
-	{ /* sentinel */ }
+	{
+		.int_msk = BIT(0),
+		.msg = "roc_pkt_without_key_port",
+		.reset_level = HNAE3_FUNC_RESET
+	}, {
+		.int_msk = BIT(9),
+		.msg = "low_water_line_err_port",
+		.reset_level = HNAE3_NONE_RESET
+	}, {
+		.int_msk = BIT(10),
+		.msg = "hi_water_line_err_port",
+		.reset_level = HNAE3_GLOBAL_RESET
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_error hclge_rocee_qmm_ovf_err_int[] = {
-	{ .int_msk = 0, .msg = "rocee qmm ovf: sgid invalid err" },
-	{ .int_msk = 0x4, .msg = "rocee qmm ovf: sgid ovf err" },
-	{ .int_msk = 0x8, .msg = "rocee qmm ovf: smac invalid err" },
-	{ .int_msk = 0xC, .msg = "rocee qmm ovf: smac ovf err" },
-	{ .int_msk = 0x10, .msg = "rocee qmm ovf: cqc invalid err" },
-	{ .int_msk = 0x11, .msg = "rocee qmm ovf: cqc ovf err" },
-	{ .int_msk = 0x12, .msg = "rocee qmm ovf: cqc hopnum err" },
-	{ .int_msk = 0x13, .msg = "rocee qmm ovf: cqc ba0 err" },
-	{ .int_msk = 0x14, .msg = "rocee qmm ovf: srqc invalid err" },
-	{ .int_msk = 0x15, .msg = "rocee qmm ovf: srqc ovf err" },
-	{ .int_msk = 0x16, .msg = "rocee qmm ovf: srqc hopnum err" },
-	{ .int_msk = 0x17, .msg = "rocee qmm ovf: srqc ba0 err" },
-	{ .int_msk = 0x18, .msg = "rocee qmm ovf: mpt invalid err" },
-	{ .int_msk = 0x19, .msg = "rocee qmm ovf: mpt ovf err" },
-	{ .int_msk = 0x1A, .msg = "rocee qmm ovf: mpt hopnum err" },
-	{ .int_msk = 0x1B, .msg = "rocee qmm ovf: mpt ba0 err" },
-	{ .int_msk = 0x1C, .msg = "rocee qmm ovf: qpc invalid err" },
-	{ .int_msk = 0x1D, .msg = "rocee qmm ovf: qpc ovf err" },
-	{ .int_msk = 0x1E, .msg = "rocee qmm ovf: qpc hopnum err" },
-	{ .int_msk = 0x1F, .msg = "rocee qmm ovf: qpc ba0 err" },
-	{ /* sentinel */ }
+	{
+		.int_msk = 0,
+		.msg = "rocee qmm ovf: sgid invalid err"
+	}, {
+		.int_msk = 0x4,
+		.msg = "rocee qmm ovf: sgid ovf err"
+	}, {
+		.int_msk = 0x8,
+		.msg = "rocee qmm ovf: smac invalid err"
+	}, {
+		.int_msk = 0xC,
+		.msg = "rocee qmm ovf: smac ovf err"
+	}, {
+		.int_msk = 0x10,
+		.msg = "rocee qmm ovf: cqc invalid err"
+	}, {
+		.int_msk = 0x11,
+		.msg = "rocee qmm ovf: cqc ovf err"
+	}, {
+		.int_msk = 0x12,
+		.msg = "rocee qmm ovf: cqc hopnum err"
+	}, {
+		.int_msk = 0x13,
+		.msg = "rocee qmm ovf: cqc ba0 err"
+	}, {
+		.int_msk = 0x14,
+		.msg = "rocee qmm ovf: srqc invalid err"
+	}, {
+		.int_msk = 0x15,
+		.msg = "rocee qmm ovf: srqc ovf err"
+	}, {
+		.int_msk = 0x16,
+		.msg = "rocee qmm ovf: srqc hopnum err"
+	}, {
+		.int_msk = 0x17,
+		.msg = "rocee qmm ovf: srqc ba0 err"
+	}, {
+		.int_msk = 0x18,
+		.msg = "rocee qmm ovf: mpt invalid err"
+	}, {
+		.int_msk = 0x19,
+		.msg = "rocee qmm ovf: mpt ovf err"
+	}, {
+		.int_msk = 0x1A,
+		.msg = "rocee qmm ovf: mpt hopnum err"
+	}, {
+		.int_msk = 0x1B,
+		.msg = "rocee qmm ovf: mpt ba0 err"
+	}, {
+		.int_msk = 0x1C,
+		.msg = "rocee qmm ovf: qpc invalid err"
+	}, {
+		.int_msk = 0x1D,
+		.msg = "rocee qmm ovf: qpc ovf err"
+	}, {
+		.int_msk = 0x1E,
+		.msg = "rocee qmm ovf: qpc hopnum err"
+	}, {
+		.int_msk = 0x1F,
+		.msg = "rocee qmm ovf: qpc ba0 err"
+	}, {
+		/* sentinel */
+	}
 };
 
 static const struct hclge_hw_module_id hclge_hw_module_id_st[] = {
@@ -1709,34 +2274,36 @@ static void hclge_handle_rocee_ras_error(struct hnae3_ae_dev *ae_dev)
 
 static const struct hclge_hw_blk hw_blk[] = {
 	{
-	  .msk = BIT(0), .name = "IGU_EGU",
-	  .config_err_int = hclge_config_igu_egu_hw_err_int,
-	},
-	{
-	  .msk = BIT(1), .name = "PPP",
-	  .config_err_int = hclge_config_ppp_hw_err_int,
-	},
-	{
-	  .msk = BIT(2), .name = "SSU",
-	  .config_err_int = hclge_config_ssu_hw_err_int,
-	},
-	{
-	  .msk = BIT(3), .name = "PPU",
-	  .config_err_int = hclge_config_ppu_hw_err_int,
-	},
-	{
-	  .msk = BIT(4), .name = "TM",
-	  .config_err_int = hclge_config_tm_hw_err_int,
-	},
-	{
-	  .msk = BIT(5), .name = "COMMON",
-	  .config_err_int = hclge_config_common_hw_err_int,
-	},
-	{
-	  .msk = BIT(8), .name = "MAC",
-	  .config_err_int = hclge_config_mac_err_int,
-	},
-	{ /* sentinel */ }
+		.msk = BIT(0),
+		.name = "IGU_EGU",
+		.config_err_int = hclge_config_igu_egu_hw_err_int,
+	}, {
+		.msk = BIT(1),
+		.name = "PPP",
+		.config_err_int = hclge_config_ppp_hw_err_int,
+	}, {
+		.msk = BIT(2),
+		.name = "SSU",
+		.config_err_int = hclge_config_ssu_hw_err_int,
+	}, {
+		.msk = BIT(3),
+		.name = "PPU",
+		.config_err_int = hclge_config_ppu_hw_err_int,
+	}, {
+		.msk = BIT(4),
+		.name = "TM",
+		.config_err_int = hclge_config_tm_hw_err_int,
+	}, {
+		.msk = BIT(5),
+		.name = "COMMON",
+		.config_err_int = hclge_config_common_hw_err_int,
+	}, {
+		.msk = BIT(8),
+		.name = "MAC",
+		.config_err_int = hclge_config_mac_err_int,
+	}, {
+		/* sentinel */
+	}
 };
 
 static void hclge_config_all_msix_error(struct hclge_dev *hdev, bool enable)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 03ae122f1c9a..e55ba2e511b1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -23,6 +23,7 @@
 #include "hclge_tm.h"
 #include "hclge_err.h"
 #include "hnae3.h"
+#include "hclge_devlink.h"
 
 #define HCLGE_NAME			"hclge"
 #define HCLGE_STATS_READ(p, offset) (*(u64 *)((u8 *)(p) + (offset)))
@@ -91,23 +92,23 @@ static const struct pci_device_id ae_algo_pci_tbl[] = {
 
 MODULE_DEVICE_TABLE(pci, ae_algo_pci_tbl);
 
-static const u32 cmdq_reg_addr_list[] = {HCLGE_CMDQ_TX_ADDR_L_REG,
-					 HCLGE_CMDQ_TX_ADDR_H_REG,
-					 HCLGE_CMDQ_TX_DEPTH_REG,
-					 HCLGE_CMDQ_TX_TAIL_REG,
-					 HCLGE_CMDQ_TX_HEAD_REG,
-					 HCLGE_CMDQ_RX_ADDR_L_REG,
-					 HCLGE_CMDQ_RX_ADDR_H_REG,
-					 HCLGE_CMDQ_RX_DEPTH_REG,
-					 HCLGE_CMDQ_RX_TAIL_REG,
-					 HCLGE_CMDQ_RX_HEAD_REG,
+static const u32 cmdq_reg_addr_list[] = {HCLGE_NIC_CSQ_BASEADDR_L_REG,
+					 HCLGE_NIC_CSQ_BASEADDR_H_REG,
+					 HCLGE_NIC_CSQ_DEPTH_REG,
+					 HCLGE_NIC_CSQ_TAIL_REG,
+					 HCLGE_NIC_CSQ_HEAD_REG,
+					 HCLGE_NIC_CRQ_BASEADDR_L_REG,
+					 HCLGE_NIC_CRQ_BASEADDR_H_REG,
+					 HCLGE_NIC_CRQ_DEPTH_REG,
+					 HCLGE_NIC_CRQ_TAIL_REG,
+					 HCLGE_NIC_CRQ_HEAD_REG,
 					 HCLGE_VECTOR0_CMDQ_SRC_REG,
 					 HCLGE_CMDQ_INTR_STS_REG,
 					 HCLGE_CMDQ_INTR_EN_REG,
 					 HCLGE_CMDQ_INTR_GEN_REG};
 
 static const u32 common_reg_addr_list[] = {HCLGE_MISC_VECTOR_REG_BASE,
-					   HCLGE_VECTOR0_OTER_EN_REG,
+					   HCLGE_PF_OTHER_INT_REG,
 					   HCLGE_MISC_RESET_STS_REG,
 					   HCLGE_MISC_VECTOR_INT_STS,
 					   HCLGE_GLOBAL_RESET_REG,
@@ -374,14 +375,14 @@ static const enum hclge_opcode_type hclge_dfx_reg_opcode_list[] = {
 };
 
 static const struct key_info meta_data_key_info[] = {
-	{ PACKET_TYPE_ID, 6},
-	{ IP_FRAGEMENT, 1},
-	{ ROCE_TYPE, 1},
-	{ NEXT_KEY, 5},
-	{ VLAN_NUMBER, 2},
-	{ SRC_VPORT, 12},
-	{ DST_VPORT, 12},
-	{ TUNNEL_PACKET, 1},
+	{ PACKET_TYPE_ID, 6 },
+	{ IP_FRAGEMENT, 1 },
+	{ ROCE_TYPE, 1 },
+	{ NEXT_KEY, 5 },
+	{ VLAN_NUMBER, 2 },
+	{ SRC_VPORT, 12 },
+	{ DST_VPORT, 12 },
+	{ TUNNEL_PACKET, 1 },
 };
 
 static const struct key_info tuple_key_info[] = {
@@ -748,9 +749,9 @@ static void hclge_update_stats(struct hnae3_handle *handle,
 
 static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset)
 {
-#define HCLGE_LOOPBACK_TEST_FLAGS (HNAE3_SUPPORT_APP_LOOPBACK |\
-		HNAE3_SUPPORT_PHY_LOOPBACK |\
-		HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK |\
+#define HCLGE_LOOPBACK_TEST_FLAGS (HNAE3_SUPPORT_APP_LOOPBACK | \
+		HNAE3_SUPPORT_PHY_LOOPBACK | \
+		HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK | \
 		HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK)
 
 	struct hclge_vport *vport = hclge_get_vport(handle);
@@ -958,31 +959,31 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 static int hclge_parse_speed(u8 speed_cmd, u32 *speed)
 {
 	switch (speed_cmd) {
-	case 6:
+	case HCLGE_FW_MAC_SPEED_10M:
 		*speed = HCLGE_MAC_SPEED_10M;
 		break;
-	case 7:
+	case HCLGE_FW_MAC_SPEED_100M:
 		*speed = HCLGE_MAC_SPEED_100M;
 		break;
-	case 0:
+	case HCLGE_FW_MAC_SPEED_1G:
 		*speed = HCLGE_MAC_SPEED_1G;
 		break;
-	case 1:
+	case HCLGE_FW_MAC_SPEED_10G:
 		*speed = HCLGE_MAC_SPEED_10G;
 		break;
-	case 2:
+	case HCLGE_FW_MAC_SPEED_25G:
 		*speed = HCLGE_MAC_SPEED_25G;
 		break;
-	case 3:
+	case HCLGE_FW_MAC_SPEED_40G:
 		*speed = HCLGE_MAC_SPEED_40G;
 		break;
-	case 4:
+	case HCLGE_FW_MAC_SPEED_50G:
 		*speed = HCLGE_MAC_SPEED_50G;
 		break;
-	case 5:
+	case HCLGE_FW_MAC_SPEED_100G:
 		*speed = HCLGE_MAC_SPEED_100G;
 		break;
-	case 8:
+	case HCLGE_FW_MAC_SPEED_200G:
 		*speed = HCLGE_MAC_SPEED_200G;
 		break;
 	default:
@@ -992,44 +993,43 @@ static int hclge_parse_speed(u8 speed_cmd, u32 *speed)
 	return 0;
 }
 
+static const struct hclge_speed_bit_map speed_bit_map[] = {
+	{HCLGE_MAC_SPEED_10M, HCLGE_SUPPORT_10M_BIT},
+	{HCLGE_MAC_SPEED_100M, HCLGE_SUPPORT_100M_BIT},
+	{HCLGE_MAC_SPEED_1G, HCLGE_SUPPORT_1G_BIT},
+	{HCLGE_MAC_SPEED_10G, HCLGE_SUPPORT_10G_BIT},
+	{HCLGE_MAC_SPEED_25G, HCLGE_SUPPORT_25G_BIT},
+	{HCLGE_MAC_SPEED_40G, HCLGE_SUPPORT_40G_BIT},
+	{HCLGE_MAC_SPEED_50G, HCLGE_SUPPORT_50G_BIT},
+	{HCLGE_MAC_SPEED_100G, HCLGE_SUPPORT_100G_BIT},
+	{HCLGE_MAC_SPEED_200G, HCLGE_SUPPORT_200G_BIT},
+};
+
+static int hclge_get_speed_bit(u32 speed, u32 *speed_bit)
+{
+	u16 i;
+
+	for (i = 0; i < ARRAY_SIZE(speed_bit_map); i++) {
+		if (speed == speed_bit_map[i].speed) {
+			*speed_bit = speed_bit_map[i].speed_bit;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
 static int hclge_check_port_speed(struct hnae3_handle *handle, u32 speed)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 	u32 speed_ability = hdev->hw.mac.speed_ability;
 	u32 speed_bit = 0;
+	int ret;
 
-	switch (speed) {
-	case HCLGE_MAC_SPEED_10M:
-		speed_bit = HCLGE_SUPPORT_10M_BIT;
-		break;
-	case HCLGE_MAC_SPEED_100M:
-		speed_bit = HCLGE_SUPPORT_100M_BIT;
-		break;
-	case HCLGE_MAC_SPEED_1G:
-		speed_bit = HCLGE_SUPPORT_1G_BIT;
-		break;
-	case HCLGE_MAC_SPEED_10G:
-		speed_bit = HCLGE_SUPPORT_10G_BIT;
-		break;
-	case HCLGE_MAC_SPEED_25G:
-		speed_bit = HCLGE_SUPPORT_25G_BIT;
-		break;
-	case HCLGE_MAC_SPEED_40G:
-		speed_bit = HCLGE_SUPPORT_40G_BIT;
-		break;
-	case HCLGE_MAC_SPEED_50G:
-		speed_bit = HCLGE_SUPPORT_50G_BIT;
-		break;
-	case HCLGE_MAC_SPEED_100G:
-		speed_bit = HCLGE_SUPPORT_100G_BIT;
-		break;
-	case HCLGE_MAC_SPEED_200G:
-		speed_bit = HCLGE_SUPPORT_200G_BIT;
-		break;
-	default:
-		return -EINVAL;
-	}
+	ret = hclge_get_speed_bit(speed, &speed_bit);
+	if (ret)
+		return ret;
 
 	if (speed_bit & speed_ability)
 		return 0;
@@ -1814,6 +1814,7 @@ static int hclge_vport_setup(struct hclge_vport *vport, u16 num_tqps)
 	nic->pdev = hdev->pdev;
 	nic->ae_algo = &ae_algo;
 	nic->numa_node_mask = hdev->numa_node_mask;
+	nic->kinfo.io_base = hdev->hw.io_base;
 
 	ret = hclge_knic_setup(vport, num_tqps,
 			       hdev->num_tx_desc, hdev->num_rx_desc);
@@ -2580,39 +2581,39 @@ static int hclge_cfg_mac_speed_dup_hw(struct hclge_dev *hdev, int speed,
 	switch (speed) {
 	case HCLGE_MAC_SPEED_10M:
 		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-				HCLGE_CFG_SPEED_S, 6);
+				HCLGE_CFG_SPEED_S, HCLGE_FW_MAC_SPEED_10M);
 		break;
 	case HCLGE_MAC_SPEED_100M:
 		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-				HCLGE_CFG_SPEED_S, 7);
+				HCLGE_CFG_SPEED_S, HCLGE_FW_MAC_SPEED_100M);
 		break;
 	case HCLGE_MAC_SPEED_1G:
 		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-				HCLGE_CFG_SPEED_S, 0);
+				HCLGE_CFG_SPEED_S, HCLGE_FW_MAC_SPEED_1G);
 		break;
 	case HCLGE_MAC_SPEED_10G:
 		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-				HCLGE_CFG_SPEED_S, 1);
+				HCLGE_CFG_SPEED_S, HCLGE_FW_MAC_SPEED_10G);
 		break;
 	case HCLGE_MAC_SPEED_25G:
 		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-				HCLGE_CFG_SPEED_S, 2);
+				HCLGE_CFG_SPEED_S, HCLGE_FW_MAC_SPEED_25G);
 		break;
 	case HCLGE_MAC_SPEED_40G:
 		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-				HCLGE_CFG_SPEED_S, 3);
+				HCLGE_CFG_SPEED_S, HCLGE_FW_MAC_SPEED_40G);
 		break;
 	case HCLGE_MAC_SPEED_50G:
 		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-				HCLGE_CFG_SPEED_S, 4);
+				HCLGE_CFG_SPEED_S, HCLGE_FW_MAC_SPEED_50G);
 		break;
 	case HCLGE_MAC_SPEED_100G:
 		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-				HCLGE_CFG_SPEED_S, 5);
+				HCLGE_CFG_SPEED_S, HCLGE_FW_MAC_SPEED_100G);
 		break;
 	case HCLGE_MAC_SPEED_200G:
 		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-				HCLGE_CFG_SPEED_S, 8);
+				HCLGE_CFG_SPEED_S, HCLGE_FW_MAC_SPEED_200G);
 		break;
 	default:
 		dev_err(&hdev->pdev->dev, "invalid speed (%d)\n", speed);
@@ -3420,7 +3421,7 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data)
 	hclge_enable_vector(&hdev->misc_vector, false);
 	event_cause = hclge_check_event_cause(hdev, &clearval);
 
-	/* vector 0 interrupt is shared with reset and mailbox source events.*/
+	/* vector 0 interrupt is shared with reset and mailbox source events. */
 	switch (event_cause) {
 	case HCLGE_VECTOR0_EVENT_ERR:
 		hclge_errhand_task_schedule(hdev);
@@ -3789,6 +3790,12 @@ static void hclge_do_reset(struct hclge_dev *hdev)
 	}
 
 	switch (hdev->reset_type) {
+	case HNAE3_IMP_RESET:
+		dev_info(&pdev->dev, "IMP reset requested\n");
+		val = hclge_read_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG);
+		hnae3_set_bit(val, HCLGE_TRIGGER_IMP_RESET_B, 1);
+		hclge_write_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG, val);
+		break;
 	case HNAE3_GLOBAL_RESET:
 		dev_info(&pdev->dev, "global reset requested\n");
 		val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG);
@@ -5937,7 +5944,7 @@ static int hclge_config_key(struct hclge_dev *hdev, u8 stage,
 	cur_key_x = key_x;
 	cur_key_y = key_y;
 
-	for (i = 0 ; i < MAX_TUPLE; i++) {
+	for (i = 0; i < MAX_TUPLE; i++) {
 		bool tuple_valid;
 
 		tuple_size = tuple_key_info[i].key_length / 8;
@@ -11509,10 +11516,14 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	if (ret)
 		goto out;
 
+	ret = hclge_devlink_init(hdev);
+	if (ret)
+		goto err_pci_uninit;
+
 	/* Firmware command queue initialize */
 	ret = hclge_cmd_queue_init(hdev);
 	if (ret)
-		goto err_pci_uninit;
+		goto err_devlink_uninit;
 
 	/* Firmware command initialize */
 	ret = hclge_cmd_init(hdev);
@@ -11689,6 +11700,8 @@ err_msi_uninit:
 	pci_free_irq_vectors(pdev);
 err_cmd_uninit:
 	hclge_cmd_uninit(hdev);
+err_devlink_uninit:
+	hclge_devlink_uninit(hdev);
 err_pci_uninit:
 	pcim_iounmap(pdev, hdev->hw.io_base);
 	pci_clear_master(pdev);
@@ -12079,6 +12092,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 
 	hclge_cmd_uninit(hdev);
 	hclge_misc_irq_uninit(hdev);
+	hclge_devlink_uninit(hdev);
 	hclge_pci_uninit(hdev);
 	mutex_destroy(&hdev->vport_lock);
 	hclge_uninit_vport_vlan_table(hdev);
@@ -12867,6 +12881,29 @@ static int hclge_get_module_eeprom(struct hnae3_handle *handle, u32 offset,
 	return 0;
 }
 
+static int hclge_get_link_diagnosis_info(struct hnae3_handle *handle,
+					 u32 *status_code)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	struct hclge_desc desc;
+	int ret;
+
+	if (hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2)
+		return -EOPNOTSUPP;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_LINK_DIAGNOSIS, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to query link diagnosis info, ret = %d\n", ret);
+		return ret;
+	}
+
+	*status_code = le32_to_cpu(desc.data[0]);
+	return 0;
+}
+
 static const struct hnae3_ae_ops hclge_ops = {
 	.init_ae_dev = hclge_init_ae_dev,
 	.uninit_ae_dev = hclge_uninit_ae_dev,
@@ -12967,6 +13004,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_tx_hwts_info = hclge_ptp_set_tx_info,
 	.get_rx_hwts = hclge_ptp_get_rx_hwts,
 	.get_ts_info = hclge_ptp_get_ts_info,
+	.get_link_diagnosis_info = hclge_get_link_diagnosis_info,
 };
 
 static struct hnae3_ae_algo ae_algo = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index e446b839a371..de6afbcbfbac 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -8,6 +8,7 @@
 #include <linux/phy.h>
 #include <linux/if_vlan.h>
 #include <linux/kfifo.h>
+#include <net/devlink.h>
 
 #include "hclge_cmd.h"
 #include "hclge_ptp.h"
@@ -37,22 +38,22 @@
 #define HCLGE_VECTOR_REG_OFFSET_H	0x1000
 #define HCLGE_VECTOR_VF_OFFSET		0x100000
 
-#define HCLGE_CMDQ_TX_ADDR_L_REG	0x27000
-#define HCLGE_CMDQ_TX_ADDR_H_REG	0x27004
-#define HCLGE_CMDQ_TX_DEPTH_REG		0x27008
-#define HCLGE_CMDQ_TX_TAIL_REG		0x27010
-#define HCLGE_CMDQ_TX_HEAD_REG		0x27014
-#define HCLGE_CMDQ_RX_ADDR_L_REG	0x27018
-#define HCLGE_CMDQ_RX_ADDR_H_REG	0x2701C
-#define HCLGE_CMDQ_RX_DEPTH_REG		0x27020
-#define HCLGE_CMDQ_RX_TAIL_REG		0x27024
-#define HCLGE_CMDQ_RX_HEAD_REG		0x27028
+#define HCLGE_NIC_CSQ_BASEADDR_L_REG	0x27000
+#define HCLGE_NIC_CSQ_BASEADDR_H_REG	0x27004
+#define HCLGE_NIC_CSQ_DEPTH_REG		0x27008
+#define HCLGE_NIC_CSQ_TAIL_REG		0x27010
+#define HCLGE_NIC_CSQ_HEAD_REG		0x27014
+#define HCLGE_NIC_CRQ_BASEADDR_L_REG	0x27018
+#define HCLGE_NIC_CRQ_BASEADDR_H_REG	0x2701C
+#define HCLGE_NIC_CRQ_DEPTH_REG		0x27020
+#define HCLGE_NIC_CRQ_TAIL_REG		0x27024
+#define HCLGE_NIC_CRQ_HEAD_REG		0x27028
+
 #define HCLGE_CMDQ_INTR_STS_REG		0x27104
 #define HCLGE_CMDQ_INTR_EN_REG		0x27108
 #define HCLGE_CMDQ_INTR_GEN_REG		0x2710C
 
 /* bar registers for common func */
-#define HCLGE_VECTOR0_OTER_EN_REG	0x20600
 #define HCLGE_GRO_EN_REG		0x28000
 #define HCLGE_RXD_ADV_LAYOUT_EN_REG	0x28008
 
@@ -193,6 +194,7 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_VECTOR0_IMP_CMDQ_ERR_B	4U
 #define HCLGE_VECTOR0_IMP_RD_POISON_B	5U
 #define HCLGE_VECTOR0_ALL_MSIX_ERR_B	6U
+#define HCLGE_TRIGGER_IMP_RESET_B	7U
 
 #define HCLGE_MAC_DEFAULT_FRAME \
 	(ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN + ETH_DATA_LEN)
@@ -944,6 +946,7 @@ struct hclge_dev {
 	cpumask_t affinity_mask;
 	struct irq_affinity_notify affinity_notify;
 	struct hclge_ptp *ptp;
+	struct devlink *devlink;
 };
 
 /* VPort level vlan tag configuration for TX direction */
@@ -1055,6 +1058,11 @@ struct hclge_vport {
 	struct list_head vlan_list;     /* Store VF vlan table */
 };
 
+struct hclge_speed_bit_map {
+	u32 speed;
+	u32 speed_bit;
+};
+
 int hclge_set_vport_promisc_mode(struct hclge_vport *vport, bool en_uc_pmc,
 				 bool en_mc_pmc, bool en_bc_pmc);
 int hclge_add_uc_addr_common(struct hclge_vport *vport,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index c0a478ae9583..2ce5302c5956 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -10,7 +10,14 @@
 
 static u16 hclge_errno_to_resp(int errno)
 {
-	return abs(errno);
+	int resp = abs(errno);
+
+	/* The status for pf to vf msg cmd is u16, constrainted by HW.
+	 * We need to keep the same type with it.
+	 * The intput errno is the stander error code, it's safely to
+	 * use a u16 to store the abs(errno).
+	 */
+	return (u16)resp;
 }
 
 /* hclge_gen_resp_to_vf: used to generate a synchronous response to VF when PF
@@ -66,6 +73,8 @@ static int hclge_gen_resp_to_vf(struct hclge_vport *vport,
 		memcpy(resp_pf_to_vf->msg.resp_data, resp_msg->data,
 		       resp_msg->len);
 
+	trace_hclge_pf_mbx_send(hdev, resp_pf_to_vf);
+
 	status = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (status)
 		dev_err(&hdev->pdev->dev,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h
index dbf5f4c08019..7a9b77de632a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h
@@ -127,7 +127,7 @@ static inline struct hclge_dev *hclge_ptp_get_hdev(struct ptp_clock_info *info)
 }
 
 bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb);
-void hclge_ptp_clean_tx_hwts(struct hclge_dev *dev);
+void hclge_ptp_clean_tx_hwts(struct hclge_dev *hdev);
 void hclge_ptp_get_rx_hwts(struct hnae3_handle *handle, struct sk_buff *skb,
 			   u32 nsec, u32 sec);
 int hclge_ptp_get_cfg(struct hclge_dev *hdev, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
index 2c26ea607a53..51ff7d86ee90 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
@@ -7,4 +7,4 @@ ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
 ccflags-y += -I $(srctree)/$(src)
 
 obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o
-hclgevf-objs = hclgevf_main.o hclgevf_cmd.o hclgevf_mbx.o
+hclgevf-objs = hclgevf_main.o hclgevf_cmd.o hclgevf_mbx.o  hclgevf_devlink.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index d9ddb0a243d4..59772b0e9531 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -71,7 +71,7 @@ static bool hclgevf_cmd_csq_done(struct hclgevf_hw *hw)
 
 static bool hclgevf_is_special_opcode(u16 opcode)
 {
-	static const u16 spec_opcode[] = {0x30, 0x31, 0x32};
+	const u16 spec_opcode[] = {0x30, 0x31, 0x32};
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(spec_opcode); i++) {
@@ -342,25 +342,26 @@ static void hclgevf_set_default_capability(struct hclgevf_dev *hdev)
 	set_bit(HNAE3_DEV_SUPPORT_FEC_B, ae_dev->caps);
 }
 
+const struct hclgevf_caps_bit_map hclgevf_cmd_caps_bit_map0[] = {
+	{HCLGEVF_CAP_UDP_GSO_B, HNAE3_DEV_SUPPORT_UDP_GSO_B},
+	{HCLGEVF_CAP_INT_QL_B, HNAE3_DEV_SUPPORT_INT_QL_B},
+	{HCLGEVF_CAP_TQP_TXRX_INDEP_B, HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B},
+	{HCLGEVF_CAP_HW_TX_CSUM_B, HNAE3_DEV_SUPPORT_HW_TX_CSUM_B},
+	{HCLGEVF_CAP_UDP_TUNNEL_CSUM_B, HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B},
+	{HCLGEVF_CAP_RXD_ADV_LAYOUT_B, HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B},
+};
+
 static void hclgevf_parse_capability(struct hclgevf_dev *hdev,
 				     struct hclgevf_query_version_cmd *cmd)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
-	u32 caps;
+	u32 caps, i;
 
 	caps = __le32_to_cpu(cmd->caps[0]);
-	if (hnae3_get_bit(caps, HCLGEVF_CAP_UDP_GSO_B))
-		set_bit(HNAE3_DEV_SUPPORT_UDP_GSO_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGEVF_CAP_INT_QL_B))
-		set_bit(HNAE3_DEV_SUPPORT_INT_QL_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGEVF_CAP_TQP_TXRX_INDEP_B))
-		set_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGEVF_CAP_HW_TX_CSUM_B))
-		set_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGEVF_CAP_UDP_TUNNEL_CSUM_B))
-		set_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, ae_dev->caps);
-	if (hnae3_get_bit(caps, HCLGEVF_CAP_RXD_ADV_LAYOUT_B))
-		set_bit(HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B, ae_dev->caps);
+	for (i = 0; i < ARRAY_SIZE(hclgevf_cmd_caps_bit_map0); i++)
+		if (hnae3_get_bit(caps, hclgevf_cmd_caps_bit_map0[i].imp_bit))
+			set_bit(hclgevf_cmd_caps_bit_map0[i].local_bit,
+				ae_dev->caps);
 }
 
 static __le32 hclgevf_build_api_caps(void)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index 5b82177f98b4..39d0b589c720 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -266,16 +266,6 @@ struct hclgevf_cfg_tx_queue_pointer_cmd {
 
 #define HCLGEVF_TYPE_CRQ		0
 #define HCLGEVF_TYPE_CSQ		1
-#define HCLGEVF_NIC_CSQ_BASEADDR_L_REG	0x27000
-#define HCLGEVF_NIC_CSQ_BASEADDR_H_REG	0x27004
-#define HCLGEVF_NIC_CSQ_DEPTH_REG	0x27008
-#define HCLGEVF_NIC_CSQ_TAIL_REG	0x27010
-#define HCLGEVF_NIC_CSQ_HEAD_REG	0x27014
-#define HCLGEVF_NIC_CRQ_BASEADDR_L_REG	0x27018
-#define HCLGEVF_NIC_CRQ_BASEADDR_H_REG	0x2701c
-#define HCLGEVF_NIC_CRQ_DEPTH_REG	0x27020
-#define HCLGEVF_NIC_CRQ_TAIL_REG	0x27024
-#define HCLGEVF_NIC_CRQ_HEAD_REG	0x27028
 
 /* this bit indicates that the driver is ready for hardware reset */
 #define HCLGEVF_NIC_SW_RST_RDY_B	16
@@ -306,6 +296,12 @@ struct hclgevf_dev_specs_1_cmd {
 	u8 rsv1[18];
 };
 
+/* capabilities bits map between imp firmware and local driver */
+struct hclgevf_caps_bit_map {
+	u16 imp_bit;
+	u16 local_bit;
+};
+
 static inline void hclgevf_write_reg(void __iomem *base, u32 reg, u32 value)
 {
 	writel(value, base + reg);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c
new file mode 100644
index 000000000000..f478770299c6
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (c) 2021 Hisilicon Limited. */
+
+#include <net/devlink.h>
+
+#include "hclgevf_devlink.h"
+
+static int hclgevf_devlink_info_get(struct devlink *devlink,
+				    struct devlink_info_req *req,
+				    struct netlink_ext_ack *extack)
+{
+#define	HCLGEVF_DEVLINK_FW_STRING_LEN	32
+	struct hclgevf_devlink_priv *priv = devlink_priv(devlink);
+	char version_str[HCLGEVF_DEVLINK_FW_STRING_LEN];
+	struct hclgevf_dev *hdev = priv->hdev;
+	int ret;
+
+	ret = devlink_info_driver_name_put(req, KBUILD_MODNAME);
+	if (ret)
+		return ret;
+
+	snprintf(version_str, sizeof(version_str), "%lu.%lu.%lu.%lu",
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE3_MASK,
+				 HNAE3_FW_VERSION_BYTE3_SHIFT),
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE2_MASK,
+				 HNAE3_FW_VERSION_BYTE2_SHIFT),
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE1_MASK,
+				 HNAE3_FW_VERSION_BYTE1_SHIFT),
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE0_MASK,
+				 HNAE3_FW_VERSION_BYTE0_SHIFT));
+
+	return devlink_info_version_running_put(req,
+						DEVLINK_INFO_VERSION_GENERIC_FW,
+						version_str);
+}
+
+static int hclgevf_devlink_reload_down(struct devlink *devlink,
+				       bool netns_change,
+				       enum devlink_reload_action action,
+				       enum devlink_reload_limit limit,
+				       struct netlink_ext_ack *extack)
+{
+	struct hclgevf_devlink_priv *priv = devlink_priv(devlink);
+	struct hclgevf_dev *hdev = priv->hdev;
+	struct hnae3_handle *h = &hdev->nic;
+	struct pci_dev *pdev = hdev->pdev;
+	int ret;
+
+	if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) {
+		dev_err(&pdev->dev, "reset is handling\n");
+		return -EBUSY;
+	}
+
+	switch (action) {
+	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
+		rtnl_lock();
+		ret = hdev->nic_client->ops->reset_notify(h, HNAE3_DOWN_CLIENT);
+		if (ret) {
+			rtnl_unlock();
+			return ret;
+		}
+
+		ret = hdev->nic_client->ops->reset_notify(h,
+							  HNAE3_UNINIT_CLIENT);
+		rtnl_unlock();
+		return ret;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int hclgevf_devlink_reload_up(struct devlink *devlink,
+				     enum devlink_reload_action action,
+				     enum devlink_reload_limit limit,
+				     u32 *actions_performed,
+				     struct netlink_ext_ack *extack)
+{
+	struct hclgevf_devlink_priv *priv = devlink_priv(devlink);
+	struct hclgevf_dev *hdev = priv->hdev;
+	struct hnae3_handle *h = &hdev->nic;
+	int ret;
+
+	*actions_performed = BIT(action);
+	switch (action) {
+	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
+		rtnl_lock();
+		ret = hdev->nic_client->ops->reset_notify(h, HNAE3_INIT_CLIENT);
+		if (ret) {
+			rtnl_unlock();
+			return ret;
+		}
+
+		ret = hdev->nic_client->ops->reset_notify(h, HNAE3_UP_CLIENT);
+		rtnl_unlock();
+		return ret;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct devlink_ops hclgevf_devlink_ops = {
+	.info_get = hclgevf_devlink_info_get,
+	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
+	.reload_down = hclgevf_devlink_reload_down,
+	.reload_up = hclgevf_devlink_reload_up,
+};
+
+int hclgevf_devlink_init(struct hclgevf_dev *hdev)
+{
+	struct pci_dev *pdev = hdev->pdev;
+	struct hclgevf_devlink_priv *priv;
+	struct devlink *devlink;
+	int ret;
+
+	devlink =
+		devlink_alloc(&hclgevf_devlink_ops,
+			      sizeof(struct hclgevf_devlink_priv), &pdev->dev);
+	if (!devlink)
+		return -ENOMEM;
+
+	priv = devlink_priv(devlink);
+	priv->hdev = hdev;
+	hdev->devlink = devlink;
+
+	ret = devlink_register(devlink);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register devlink, ret = %d\n",
+			ret);
+		goto out_reg_fail;
+	}
+
+	devlink_reload_enable(devlink);
+
+	return 0;
+
+out_reg_fail:
+	devlink_free(devlink);
+	return ret;
+}
+
+void hclgevf_devlink_uninit(struct hclgevf_dev *hdev)
+{
+	struct devlink *devlink = hdev->devlink;
+
+	devlink_reload_disable(devlink);
+
+	devlink_unregister(devlink);
+
+	devlink_free(devlink);
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.h
new file mode 100644
index 000000000000..e09ea3d8a963
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2021 Hisilicon Limited. */
+
+#ifndef __HCLGEVF_DEVLINK_H
+#define __HCLGEVF_DEVLINK_H
+
+#include "hclgevf_main.h"
+
+struct hclgevf_devlink_priv {
+	struct hclgevf_dev *hdev;
+};
+
+int hclgevf_devlink_init(struct hclgevf_dev *hdev);
+void hclgevf_devlink_uninit(struct hclgevf_dev *hdev);
+#endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 938654778979..82e727020120 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -8,6 +8,7 @@
 #include "hclgevf_main.h"
 #include "hclge_mbx.h"
 #include "hnae3.h"
+#include "hclgevf_devlink.h"
 
 #define HCLGEVF_NAME	"hclgevf"
 
@@ -39,16 +40,16 @@ static const u8 hclgevf_hash_key[] = {
 
 MODULE_DEVICE_TABLE(pci, ae_algovf_pci_tbl);
 
-static const u32 cmdq_reg_addr_list[] = {HCLGEVF_CMDQ_TX_ADDR_L_REG,
-					 HCLGEVF_CMDQ_TX_ADDR_H_REG,
-					 HCLGEVF_CMDQ_TX_DEPTH_REG,
-					 HCLGEVF_CMDQ_TX_TAIL_REG,
-					 HCLGEVF_CMDQ_TX_HEAD_REG,
-					 HCLGEVF_CMDQ_RX_ADDR_L_REG,
-					 HCLGEVF_CMDQ_RX_ADDR_H_REG,
-					 HCLGEVF_CMDQ_RX_DEPTH_REG,
-					 HCLGEVF_CMDQ_RX_TAIL_REG,
-					 HCLGEVF_CMDQ_RX_HEAD_REG,
+static const u32 cmdq_reg_addr_list[] = {HCLGEVF_NIC_CSQ_BASEADDR_L_REG,
+					 HCLGEVF_NIC_CSQ_BASEADDR_H_REG,
+					 HCLGEVF_NIC_CSQ_DEPTH_REG,
+					 HCLGEVF_NIC_CSQ_TAIL_REG,
+					 HCLGEVF_NIC_CSQ_HEAD_REG,
+					 HCLGEVF_NIC_CRQ_BASEADDR_L_REG,
+					 HCLGEVF_NIC_CRQ_BASEADDR_H_REG,
+					 HCLGEVF_NIC_CRQ_DEPTH_REG,
+					 HCLGEVF_NIC_CRQ_TAIL_REG,
+					 HCLGEVF_NIC_CRQ_HEAD_REG,
 					 HCLGEVF_VECTOR0_CMDQ_SRC_REG,
 					 HCLGEVF_VECTOR0_CMDQ_STATE_REG,
 					 HCLGEVF_CMDQ_INTR_EN_REG,
@@ -538,6 +539,7 @@ static int hclgevf_set_handle_info(struct hclgevf_dev *hdev)
 	nic->pdev = hdev->pdev;
 	nic->numa_node_mask = hdev->numa_node_mask;
 	nic->flags |= HNAE3_SUPPORT_VF;
+	nic->kinfo.io_base = hdev->hw.io_base;
 
 	ret = hclgevf_knic_setup(hdev);
 	if (ret)
@@ -1961,7 +1963,7 @@ static void hclgevf_dump_rst_info(struct hclgevf_dev *hdev)
 	dev_info(&hdev->pdev->dev, "vector0 interrupt status: 0x%x\n",
 		 hclgevf_read_dev(&hdev->hw, HCLGEVF_VECTOR0_CMDQ_STATE_REG));
 	dev_info(&hdev->pdev->dev, "handshake status: 0x%x\n",
-		 hclgevf_read_dev(&hdev->hw, HCLGEVF_CMDQ_TX_DEPTH_REG));
+		 hclgevf_read_dev(&hdev->hw, HCLGEVF_NIC_CSQ_DEPTH_REG));
 	dev_info(&hdev->pdev->dev, "function reset status: 0x%x\n",
 		 hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING));
 	dev_info(&hdev->pdev->dev, "hdev state: 0x%lx\n", hdev->state);
@@ -3339,6 +3341,10 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 	if (ret)
 		return ret;
 
+	ret = hclgevf_devlink_init(hdev);
+	if (ret)
+		goto err_devlink_init;
+
 	ret = hclgevf_cmd_queue_init(hdev);
 	if (ret)
 		goto err_cmd_queue_init;
@@ -3443,6 +3449,8 @@ err_misc_irq_init:
 err_cmd_init:
 	hclgevf_cmd_uninit(hdev);
 err_cmd_queue_init:
+	hclgevf_devlink_uninit(hdev);
+err_devlink_init:
 	hclgevf_pci_uninit(hdev);
 	clear_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state);
 	return ret;
@@ -3464,6 +3472,7 @@ static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev)
 	}
 
 	hclgevf_cmd_uninit(hdev);
+	hclgevf_devlink_uninit(hdev);
 	hclgevf_pci_uninit(hdev);
 	hclgevf_uninit_mac_list(hdev);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index e8013be055f8..883130a9b48f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -6,6 +6,7 @@
 #include <linux/fs.h>
 #include <linux/if_vlan.h>
 #include <linux/types.h>
+#include <net/devlink.h>
 #include "hclge_mbx.h"
 #include "hclgevf_cmd.h"
 #include "hnae3.h"
@@ -32,16 +33,17 @@
 #define HCLGEVF_VECTOR_VF_OFFSET		0x100000
 
 /* bar registers for cmdq */
-#define HCLGEVF_CMDQ_TX_ADDR_L_REG		0x27000
-#define HCLGEVF_CMDQ_TX_ADDR_H_REG		0x27004
-#define HCLGEVF_CMDQ_TX_DEPTH_REG		0x27008
-#define HCLGEVF_CMDQ_TX_TAIL_REG		0x27010
-#define HCLGEVF_CMDQ_TX_HEAD_REG		0x27014
-#define HCLGEVF_CMDQ_RX_ADDR_L_REG		0x27018
-#define HCLGEVF_CMDQ_RX_ADDR_H_REG		0x2701C
-#define HCLGEVF_CMDQ_RX_DEPTH_REG		0x27020
-#define HCLGEVF_CMDQ_RX_TAIL_REG		0x27024
-#define HCLGEVF_CMDQ_RX_HEAD_REG		0x27028
+#define HCLGEVF_NIC_CSQ_BASEADDR_L_REG		0x27000
+#define HCLGEVF_NIC_CSQ_BASEADDR_H_REG		0x27004
+#define HCLGEVF_NIC_CSQ_DEPTH_REG		0x27008
+#define HCLGEVF_NIC_CSQ_TAIL_REG		0x27010
+#define HCLGEVF_NIC_CSQ_HEAD_REG		0x27014
+#define HCLGEVF_NIC_CRQ_BASEADDR_L_REG		0x27018
+#define HCLGEVF_NIC_CRQ_BASEADDR_H_REG		0x2701C
+#define HCLGEVF_NIC_CRQ_DEPTH_REG		0x27020
+#define HCLGEVF_NIC_CRQ_TAIL_REG		0x27024
+#define HCLGEVF_NIC_CRQ_HEAD_REG		0x27028
+
 #define HCLGEVF_CMDQ_INTR_EN_REG		0x27108
 #define HCLGEVF_CMDQ_INTR_GEN_REG		0x2710C
 
@@ -316,7 +318,6 @@ struct hclgevf_dev {
 
 	struct hclgevf_mac_table_cfg mac_table;
 
-	bool mbx_event_pending;
 	struct hclgevf_mbx_resp_status mbx_resp; /* mailbox response */
 	struct hclgevf_mbx_arq_ring arq; /* mailbox async rx queue */
 
@@ -332,6 +333,8 @@ struct hclgevf_dev {
 	u32 flag;
 	unsigned long serv_processed_cnt;
 	unsigned long last_serv_processed;
+
+	struct devlink *devlink;
 };
 
 static inline bool hclgevf_is_reset_pending(struct hclgevf_dev *hdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index b339b9bc0625..fdc66fae0960 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -155,18 +155,66 @@ static bool hclgevf_cmd_crq_empty(struct hclgevf_hw *hw)
 	return tail == hw->cmq.crq.next_to_use;
 }
 
+static void hclgevf_handle_mbx_response(struct hclgevf_dev *hdev,
+					struct hclge_mbx_pf_to_vf_cmd *req)
+{
+	struct hclgevf_mbx_resp_status *resp = &hdev->mbx_resp;
+
+	if (resp->received_resp)
+		dev_warn(&hdev->pdev->dev,
+			 "VF mbx resp flag not clear(%u)\n",
+			 req->msg.vf_mbx_msg_code);
+
+	resp->origin_mbx_msg =
+			(req->msg.vf_mbx_msg_code << 16);
+	resp->origin_mbx_msg |= req->msg.vf_mbx_msg_subcode;
+	resp->resp_status =
+		hclgevf_resp_to_errno(req->msg.resp_status);
+	memcpy(resp->additional_info, req->msg.resp_data,
+	       HCLGE_MBX_MAX_RESP_DATA_SIZE * sizeof(u8));
+	if (req->match_id) {
+		/* If match_id is not zero, it means PF support match_id.
+		 * if the match_id is right, VF get the right response, or
+		 * ignore the response. and driver will clear hdev->mbx_resp
+		 * when send next message which need response.
+		 */
+		if (req->match_id == resp->match_id)
+			resp->received_resp = true;
+	} else {
+		resp->received_resp = true;
+	}
+}
+
+static void hclgevf_handle_mbx_msg(struct hclgevf_dev *hdev,
+				   struct hclge_mbx_pf_to_vf_cmd *req)
+{
+	/* we will drop the async msg if we find ARQ as full
+	 * and continue with next message
+	 */
+	if (atomic_read(&hdev->arq.count) >=
+	    HCLGE_MBX_MAX_ARQ_MSG_NUM) {
+		dev_warn(&hdev->pdev->dev,
+			 "Async Q full, dropping msg(%u)\n",
+			 req->msg.code);
+		return;
+	}
+
+	/* tail the async message in arq */
+	memcpy(hdev->arq.msg_q[hdev->arq.tail], &req->msg,
+	       HCLGE_MBX_MAX_ARQ_MSG_SIZE * sizeof(u16));
+	hclge_mbx_tail_ptr_move_arq(hdev->arq);
+	atomic_inc(&hdev->arq.count);
+
+	hclgevf_mbx_task_schedule(hdev);
+}
+
 void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 {
-	struct hclgevf_mbx_resp_status *resp;
 	struct hclge_mbx_pf_to_vf_cmd *req;
 	struct hclgevf_cmq_ring *crq;
 	struct hclgevf_desc *desc;
-	u16 *msg_q;
 	u16 flag;
-	u8 *temp;
-	int i;
 
-	resp = &hdev->mbx_resp;
 	crq = &hdev->hw.cmq.crq;
 
 	while (!hclgevf_cmd_crq_empty(&hdev->hw)) {
@@ -200,69 +248,14 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 		 */
 		switch (req->msg.code) {
 		case HCLGE_MBX_PF_VF_RESP:
-			if (resp->received_resp)
-				dev_warn(&hdev->pdev->dev,
-					 "VF mbx resp flag not clear(%u)\n",
-					 req->msg.vf_mbx_msg_code);
-			resp->received_resp = true;
-
-			resp->origin_mbx_msg =
-					(req->msg.vf_mbx_msg_code << 16);
-			resp->origin_mbx_msg |= req->msg.vf_mbx_msg_subcode;
-			resp->resp_status =
-				hclgevf_resp_to_errno(req->msg.resp_status);
-
-			temp = (u8 *)req->msg.resp_data;
-			for (i = 0; i < HCLGE_MBX_MAX_RESP_DATA_SIZE; i++) {
-				resp->additional_info[i] = *temp;
-				temp++;
-			}
-
-			/* If match_id is not zero, it means PF support
-			 * match_id. If the match_id is right, VF get the
-			 * right response, otherwise ignore the response.
-			 * Driver will clear hdev->mbx_resp when send
-			 * next message which need response.
-			 */
-			if (req->match_id) {
-				if (req->match_id == resp->match_id)
-					resp->received_resp = true;
-			} else {
-				resp->received_resp = true;
-			}
+			hclgevf_handle_mbx_response(hdev, req);
 			break;
 		case HCLGE_MBX_LINK_STAT_CHANGE:
 		case HCLGE_MBX_ASSERTING_RESET:
 		case HCLGE_MBX_LINK_STAT_MODE:
 		case HCLGE_MBX_PUSH_VLAN_INFO:
 		case HCLGE_MBX_PUSH_PROMISC_INFO:
-			/* set this mbx event as pending. This is required as we
-			 * might loose interrupt event when mbx task is busy
-			 * handling. This shall be cleared when mbx task just
-			 * enters handling state.
-			 */
-			hdev->mbx_event_pending = true;
-
-			/* we will drop the async msg if we find ARQ as full
-			 * and continue with next message
-			 */
-			if (atomic_read(&hdev->arq.count) >=
-			    HCLGE_MBX_MAX_ARQ_MSG_NUM) {
-				dev_warn(&hdev->pdev->dev,
-					 "Async Q full, dropping msg(%u)\n",
-					 req->msg.code);
-				break;
-			}
-
-			/* tail the async message in arq */
-			msg_q = hdev->arq.msg_q[hdev->arq.tail];
-			memcpy(&msg_q[0], &req->msg,
-			       HCLGE_MBX_MAX_ARQ_MSG_SIZE * sizeof(u16));
-			hclge_mbx_tail_ptr_move_arq(hdev->arq);
-			atomic_inc(&hdev->arq.count);
-
-			hclgevf_mbx_task_schedule(hdev);
-
+			hclgevf_handle_mbx_msg(hdev, req);
 			break;
 		default:
 			dev_err(&hdev->pdev->dev,
@@ -298,11 +291,6 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 	u8 flag;
 	u8 idx;
 
-	/* we can safely clear it now as we are at start of the async message
-	 * processing
-	 */
-	hdev->mbx_event_pending = false;
-
 	tail = hdev->arq.tail;
 
 	/* process all the async queue messages */
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
index 58d5646444b0..6e11ee339f12 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
@@ -293,9 +293,9 @@ static const struct devlink_ops hinic_devlink_ops = {
 	.flash_update = hinic_devlink_flash_update,
 };
 
-struct devlink *hinic_devlink_alloc(void)
+struct devlink *hinic_devlink_alloc(struct device *dev)
 {
-	return devlink_alloc(&hinic_devlink_ops, sizeof(struct hinic_dev));
+	return devlink_alloc(&hinic_devlink_ops, sizeof(struct hinic_dev), dev);
 }
 
 void hinic_devlink_free(struct devlink *devlink)
@@ -303,11 +303,11 @@ void hinic_devlink_free(struct devlink *devlink)
 	devlink_free(devlink);
 }
 
-int hinic_devlink_register(struct hinic_devlink_priv *priv, struct device *dev)
+int hinic_devlink_register(struct hinic_devlink_priv *priv)
 {
 	struct devlink *devlink = priv_to_devlink(priv);
 
-	return devlink_register(devlink, dev);
+	return devlink_register(devlink);
 }
 
 void hinic_devlink_unregister(struct hinic_devlink_priv *priv)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.h b/drivers/net/ethernet/huawei/hinic/hinic_devlink.h
index a090ebcfaabb..9e315011015c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.h
@@ -108,9 +108,9 @@ struct host_image_st {
 	u32 device_id;
 };
 
-struct devlink *hinic_devlink_alloc(void);
+struct devlink *hinic_devlink_alloc(struct device *dev);
 void hinic_devlink_free(struct devlink *devlink);
-int hinic_devlink_register(struct hinic_devlink_priv *priv, struct device *dev);
+int hinic_devlink_register(struct hinic_devlink_priv *priv);
 void hinic_devlink_unregister(struct hinic_devlink_priv *priv);
 
 int hinic_health_reporters_create(struct hinic_devlink_priv *priv);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
index 162d3c330dec..b431c300ef1b 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
@@ -795,13 +795,17 @@ static int __hinic_set_coalesce(struct net_device *netdev,
 }
 
 static int hinic_get_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *coal)
+			      struct ethtool_coalesce *coal,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	return __hinic_get_coalesce(netdev, coal, COALESCE_ALL_QUEUE);
 }
 
 static int hinic_set_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *coal)
+			      struct ethtool_coalesce *coal,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	return __hinic_set_coalesce(netdev, coal, COALESCE_ALL_QUEUE);
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 428108eb10d2..56b6b04e209b 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -754,7 +754,7 @@ static int init_pfhwdev(struct hinic_pfhwdev *pfhwdev)
 		return err;
 	}
 
-	err = hinic_devlink_register(hwdev->devlink_dev, &pdev->dev);
+	err = hinic_devlink_register(hwdev->devlink_dev);
 	if (err) {
 		dev_err(&hwif->pdev->dev, "Failed to register devlink\n");
 		hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 405ee4d2d2b1..ae707e305684 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -1183,7 +1183,7 @@ static int nic_dev_init(struct pci_dev *pdev)
 	struct devlink *devlink;
 	int err, num_qps;
 
-	devlink = hinic_devlink_alloc();
+	devlink = hinic_devlink_alloc(&pdev->dev);
 	if (!devlink) {
 		dev_err(&pdev->dev, "Hinic devlink alloc failed\n");
 		return -ENOMEM;
@@ -1392,28 +1392,16 @@ static int hinic_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (err) {
 		dev_warn(&pdev->dev, "Couldn't set 64-bit DMA mask\n");
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
 			dev_err(&pdev->dev, "Failed to set DMA mask\n");
 			goto err_dma_mask;
 		}
 	}
 
-	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (err) {
-		dev_warn(&pdev->dev,
-			 "Couldn't set 64-bit consistent DMA mask\n");
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (err) {
-			dev_err(&pdev->dev,
-				"Failed to set consistent DMA mask\n");
-			goto err_dma_consistent_mask;
-		}
-	}
-
 	err = nic_dev_init(pdev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to initialize NIC device\n");
@@ -1424,7 +1412,6 @@ static int hinic_probe(struct pci_dev *pdev,
 	return 0;
 
 err_nic_dev_init:
-err_dma_consistent_mask:
 err_dma_mask:
 	pci_release_regions(pdev);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
index f8a26459ff65..a78c398bf5b2 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
@@ -836,8 +836,10 @@ int hinic_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting)
 int hinic_ndo_set_vf_bw(struct net_device *netdev,
 			int vf, int min_tx_rate, int max_tx_rate)
 {
-	u32 speeds[] = {SPEED_10, SPEED_100, SPEED_1000, SPEED_10000,
-			SPEED_25000, SPEED_40000, SPEED_100000};
+	static const u32 speeds[] = {
+		SPEED_10, SPEED_100, SPEED_1000, SPEED_10000,
+		SPEED_25000, SPEED_40000, SPEED_100000
+	};
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	struct hinic_port_cap port_cap = { 0 };
 	enum hinic_port_link_state link_state;
diff --git a/drivers/net/ethernet/i825xx/82596.c b/drivers/net/ethernet/i825xx/82596.c
index fc8c7cd67471..b8a40146b895 100644
--- a/drivers/net/ethernet/i825xx/82596.c
+++ b/drivers/net/ethernet/i825xx/82596.c
@@ -1110,9 +1110,6 @@ static void print_eth(unsigned char *add, char *str)
 	       add, add + 6, add, add[12], add[13], str);
 }
 
-static int io = 0x300;
-static int irq = 10;
-
 static const struct net_device_ops i596_netdev_ops = {
 	.ndo_open 		= i596_open,
 	.ndo_stop		= i596_close,
@@ -1123,7 +1120,7 @@ static const struct net_device_ops i596_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
-struct net_device * __init i82596_probe(int unit)
+static struct net_device * __init i82596_probe(void)
 {
 	struct net_device *dev;
 	int i;
@@ -1140,14 +1137,6 @@ struct net_device * __init i82596_probe(int unit)
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	if (unit >= 0) {
-		sprintf(dev->name, "eth%d", unit);
-		netdev_boot_setup_check(dev);
-	} else {
-		dev->base_addr = io;
-		dev->irq = irq;
-	}
-
 #ifdef ENABLE_MVME16x_NET
 	if (MACH_IS_MVME16x) {
 		if (mvme16x_config & MVME16x_CONFIG_NO_ETHERNET) {
@@ -1515,22 +1504,22 @@ static void set_multicast_list(struct net_device *dev)
 	}
 }
 
-#ifdef MODULE
 static struct net_device *dev_82596;
 
 static int debug = -1;
 module_param(debug, int, 0);
 MODULE_PARM_DESC(debug, "i82596 debug mask");
 
-int __init init_module(void)
+static int __init i82596_init(void)
 {
 	if (debug >= 0)
 		i596_debug = debug;
-	dev_82596 = i82596_probe(-1);
+	dev_82596 = i82596_probe();
 	return PTR_ERR_OR_ZERO(dev_82596);
 }
+module_init(i82596_init);
 
-void __exit cleanup_module(void)
+static void __exit i82596_cleanup(void)
 {
 	unregister_netdev(dev_82596);
 #ifdef __mc68000__
@@ -1544,5 +1533,4 @@ void __exit cleanup_module(void)
 	free_page ((u32)(dev_82596->mem_start));
 	free_netdev(dev_82596);
 }
-
-#endif				/* MODULE */
+module_exit(i82596_cleanup);
diff --git a/drivers/net/ethernet/i825xx/sun3_82586.c b/drivers/net/ethernet/i825xx/sun3_82586.c
index 4564ee02c95f..893e0ddcb611 100644
--- a/drivers/net/ethernet/i825xx/sun3_82586.c
+++ b/drivers/net/ethernet/i825xx/sun3_82586.c
@@ -29,6 +29,7 @@ static int rfdadd = 0; /* rfdadd=1 may be better for 8K MEM cards */
 static int fifo=0x8;	/* don't change */
 
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/ioport.h>
@@ -276,7 +277,7 @@ static void alloc586(struct net_device *dev)
 	memset((char *)p->scb,0,sizeof(struct scb_struct));
 }
 
-struct net_device * __init sun3_82586_probe(int unit)
+static int __init sun3_82586_probe(void)
 {
 	struct net_device *dev;
 	unsigned long ioaddr;
@@ -291,25 +292,20 @@ struct net_device * __init sun3_82586_probe(int unit)
 		break;
 
 	default:
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 	}
 
 	if (found)
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	ioaddr = (unsigned long)ioremap(IE_OBIO, SUN3_82586_TOTAL_SIZE);
 	if (!ioaddr)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 	found = 1;
 
 	dev = alloc_etherdev(sizeof(struct priv));
 	if (!dev)
 		goto out;
-	if (unit >= 0) {
-		sprintf(dev->name, "eth%d", unit);
-		netdev_boot_setup_check(dev);
-	}
-
 	dev->irq = IE_IRQ;
 	dev->base_addr = ioaddr;
 	err = sun3_82586_probe1(dev, ioaddr);
@@ -326,8 +322,9 @@ out1:
 	free_netdev(dev);
 out:
 	iounmap((void __iomem *)ioaddr);
-	return ERR_PTR(err);
+	return err;
 }
+module_init(sun3_82586_probe);
 
 static const struct net_device_ops sun3_82586_netdev_ops = {
 	.ndo_open		= sun3_82586_open,
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 471be6ec7e8a..664a91af662d 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -3011,7 +3011,7 @@ static const struct net_device_ops emac_netdev_ops = {
 	.ndo_stop		= emac_close,
 	.ndo_get_stats		= emac_stats,
 	.ndo_set_rx_mode	= emac_set_multicast_list,
-	.ndo_do_ioctl		= emac_ioctl,
+	.ndo_eth_ioctl		= emac_ioctl,
 	.ndo_tx_timeout		= emac_tx_timeout,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= emac_set_mac_address,
@@ -3023,7 +3023,7 @@ static const struct net_device_ops emac_gige_netdev_ops = {
 	.ndo_stop		= emac_close,
 	.ndo_get_stats		= emac_stats,
 	.ndo_set_rx_mode	= emac_set_multicast_list,
-	.ndo_do_ioctl		= emac_ioctl,
+	.ndo_eth_ioctl		= emac_ioctl,
 	.ndo_tx_timeout		= emac_tx_timeout,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= emac_set_mac_address,
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 737ba85e409f..3d9b4f99d357 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1630,7 +1630,7 @@ static const struct net_device_ops ibmveth_netdev_ops = {
 	.ndo_stop		= ibmveth_close,
 	.ndo_start_xmit		= ibmveth_start_xmit,
 	.ndo_set_rx_mode	= ibmveth_set_multicast_list,
-	.ndo_do_ioctl		= ibmveth_ioctl,
+	.ndo_eth_ioctl		= ibmveth_ioctl,
 	.ndo_change_mtu		= ibmveth_change_mtu,
 	.ndo_fix_features	= ibmveth_fix_features,
 	.ndo_set_features	= ibmveth_set_features,
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 82744a7501c7..b0b6f90deb7d 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -58,8 +58,8 @@ config E1000
 config E1000E
 	tristate "Intel(R) PRO/1000 PCI-Express Gigabit Ethernet support"
 	depends on PCI && (!SPARC32 || BROKEN)
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select CRC32
-	imply PTP_1588_CLOCK
 	help
 	  This driver supports the PCI-Express Intel(R) PRO/1000 gigabit
 	  ethernet family of adapters. For PCI or PCI-X e1000 adapters,
@@ -87,7 +87,7 @@ config E1000E_HWTS
 config IGB
 	tristate "Intel(R) 82575/82576 PCI-Express Gigabit Ethernet support"
 	depends on PCI
-	imply PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select I2C
 	select I2C_ALGOBIT
 	help
@@ -159,9 +159,9 @@ config IXGB
 config IXGBE
 	tristate "Intel(R) 10GbE PCI Express adapters support"
 	depends on PCI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select MDIO
 	select PHYLIB
-	imply PTP_1588_CLOCK
 	help
 	  This driver supports Intel(R) 10GbE PCI Express family of
 	  adapters.  For more information on how to identify your adapter, go
@@ -239,7 +239,7 @@ config IXGBEVF_IPSEC
 
 config I40E
 	tristate "Intel(R) Ethernet Controller XL710 Family support"
-	imply PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	depends on PCI
 	select AUXILIARY_BUS
 	help
@@ -295,11 +295,11 @@ config ICE
 	tristate "Intel(R) Ethernet Connection E800 Series Support"
 	default n
 	depends on PCI_MSI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select AUXILIARY_BUS
 	select DIMLIB
 	select NET_DEVLINK
 	select PLDMFW
-	imply PTP_1588_CLOCK
 	help
 	  This driver supports Intel(R) Ethernet Connection E800 Series of
 	  devices.  For more information on how to identify your adapter, go
@@ -317,7 +317,7 @@ config FM10K
 	tristate "Intel(R) FM10000 Ethernet Switch Host Interface Support"
 	default n
 	depends on PCI_MSI
-	imply PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  This driver supports Intel(R) FM10000 Ethernet Switch Host
 	  Interface.  For more information on how to identify your adapter,
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 1b0958bd24f6..373eb027b925 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -2715,10 +2715,10 @@ static void e100_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 {
 	switch (stringset) {
 	case ETH_SS_TEST:
-		memcpy(data, *e100_gstrings_test, sizeof(e100_gstrings_test));
+		memcpy(data, e100_gstrings_test, sizeof(e100_gstrings_test));
 		break;
 	case ETH_SS_STATS:
-		memcpy(data, *e100_gstrings_stats, sizeof(e100_gstrings_stats));
+		memcpy(data, e100_gstrings_stats, sizeof(e100_gstrings_stats));
 		break;
 	}
 }
@@ -2809,7 +2809,7 @@ static const struct net_device_ops e100_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= e100_set_multicast_list,
 	.ndo_set_mac_address	= e100_set_mac_address,
-	.ndo_do_ioctl		= e100_do_ioctl,
+	.ndo_eth_ioctl		= e100_do_ioctl,
 	.ndo_tx_timeout		= e100_tx_timeout,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= e100_netpoll,
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index 3c51ee94fa00..0a57172dfcbc 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -1739,7 +1739,9 @@ static int e1000_set_phys_id(struct net_device *netdev,
 }
 
 static int e1000_get_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 
@@ -1755,7 +1757,9 @@ static int e1000_get_coalesce(struct net_device *netdev,
 }
 
 static int e1000_set_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index c2a109126c27..bed4f040face 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -832,7 +832,7 @@ static const struct net_device_ops e1000_netdev_ops = {
 	.ndo_set_mac_address	= e1000_set_mac,
 	.ndo_tx_timeout		= e1000_tx_timeout,
 	.ndo_change_mtu		= e1000_change_mtu,
-	.ndo_do_ioctl		= e1000_ioctl,
+	.ndo_eth_ioctl		= e1000_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_vlan_rx_add_vid	= e1000_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= e1000_vlan_rx_kill_vid,
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 06442e6bef73..8515e00d1b40 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -903,6 +903,7 @@ static int e1000_reg_test(struct e1000_adapter *adapter, u64 *data)
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
 	case e1000_pch_mtp:
+	case e1000_pch_lnp:
 		mask |= BIT(18);
 		break;
 	default:
@@ -1569,6 +1570,7 @@ static void e1000_loopback_cleanup(struct e1000_adapter *adapter)
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
 	case e1000_pch_mtp:
+	case e1000_pch_lnp:
 		fext_nvm11 = er32(FEXTNVM11);
 		fext_nvm11 &= ~E1000_FEXTNVM11_DISABLE_MULR_FIX;
 		ew32(FEXTNVM11, fext_nvm11);
@@ -1991,7 +1993,9 @@ static int e1000_set_phys_id(struct net_device *netdev,
 }
 
 static int e1000_get_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 
@@ -2004,7 +2008,9 @@ static int e1000_get_coalesce(struct net_device *netdev,
 }
 
 static int e1000_set_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index db79c4e6413e..bcf680e83811 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -98,14 +98,22 @@ struct e1000_hw;
 #define E1000_DEV_ID_PCH_TGP_I219_V14		0x15FA
 #define E1000_DEV_ID_PCH_TGP_I219_LM15		0x15F4
 #define E1000_DEV_ID_PCH_TGP_I219_V15		0x15F5
+#define E1000_DEV_ID_PCH_RPL_I219_LM23		0x0DC5
+#define E1000_DEV_ID_PCH_RPL_I219_V23		0x0DC6
 #define E1000_DEV_ID_PCH_ADP_I219_LM16		0x1A1E
 #define E1000_DEV_ID_PCH_ADP_I219_V16		0x1A1F
 #define E1000_DEV_ID_PCH_ADP_I219_LM17		0x1A1C
 #define E1000_DEV_ID_PCH_ADP_I219_V17		0x1A1D
+#define E1000_DEV_ID_PCH_RPL_I219_LM22		0x0DC7
+#define E1000_DEV_ID_PCH_RPL_I219_V22		0x0DC8
 #define E1000_DEV_ID_PCH_MTP_I219_LM18		0x550A
 #define E1000_DEV_ID_PCH_MTP_I219_V18		0x550B
 #define E1000_DEV_ID_PCH_MTP_I219_LM19		0x550C
 #define E1000_DEV_ID_PCH_MTP_I219_V19		0x550D
+#define E1000_DEV_ID_PCH_LNP_I219_LM20		0x550E
+#define E1000_DEV_ID_PCH_LNP_I219_V20		0x550F
+#define E1000_DEV_ID_PCH_LNP_I219_LM21		0x5510
+#define E1000_DEV_ID_PCH_LNP_I219_V21		0x5511
 
 #define E1000_REVISION_4	4
 
@@ -132,6 +140,7 @@ enum e1000_mac_type {
 	e1000_pch_tgp,
 	e1000_pch_adp,
 	e1000_pch_mtp,
+	e1000_pch_lnp,
 };
 
 enum e1000_media_type {
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index a80336c4319b..60c582a16821 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -321,6 +321,7 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
 	case e1000_pch_mtp:
+	case e1000_pch_lnp:
 		if (e1000_phy_is_accessible_pchlan(hw))
 			break;
 
@@ -466,6 +467,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw)
 		case e1000_pch_tgp:
 		case e1000_pch_adp:
 		case e1000_pch_mtp:
+		case e1000_pch_lnp:
 			/* In case the PHY needs to be in mdio slow mode,
 			 * set slow mode and try to get the PHY id again.
 			 */
@@ -711,6 +713,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw)
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
 	case e1000_pch_mtp:
+	case e1000_pch_lnp:
 	case e1000_pchlan:
 		/* check management mode */
 		mac->ops.check_mng_mode = e1000_check_mng_mode_pchlan;
@@ -1278,9 +1281,11 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force)
 			usleep_range(10000, 11000);
 		}
 		if (firmware_bug)
-			e_warn("ULP_CONFIG_DONE took %dmsec.  This is a firmware bug\n", i * 10);
+			e_warn("ULP_CONFIG_DONE took %d msec. This is a firmware bug\n",
+			       i * 10);
 		else
-			e_dbg("ULP_CONFIG_DONE cleared after %dmsec\n", i * 10);
+			e_dbg("ULP_CONFIG_DONE cleared after %d msec\n",
+			      i * 10);
 
 		if (force) {
 			mac_reg = er32(H2ME);
@@ -1675,6 +1680,7 @@ static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter)
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
 	case e1000_pch_mtp:
+	case e1000_pch_lnp:
 		rc = e1000_init_phy_params_pchlan(hw);
 		break;
 	default:
@@ -2130,6 +2136,7 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw)
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
 	case e1000_pch_mtp:
+	case e1000_pch_lnp:
 		sw_cfg_mask = E1000_FEXTNVM_SW_CONFIG_ICH8M;
 		break;
 	default:
@@ -3174,6 +3181,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank)
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
 	case e1000_pch_mtp:
+	case e1000_pch_lnp:
 		bank1_offset = nvm->flash_bank_size;
 		act_offset = E1000_ICH_NVM_SIG_WORD;
 
@@ -4113,6 +4121,7 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw)
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
 	case e1000_pch_mtp:
+	case e1000_pch_lnp:
 		word = NVM_COMPAT;
 		valid_csum_mask = NVM_COMPAT_VALID_CSUM;
 		break;
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h
index e757896287eb..d6a092e5ee74 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.h
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h
@@ -41,12 +41,15 @@
 #define E1000_FWSM_WLOCK_MAC_MASK	0x0380
 #define E1000_FWSM_WLOCK_MAC_SHIFT	7
 #define E1000_FWSM_ULP_CFG_DONE		0x00000400	/* Low power cfg done */
+#define E1000_EXFWSM_DPG_EXIT_DONE	0x00000001
 
 /* Shared Receive Address Registers */
 #define E1000_SHRAL_PCH_LPT(_i)		(0x05408 + ((_i) * 8))
 #define E1000_SHRAH_PCH_LPT(_i)		(0x0540C + ((_i) * 8))
 
 #define E1000_H2ME		0x05B50	/* Host to ME */
+#define E1000_H2ME_START_DPG	0x00000001	/* indicate the ME of DPG */
+#define E1000_H2ME_EXIT_DPG	0x00000002	/* indicate the ME exit DPG */
 #define E1000_H2ME_ULP		0x00000800	/* ULP Indication Bit */
 #define E1000_H2ME_ENFORCE_SETTINGS	0x00001000	/* Enforce Settings */
 
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 757a54c39eef..900b3ab998bd 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3550,6 +3550,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
 	case e1000_pch_mtp:
+	case e1000_pch_lnp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
 			/* Stable 24MHz frequency */
 			incperiod = INCPERIOD_24MHZ;
@@ -4068,6 +4069,7 @@ void e1000e_reset(struct e1000_adapter *adapter)
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
 	case e1000_pch_mtp:
+	case e1000_pch_lnp:
 		fc->refresh_time = 0xFFFF;
 		fc->pause_time = 0xFFFF;
 
@@ -6343,42 +6345,110 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter)
 	u32 mac_data;
 	u16 phy_data;
 
-	/* Disable the periodic inband message,
-	 * don't request PCIe clock in K1 page770_17[10:9] = 10b
-	 */
-	e1e_rphy(hw, HV_PM_CTRL, &phy_data);
-	phy_data &= ~HV_PM_CTRL_K1_CLK_REQ;
-	phy_data |= BIT(10);
-	e1e_wphy(hw, HV_PM_CTRL, phy_data);
+	if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) {
+		/* Request ME configure the device for S0ix */
+		mac_data = er32(H2ME);
+		mac_data |= E1000_H2ME_START_DPG;
+		mac_data &= ~E1000_H2ME_EXIT_DPG;
+		ew32(H2ME, mac_data);
+	} else {
+		/* Request driver configure the device to S0ix */
+		/* Disable the periodic inband message,
+		 * don't request PCIe clock in K1 page770_17[10:9] = 10b
+		 */
+		e1e_rphy(hw, HV_PM_CTRL, &phy_data);
+		phy_data &= ~HV_PM_CTRL_K1_CLK_REQ;
+		phy_data |= BIT(10);
+		e1e_wphy(hw, HV_PM_CTRL, phy_data);
 
-	/* Make sure we don't exit K1 every time a new packet arrives
-	 * 772_29[5] = 1 CS_Mode_Stay_In_K1
-	 */
-	e1e_rphy(hw, I217_CGFREG, &phy_data);
-	phy_data |= BIT(5);
-	e1e_wphy(hw, I217_CGFREG, phy_data);
+		/* Make sure we don't exit K1 every time a new packet arrives
+		 * 772_29[5] = 1 CS_Mode_Stay_In_K1
+		 */
+		e1e_rphy(hw, I217_CGFREG, &phy_data);
+		phy_data |= BIT(5);
+		e1e_wphy(hw, I217_CGFREG, phy_data);
 
-	/* Change the MAC/PHY interface to SMBus
-	 * Force the SMBus in PHY page769_23[0] = 1
-	 * Force the SMBus in MAC CTRL_EXT[11] = 1
-	 */
-	e1e_rphy(hw, CV_SMB_CTRL, &phy_data);
-	phy_data |= CV_SMB_CTRL_FORCE_SMBUS;
-	e1e_wphy(hw, CV_SMB_CTRL, phy_data);
-	mac_data = er32(CTRL_EXT);
-	mac_data |= E1000_CTRL_EXT_FORCE_SMBUS;
-	ew32(CTRL_EXT, mac_data);
+		/* Change the MAC/PHY interface to SMBus
+		 * Force the SMBus in PHY page769_23[0] = 1
+		 * Force the SMBus in MAC CTRL_EXT[11] = 1
+		 */
+		e1e_rphy(hw, CV_SMB_CTRL, &phy_data);
+		phy_data |= CV_SMB_CTRL_FORCE_SMBUS;
+		e1e_wphy(hw, CV_SMB_CTRL, phy_data);
+		mac_data = er32(CTRL_EXT);
+		mac_data |= E1000_CTRL_EXT_FORCE_SMBUS;
+		ew32(CTRL_EXT, mac_data);
+
+		/* DFT control: PHY bit: page769_20[0] = 1
+		 * page769_20[7] - PHY PLL stop
+		 * page769_20[8] - PHY go to the electrical idle
+		 * page769_20[9] - PHY serdes disable
+		 * Gate PPW via EXTCNF_CTRL - set 0x0F00[7] = 1
+		 */
+		e1e_rphy(hw, I82579_DFT_CTRL, &phy_data);
+		phy_data |= BIT(0);
+		phy_data |= BIT(7);
+		phy_data |= BIT(8);
+		phy_data |= BIT(9);
+		e1e_wphy(hw, I82579_DFT_CTRL, phy_data);
+
+		mac_data = er32(EXTCNF_CTRL);
+		mac_data |= E1000_EXTCNF_CTRL_GATE_PHY_CFG;
+		ew32(EXTCNF_CTRL, mac_data);
+
+		/* Enable the Dynamic Power Gating in the MAC */
+		mac_data = er32(FEXTNVM7);
+		mac_data |= BIT(22);
+		ew32(FEXTNVM7, mac_data);
+
+		/* Disable disconnected cable conditioning for Power Gating */
+		mac_data = er32(DPGFR);
+		mac_data |= BIT(2);
+		ew32(DPGFR, mac_data);
+
+		/* Don't wake from dynamic Power Gating with clock request */
+		mac_data = er32(FEXTNVM12);
+		mac_data |= BIT(12);
+		ew32(FEXTNVM12, mac_data);
+
+		/* Ungate PGCB clock */
+		mac_data = er32(FEXTNVM9);
+		mac_data &= ~BIT(28);
+		ew32(FEXTNVM9, mac_data);
+
+		/* Enable K1 off to enable mPHY Power Gating */
+		mac_data = er32(FEXTNVM6);
+		mac_data |= BIT(31);
+		ew32(FEXTNVM6, mac_data);
+
+		/* Enable mPHY power gating for any link and speed */
+		mac_data = er32(FEXTNVM8);
+		mac_data |= BIT(9);
+		ew32(FEXTNVM8, mac_data);
+
+		/* Enable the Dynamic Clock Gating in the DMA and MAC */
+		mac_data = er32(CTRL_EXT);
+		mac_data |= E1000_CTRL_EXT_DMA_DYN_CLK_EN;
+		ew32(CTRL_EXT, mac_data);
+
+		/* No MAC DPG gating SLP_S0 in modern standby
+		 * Switch the logic of the lanphypc to use PMC counter
+		 */
+		mac_data = er32(FEXTNVM5);
+		mac_data |= BIT(7);
+		ew32(FEXTNVM5, mac_data);
+	}
 
-	/* DFT control: PHY bit: page769_20[0] = 1
-	 * Gate PPW via EXTCNF_CTRL - set 0x0F00[7] = 1
-	 */
-	e1e_rphy(hw, I82579_DFT_CTRL, &phy_data);
-	phy_data |= BIT(0);
-	e1e_wphy(hw, I82579_DFT_CTRL, phy_data);
+	/* Disable the time synchronization clock */
+	mac_data = er32(FEXTNVM7);
+	mac_data |= BIT(31);
+	mac_data &= ~BIT(0);
+	ew32(FEXTNVM7, mac_data);
 
-	mac_data = er32(EXTCNF_CTRL);
-	mac_data |= E1000_EXTCNF_CTRL_GATE_PHY_CFG;
-	ew32(EXTCNF_CTRL, mac_data);
+	/* Dynamic Power Gating Enable */
+	mac_data = er32(CTRL_EXT);
+	mac_data |= BIT(3);
+	ew32(CTRL_EXT, mac_data);
 
 	/* Check MAC Tx/Rx packet buffer pointers.
 	 * Reset MAC Tx/Rx packet buffer pointers to suppress any
@@ -6414,148 +6484,130 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter)
 	mac_data = er32(RDFPC);
 	if (mac_data)
 		ew32(RDFPC, 0);
-
-	/* Enable the Dynamic Power Gating in the MAC */
-	mac_data = er32(FEXTNVM7);
-	mac_data |= BIT(22);
-	ew32(FEXTNVM7, mac_data);
-
-	/* Disable the time synchronization clock */
-	mac_data = er32(FEXTNVM7);
-	mac_data |= BIT(31);
-	mac_data &= ~BIT(0);
-	ew32(FEXTNVM7, mac_data);
-
-	/* Dynamic Power Gating Enable */
-	mac_data = er32(CTRL_EXT);
-	mac_data |= BIT(3);
-	ew32(CTRL_EXT, mac_data);
-
-	/* Disable disconnected cable conditioning for Power Gating */
-	mac_data = er32(DPGFR);
-	mac_data |= BIT(2);
-	ew32(DPGFR, mac_data);
-
-	/* Don't wake from dynamic Power Gating with clock request */
-	mac_data = er32(FEXTNVM12);
-	mac_data |= BIT(12);
-	ew32(FEXTNVM12, mac_data);
-
-	/* Ungate PGCB clock */
-	mac_data = er32(FEXTNVM9);
-	mac_data &= ~BIT(28);
-	ew32(FEXTNVM9, mac_data);
-
-	/* Enable K1 off to enable mPHY Power Gating */
-	mac_data = er32(FEXTNVM6);
-	mac_data |= BIT(31);
-	ew32(FEXTNVM6, mac_data);
-
-	/* Enable mPHY power gating for any link and speed */
-	mac_data = er32(FEXTNVM8);
-	mac_data |= BIT(9);
-	ew32(FEXTNVM8, mac_data);
-
-	/* Enable the Dynamic Clock Gating in the DMA and MAC */
-	mac_data = er32(CTRL_EXT);
-	mac_data |= E1000_CTRL_EXT_DMA_DYN_CLK_EN;
-	ew32(CTRL_EXT, mac_data);
-
-	/* No MAC DPG gating SLP_S0 in modern standby
-	 * Switch the logic of the lanphypc to use PMC counter
-	 */
-	mac_data = er32(FEXTNVM5);
-	mac_data |= BIT(7);
-	ew32(FEXTNVM5, mac_data);
 }
 
 static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
+	bool firmware_bug = false;
 	u32 mac_data;
 	u16 phy_data;
+	u32 i = 0;
+
+	if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) {
+		/* Request ME unconfigure the device from S0ix */
+		mac_data = er32(H2ME);
+		mac_data &= ~E1000_H2ME_START_DPG;
+		mac_data |= E1000_H2ME_EXIT_DPG;
+		ew32(H2ME, mac_data);
+
+		/* Poll up to 2.5 seconds for ME to unconfigure DPG.
+		 * If this takes more than 1 second, show a warning indicating a
+		 * firmware bug
+		 */
+		while (!(er32(EXFWSM) & E1000_EXFWSM_DPG_EXIT_DONE)) {
+			if (i > 100 && !firmware_bug)
+				firmware_bug = true;
 
-	/* Disable the Dynamic Power Gating in the MAC */
-	mac_data = er32(FEXTNVM7);
-	mac_data &= 0xFFBFFFFF;
-	ew32(FEXTNVM7, mac_data);
+			if (i++ == 250) {
+				e_dbg("Timeout (firmware bug): %d msec\n",
+				      i * 10);
+				break;
+			}
 
-	/* Enable the time synchronization clock */
-	mac_data = er32(FEXTNVM7);
-	mac_data |= BIT(0);
-	ew32(FEXTNVM7, mac_data);
+			usleep_range(10000, 11000);
+		}
+		if (firmware_bug)
+			e_warn("DPG_EXIT_DONE took %d msec. This is a firmware bug\n",
+			       i * 10);
+		else
+			e_dbg("DPG_EXIT_DONE cleared after %d msec\n", i * 10);
+	} else {
+		/* Request driver unconfigure the device from S0ix */
+
+		/* Disable the Dynamic Power Gating in the MAC */
+		mac_data = er32(FEXTNVM7);
+		mac_data &= 0xFFBFFFFF;
+		ew32(FEXTNVM7, mac_data);
+
+		/* Disable mPHY power gating for any link and speed */
+		mac_data = er32(FEXTNVM8);
+		mac_data &= ~BIT(9);
+		ew32(FEXTNVM8, mac_data);
+
+		/* Disable K1 off */
+		mac_data = er32(FEXTNVM6);
+		mac_data &= ~BIT(31);
+		ew32(FEXTNVM6, mac_data);
+
+		/* Disable Ungate PGCB clock */
+		mac_data = er32(FEXTNVM9);
+		mac_data |= BIT(28);
+		ew32(FEXTNVM9, mac_data);
+
+		/* Cancel not waking from dynamic
+		 * Power Gating with clock request
+		 */
+		mac_data = er32(FEXTNVM12);
+		mac_data &= ~BIT(12);
+		ew32(FEXTNVM12, mac_data);
 
-	/* Disable mPHY power gating for any link and speed */
-	mac_data = er32(FEXTNVM8);
-	mac_data &= ~BIT(9);
-	ew32(FEXTNVM8, mac_data);
+		/* Cancel disable disconnected cable conditioning
+		 * for Power Gating
+		 */
+		mac_data = er32(DPGFR);
+		mac_data &= ~BIT(2);
+		ew32(DPGFR, mac_data);
 
-	/* Disable K1 off */
-	mac_data = er32(FEXTNVM6);
-	mac_data &= ~BIT(31);
-	ew32(FEXTNVM6, mac_data);
+		/* Disable the Dynamic Clock Gating in the DMA and MAC */
+		mac_data = er32(CTRL_EXT);
+		mac_data &= 0xFFF7FFFF;
+		ew32(CTRL_EXT, mac_data);
 
-	/* Disable Ungate PGCB clock */
-	mac_data = er32(FEXTNVM9);
-	mac_data |= BIT(28);
-	ew32(FEXTNVM9, mac_data);
+		/* Revert the lanphypc logic to use the internal Gbe counter
+		 * and not the PMC counter
+		 */
+		mac_data = er32(FEXTNVM5);
+		mac_data &= 0xFFFFFF7F;
+		ew32(FEXTNVM5, mac_data);
 
-	/* Cancel not waking from dynamic
-	 * Power Gating with clock request
-	 */
-	mac_data = er32(FEXTNVM12);
-	mac_data &= ~BIT(12);
-	ew32(FEXTNVM12, mac_data);
+		/* Enable the periodic inband message,
+		 * Request PCIe clock in K1 page770_17[10:9] =01b
+		 */
+		e1e_rphy(hw, HV_PM_CTRL, &phy_data);
+		phy_data &= 0xFBFF;
+		phy_data |= HV_PM_CTRL_K1_CLK_REQ;
+		e1e_wphy(hw, HV_PM_CTRL, phy_data);
 
-	/* Cancel disable disconnected cable conditioning
-	 * for Power Gating
-	 */
-	mac_data = er32(DPGFR);
-	mac_data &= ~BIT(2);
-	ew32(DPGFR, mac_data);
+		/* Return back configuration
+		 * 772_29[5] = 0 CS_Mode_Stay_In_K1
+		 */
+		e1e_rphy(hw, I217_CGFREG, &phy_data);
+		phy_data &= 0xFFDF;
+		e1e_wphy(hw, I217_CGFREG, phy_data);
+
+		/* Change the MAC/PHY interface to Kumeran
+		 * Unforce the SMBus in PHY page769_23[0] = 0
+		 * Unforce the SMBus in MAC CTRL_EXT[11] = 0
+		 */
+		e1e_rphy(hw, CV_SMB_CTRL, &phy_data);
+		phy_data &= ~CV_SMB_CTRL_FORCE_SMBUS;
+		e1e_wphy(hw, CV_SMB_CTRL, phy_data);
+		mac_data = er32(CTRL_EXT);
+		mac_data &= ~E1000_CTRL_EXT_FORCE_SMBUS;
+		ew32(CTRL_EXT, mac_data);
+	}
 
 	/* Disable Dynamic Power Gating */
 	mac_data = er32(CTRL_EXT);
 	mac_data &= 0xFFFFFFF7;
 	ew32(CTRL_EXT, mac_data);
 
-	/* Disable the Dynamic Clock Gating in the DMA and MAC */
-	mac_data = er32(CTRL_EXT);
-	mac_data &= 0xFFF7FFFF;
-	ew32(CTRL_EXT, mac_data);
-
-	/* Revert the lanphypc logic to use the internal Gbe counter
-	 * and not the PMC counter
-	 */
-	mac_data = er32(FEXTNVM5);
-	mac_data &= 0xFFFFFF7F;
-	ew32(FEXTNVM5, mac_data);
-
-	/* Enable the periodic inband message,
-	 * Request PCIe clock in K1 page770_17[10:9] =01b
-	 */
-	e1e_rphy(hw, HV_PM_CTRL, &phy_data);
-	phy_data &= 0xFBFF;
-	phy_data |= HV_PM_CTRL_K1_CLK_REQ;
-	e1e_wphy(hw, HV_PM_CTRL, phy_data);
-
-	/* Return back configuration
-	 * 772_29[5] = 0 CS_Mode_Stay_In_K1
-	 */
-	e1e_rphy(hw, I217_CGFREG, &phy_data);
-	phy_data &= 0xFFDF;
-	e1e_wphy(hw, I217_CGFREG, phy_data);
-
-	/* Change the MAC/PHY interface to Kumeran
-	 * Unforce the SMBus in PHY page769_23[0] = 0
-	 * Unforce the SMBus in MAC CTRL_EXT[11] = 0
-	 */
-	e1e_rphy(hw, CV_SMB_CTRL, &phy_data);
-	phy_data &= ~CV_SMB_CTRL_FORCE_SMBUS;
-	e1e_wphy(hw, CV_SMB_CTRL, phy_data);
-	mac_data = er32(CTRL_EXT);
-	mac_data &= ~E1000_CTRL_EXT_FORCE_SMBUS;
-	ew32(CTRL_EXT, mac_data);
+	/* Enable the time synchronization clock */
+	mac_data = er32(FEXTNVM7);
+	mac_data &= ~BIT(31);
+	mac_data |= BIT(0);
+	ew32(FEXTNVM7, mac_data);
 }
 
 static int e1000e_pm_freeze(struct device *dev)
@@ -7302,7 +7354,7 @@ static const struct net_device_ops e1000e_netdev_ops = {
 	.ndo_set_rx_mode	= e1000e_set_rx_mode,
 	.ndo_set_mac_address	= e1000_set_mac,
 	.ndo_change_mtu		= e1000_change_mtu,
-	.ndo_do_ioctl		= e1000_ioctl,
+	.ndo_eth_ioctl		= e1000_ioctl,
 	.ndo_tx_timeout		= e1000_tx_timeout,
 	.ndo_validate_addr	= eth_validate_addr,
 
@@ -7677,7 +7729,7 @@ err_dma:
  * @pdev: PCI device information struct
  *
  * e1000_remove is called by the PCI subsystem to alert the driver
- * that it should release a PCI device.  The could be caused by a
+ * that it should release a PCI device.  This could be caused by a
  * Hot-Plug event, or because the driver is going to be removed from
  * memory.
  **/
@@ -7850,14 +7902,22 @@ static const struct pci_device_id e1000_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V14), board_pch_cnp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM15), board_pch_cnp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V15), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_cnp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_cnp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_cnp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_cnp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_cnp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_cnp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_cnp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_cnp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_cnp },
 
 	{ 0, 0, 0, 0, 0, 0, 0 }	/* terminate list */
 };
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 9e79d672f4f1..eb5c014c02fb 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -298,6 +298,7 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
 	case e1000_pch_mtp:
+	case e1000_pch_lnp:
 		if ((hw->mac.type < e1000_pch_lpt) ||
 		    (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) {
 			adapter->ptp_clock_info.max_adj = 24000000 - 1;
diff --git a/drivers/net/ethernet/intel/e1000e/regs.h b/drivers/net/ethernet/intel/e1000e/regs.h
index 8165ba2619a4..6c0cd8cab3ef 100644
--- a/drivers/net/ethernet/intel/e1000e/regs.h
+++ b/drivers/net/ethernet/intel/e1000e/regs.h
@@ -213,6 +213,7 @@
 #define E1000_FACTPS	0x05B30	/* Function Active and Power State to MNG */
 #define E1000_SWSM	0x05B50	/* SW Semaphore */
 #define E1000_FWSM	0x05B54	/* FW Semaphore */
+#define E1000_EXFWSM	0x05B58	/* Extended FW Semaphore */
 /* Driver-only SW semaphore (not used by BOOT agents) */
 #define E1000_SWSM2	0x05B58
 #define E1000_FFLT_DBG	0x05F04	/* Debug Register */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
index 66776ba7bfb6..0d37f011d0ce 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
@@ -632,7 +632,9 @@ clear_reset:
 }
 
 static int fm10k_get_coalesce(struct net_device *dev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct fm10k_intfc *interface = netdev_priv(dev);
 
@@ -646,7 +648,9 @@ static int fm10k_get_coalesce(struct net_device *dev,
 }
 
 static int fm10k_set_coalesce(struct net_device *dev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct fm10k_intfc *interface = netdev_priv(dev);
 	u16 tx_itr, rx_itr;
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index b9417dc0007c..39fb3d57c057 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -428,6 +428,8 @@ struct i40e_channel {
 	struct i40e_vsi *parent_vsi;
 };
 
+struct i40e_ptp_pins_settings;
+
 static inline bool i40e_is_channel_macvlan(struct i40e_channel *ch)
 {
 	return !!ch->fwd;
@@ -644,12 +646,83 @@ struct i40e_pf {
 	struct i40e_rx_pb_config pb_cfg; /* Current Rx packet buffer config */
 	struct i40e_dcbx_config tmp_cfg;
 
+/* GPIO defines used by PTP */
+#define I40E_SDP3_2			18
+#define I40E_SDP3_3			19
+#define I40E_GPIO_4			20
+#define I40E_LED2_0			26
+#define I40E_LED2_1			27
+#define I40E_LED3_0			28
+#define I40E_LED3_1			29
+#define I40E_GLGEN_GPIO_SET_SDP_DATA_HI \
+	(1 << I40E_GLGEN_GPIO_SET_SDP_DATA_SHIFT)
+#define I40E_GLGEN_GPIO_SET_DRV_SDP_DATA \
+	(1 << I40E_GLGEN_GPIO_SET_DRIVE_SDP_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_PRT_NUM_0 \
+	(0 << I40E_GLGEN_GPIO_CTL_PRT_NUM_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_PRT_NUM_1 \
+	(1 << I40E_GLGEN_GPIO_CTL_PRT_NUM_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_RESERVED	BIT(2)
+#define I40E_GLGEN_GPIO_CTL_PRT_NUM_NA_Z \
+	(1 << I40E_GLGEN_GPIO_CTL_PRT_NUM_NA_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_DIR_OUT \
+	(1 << I40E_GLGEN_GPIO_CTL_PIN_DIR_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_TRI_DRV_HI \
+	(1 << I40E_GLGEN_GPIO_CTL_TRI_CTL_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_OUT_HI_RST \
+	(1 << I40E_GLGEN_GPIO_CTL_OUT_CTL_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_TIMESYNC_0 \
+	(3 << I40E_GLGEN_GPIO_CTL_PIN_FUNC_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_TIMESYNC_1 \
+	(4 << I40E_GLGEN_GPIO_CTL_PIN_FUNC_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_NOT_FOR_PHY_CONN \
+	(0x3F << I40E_GLGEN_GPIO_CTL_PHY_PIN_NAME_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_OUT_DEFAULT \
+	(1 << I40E_GLGEN_GPIO_CTL_OUT_DEFAULT_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_PORT_0_IN_TIMESYNC_0 \
+	(I40E_GLGEN_GPIO_CTL_NOT_FOR_PHY_CONN | \
+	 I40E_GLGEN_GPIO_CTL_TIMESYNC_0 | \
+	 I40E_GLGEN_GPIO_CTL_RESERVED | I40E_GLGEN_GPIO_CTL_PRT_NUM_0)
+#define I40E_GLGEN_GPIO_CTL_PORT_1_IN_TIMESYNC_0 \
+	(I40E_GLGEN_GPIO_CTL_NOT_FOR_PHY_CONN | \
+	 I40E_GLGEN_GPIO_CTL_TIMESYNC_0 | \
+	 I40E_GLGEN_GPIO_CTL_RESERVED | I40E_GLGEN_GPIO_CTL_PRT_NUM_1)
+#define I40E_GLGEN_GPIO_CTL_PORT_0_OUT_TIMESYNC_1 \
+	(I40E_GLGEN_GPIO_CTL_NOT_FOR_PHY_CONN | \
+	 I40E_GLGEN_GPIO_CTL_TIMESYNC_1 | I40E_GLGEN_GPIO_CTL_OUT_HI_RST | \
+	 I40E_GLGEN_GPIO_CTL_TRI_DRV_HI | I40E_GLGEN_GPIO_CTL_DIR_OUT | \
+	 I40E_GLGEN_GPIO_CTL_RESERVED | I40E_GLGEN_GPIO_CTL_PRT_NUM_0)
+#define I40E_GLGEN_GPIO_CTL_PORT_1_OUT_TIMESYNC_1 \
+	(I40E_GLGEN_GPIO_CTL_NOT_FOR_PHY_CONN | \
+	 I40E_GLGEN_GPIO_CTL_TIMESYNC_1 | I40E_GLGEN_GPIO_CTL_OUT_HI_RST | \
+	 I40E_GLGEN_GPIO_CTL_TRI_DRV_HI | I40E_GLGEN_GPIO_CTL_DIR_OUT | \
+	 I40E_GLGEN_GPIO_CTL_RESERVED | I40E_GLGEN_GPIO_CTL_PRT_NUM_1)
+#define I40E_GLGEN_GPIO_CTL_LED_INIT \
+	(I40E_GLGEN_GPIO_CTL_PRT_NUM_NA_Z | \
+	 I40E_GLGEN_GPIO_CTL_DIR_OUT | \
+	 I40E_GLGEN_GPIO_CTL_TRI_DRV_HI | \
+	 I40E_GLGEN_GPIO_CTL_OUT_HI_RST | \
+	 I40E_GLGEN_GPIO_CTL_OUT_DEFAULT | \
+	 I40E_GLGEN_GPIO_CTL_NOT_FOR_PHY_CONN)
+#define I40E_PRTTSYN_AUX_1_INSTNT \
+	(1 << I40E_PRTTSYN_AUX_1_INSTNT_SHIFT)
+#define I40E_PRTTSYN_AUX_0_OUT_ENABLE \
+	(1 << I40E_PRTTSYN_AUX_0_OUT_ENA_SHIFT)
+#define I40E_PRTTSYN_AUX_0_OUT_CLK_MOD	(3 << I40E_PRTTSYN_AUX_0_OUTMOD_SHIFT)
+#define I40E_PRTTSYN_AUX_0_OUT_ENABLE_CLK_MOD \
+	(I40E_PRTTSYN_AUX_0_OUT_ENABLE | I40E_PRTTSYN_AUX_0_OUT_CLK_MOD)
+#define I40E_PTP_HALF_SECOND		500000000LL /* nano seconds */
+#define I40E_PTP_2_SEC_DELAY		2
+
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_caps;
 	struct sk_buff *ptp_tx_skb;
 	unsigned long ptp_tx_start;
 	struct hwtstamp_config tstamp_config;
 	struct timespec64 ptp_prev_hw_time;
+	struct work_struct ptp_pps_work;
+	struct work_struct ptp_extts0_work;
+	struct work_struct ptp_extts1_work;
 	ktime_t ptp_reset_start;
 	struct mutex tmreg_lock; /* Used to protect the SYSTIME registers. */
 	u32 ptp_adj_mult;
@@ -657,10 +730,14 @@ struct i40e_pf {
 	u32 tx_hwtstamp_skipped;
 	u32 rx_hwtstamp_cleared;
 	u32 latch_event_flags;
+	u64 ptp_pps_start;
+	u32 pps_delay;
 	spinlock_t ptp_rx_lock; /* Used to protect Rx timestamp registers. */
+	struct ptp_pin_desc ptp_pin[3];
 	unsigned long latch_events[4];
 	bool ptp_tx;
 	bool ptp_rx;
+	struct i40e_ptp_pins_settings *ptp_pins;
 	u16 rss_table_size; /* HW RSS table size */
 	u32 max_bw;
 	u32 min_bw;
@@ -1169,6 +1246,7 @@ void i40e_ptp_save_hw_time(struct i40e_pf *pf);
 void i40e_ptp_restore_hw_time(struct i40e_pf *pf);
 void i40e_ptp_init(struct i40e_pf *pf);
 void i40e_ptp_stop(struct i40e_pf *pf);
+int i40e_ptp_alloc_pins(struct i40e_pf *pf);
 int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi);
 i40e_status i40e_get_partition_bw_setting(struct i40e_pf *pf);
 i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 2c9e4eeb7270..513ba6974355 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -2812,13 +2812,17 @@ static int __i40e_get_coalesce(struct net_device *netdev,
  * i40e_get_coalesce - get a netdev's coalesce settings
  * @netdev: the netdev to check
  * @ec: ethtool coalesce data structure
+ * @kernel_coal: ethtool CQE mode setting structure
+ * @extack: extack for reporting error messages
  *
  * Gets the coalesce settings for a particular netdev. Note that if user has
  * modified per-queue settings, this only guarantees to represent queue 0. See
  * __i40e_get_coalesce for more details.
  **/
 static int i40e_get_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *ec)
+			     struct ethtool_coalesce *ec,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	return __i40e_get_coalesce(netdev, ec, -1);
 }
@@ -2986,11 +2990,15 @@ static int __i40e_set_coalesce(struct net_device *netdev,
  * i40e_set_coalesce - set coalesce settings for every queue on the netdev
  * @netdev: the netdev to change
  * @ec: ethtool coalesce settings
+ * @kernel_coal: ethtool CQE mode setting structure
+ * @extack: extack for reporting error messages
  *
  * This will set each queue to the same coalesce settings.
  **/
 static int i40e_set_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *ec)
+			     struct ethtool_coalesce *ec,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	return __i40e_set_coalesce(netdev, ec, -1);
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 1d1f52756a93..2f20980dd9a5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4079,10 +4079,13 @@ static irqreturn_t i40e_intr(int irq, void *data)
 	if (icr0 & I40E_PFINT_ICR0_TIMESYNC_MASK) {
 		u32 prttsyn_stat = rd32(hw, I40E_PRTTSYN_STAT_0);
 
-		if (prttsyn_stat & I40E_PRTTSYN_STAT_0_TXTIME_MASK) {
-			icr0 &= ~I40E_PFINT_ICR0_ENA_TIMESYNC_MASK;
+		if (prttsyn_stat & I40E_PRTTSYN_STAT_0_EVENT0_MASK)
+			schedule_work(&pf->ptp_extts0_work);
+
+		if (prttsyn_stat & I40E_PRTTSYN_STAT_0_TXTIME_MASK)
 			i40e_ptp_tx_hwtstamp(pf);
-		}
+
+		icr0 &= ~I40E_PFINT_ICR0_ENA_TIMESYNC_MASK;
 	}
 
 	/* If a critical error is pending we have no choice but to reset the
@@ -4635,7 +4638,7 @@ void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
 		err = i40e_control_wait_rx_q(pf, pf_q, false);
 		if (err)
 			dev_info(&pf->pdev->dev,
-				 "VSI seid %d Rx ring %d dissable timeout\n",
+				 "VSI seid %d Rx ring %d disable timeout\n",
 				 vsi->seid, pf_q);
 	}
 
@@ -13265,7 +13268,7 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= i40e_set_mac,
 	.ndo_change_mtu		= i40e_change_mtu,
-	.ndo_do_ioctl		= i40e_ioctl,
+	.ndo_eth_ioctl		= i40e_ioctl,
 	.ndo_tx_timeout		= i40e_tx_timeout,
 	.ndo_vlan_rx_add_vid	= i40e_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= i40e_vlan_rx_kill_vid,
@@ -15181,6 +15184,22 @@ err_switch_setup:
 }
 
 /**
+ * i40e_set_subsystem_device_id - set subsystem device id
+ * @hw: pointer to the hardware info
+ *
+ * Set PCI subsystem device id either from a pci_dev structure or
+ * a specific FW register.
+ **/
+static inline void i40e_set_subsystem_device_id(struct i40e_hw *hw)
+{
+	struct pci_dev *pdev = ((struct i40e_pf *)hw->back)->pdev;
+
+	hw->subsystem_device_id = pdev->subsystem_device ?
+		pdev->subsystem_device :
+		(ushort)(rd32(hw, I40E_PFPCI_SUBSYSID) & USHRT_MAX);
+}
+
+/**
  * i40e_probe - Device initialization routine
  * @pdev: PCI device information struct
  * @ent: entry in i40e_pci_tbl
@@ -15275,7 +15294,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hw->device_id = pdev->device;
 	pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id);
 	hw->subsystem_vendor_id = pdev->subsystem_vendor;
-	hw->subsystem_device_id = pdev->subsystem_device;
+	i40e_set_subsystem_device_id(hw);
 	hw->bus.device = PCI_SLOT(pdev->devfn);
 	hw->bus.func = PCI_FUNC(pdev->devfn);
 	hw->bus.bus_id = pdev->bus->number;
@@ -15455,6 +15474,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (is_valid_ether_addr(hw->mac.port_addr))
 		pf->hw_features |= I40E_HW_PORT_ID_VALID;
 
+	i40e_ptp_alloc_pins(pf);
 	pci_set_drvdata(pdev, pf);
 	pci_save_state(pdev);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index 7b971b205d36..09b1d5aed1c9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -3,6 +3,7 @@
 
 #include "i40e.h"
 #include <linux/ptp_classify.h>
+#include <linux/posix-clock.h>
 
 /* The XL710 timesync is very much like Intel's 82599 design when it comes to
  * the fundamental clock design. However, the clock operations are much simpler
@@ -20,10 +21,252 @@
 #define I40E_PTP_10GB_INCVAL_MULT	2
 #define I40E_PTP_5GB_INCVAL_MULT	2
 #define I40E_PTP_1GB_INCVAL_MULT	20
+#define I40E_ISGN			0x80000000
 
 #define I40E_PRTTSYN_CTL1_TSYNTYPE_V1  BIT(I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT)
 #define I40E_PRTTSYN_CTL1_TSYNTYPE_V2  (2 << \
 					I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT)
+#define I40E_SUBDEV_ID_25G_PTP_PIN	0xB
+#define to_dev(obj) container_of(obj, struct device, kobj)
+
+enum i40e_ptp_pin {
+	SDP3_2 = 0,
+	SDP3_3,
+	GPIO_4
+};
+
+enum i40e_can_set_pins_t {
+	CANT_DO_PINS = -1,
+	CAN_SET_PINS,
+	CAN_DO_PINS
+};
+
+static struct ptp_pin_desc sdp_desc[] = {
+	/* name     idx      func      chan */
+	{"SDP3_2", SDP3_2, PTP_PF_NONE, 0},
+	{"SDP3_3", SDP3_3, PTP_PF_NONE, 1},
+	{"GPIO_4", GPIO_4, PTP_PF_NONE, 1},
+};
+
+enum i40e_ptp_gpio_pin_state {
+	end = -2,
+	invalid,
+	off,
+	in_A,
+	in_B,
+	out_A,
+	out_B,
+};
+
+static const char * const i40e_ptp_gpio_pin_state2str[] = {
+	"off", "in_A", "in_B", "out_A", "out_B"
+};
+
+enum i40e_ptp_led_pin_state {
+	led_end = -2,
+	low = 0,
+	high,
+};
+
+struct i40e_ptp_pins_settings {
+	enum i40e_ptp_gpio_pin_state sdp3_2;
+	enum i40e_ptp_gpio_pin_state sdp3_3;
+	enum i40e_ptp_gpio_pin_state gpio_4;
+	enum i40e_ptp_led_pin_state led2_0;
+	enum i40e_ptp_led_pin_state led2_1;
+	enum i40e_ptp_led_pin_state led3_0;
+	enum i40e_ptp_led_pin_state led3_1;
+};
+
+static const struct i40e_ptp_pins_settings
+	i40e_ptp_pin_led_allowed_states[] = {
+	{off,	off,	off,		high,	high,	high,	high},
+	{off,	in_A,	off,		high,	high,	high,	low},
+	{off,	out_A,	off,		high,	low,	high,	high},
+	{off,	in_B,	off,		high,	high,	high,	low},
+	{off,	out_B,	off,		high,	low,	high,	high},
+	{in_A,	off,	off,		high,	high,	high,	low},
+	{in_A,	in_B,	off,		high,	high,	high,	low},
+	{in_A,	out_B,	off,		high,	low,	high,	high},
+	{out_A,	off,	off,		high,	low,	high,	high},
+	{out_A,	in_B,	off,		high,	low,	high,	high},
+	{in_B,	off,	off,		high,	high,	high,	low},
+	{in_B,	in_A,	off,		high,	high,	high,	low},
+	{in_B,	out_A,	off,		high,	low,	high,	high},
+	{out_B,	off,	off,		high,	low,	high,	high},
+	{out_B,	in_A,	off,		high,	low,	high,	high},
+	{off,	off,	in_A,		high,	high,	low,	high},
+	{off,	out_A,	in_A,		high,	low,	low,	high},
+	{off,	in_B,	in_A,		high,	high,	low,	low},
+	{off,	out_B,	in_A,		high,	low,	low,	high},
+	{out_A,	off,	in_A,		high,	low,	low,	high},
+	{out_A,	in_B,	in_A,		high,	low,	low,	high},
+	{in_B,	off,	in_A,		high,	high,	low,	low},
+	{in_B,	out_A,	in_A,		high,	low,	low,	high},
+	{out_B,	off,	in_A,		high,	low,	low,	high},
+	{off,	off,	out_A,		low,	high,	high,	high},
+	{off,	in_A,	out_A,		low,	high,	high,	low},
+	{off,	in_B,	out_A,		low,	high,	high,	low},
+	{off,	out_B,	out_A,		low,	low,	high,	high},
+	{in_A,	off,	out_A,		low,	high,	high,	low},
+	{in_A,	in_B,	out_A,		low,	high,	high,	low},
+	{in_A,	out_B,	out_A,		low,	low,	high,	high},
+	{in_B,	off,	out_A,		low,	high,	high,	low},
+	{in_B,	in_A,	out_A,		low,	high,	high,	low},
+	{out_B,	off,	out_A,		low,	low,	high,	high},
+	{out_B,	in_A,	out_A,		low,	low,	high,	high},
+	{off,	off,	in_B,		high,	high,	low,	high},
+	{off,	in_A,	in_B,		high,	high,	low,	low},
+	{off,	out_A,	in_B,		high,	low,	low,	high},
+	{off,	out_B,	in_B,		high,	low,	low,	high},
+	{in_A,	off,	in_B,		high,	high,	low,	low},
+	{in_A,	out_B,	in_B,		high,	low,	low,	high},
+	{out_A,	off,	in_B,		high,	low,	low,	high},
+	{out_B,	off,	in_B,		high,	low,	low,	high},
+	{out_B,	in_A,	in_B,		high,	low,	low,	high},
+	{off,	off,	out_B,		low,	high,	high,	high},
+	{off,	in_A,	out_B,		low,	high,	high,	low},
+	{off,	out_A,	out_B,		low,	low,	high,	high},
+	{off,	in_B,	out_B,		low,	high,	high,	low},
+	{in_A,	off,	out_B,		low,	high,	high,	low},
+	{in_A,	in_B,	out_B,		low,	high,	high,	low},
+	{out_A,	off,	out_B,		low,	low,	high,	high},
+	{out_A,	in_B,	out_B,		low,	low,	high,	high},
+	{in_B,	off,	out_B,		low,	high,	high,	low},
+	{in_B,	in_A,	out_B,		low,	high,	high,	low},
+	{in_B,	out_A,	out_B,		low,	low,	high,	high},
+	{end,	end,	end,	led_end, led_end, led_end, led_end}
+};
+
+static int i40e_ptp_set_pins(struct i40e_pf *pf,
+			     struct i40e_ptp_pins_settings *pins);
+
+/**
+ * i40e_ptp_extts0_work - workqueue task function
+ * @work: workqueue task structure
+ *
+ * Service for PTP external clock event
+ **/
+static void i40e_ptp_extts0_work(struct work_struct *work)
+{
+	struct i40e_pf *pf = container_of(work, struct i40e_pf,
+					  ptp_extts0_work);
+	struct i40e_hw *hw = &pf->hw;
+	struct ptp_clock_event event;
+	u32 hi, lo;
+
+	/* Event time is captured by one of the two matched registers
+	 *      PRTTSYN_EVNT_L: 32 LSB of sampled time event
+	 *      PRTTSYN_EVNT_H: 32 MSB of sampled time event
+	 * Event is defined in PRTTSYN_EVNT_0 register
+	 */
+	lo = rd32(hw, I40E_PRTTSYN_EVNT_L(0));
+	hi = rd32(hw, I40E_PRTTSYN_EVNT_H(0));
+
+	event.timestamp = (((u64)hi) << 32) | lo;
+
+	event.type = PTP_CLOCK_EXTTS;
+	event.index = hw->pf_id;
+
+	/* fire event */
+	ptp_clock_event(pf->ptp_clock, &event);
+}
+
+/**
+ * i40e_is_ptp_pin_dev - check if device supports PTP pins
+ * @hw: pointer to the hardware structure
+ *
+ * Return true if device supports PTP pins, false otherwise.
+ **/
+static bool i40e_is_ptp_pin_dev(struct i40e_hw *hw)
+{
+	return hw->device_id == I40E_DEV_ID_25G_SFP28 &&
+	       hw->subsystem_device_id == I40E_SUBDEV_ID_25G_PTP_PIN;
+}
+
+/**
+ * i40e_can_set_pins - check possibility of manipulating the pins
+ * @pf: board private structure
+ *
+ * Check if all conditions are satisfied to manipulate PTP pins.
+ * Return CAN_SET_PINS if pins can be set on a specific PF or
+ * return CAN_DO_PINS if pins can be manipulated within a NIC or
+ * return CANT_DO_PINS otherwise.
+ **/
+static enum i40e_can_set_pins_t i40e_can_set_pins(struct i40e_pf *pf)
+{
+	if (!i40e_is_ptp_pin_dev(&pf->hw)) {
+		dev_warn(&pf->pdev->dev,
+			 "PTP external clock not supported.\n");
+		return CANT_DO_PINS;
+	}
+
+	if (!pf->ptp_pins) {
+		dev_warn(&pf->pdev->dev,
+			 "PTP PIN manipulation not allowed.\n");
+		return CANT_DO_PINS;
+	}
+
+	if (pf->hw.pf_id) {
+		dev_warn(&pf->pdev->dev,
+			 "PTP PINs should be accessed via PF0.\n");
+		return CAN_DO_PINS;
+	}
+
+	return CAN_SET_PINS;
+}
+
+/**
+ * i40_ptp_reset_timing_events - Reset PTP timing events
+ * @pf: Board private structure
+ *
+ * This function resets timing events for pf.
+ **/
+static void i40_ptp_reset_timing_events(struct i40e_pf *pf)
+{
+	u32 i;
+
+	spin_lock_bh(&pf->ptp_rx_lock);
+	for (i = 0; i <= I40E_PRTTSYN_RXTIME_L_MAX_INDEX; i++) {
+		/* reading and automatically clearing timing events registers */
+		rd32(&pf->hw, I40E_PRTTSYN_RXTIME_L(i));
+		rd32(&pf->hw, I40E_PRTTSYN_RXTIME_H(i));
+		pf->latch_events[i] = 0;
+	}
+	/* reading and automatically clearing timing events registers */
+	rd32(&pf->hw, I40E_PRTTSYN_TXTIME_L);
+	rd32(&pf->hw, I40E_PRTTSYN_TXTIME_H);
+
+	pf->tx_hwtstamp_timeouts = 0;
+	pf->tx_hwtstamp_skipped = 0;
+	pf->rx_hwtstamp_cleared = 0;
+	pf->latch_event_flags = 0;
+	spin_unlock_bh(&pf->ptp_rx_lock);
+}
+
+/**
+ * i40e_ptp_verify - check pins
+ * @ptp: ptp clock
+ * @pin: pin index
+ * @func: assigned function
+ * @chan: channel
+ *
+ * Check pins consistency.
+ * Return 0 on success or error on failure.
+ **/
+static int i40e_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
+			   enum ptp_pin_function func, unsigned int chan)
+{
+	switch (func) {
+	case PTP_PF_NONE:
+	case PTP_PF_EXTTS:
+	case PTP_PF_PEROUT:
+		break;
+	case PTP_PF_PHYSYNC:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
 
 /**
  * i40e_ptp_read - Read the PHC time from the device
@@ -137,6 +380,37 @@ static int i40e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 }
 
 /**
+ * i40e_ptp_set_1pps_signal_hw - configure 1PPS PTP signal for pins
+ * @pf: the PF private data structure
+ *
+ * Configure 1PPS signal used for PTP pins
+ **/
+static void i40e_ptp_set_1pps_signal_hw(struct i40e_pf *pf)
+{
+	struct i40e_hw *hw = &pf->hw;
+	struct timespec64 now;
+	u64 ns;
+
+	wr32(hw, I40E_PRTTSYN_AUX_0(1), 0);
+	wr32(hw, I40E_PRTTSYN_AUX_1(1), I40E_PRTTSYN_AUX_1_INSTNT);
+	wr32(hw, I40E_PRTTSYN_AUX_0(1), I40E_PRTTSYN_AUX_0_OUT_ENABLE);
+
+	i40e_ptp_read(pf, &now, NULL);
+	now.tv_sec += I40E_PTP_2_SEC_DELAY;
+	now.tv_nsec = 0;
+	ns = timespec64_to_ns(&now);
+
+	/* I40E_PRTTSYN_TGT_L(1) */
+	wr32(hw, I40E_PRTTSYN_TGT_L(1), ns & 0xFFFFFFFF);
+	/* I40E_PRTTSYN_TGT_H(1) */
+	wr32(hw, I40E_PRTTSYN_TGT_H(1), ns >> 32);
+	wr32(hw, I40E_PRTTSYN_CLKO(1), I40E_PTP_HALF_SECOND);
+	wr32(hw, I40E_PRTTSYN_AUX_1(1), I40E_PRTTSYN_AUX_1_INSTNT);
+	wr32(hw, I40E_PRTTSYN_AUX_0(1),
+	     I40E_PRTTSYN_AUX_0_OUT_ENABLE_CLK_MOD);
+}
+
+/**
  * i40e_ptp_adjtime - Adjust the PHC time
  * @ptp: The PTP clock structure
  * @delta: Offset in nanoseconds to adjust the PHC time by
@@ -146,14 +420,35 @@ static int i40e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
 	struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
-	struct timespec64 now, then;
+	struct i40e_hw *hw = &pf->hw;
 
-	then = ns_to_timespec64(delta);
 	mutex_lock(&pf->tmreg_lock);
 
-	i40e_ptp_read(pf, &now, NULL);
-	now = timespec64_add(now, then);
-	i40e_ptp_write(pf, (const struct timespec64 *)&now);
+	if (delta > -999999900LL && delta < 999999900LL) {
+		int neg_adj = 0;
+		u32 timadj;
+		u64 tohw;
+
+		if (delta < 0) {
+			neg_adj = 1;
+			tohw = -delta;
+		} else {
+			tohw = delta;
+		}
+
+		timadj = tohw & 0x3FFFFFFF;
+		if (neg_adj)
+			timadj |= I40E_ISGN;
+		wr32(hw, I40E_PRTTSYN_ADJ, timadj);
+	} else {
+		struct timespec64 then, now;
+
+		then = ns_to_timespec64(delta);
+		i40e_ptp_read(pf, &now, NULL);
+		now = timespec64_add(now, then);
+		i40e_ptp_write(pf, (const struct timespec64 *)&now);
+		i40e_ptp_set_1pps_signal_hw(pf);
+	}
 
 	mutex_unlock(&pf->tmreg_lock);
 
@@ -184,7 +479,7 @@ static int i40e_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 /**
  * i40e_ptp_settime - Set the time of the PHC
  * @ptp: The PTP clock structure
- * @ts: timespec structure that holds the new time value
+ * @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.
@@ -202,18 +497,145 @@ static int i40e_ptp_settime(struct ptp_clock_info *ptp,
 }
 
 /**
- * i40e_ptp_feature_enable - Enable/disable ancillary features of the PHC subsystem
+ * i40e_pps_configure - configure PPS events
+ * @ptp: ptp clock
+ * @rq: clock request
+ * @on: status
+ *
+ * Configure PPS events for external clock source.
+ * Return 0 on success or error on failure.
+ **/
+static int i40e_pps_configure(struct ptp_clock_info *ptp,
+			      struct ptp_clock_request *rq,
+			      int on)
+{
+	struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
+
+	if (!!on)
+		i40e_ptp_set_1pps_signal_hw(pf);
+
+	return 0;
+}
+
+/**
+ * i40e_pin_state - determine PIN state
+ * @index: PIN index
+ * @func: function assigned to PIN
+ *
+ * Determine PIN state based on PIN index and function assigned.
+ * Return PIN state.
+ **/
+static enum i40e_ptp_gpio_pin_state i40e_pin_state(int index, int func)
+{
+	enum i40e_ptp_gpio_pin_state state = off;
+
+	if (index == 0 && func == PTP_PF_EXTTS)
+		state = in_A;
+	if (index == 1 && func == PTP_PF_EXTTS)
+		state = in_B;
+	if (index == 0 && func == PTP_PF_PEROUT)
+		state = out_A;
+	if (index == 1 && func == PTP_PF_PEROUT)
+		state = out_B;
+
+	return state;
+}
+
+/**
+ * i40e_ptp_enable_pin - enable PINs.
+ * @pf: private board structure
+ * @chan: channel
+ * @func: PIN function
+ * @on: state
+ *
+ * Enable PTP pins for external clock source.
+ * Return 0 on success or error code on failure.
+ **/
+static int i40e_ptp_enable_pin(struct i40e_pf *pf, unsigned int chan,
+			       enum ptp_pin_function func, int on)
+{
+	enum i40e_ptp_gpio_pin_state *pin = NULL;
+	struct i40e_ptp_pins_settings pins;
+	int pin_index;
+
+	/* Use PF0 to set pins. Return success for user space tools */
+	if (pf->hw.pf_id)
+		return 0;
+
+	/* Preserve previous state of pins that we don't touch */
+	pins.sdp3_2 = pf->ptp_pins->sdp3_2;
+	pins.sdp3_3 = pf->ptp_pins->sdp3_3;
+	pins.gpio_4 = pf->ptp_pins->gpio_4;
+
+	/* To turn on the pin - find the corresponding one based on
+	 * the given index. To to turn the function off - find
+	 * which pin had it assigned. Don't use ptp_find_pin here
+	 * because it tries to lock the pincfg_mux which is locked by
+	 * ptp_pin_store() that calls here.
+	 */
+	if (on) {
+		pin_index = ptp_find_pin(pf->ptp_clock, func, chan);
+		if (pin_index < 0)
+			return -EBUSY;
+
+		switch (pin_index) {
+		case SDP3_2:
+			pin = &pins.sdp3_2;
+			break;
+		case SDP3_3:
+			pin = &pins.sdp3_3;
+			break;
+		case GPIO_4:
+			pin = &pins.gpio_4;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		*pin = i40e_pin_state(chan, func);
+	} else {
+		pins.sdp3_2 = off;
+		pins.sdp3_3 = off;
+		pins.gpio_4 = off;
+	}
+
+	return i40e_ptp_set_pins(pf, &pins) ? -EINVAL : 0;
+}
+
+/**
+ * i40e_ptp_feature_enable - Enable external clock pins
  * @ptp: The PTP clock structure
- * @rq: The requested feature to change
- * @on: Enable/disable flag
+ * @rq: The PTP clock request structure
+ * @on: To turn feature on/off
  *
- * The XL710 does not support any of the ancillary features of the PHC
- * subsystem, so this function may just return.
+ * Setting on/off PTP PPS feature for pin.
  **/
 static int i40e_ptp_feature_enable(struct ptp_clock_info *ptp,
-				   struct ptp_clock_request *rq, int on)
+				   struct ptp_clock_request *rq,
+				   int on)
 {
-	return -EOPNOTSUPP;
+	struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
+
+	enum ptp_pin_function func;
+	unsigned int chan;
+
+	/* TODO: Implement flags handling for EXTTS and PEROUT */
+	switch (rq->type) {
+	case PTP_CLK_REQ_EXTTS:
+		func = PTP_PF_EXTTS;
+		chan = rq->extts.index;
+		break;
+	case PTP_CLK_REQ_PEROUT:
+		func = PTP_PF_PEROUT;
+		chan = rq->perout.index;
+		break;
+	case PTP_CLK_REQ_PPS:
+		return i40e_pps_configure(ptp, rq, on);
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return i40e_ptp_enable_pin(pf, chan, func, on);
 }
 
 /**
@@ -528,6 +950,229 @@ int i40e_ptp_get_ts_config(struct i40e_pf *pf, struct ifreq *ifr)
 }
 
 /**
+ * i40e_ptp_free_pins - free memory used by PTP pins
+ * @pf: Board private structure
+ *
+ * Release memory allocated for PTP pins.
+ **/
+static void i40e_ptp_free_pins(struct i40e_pf *pf)
+{
+	if (i40e_is_ptp_pin_dev(&pf->hw)) {
+		kfree(pf->ptp_pins);
+		kfree(pf->ptp_caps.pin_config);
+		pf->ptp_pins = NULL;
+	}
+}
+
+/**
+ * i40e_ptp_set_pin_hw - Set HW GPIO pin
+ * @hw: pointer to the hardware structure
+ * @pin: pin index
+ * @state: pin state
+ *
+ * Set status of GPIO pin for external clock handling.
+ **/
+static void i40e_ptp_set_pin_hw(struct i40e_hw *hw,
+				unsigned int pin,
+				enum i40e_ptp_gpio_pin_state state)
+{
+	switch (state) {
+	case off:
+		wr32(hw, I40E_GLGEN_GPIO_CTL(pin), 0);
+		break;
+	case in_A:
+		wr32(hw, I40E_GLGEN_GPIO_CTL(pin),
+		     I40E_GLGEN_GPIO_CTL_PORT_0_IN_TIMESYNC_0);
+		break;
+	case in_B:
+		wr32(hw, I40E_GLGEN_GPIO_CTL(pin),
+		     I40E_GLGEN_GPIO_CTL_PORT_1_IN_TIMESYNC_0);
+		break;
+	case out_A:
+		wr32(hw, I40E_GLGEN_GPIO_CTL(pin),
+		     I40E_GLGEN_GPIO_CTL_PORT_0_OUT_TIMESYNC_1);
+		break;
+	case out_B:
+		wr32(hw, I40E_GLGEN_GPIO_CTL(pin),
+		     I40E_GLGEN_GPIO_CTL_PORT_1_OUT_TIMESYNC_1);
+		break;
+	default:
+		break;
+	}
+}
+
+/**
+ * i40e_ptp_set_led_hw - Set HW GPIO led
+ * @hw: pointer to the hardware structure
+ * @led: led index
+ * @state: led state
+ *
+ * Set status of GPIO led for external clock handling.
+ **/
+static void i40e_ptp_set_led_hw(struct i40e_hw *hw,
+				unsigned int led,
+				enum i40e_ptp_led_pin_state state)
+{
+	switch (state) {
+	case low:
+		wr32(hw, I40E_GLGEN_GPIO_SET,
+		     I40E_GLGEN_GPIO_SET_DRV_SDP_DATA | led);
+		break;
+	case high:
+		wr32(hw, I40E_GLGEN_GPIO_SET,
+		     I40E_GLGEN_GPIO_SET_DRV_SDP_DATA |
+		     I40E_GLGEN_GPIO_SET_SDP_DATA_HI | led);
+		break;
+	default:
+		break;
+	}
+}
+
+/**
+ * i40e_ptp_init_leds_hw - init LEDs
+ * @hw: pointer to a hardware structure
+ *
+ * Set initial state of LEDs
+ **/
+static void i40e_ptp_init_leds_hw(struct i40e_hw *hw)
+{
+	wr32(hw, I40E_GLGEN_GPIO_CTL(I40E_LED2_0),
+	     I40E_GLGEN_GPIO_CTL_LED_INIT);
+	wr32(hw, I40E_GLGEN_GPIO_CTL(I40E_LED2_1),
+	     I40E_GLGEN_GPIO_CTL_LED_INIT);
+	wr32(hw, I40E_GLGEN_GPIO_CTL(I40E_LED3_0),
+	     I40E_GLGEN_GPIO_CTL_LED_INIT);
+	wr32(hw, I40E_GLGEN_GPIO_CTL(I40E_LED3_1),
+	     I40E_GLGEN_GPIO_CTL_LED_INIT);
+}
+
+/**
+ * i40e_ptp_set_pins_hw - Set HW GPIO pins
+ * @pf: Board private structure
+ *
+ * This function sets GPIO pins for PTP
+ **/
+static void i40e_ptp_set_pins_hw(struct i40e_pf *pf)
+{
+	const struct i40e_ptp_pins_settings *pins = pf->ptp_pins;
+	struct i40e_hw *hw = &pf->hw;
+
+	/* pin must be disabled before it may be used */
+	i40e_ptp_set_pin_hw(hw, I40E_SDP3_2, off);
+	i40e_ptp_set_pin_hw(hw, I40E_SDP3_3, off);
+	i40e_ptp_set_pin_hw(hw, I40E_GPIO_4, off);
+
+	i40e_ptp_set_pin_hw(hw, I40E_SDP3_2, pins->sdp3_2);
+	i40e_ptp_set_pin_hw(hw, I40E_SDP3_3, pins->sdp3_3);
+	i40e_ptp_set_pin_hw(hw, I40E_GPIO_4, pins->gpio_4);
+
+	i40e_ptp_set_led_hw(hw, I40E_LED2_0, pins->led2_0);
+	i40e_ptp_set_led_hw(hw, I40E_LED2_1, pins->led2_1);
+	i40e_ptp_set_led_hw(hw, I40E_LED3_0, pins->led3_0);
+	i40e_ptp_set_led_hw(hw, I40E_LED3_1, pins->led3_1);
+
+	dev_info(&pf->pdev->dev,
+		 "PTP configuration set to: SDP3_2: %s,  SDP3_3: %s,  GPIO_4: %s.\n",
+		 i40e_ptp_gpio_pin_state2str[pins->sdp3_2],
+		 i40e_ptp_gpio_pin_state2str[pins->sdp3_3],
+		 i40e_ptp_gpio_pin_state2str[pins->gpio_4]);
+}
+
+/**
+ * i40e_ptp_set_pins - set PTP pins in HW
+ * @pf: Board private structure
+ * @pins: PTP pins to be applied
+ *
+ * Validate and set PTP pins in HW for specific PF.
+ * Return 0 on success or negative value on error.
+ **/
+static int i40e_ptp_set_pins(struct i40e_pf *pf,
+			     struct i40e_ptp_pins_settings *pins)
+{
+	enum i40e_can_set_pins_t pin_caps = i40e_can_set_pins(pf);
+	int i = 0;
+
+	if (pin_caps == CANT_DO_PINS)
+		return -EOPNOTSUPP;
+	else if (pin_caps == CAN_DO_PINS)
+		return 0;
+
+	if (pins->sdp3_2 == invalid)
+		pins->sdp3_2 = pf->ptp_pins->sdp3_2;
+	if (pins->sdp3_3 == invalid)
+		pins->sdp3_3 = pf->ptp_pins->sdp3_3;
+	if (pins->gpio_4 == invalid)
+		pins->gpio_4 = pf->ptp_pins->gpio_4;
+	while (i40e_ptp_pin_led_allowed_states[i].sdp3_2 != end) {
+		if (pins->sdp3_2 == i40e_ptp_pin_led_allowed_states[i].sdp3_2 &&
+		    pins->sdp3_3 == i40e_ptp_pin_led_allowed_states[i].sdp3_3 &&
+		    pins->gpio_4 == i40e_ptp_pin_led_allowed_states[i].gpio_4) {
+			pins->led2_0 =
+				i40e_ptp_pin_led_allowed_states[i].led2_0;
+			pins->led2_1 =
+				i40e_ptp_pin_led_allowed_states[i].led2_1;
+			pins->led3_0 =
+				i40e_ptp_pin_led_allowed_states[i].led3_0;
+			pins->led3_1 =
+				i40e_ptp_pin_led_allowed_states[i].led3_1;
+			break;
+		}
+		i++;
+	}
+	if (i40e_ptp_pin_led_allowed_states[i].sdp3_2 == end) {
+		dev_warn(&pf->pdev->dev,
+			 "Unsupported PTP pin configuration: SDP3_2: %s,  SDP3_3: %s,  GPIO_4: %s.\n",
+			 i40e_ptp_gpio_pin_state2str[pins->sdp3_2],
+			 i40e_ptp_gpio_pin_state2str[pins->sdp3_3],
+			 i40e_ptp_gpio_pin_state2str[pins->gpio_4]);
+
+		return -EPERM;
+	}
+	memcpy(pf->ptp_pins, pins, sizeof(*pins));
+	i40e_ptp_set_pins_hw(pf);
+	i40_ptp_reset_timing_events(pf);
+
+	return 0;
+}
+
+/**
+ * i40e_ptp_alloc_pins - allocate PTP pins structure
+ * @pf: Board private structure
+ *
+ * allocate PTP pins structure
+ **/
+int i40e_ptp_alloc_pins(struct i40e_pf *pf)
+{
+	if (!i40e_is_ptp_pin_dev(&pf->hw))
+		return 0;
+
+	pf->ptp_pins =
+		kzalloc(sizeof(struct i40e_ptp_pins_settings), GFP_KERNEL);
+
+	if (!pf->ptp_pins) {
+		dev_warn(&pf->pdev->dev, "Cannot allocate memory for PTP pins structure.\n");
+		return -I40E_ERR_NO_MEMORY;
+	}
+
+	pf->ptp_pins->sdp3_2 = off;
+	pf->ptp_pins->sdp3_3 = off;
+	pf->ptp_pins->gpio_4 = off;
+	pf->ptp_pins->led2_0 = high;
+	pf->ptp_pins->led2_1 = high;
+	pf->ptp_pins->led3_0 = high;
+	pf->ptp_pins->led3_1 = high;
+
+	/* Use PF0 to set pins in HW. Return success for user space tools */
+	if (pf->hw.pf_id)
+		return 0;
+
+	i40e_ptp_init_leds_hw(&pf->hw);
+	i40e_ptp_set_pins_hw(pf);
+
+	return 0;
+}
+
+/**
  * i40e_ptp_set_timestamp_mode - setup hardware for requested timestamp mode
  * @pf: Board private structure
  * @config: hwtstamp settings requested or saved
@@ -545,6 +1190,21 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf,
 	struct i40e_hw *hw = &pf->hw;
 	u32 tsyntype, regval;
 
+	/* Selects external trigger to cause event */
+	regval = rd32(hw, I40E_PRTTSYN_AUX_0(0));
+	/* Bit 17:16 is EVNTLVL, 01B rising edge */
+	regval &= 0;
+	regval |= (1 << I40E_PRTTSYN_AUX_0_EVNTLVL_SHIFT);
+	/* regval: 0001 0000 0000 0000 0000 */
+	wr32(hw, I40E_PRTTSYN_AUX_0(0), regval);
+
+	/* Enabel interrupts */
+	regval = rd32(hw, I40E_PRTTSYN_CTL0);
+	regval |= 1 << I40E_PRTTSYN_CTL0_EVENT_INT_ENA_SHIFT;
+	wr32(hw, I40E_PRTTSYN_CTL0, regval);
+
+	INIT_WORK(&pf->ptp_extts0_work, i40e_ptp_extts0_work);
+
 	/* Reserved for future extensions. */
 	if (config->flags)
 		return -EINVAL;
@@ -688,6 +1348,45 @@ int i40e_ptp_set_ts_config(struct i40e_pf *pf, struct ifreq *ifr)
 }
 
 /**
+ * i40e_init_pin_config - initialize pins.
+ * @pf: private board structure
+ *
+ * Initialize pins for external clock source.
+ * Return 0 on success or error code on failure.
+ **/
+static int i40e_init_pin_config(struct i40e_pf *pf)
+{
+	int i;
+
+	pf->ptp_caps.n_pins = 3;
+	pf->ptp_caps.n_ext_ts = 2;
+	pf->ptp_caps.pps = 1;
+	pf->ptp_caps.n_per_out = 2;
+
+	pf->ptp_caps.pin_config = kcalloc(pf->ptp_caps.n_pins,
+					  sizeof(*pf->ptp_caps.pin_config),
+					  GFP_KERNEL);
+	if (!pf->ptp_caps.pin_config)
+		return -ENOMEM;
+
+	for (i = 0; i < pf->ptp_caps.n_pins; i++) {
+		snprintf(pf->ptp_caps.pin_config[i].name,
+			 sizeof(pf->ptp_caps.pin_config[i].name),
+			 "%s", sdp_desc[i].name);
+		pf->ptp_caps.pin_config[i].index = sdp_desc[i].index;
+		pf->ptp_caps.pin_config[i].func = PTP_PF_NONE;
+		pf->ptp_caps.pin_config[i].chan = sdp_desc[i].chan;
+	}
+
+	pf->ptp_caps.verify = i40e_ptp_verify;
+	pf->ptp_caps.enable = i40e_ptp_feature_enable;
+
+	pf->ptp_caps.pps = 1;
+
+	return 0;
+}
+
+/**
  * i40e_ptp_create_clock - Create PTP clock device for userspace
  * @pf: Board private structure
  *
@@ -707,13 +1406,16 @@ static long i40e_ptp_create_clock(struct i40e_pf *pf)
 		sizeof(pf->ptp_caps.name) - 1);
 	pf->ptp_caps.owner = THIS_MODULE;
 	pf->ptp_caps.max_adj = 999999999;
-	pf->ptp_caps.n_ext_ts = 0;
-	pf->ptp_caps.pps = 0;
 	pf->ptp_caps.adjfreq = i40e_ptp_adjfreq;
 	pf->ptp_caps.adjtime = i40e_ptp_adjtime;
 	pf->ptp_caps.gettimex64 = i40e_ptp_gettimex;
 	pf->ptp_caps.settime64 = i40e_ptp_settime;
-	pf->ptp_caps.enable = i40e_ptp_feature_enable;
+	if (i40e_is_ptp_pin_dev(&pf->hw)) {
+		int err = i40e_init_pin_config(pf);
+
+		if (err)
+			return err;
+	}
 
 	/* Attempt to register the clock before enabling the hardware. */
 	pf->ptp_clock = ptp_clock_register(&pf->ptp_caps, &pf->pdev->dev);
@@ -843,6 +1545,8 @@ void i40e_ptp_init(struct i40e_pf *pf)
 		/* Restore the clock time based on last known value */
 		i40e_ptp_restore_hw_time(pf);
 	}
+
+	i40e_ptp_set_1pps_signal_hw(pf);
 }
 
 /**
@@ -854,6 +1558,9 @@ void i40e_ptp_init(struct i40e_pf *pf)
  **/
 void i40e_ptp_stop(struct i40e_pf *pf)
 {
+	struct i40e_hw *hw = &pf->hw;
+	u32 regval;
+
 	pf->flags &= ~I40E_FLAG_PTP;
 	pf->ptp_tx = false;
 	pf->ptp_rx = false;
@@ -872,4 +1579,21 @@ void i40e_ptp_stop(struct i40e_pf *pf)
 		dev_info(&pf->pdev->dev, "%s: removed PHC on %s\n", __func__,
 			 pf->vsi[pf->lan_vsi]->netdev->name);
 	}
+
+	if (i40e_is_ptp_pin_dev(&pf->hw)) {
+		i40e_ptp_set_pin_hw(hw, I40E_SDP3_2, off);
+		i40e_ptp_set_pin_hw(hw, I40E_SDP3_3, off);
+		i40e_ptp_set_pin_hw(hw, I40E_GPIO_4, off);
+	}
+
+	regval = rd32(hw, I40E_PRTTSYN_AUX_0(0));
+	regval &= ~I40E_PRTTSYN_AUX_0_PTPFLAG_MASK;
+	wr32(hw, I40E_PRTTSYN_AUX_0(0), regval);
+
+	/* Disable interrupts */
+	regval = rd32(hw, I40E_PRTTSYN_CTL0);
+	regval &= ~I40E_PRTTSYN_CTL0_EVENT_INT_ENA_MASK;
+	wr32(hw, I40E_PRTTSYN_CTL0, regval);
+
+	i40e_ptp_free_pins(pf);
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index 36f7b27a04ae..8d0588a27a05 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -182,11 +182,20 @@
 #define I40E_GLGEN_GPIO_CTL_PRT_NUM_MASK I40E_MASK(0x3, I40E_GLGEN_GPIO_CTL_PRT_NUM_SHIFT)
 #define I40E_GLGEN_GPIO_CTL_PRT_NUM_NA_SHIFT 3
 #define I40E_GLGEN_GPIO_CTL_PRT_NUM_NA_MASK I40E_MASK(0x1, I40E_GLGEN_GPIO_CTL_PRT_NUM_NA_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_PIN_DIR_SHIFT 4
+#define I40E_GLGEN_GPIO_CTL_TRI_CTL_SHIFT 5
+#define I40E_GLGEN_GPIO_CTL_OUT_CTL_SHIFT 6
 #define I40E_GLGEN_GPIO_CTL_PIN_FUNC_SHIFT 7
 #define I40E_GLGEN_GPIO_CTL_PIN_FUNC_MASK I40E_MASK(0x7, I40E_GLGEN_GPIO_CTL_PIN_FUNC_SHIFT)
 #define I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT 11
 #define I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT 12
 #define I40E_GLGEN_GPIO_CTL_LED_MODE_MASK I40E_MASK(0x1F, I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_OUT_DEFAULT_SHIFT  19
+#define I40E_GLGEN_GPIO_CTL_OUT_DEFAULT_MASK   I40E_MASK(0x1, I40E_GLGEN_GPIO_CTL_OUT_DEFAULT_SHIFT)
+#define I40E_GLGEN_GPIO_CTL_PHY_PIN_NAME_SHIFT 20
+#define I40E_GLGEN_GPIO_SET 0x00088184 /* Reset: POR */
+#define I40E_GLGEN_GPIO_SET_SDP_DATA_SHIFT 5
+#define I40E_GLGEN_GPIO_SET_DRIVE_SDP_SHIFT 6
 #define I40E_GLGEN_MDIO_I2C_SEL(_i) (0x000881C0 + ((_i) * 4)) /* _i=0...3 */ /* Reset: POR */
 #define I40E_GLGEN_MSCA(_i) (0x0008818C + ((_i) * 4)) /* _i=0...3 */ /* Reset: POR */
 #define I40E_GLGEN_MSCA_MDIADD_SHIFT 0
@@ -540,6 +549,7 @@
 #define I40E_PF_PCI_CIAA_VF_NUM_SHIFT 12
 #define I40E_PF_PCI_CIAD 0x0009C100 /* Reset: FLR */
 #define I40E_PRTPM_EEE_STAT 0x001E4320 /* Reset: GLOBR */
+#define I40E_PFPCI_SUBSYSID 0x000BE100 /* Reset: PCIR */
 #define I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_SHIFT 30
 #define I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_MASK I40E_MASK(0x1, I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_SHIFT)
 #define I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_SHIFT 31
@@ -742,6 +752,8 @@
 #define I40E_PRTTSYN_CTL0 0x001E4200 /* Reset: GLOBR */
 #define I40E_PRTTSYN_CTL0_TXTIME_INT_ENA_SHIFT 1
 #define I40E_PRTTSYN_CTL0_TXTIME_INT_ENA_MASK I40E_MASK(0x1, I40E_PRTTSYN_CTL0_TXTIME_INT_ENA_SHIFT)
+#define I40E_PRTTSYN_CTL0_EVENT_INT_ENA_SHIFT 2
+#define I40E_PRTTSYN_CTL0_EVENT_INT_ENA_MASK I40E_MASK(0x1, I40E_PRTTSYN_CTL0_EVENT_INT_ENA_SHIFT)
 #define I40E_PRTTSYN_CTL0_PF_ID_SHIFT 8
 #define I40E_PRTTSYN_CTL0_PF_ID_MASK I40E_MASK(0xF, I40E_PRTTSYN_CTL0_PF_ID_SHIFT)
 #define I40E_PRTTSYN_CTL0_TSYNENA_SHIFT 31
@@ -760,7 +772,10 @@
 #define I40E_PRTTSYN_INC_L 0x001E4040 /* Reset: GLOBR */
 #define I40E_PRTTSYN_RXTIME_H(_i) (0x00085040 + ((_i) * 32)) /* _i=0...3 */ /* Reset: CORER */
 #define I40E_PRTTSYN_RXTIME_L(_i) (0x000850C0 + ((_i) * 32)) /* _i=0...3 */ /* Reset: CORER */
+#define I40E_PRTTSYN_RXTIME_L_MAX_INDEX 3
 #define I40E_PRTTSYN_STAT_0 0x001E4220 /* Reset: GLOBR */
+#define I40E_PRTTSYN_STAT_0_EVENT0_SHIFT 0
+#define I40E_PRTTSYN_STAT_0_EVENT0_MASK I40E_MASK(0x1, I40E_PRTTSYN_STAT_0_EVENT0_SHIFT)
 #define I40E_PRTTSYN_STAT_0_TXTIME_SHIFT 4
 #define I40E_PRTTSYN_STAT_0_TXTIME_MASK I40E_MASK(0x1, I40E_PRTTSYN_STAT_0_TXTIME_SHIFT)
 #define I40E_PRTTSYN_STAT_1 0x00085140 /* Reset: CORER */
@@ -768,6 +783,20 @@
 #define I40E_PRTTSYN_TIME_L 0x001E4100 /* Reset: GLOBR */
 #define I40E_PRTTSYN_TXTIME_H 0x001E41E0 /* Reset: GLOBR */
 #define I40E_PRTTSYN_TXTIME_L 0x001E41C0 /* Reset: GLOBR */
+#define I40E_PRTTSYN_EVNT_H(_i) (0x001E40C0 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
+#define I40E_PRTTSYN_EVNT_L(_i) (0x001E4080 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
+#define I40E_PRTTSYN_AUX_0(_i) (0x001E42A0 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
+#define I40E_PRTTSYN_AUX_0_OUT_ENA_SHIFT 0
+#define I40E_PRTTSYN_AUX_0_OUTMOD_SHIFT 1
+#define I40E_PRTTSYN_AUX_0_EVNTLVL_SHIFT 16
+#define I40E_PRTTSYN_AUX_0_PTPFLAG_SHIFT 17
+#define I40E_PRTTSYN_AUX_0_PTPFLAG_MASK I40E_MASK(0x1, I40E_PRTTSYN_AUX_0_PTPFLAG_SHIFT)
+#define I40E_PRTTSYN_AUX_1(_i) (0x001E42E0 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
+#define I40E_PRTTSYN_AUX_1_INSTNT_SHIFT 0
+#define I40E_PRTTSYN_TGT_H(_i) (0x001E4180 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
+#define I40E_PRTTSYN_TGT_L(_i) (0x001E4140 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
+#define I40E_PRTTSYN_CLKO(_i) (0x001E4240 + ((_i) * 32)) /* _i=0...1 */ /* Reset: GLOBR */
+#define I40E_PRTTSYN_ADJ 0x001E4280 /* Reset: GLOBR */
 #define I40E_GL_MDET_RX 0x0012A510 /* Reset: CORER */
 #define I40E_GL_MDET_RX_FUNCTION_SHIFT 0
 #define I40E_GL_MDET_RX_FUNCTION_MASK I40E_MASK(0xFF, I40E_GL_MDET_RX_FUNCTION_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index eff0a30790dd..472f56b360b8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1160,12 +1160,12 @@ static int i40e_quiesce_vf_pci(struct i40e_vf *vf)
 }
 
 /**
- * i40e_getnum_vf_vsi_vlan_filters
+ * __i40e_getnum_vf_vsi_vlan_filters
  * @vsi: pointer to the vsi
  *
  * called to get the number of VLANs offloaded on this VF
  **/
-static int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi)
+static int __i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi)
 {
 	struct i40e_mac_filter *f;
 	u16 num_vlans = 0, bkt;
@@ -1179,6 +1179,23 @@ static int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi)
 }
 
 /**
+ * i40e_getnum_vf_vsi_vlan_filters
+ * @vsi: pointer to the vsi
+ *
+ * wrapper for __i40e_getnum_vf_vsi_vlan_filters() with spinlock held
+ **/
+static int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi)
+{
+	int num_vlans;
+
+	spin_lock_bh(&vsi->mac_filter_hash_lock);
+	num_vlans = __i40e_getnum_vf_vsi_vlan_filters(vsi);
+	spin_unlock_bh(&vsi->mac_filter_hash_lock);
+
+	return num_vlans;
+}
+
+/**
  * i40e_get_vlan_list_sync
  * @vsi: pointer to the VSI
  * @num_vlans: number of VLANs in mac_filter_hash, returned to caller
@@ -1195,7 +1212,7 @@ static void i40e_get_vlan_list_sync(struct i40e_vsi *vsi, u16 *num_vlans,
 	int bkt;
 
 	spin_lock_bh(&vsi->mac_filter_hash_lock);
-	*num_vlans = i40e_getnum_vf_vsi_vlan_filters(vsi);
+	*num_vlans = __i40e_getnum_vf_vsi_vlan_filters(vsi);
 	*vlan_list = kcalloc(*num_vlans, sizeof(**vlan_list), GFP_ATOMIC);
 	if (!(*vlan_list))
 		goto err;
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 90793b36126e..68c80f04113c 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -186,12 +186,6 @@ enum iavf_state_t {
 	__IAVF_RUNNING,		/* opened, working */
 };
 
-enum iavf_critical_section_t {
-	__IAVF_IN_CRITICAL_TASK,	/* cannot be interrupted */
-	__IAVF_IN_CLIENT_TASK,
-	__IAVF_IN_REMOVE_TASK,	/* device being removed */
-};
-
 #define IAVF_CLOUD_FIELD_OMAC		0x01
 #define IAVF_CLOUD_FIELD_IMAC		0x02
 #define IAVF_CLOUD_FIELD_IVLAN	0x04
@@ -236,6 +230,9 @@ struct iavf_adapter {
 	struct iavf_q_vector *q_vectors;
 	struct list_head vlan_filter_list;
 	struct list_head mac_filter_list;
+	struct mutex crit_lock;
+	struct mutex client_lock;
+	struct mutex remove_lock;
 	/* Lock to protect accesses to MAC and VLAN lists */
 	spinlock_t mac_vlan_list_lock;
 	char misc_vector_name[IFNAMSIZ + 9];
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index af43fbd8cb75..5a359a0a20ec 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -685,6 +685,8 @@ static int __iavf_get_coalesce(struct net_device *netdev,
  * iavf_get_coalesce - Get interrupt coalescing settings
  * @netdev: network interface device structure
  * @ec: ethtool coalesce structure
+ * @kernel_coal: ethtool CQE mode setting structure
+ * @extack: extack for reporting error messages
  *
  * Returns current coalescing settings. This is referred to elsewhere in the
  * driver as Interrupt Throttle Rate, as this is how the hardware describes
@@ -692,7 +694,9 @@ static int __iavf_get_coalesce(struct net_device *netdev,
  * only represents the settings of queue 0.
  **/
 static int iavf_get_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *ec)
+			     struct ethtool_coalesce *ec,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	return __iavf_get_coalesce(netdev, ec, -1);
 }
@@ -804,11 +808,15 @@ static int __iavf_set_coalesce(struct net_device *netdev,
  * iavf_set_coalesce - Set interrupt coalescing settings
  * @netdev: network interface device structure
  * @ec: ethtool coalesce structure
+ * @kernel_coal: ethtool CQE mode setting structure
+ * @extack: extack for reporting error messages
  *
  * Change current coalescing settings for every queue.
  **/
 static int iavf_set_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *ec)
+			     struct ethtool_coalesce *ec,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	return __iavf_set_coalesce(netdev, ec, -1);
 }
@@ -1352,8 +1360,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	if (!fltr)
 		return -ENOMEM;
 
-	while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK,
-				&adapter->crit_section)) {
+	while (!mutex_trylock(&adapter->crit_lock)) {
 		if (--count == 0) {
 			kfree(fltr);
 			return -EINVAL;
@@ -1378,7 +1385,7 @@ ret:
 	if (err && fltr)
 		kfree(fltr);
 
-	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mutex_unlock(&adapter->crit_lock);
 	return err;
 }
 
@@ -1563,8 +1570,7 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 		return -EINVAL;
 	}
 
-	while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK,
-				&adapter->crit_section)) {
+	while (!mutex_trylock(&adapter->crit_lock)) {
 		if (--count == 0) {
 			kfree(rss_new);
 			return -EINVAL;
@@ -1600,7 +1606,7 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 	if (!err)
 		mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
 
-	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mutex_unlock(&adapter->crit_lock);
 
 	if (!rss_new_add)
 		kfree(rss_new);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 606a01ce4073..23762a7ef740 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -132,6 +132,27 @@ enum iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw,
 }
 
 /**
+ * iavf_lock_timeout - try to lock mutex but give up after timeout
+ * @lock: mutex that should be locked
+ * @msecs: timeout in msecs
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs)
+{
+	unsigned int wait, delay = 10;
+
+	for (wait = 0; wait < msecs; wait += delay) {
+		if (mutex_trylock(lock))
+			return 0;
+
+		msleep(delay);
+	}
+
+	return -1;
+}
+
+/**
  * iavf_schedule_reset - Set the flags and schedule a reset event
  * @adapter: board private structure
  **/
@@ -1916,7 +1937,7 @@ static void iavf_watchdog_task(struct work_struct *work)
 	struct iavf_hw *hw = &adapter->hw;
 	u32 reg_val;
 
-	if (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section))
+	if (!mutex_trylock(&adapter->crit_lock))
 		goto restart_watchdog;
 
 	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
@@ -1934,8 +1955,7 @@ static void iavf_watchdog_task(struct work_struct *work)
 			adapter->state = __IAVF_STARTUP;
 			adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED;
 			queue_delayed_work(iavf_wq, &adapter->init_task, 10);
-			clear_bit(__IAVF_IN_CRITICAL_TASK,
-				  &adapter->crit_section);
+			mutex_unlock(&adapter->crit_lock);
 			/* Don't reschedule the watchdog, since we've restarted
 			 * the init task. When init_task contacts the PF and
 			 * gets everything set up again, it'll restart the
@@ -1945,14 +1965,13 @@ static void iavf_watchdog_task(struct work_struct *work)
 		}
 		adapter->aq_required = 0;
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
-		clear_bit(__IAVF_IN_CRITICAL_TASK,
-			  &adapter->crit_section);
+		mutex_unlock(&adapter->crit_lock);
 		queue_delayed_work(iavf_wq,
 				   &adapter->watchdog_task,
 				   msecs_to_jiffies(10));
 		goto watchdog_done;
 	case __IAVF_RESETTING:
-		clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+		mutex_unlock(&adapter->crit_lock);
 		queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2);
 		return;
 	case __IAVF_DOWN:
@@ -1975,7 +1994,7 @@ static void iavf_watchdog_task(struct work_struct *work)
 		}
 		break;
 	case __IAVF_REMOVE:
-		clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+		mutex_unlock(&adapter->crit_lock);
 		return;
 	default:
 		goto restart_watchdog;
@@ -1984,7 +2003,6 @@ static void iavf_watchdog_task(struct work_struct *work)
 		/* check for hw reset */
 	reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK;
 	if (!reg_val) {
-		adapter->state = __IAVF_RESETTING;
 		adapter->flags |= IAVF_FLAG_RESET_PENDING;
 		adapter->aq_required = 0;
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
@@ -1998,7 +2016,7 @@ watchdog_done:
 	if (adapter->state == __IAVF_RUNNING ||
 	    adapter->state == __IAVF_COMM_FAILED)
 		iavf_detect_recover_hung(&adapter->vsi);
-	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mutex_unlock(&adapter->crit_lock);
 restart_watchdog:
 	if (adapter->aq_required)
 		queue_delayed_work(iavf_wq, &adapter->watchdog_task,
@@ -2062,7 +2080,7 @@ static void iavf_disable_vf(struct iavf_adapter *adapter)
 	memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE);
 	iavf_shutdown_adminq(&adapter->hw);
 	adapter->netdev->flags &= ~IFF_UP;
-	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mutex_unlock(&adapter->crit_lock);
 	adapter->flags &= ~IAVF_FLAG_RESET_PENDING;
 	adapter->state = __IAVF_DOWN;
 	wake_up(&adapter->down_waitqueue);
@@ -2095,11 +2113,14 @@ static void iavf_reset_task(struct work_struct *work)
 	/* When device is being removed it doesn't make sense to run the reset
 	 * task, just return in such a case.
 	 */
-	if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
+	if (mutex_is_locked(&adapter->remove_lock))
 		return;
 
-	while (test_and_set_bit(__IAVF_IN_CLIENT_TASK,
-				&adapter->crit_section))
+	if (iavf_lock_timeout(&adapter->crit_lock, 200)) {
+		schedule_work(&adapter->reset_task);
+		return;
+	}
+	while (!mutex_trylock(&adapter->client_lock))
 		usleep_range(500, 1000);
 	if (CLIENT_ENABLED(adapter)) {
 		adapter->flags &= ~(IAVF_FLAG_CLIENT_NEEDS_OPEN |
@@ -2151,7 +2172,7 @@ 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);
-		clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section);
+		mutex_unlock(&adapter->client_lock);
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}
 
@@ -2278,13 +2299,13 @@ continue_reset:
 		adapter->state = __IAVF_DOWN;
 		wake_up(&adapter->down_waitqueue);
 	}
-	clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section);
-	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mutex_unlock(&adapter->client_lock);
+	mutex_unlock(&adapter->crit_lock);
 
 	return;
 reset_err:
-	clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section);
-	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mutex_unlock(&adapter->client_lock);
+	mutex_unlock(&adapter->crit_lock);
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
 	iavf_close(netdev);
 }
@@ -2312,6 +2333,8 @@ static void iavf_adminq_task(struct work_struct *work)
 	if (!event.msg_buf)
 		goto out;
 
+	if (iavf_lock_timeout(&adapter->crit_lock, 200))
+		goto freedom;
 	do {
 		ret = iavf_clean_arq_element(hw, &event, &pending);
 		v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high);
@@ -2325,6 +2348,7 @@ static void iavf_adminq_task(struct work_struct *work)
 		if (pending != 0)
 			memset(event.msg_buf, 0, IAVF_MAX_AQ_BUF_SIZE);
 	} while (pending);
+	mutex_unlock(&adapter->crit_lock);
 
 	if ((adapter->flags &
 	     (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) ||
@@ -2391,7 +2415,7 @@ static void iavf_client_task(struct work_struct *work)
 	 * later.
 	 */
 
-	if (test_and_set_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section))
+	if (!mutex_trylock(&adapter->client_lock))
 		return;
 
 	if (adapter->flags & IAVF_FLAG_SERVICE_CLIENT_REQUESTED) {
@@ -2414,7 +2438,7 @@ static void iavf_client_task(struct work_struct *work)
 		adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_OPEN;
 	}
 out:
-	clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section);
+	mutex_unlock(&adapter->client_lock);
 }
 
 /**
@@ -3017,8 +3041,7 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter,
 	if (!filter)
 		return -ENOMEM;
 
-	while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK,
-				&adapter->crit_section)) {
+	while (!mutex_trylock(&adapter->crit_lock)) {
 		if (--count == 0)
 			goto err;
 		udelay(1);
@@ -3049,7 +3072,7 @@ err:
 	if (err)
 		kfree(filter);
 
-	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mutex_unlock(&adapter->crit_lock);
 	return err;
 }
 
@@ -3196,8 +3219,7 @@ static int iavf_open(struct net_device *netdev)
 		return -EIO;
 	}
 
-	while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK,
-				&adapter->crit_section))
+	while (!mutex_trylock(&adapter->crit_lock))
 		usleep_range(500, 1000);
 
 	if (adapter->state != __IAVF_DOWN) {
@@ -3232,7 +3254,7 @@ static int iavf_open(struct net_device *netdev)
 
 	iavf_irq_enable(adapter, true);
 
-	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mutex_unlock(&adapter->crit_lock);
 
 	return 0;
 
@@ -3244,7 +3266,7 @@ err_setup_rx:
 err_setup_tx:
 	iavf_free_all_tx_resources(adapter);
 err_unlock:
-	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mutex_unlock(&adapter->crit_lock);
 
 	return err;
 }
@@ -3268,8 +3290,7 @@ static int iavf_close(struct net_device *netdev)
 	if (adapter->state <= __IAVF_DOWN_PENDING)
 		return 0;
 
-	while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK,
-				&adapter->crit_section))
+	while (!mutex_trylock(&adapter->crit_lock))
 		usleep_range(500, 1000);
 
 	set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
@@ -3280,7 +3301,7 @@ static int iavf_close(struct net_device *netdev)
 	adapter->state = __IAVF_DOWN_PENDING;
 	iavf_free_traffic_irqs(adapter);
 
-	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mutex_unlock(&adapter->crit_lock);
 
 	/* We explicitly don't free resources here because the hardware is
 	 * still active and can DMA into memory. Resources are cleared in
@@ -3629,6 +3650,10 @@ static void iavf_init_task(struct work_struct *work)
 						    init_task.work);
 	struct iavf_hw *hw = &adapter->hw;
 
+	if (iavf_lock_timeout(&adapter->crit_lock, 5000)) {
+		dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__);
+		return;
+	}
 	switch (adapter->state) {
 	case __IAVF_STARTUP:
 		if (iavf_startup(adapter) < 0)
@@ -3641,14 +3666,14 @@ static void iavf_init_task(struct work_struct *work)
 	case __IAVF_INIT_GET_RESOURCES:
 		if (iavf_init_get_resources(adapter) < 0)
 			goto init_failed;
-		return;
+		goto out;
 	default:
 		goto init_failed;
 	}
 
 	queue_delayed_work(iavf_wq, &adapter->init_task,
 			   msecs_to_jiffies(30));
-	return;
+	goto out;
 init_failed:
 	if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) {
 		dev_err(&adapter->pdev->dev,
@@ -3657,9 +3682,11 @@ init_failed:
 		iavf_shutdown_adminq(hw);
 		adapter->state = __IAVF_STARTUP;
 		queue_delayed_work(iavf_wq, &adapter->init_task, HZ * 5);
-		return;
+		goto out;
 	}
 	queue_delayed_work(iavf_wq, &adapter->init_task, HZ);
+out:
+	mutex_unlock(&adapter->crit_lock);
 }
 
 /**
@@ -3676,9 +3703,12 @@ static void iavf_shutdown(struct pci_dev *pdev)
 	if (netif_running(netdev))
 		iavf_close(netdev);
 
+	if (iavf_lock_timeout(&adapter->crit_lock, 5000))
+		dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__);
 	/* Prevent the watchdog from running. */
 	adapter->state = __IAVF_REMOVE;
 	adapter->aq_required = 0;
+	mutex_unlock(&adapter->crit_lock);
 
 #ifdef CONFIG_PM
 	pci_save_state(pdev);
@@ -3772,6 +3802,9 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* 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(&adapter->client_lock);
+	mutex_init(&adapter->remove_lock);
 	mutex_init(&hw->aq.asq_mutex);
 	mutex_init(&hw->aq.arq_mutex);
 
@@ -3823,8 +3856,7 @@ static int __maybe_unused iavf_suspend(struct device *dev_d)
 
 	netif_device_detach(netdev);
 
-	while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK,
-				&adapter->crit_section))
+	while (!mutex_trylock(&adapter->crit_lock))
 		usleep_range(500, 1000);
 
 	if (netif_running(netdev)) {
@@ -3835,7 +3867,7 @@ static int __maybe_unused iavf_suspend(struct device *dev_d)
 	iavf_free_misc_irq(adapter);
 	iavf_reset_interrupt_capability(adapter);
 
-	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mutex_unlock(&adapter->crit_lock);
 
 	return 0;
 }
@@ -3897,7 +3929,7 @@ static void iavf_remove(struct pci_dev *pdev)
 	struct iavf_hw *hw = &adapter->hw;
 	int err;
 	/* Indicate we are in remove and not to run reset_task */
-	set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section);
+	mutex_lock(&adapter->remove_lock);
 	cancel_delayed_work_sync(&adapter->init_task);
 	cancel_work_sync(&adapter->reset_task);
 	cancel_delayed_work_sync(&adapter->client_task);
@@ -3912,10 +3944,6 @@ static void iavf_remove(struct pci_dev *pdev)
 				 err);
 	}
 
-	/* Shut down all the garbage mashers on the detention level */
-	adapter->state = __IAVF_REMOVE;
-	adapter->aq_required = 0;
-	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
 	iavf_request_reset(adapter);
 	msleep(50);
 	/* If the FW isn't responding, kick it once, but only once. */
@@ -3923,6 +3951,13 @@ static void iavf_remove(struct pci_dev *pdev)
 		iavf_request_reset(adapter);
 		msleep(50);
 	}
+	if (iavf_lock_timeout(&adapter->crit_lock, 5000))
+		dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__);
+
+	/* Shut down all the garbage mashers on the detention level */
+	adapter->state = __IAVF_REMOVE;
+	adapter->aq_required = 0;
+	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
 	iavf_free_all_tx_resources(adapter);
 	iavf_free_all_rx_resources(adapter);
 	iavf_misc_irq_disable(adapter);
@@ -3942,6 +3977,11 @@ 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_destroy(&adapter->client_lock);
+	mutex_unlock(&adapter->crit_lock);
+	mutex_destroy(&adapter->crit_lock);
+	mutex_unlock(&adapter->remove_lock);
+	mutex_destroy(&adapter->remove_lock);
 
 	iounmap(hw->hw_addr);
 	pci_release_regions(pdev);
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c
index 7fe6e8ea39f0..14afce82ef63 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.c
+++ b/drivers/net/ethernet/intel/ice/ice_devlink.c
@@ -477,7 +477,7 @@ struct ice_pf *ice_allocate_pf(struct device *dev)
 {
 	struct devlink *devlink;
 
-	devlink = devlink_alloc(&ice_devlink_ops, sizeof(struct ice_pf));
+	devlink = devlink_alloc(&ice_devlink_ops, sizeof(struct ice_pf), dev);
 	if (!devlink)
 		return NULL;
 
@@ -504,7 +504,7 @@ int ice_devlink_register(struct ice_pf *pf)
 	struct device *dev = ice_pf_to_dev(pf);
 	int err;
 
-	err = devlink_register(devlink, dev);
+	err = devlink_register(devlink);
 	if (err) {
 		dev_err(dev, "devlink registration failed: %d\n", err);
 		return err;
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index d95a5daca114..c451cf401e63 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3568,8 +3568,10 @@ __ice_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec,
 	return 0;
 }
 
-static int
-ice_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+static int ice_get_coalesce(struct net_device *netdev,
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	return __ice_get_coalesce(netdev, ec, -1);
 }
@@ -3787,8 +3789,10 @@ set_complete:
 	return 0;
 }
 
-static int
-ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+static int ice_set_coalesce(struct net_device *netdev,
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	return __ice_set_coalesce(netdev, ec, -1);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index fe2ded775f25..0d6c143f6653 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5122,6 +5122,7 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi)
 	struct ice_hw *hw = &pf->hw;
 	struct sockaddr *addr = pi;
 	enum ice_status status;
+	u8 old_mac[ETH_ALEN];
 	u8 flags = 0;
 	int err = 0;
 	u8 *mac;
@@ -5144,8 +5145,13 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi)
 	}
 
 	netif_addr_lock_bh(netdev);
+	ether_addr_copy(old_mac, netdev->dev_addr);
+	/* change the netdev's MAC address */
+	memcpy(netdev->dev_addr, mac, netdev->addr_len);
+	netif_addr_unlock_bh(netdev);
+
 	/* Clean up old MAC filter. Not an error if old filter doesn't exist */
-	status = ice_fltr_remove_mac(vsi, netdev->dev_addr, ICE_FWD_TO_VSI);
+	status = ice_fltr_remove_mac(vsi, old_mac, ICE_FWD_TO_VSI);
 	if (status && status != ICE_ERR_DOES_NOT_EXIST) {
 		err = -EADDRNOTAVAIL;
 		goto err_update_filters;
@@ -5168,13 +5174,12 @@ err_update_filters:
 	if (err) {
 		netdev_err(netdev, "can't set MAC %pM. filter update failed\n",
 			   mac);
+		netif_addr_lock_bh(netdev);
+		ether_addr_copy(netdev->dev_addr, old_mac);
 		netif_addr_unlock_bh(netdev);
 		return err;
 	}
 
-	/* change the netdev's MAC address */
-	memcpy(netdev->dev_addr, mac, netdev->addr_len);
-	netif_addr_unlock_bh(netdev);
 	netdev_dbg(vsi->netdev, "updated MAC address to %pM\n",
 		   netdev->dev_addr);
 
@@ -6570,12 +6575,12 @@ event_after:
 }
 
 /**
- * ice_do_ioctl - Access the hwtstamp interface
+ * ice_eth_ioctl - Access the hwtstamp interface
  * @netdev: network interface device structure
  * @ifr: interface request data
  * @cmd: ioctl command
  */
-static int ice_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+static int ice_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_pf *pf = np->vsi->back;
@@ -7241,7 +7246,7 @@ static const struct net_device_ops ice_netdev_ops = {
 	.ndo_change_mtu = ice_change_mtu,
 	.ndo_get_stats64 = ice_get_stats64,
 	.ndo_set_tx_maxrate = ice_set_tx_maxrate,
-	.ndo_do_ioctl = ice_do_ioctl,
+	.ndo_eth_ioctl = ice_eth_ioctl,
 	.ndo_set_vf_spoofchk = ice_set_vf_spoofchk,
 	.ndo_set_vf_mac = ice_set_vf_mac,
 	.ndo_get_vf_config = ice_get_vf_cfg,
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 9e3ddb9b8b51..05cc5870e4ef 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -22,7 +22,7 @@ static void ice_set_tx_tstamp(struct ice_pf *pf, bool on)
 		return;
 
 	/* Set the timestamp enable flag for all the Tx rings */
-	ice_for_each_rxq(vsi, i) {
+	ice_for_each_txq(vsi, i) {
 		if (!vsi->tx_rings[i])
 			continue;
 		vsi->tx_rings[i]->ptp_tx = on;
@@ -689,6 +689,41 @@ err:
 }
 
 /**
+ * ice_ptp_disable_all_clkout - Disable all currently configured outputs
+ * @pf: pointer to the PF structure
+ *
+ * Disable all currently configured clock outputs. This is necessary before
+ * certain changes to the PTP hardware clock. Use ice_ptp_enable_all_clkout to
+ * re-enable the clocks again.
+ */
+static void ice_ptp_disable_all_clkout(struct ice_pf *pf)
+{
+	uint i;
+
+	for (i = 0; i < pf->ptp.info.n_per_out; i++)
+		if (pf->ptp.perout_channels[i].ena)
+			ice_ptp_cfg_clkout(pf, i, NULL, false);
+}
+
+/**
+ * ice_ptp_enable_all_clkout - Enable all configured periodic clock outputs
+ * @pf: pointer to the PF structure
+ *
+ * Enable all currently configured clock outputs. Use this after
+ * ice_ptp_disable_all_clkout to reconfigure the output signals according to
+ * their configuration.
+ */
+static void ice_ptp_enable_all_clkout(struct ice_pf *pf)
+{
+	uint i;
+
+	for (i = 0; i < pf->ptp.info.n_per_out; i++)
+		if (pf->ptp.perout_channels[i].ena)
+			ice_ptp_cfg_clkout(pf, i, &pf->ptp.perout_channels[i],
+					   false);
+}
+
+/**
  * ice_ptp_gpio_enable_e810 - Enable/disable ancillary features of PHC
  * @info: the driver's PTP info structure
  * @rq: The requested feature to change
@@ -783,12 +818,17 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts)
 		goto exit;
 	}
 
+	/* Disable periodic outputs */
+	ice_ptp_disable_all_clkout(pf);
+
 	err = ice_ptp_write_init(pf, &ts64);
 	ice_ptp_unlock(hw);
 
 	if (!err)
 		ice_ptp_update_cached_phctime(pf);
 
+	/* Reenable periodic outputs */
+	ice_ptp_enable_all_clkout(pf);
 exit:
 	if (err) {
 		dev_err(ice_pf_to_dev(pf), "PTP failed to set time %d\n", err);
@@ -842,8 +882,14 @@ static int ice_ptp_adjtime(struct ptp_clock_info *info, s64 delta)
 		return -EBUSY;
 	}
 
+	/* Disable periodic outputs */
+	ice_ptp_disable_all_clkout(pf);
+
 	err = ice_ptp_write_adj(pf, delta);
 
+	/* Reenable periodic outputs */
+	ice_ptp_enable_all_clkout(pf);
+
 	ice_ptp_unlock(hw);
 
 	if (err) {
@@ -1064,17 +1110,6 @@ static long ice_ptp_create_clock(struct ice_pf *pf)
 	info = &pf->ptp.info;
 	dev = ice_pf_to_dev(pf);
 
-	/* Allocate memory for kernel pins interface */
-	if (info->n_pins) {
-		info->pin_config = devm_kcalloc(dev, info->n_pins,
-						sizeof(*info->pin_config),
-						GFP_KERNEL);
-		if (!info->pin_config) {
-			info->n_pins = 0;
-			return -ENOMEM;
-		}
-	}
-
 	/* Attempt to register the clock before enabling the hardware. */
 	clock = ptp_clock_register(info, dev);
 	if (IS_ERR(clock))
@@ -1278,6 +1313,8 @@ ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 {
 	u8 idx;
 
+	spin_lock(&tx->lock);
+
 	for (idx = 0; idx < tx->len; idx++) {
 		u8 phy_idx = idx + tx->quad_offset;
 
@@ -1290,6 +1327,8 @@ ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 			tx->tstamps[idx].skb = NULL;
 		}
 	}
+
+	spin_unlock(&tx->lock);
 }
 
 /**
@@ -1550,6 +1589,9 @@ void ice_ptp_release(struct ice_pf *pf)
 	if (!pf->ptp.clock)
 		return;
 
+	/* Disable periodic outputs */
+	ice_ptp_disable_all_clkout(pf);
+
 	ice_clear_ptp_clock_index(pf);
 	ptp_clock_unregister(pf->ptp.clock);
 	pf->ptp.clock = NULL;
diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c
index e63ee3cca5ea..1277c5c7d099 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mac.c
+++ b/drivers/net/ethernet/intel/igb/e1000_mac.c
@@ -492,6 +492,7 @@ static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr)
  **/
 static void igb_i21x_hw_doublecheck(struct e1000_hw *hw)
 {
+	int failed_cnt = 3;
 	bool is_failed;
 	int i;
 
@@ -502,9 +503,12 @@ static void igb_i21x_hw_doublecheck(struct e1000_hw *hw)
 				is_failed = true;
 				array_wr32(E1000_MTA, i, hw->mac.mta_shadow[i]);
 				wrfl();
-				break;
 			}
 		}
+		if (is_failed && --failed_cnt <= 0) {
+			hw_dbg("Failed to update MTA_REGISTER, too many retries");
+			break;
+		}
 	} while (is_failed);
 }
 
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 636a1b1fb7e1..fb1029352c3e 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -2182,7 +2182,9 @@ static int igb_set_phys_id(struct net_device *netdev,
 }
 
 static int igb_set_coalesce(struct net_device *netdev,
-			    struct ethtool_coalesce *ec)
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	int i;
@@ -2238,7 +2240,9 @@ static int igb_set_coalesce(struct net_device *netdev,
 }
 
 static int igb_get_coalesce(struct net_device *netdev,
-			    struct ethtool_coalesce *ec)
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 
@@ -2343,8 +2347,7 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 
 	switch (stringset) {
 	case ETH_SS_TEST:
-		memcpy(data, *igb_gstrings_test,
-			IGB_TEST_LEN*ETH_GSTRING_LEN);
+		memcpy(data, igb_gstrings_test, sizeof(igb_gstrings_test));
 		break;
 	case ETH_SS_STATS:
 		for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 171a7a629b20..751de06019a0 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2991,7 +2991,7 @@ static const struct net_device_ops igb_netdev_ops = {
 	.ndo_set_rx_mode	= igb_set_rx_mode,
 	.ndo_set_mac_address	= igb_set_mac,
 	.ndo_change_mtu		= igb_change_mtu,
-	.ndo_do_ioctl		= igb_ioctl,
+	.ndo_eth_ioctl		= igb_ioctl,
 	.ndo_tx_timeout		= igb_tx_timeout,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_vlan_rx_add_vid	= igb_vlan_rx_add_vid,
diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c
index f4835eb62fee..06e5bd646a0e 100644
--- a/drivers/net/ethernet/intel/igbvf/ethtool.c
+++ b/drivers/net/ethernet/intel/igbvf/ethtool.c
@@ -314,7 +314,9 @@ static int igbvf_set_wol(struct net_device *netdev,
 }
 
 static int igbvf_get_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct igbvf_adapter *adapter = netdev_priv(netdev);
 
@@ -327,7 +329,9 @@ static int igbvf_get_coalesce(struct net_device *netdev,
 }
 
 static int igbvf_set_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct igbvf_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 1bbe9862a758..d32e72d953c8 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -2657,7 +2657,7 @@ static const struct net_device_ops igbvf_netdev_ops = {
 	.ndo_set_rx_mode	= igbvf_set_rx_mode,
 	.ndo_set_mac_address	= igbvf_set_mac,
 	.ndo_change_mtu		= igbvf_change_mtu,
-	.ndo_do_ioctl		= igbvf_ioctl,
+	.ndo_eth_ioctl		= igbvf_ioctl,
 	.ndo_tx_timeout		= igbvf_tx_timeout,
 	.ndo_vlan_rx_add_vid	= igbvf_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= igbvf_vlan_rx_kill_vid,
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 5901ed9fb545..3e386c38d016 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -33,6 +33,8 @@ void igc_ethtool_set_ops(struct net_device *);
 #define IGC_N_PEROUT	2
 #define IGC_N_SDP	4
 
+#define MAX_FLEX_FILTER			32
+
 enum igc_mac_filter_type {
 	IGC_MAC_FILTER_TYPE_DST = 0,
 	IGC_MAC_FILTER_TYPE_SRC
@@ -96,6 +98,13 @@ struct igc_ring {
 	u32 start_time;
 	u32 end_time;
 
+	/* CBS parameters */
+	bool cbs_enable;                /* indicates if CBS is enabled */
+	s32 idleslope;                  /* idleSlope in kbps */
+	s32 sendslope;                  /* sendSlope in kbps */
+	s32 hicredit;                   /* hiCredit in bytes */
+	s32 locredit;                   /* loCredit in bytes */
+
 	/* everything past this point are written often */
 	u16 next_to_clean;
 	u16 next_to_use;
@@ -225,6 +234,7 @@ struct igc_adapter {
 	struct timecounter tc;
 	struct timespec64 prev_ptp_time; /* Pre-reset PTP clock */
 	ktime_t ptp_reset_start; /* Reset time in clock mono */
+	struct system_time_snapshot snapshot;
 
 	char fw_version[32];
 
@@ -287,6 +297,10 @@ extern char igc_driver_name[];
 #define IGC_FLAG_VLAN_PROMISC		BIT(15)
 #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_ANY_ENABLED \
+	(IGC_FLAG_TSN_QBV_ENABLED | IGC_FLAG_TSN_QAV_ENABLED)
 
 #define IGC_FLAG_RSS_FIELD_IPV4_UDP	BIT(6)
 #define IGC_FLAG_RSS_FIELD_IPV6_UDP	BIT(7)
@@ -476,18 +490,28 @@ struct igc_q_vector {
 };
 
 enum igc_filter_match_flags {
-	IGC_FILTER_FLAG_ETHER_TYPE =	0x1,
-	IGC_FILTER_FLAG_VLAN_TCI   =	0x2,
-	IGC_FILTER_FLAG_SRC_MAC_ADDR =	0x4,
-	IGC_FILTER_FLAG_DST_MAC_ADDR =	0x8,
+	IGC_FILTER_FLAG_ETHER_TYPE =	BIT(0),
+	IGC_FILTER_FLAG_VLAN_TCI   =	BIT(1),
+	IGC_FILTER_FLAG_SRC_MAC_ADDR =	BIT(2),
+	IGC_FILTER_FLAG_DST_MAC_ADDR =	BIT(3),
+	IGC_FILTER_FLAG_USER_DATA =	BIT(4),
+	IGC_FILTER_FLAG_VLAN_ETYPE =	BIT(5),
 };
 
 struct igc_nfc_filter {
 	u8 match_flags;
 	u16 etype;
+	__be16 vlan_etype;
 	u16 vlan_tci;
 	u8 src_addr[ETH_ALEN];
 	u8 dst_addr[ETH_ALEN];
+	u8 user_data[8];
+	u8 user_mask[8];
+	u8 flex_index;
+	u8 rx_queue;
+	u8 prio;
+	u8 immediate_irq;
+	u8 drop;
 };
 
 struct igc_nfc_rule {
@@ -495,12 +519,24 @@ struct igc_nfc_rule {
 	struct igc_nfc_filter filter;
 	u32 location;
 	u16 action;
+	bool flex;
 };
 
-/* IGC supports a total of 32 NFC rules: 16 MAC address based,, 8 VLAN priority
- * based, and 8 ethertype based.
+/* IGC supports a total of 32 NFC rules: 16 MAC address based, 8 VLAN priority
+ * based, 8 ethertype based and 32 Flex filter based rules.
  */
-#define IGC_MAX_RXNFC_RULES		32
+#define IGC_MAX_RXNFC_RULES		64
+
+struct igc_flex_filter {
+	u8 index;
+	u8 data[128];
+	u8 mask[16];
+	u8 length;
+	u8 rx_queue;
+	u8 prio;
+	u8 immediate_irq;
+	u8 drop;
+};
 
 /* igc_desc_unused - calculate if we have unused descriptors */
 static inline u16 igc_desc_unused(const struct igc_ring *ring)
diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index d0700d48ecf9..84f142f5e472 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -187,15 +187,7 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw)
 
 	igc_check_for_copper_link(hw);
 
-	/* Verify phy id and set remaining function pointers */
-	switch (phy->id) {
-	case I225_I_PHY_ID:
-		phy->type	= igc_phy_i225;
-		break;
-	default:
-		ret_val = -IGC_ERR_PHY;
-		goto out;
-	}
+	phy->type = igc_phy_i225;
 
 out:
 	return ret_val;
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index c3a5a5518790..a4bbee748798 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -17,11 +17,22 @@
 #define IGC_WUC_PME_EN	0x00000002 /* PME Enable */
 
 /* Wake Up Filter Control */
-#define IGC_WUFC_LNKC	0x00000001 /* Link Status Change Wakeup Enable */
-#define IGC_WUFC_MAG	0x00000002 /* Magic Packet Wakeup Enable */
-#define IGC_WUFC_EX	0x00000004 /* Directed Exact Wakeup Enable */
-#define IGC_WUFC_MC	0x00000008 /* Directed Multicast Wakeup Enable */
-#define IGC_WUFC_BC	0x00000010 /* Broadcast Wakeup Enable */
+#define IGC_WUFC_LNKC		0x00000001 /* Link Status Change Wakeup Enable */
+#define IGC_WUFC_MAG		0x00000002 /* Magic Packet Wakeup Enable */
+#define IGC_WUFC_EX		0x00000004 /* Directed Exact Wakeup Enable */
+#define IGC_WUFC_MC		0x00000008 /* Directed Multicast Wakeup Enable */
+#define IGC_WUFC_BC		0x00000010 /* Broadcast Wakeup Enable */
+#define IGC_WUFC_FLEX_HQ	BIT(14)	   /* Flex Filters Host Queuing */
+#define IGC_WUFC_FLX0		BIT(16)	   /* Flexible Filter 0 Enable */
+#define IGC_WUFC_FLX1		BIT(17)	   /* Flexible Filter 1 Enable */
+#define IGC_WUFC_FLX2		BIT(18)	   /* Flexible Filter 2 Enable */
+#define IGC_WUFC_FLX3		BIT(19)	   /* Flexible Filter 3 Enable */
+#define IGC_WUFC_FLX4		BIT(20)	   /* Flexible Filter 4 Enable */
+#define IGC_WUFC_FLX5		BIT(21)	   /* Flexible Filter 5 Enable */
+#define IGC_WUFC_FLX6		BIT(22)	   /* Flexible Filter 6 Enable */
+#define IGC_WUFC_FLX7		BIT(23)	   /* Flexible Filter 7 Enable */
+
+#define IGC_WUFC_FILTER_MASK GENMASK(23, 14)
 
 #define IGC_CTRL_ADVD3WUC	0x00100000  /* D3 WUC */
 
@@ -46,6 +57,37 @@
 /* Wake Up Packet Memory stores the first 128 bytes of the wake up packet */
 #define IGC_WUPM_BYTES	128
 
+/* Wakeup Filter Control Extended */
+#define IGC_WUFC_EXT_FLX8	BIT(8)	/* Flexible Filter 8 Enable */
+#define IGC_WUFC_EXT_FLX9	BIT(9)	/* Flexible Filter 9 Enable */
+#define IGC_WUFC_EXT_FLX10	BIT(10)	/* Flexible Filter 10 Enable */
+#define IGC_WUFC_EXT_FLX11	BIT(11)	/* Flexible Filter 11 Enable */
+#define IGC_WUFC_EXT_FLX12	BIT(12)	/* Flexible Filter 12 Enable */
+#define IGC_WUFC_EXT_FLX13	BIT(13)	/* Flexible Filter 13 Enable */
+#define IGC_WUFC_EXT_FLX14	BIT(14)	/* Flexible Filter 14 Enable */
+#define IGC_WUFC_EXT_FLX15	BIT(15)	/* Flexible Filter 15 Enable */
+#define IGC_WUFC_EXT_FLX16	BIT(16)	/* Flexible Filter 16 Enable */
+#define IGC_WUFC_EXT_FLX17	BIT(17)	/* Flexible Filter 17 Enable */
+#define IGC_WUFC_EXT_FLX18	BIT(18)	/* Flexible Filter 18 Enable */
+#define IGC_WUFC_EXT_FLX19	BIT(19)	/* Flexible Filter 19 Enable */
+#define IGC_WUFC_EXT_FLX20	BIT(20)	/* Flexible Filter 20 Enable */
+#define IGC_WUFC_EXT_FLX21	BIT(21)	/* Flexible Filter 21 Enable */
+#define IGC_WUFC_EXT_FLX22	BIT(22)	/* Flexible Filter 22 Enable */
+#define IGC_WUFC_EXT_FLX23	BIT(23)	/* Flexible Filter 23 Enable */
+#define IGC_WUFC_EXT_FLX24	BIT(24)	/* Flexible Filter 24 Enable */
+#define IGC_WUFC_EXT_FLX25	BIT(25)	/* Flexible Filter 25 Enable */
+#define IGC_WUFC_EXT_FLX26	BIT(26)	/* Flexible Filter 26 Enable */
+#define IGC_WUFC_EXT_FLX27	BIT(27)	/* Flexible Filter 27 Enable */
+#define IGC_WUFC_EXT_FLX28	BIT(28)	/* Flexible Filter 28 Enable */
+#define IGC_WUFC_EXT_FLX29	BIT(29)	/* Flexible Filter 29 Enable */
+#define IGC_WUFC_EXT_FLX30	BIT(30)	/* Flexible Filter 30 Enable */
+#define IGC_WUFC_EXT_FLX31	BIT(31)	/* Flexible Filter 31 Enable */
+
+#define IGC_WUFC_EXT_FILTER_MASK GENMASK(31, 8)
+
+/* Physical Func Reset Done Indication */
+#define IGC_CTRL_EXT_LINK_MODE_MASK	0x00C00000
+
 /* Loop limit on how long we wait for auto-negotiation to complete */
 #define COPPER_LINK_UP_LIMIT		10
 #define PHY_AUTO_NEG_LIMIT		45
@@ -476,11 +518,50 @@
 #define IGC_TXQCTL_QUEUE_MODE_LAUNCHT	0x00000001
 #define IGC_TXQCTL_STRICT_CYCLE		0x00000002
 #define IGC_TXQCTL_STRICT_END		0x00000004
+#define IGC_TXQCTL_QAV_SEL_MASK		0x000000C0
+#define IGC_TXQCTL_QAV_SEL_CBS0		0x00000080
+#define IGC_TXQCTL_QAV_SEL_CBS1		0x000000C0
+
+#define IGC_TQAVCC_IDLESLOPE_MASK	0xFFFF
+#define IGC_TQAVCC_KEEP_CREDITS		BIT(30)
+
+#define IGC_MAX_SR_QUEUES		2
 
 /* Receive Checksum Control */
 #define IGC_RXCSUM_CRCOFL	0x00000800   /* CRC32 offload enable */
 #define IGC_RXCSUM_PCSD		0x00002000   /* packet checksum disabled */
 
+/* PCIe PTM Control */
+#define IGC_PTM_CTRL_START_NOW	BIT(29) /* Start PTM Now */
+#define IGC_PTM_CTRL_EN		BIT(30) /* Enable PTM */
+#define IGC_PTM_CTRL_TRIG	BIT(31) /* PTM Cycle trigger */
+#define IGC_PTM_CTRL_SHRT_CYC(usec)	(((usec) & 0x2f) << 2)
+#define IGC_PTM_CTRL_PTM_TO(usec)	(((usec) & 0xff) << 8)
+
+#define IGC_PTM_SHORT_CYC_DEFAULT	10  /* Default Short/interrupted cycle interval */
+#define IGC_PTM_CYC_TIME_DEFAULT	5   /* Default PTM cycle time */
+#define IGC_PTM_TIMEOUT_DEFAULT		255 /* Default timeout for PTM errors */
+
+/* PCIe Digital Delay */
+#define IGC_PCIE_DIG_DELAY_DEFAULT	0x01440000
+
+/* PCIe PHY Delay */
+#define IGC_PCIE_PHY_DELAY_DEFAULT	0x40900000
+
+#define IGC_TIMADJ_ADJUST_METH		0x40000000
+
+/* PCIe PTM Status */
+#define IGC_PTM_STAT_VALID		BIT(0) /* PTM Status */
+#define IGC_PTM_STAT_RET_ERR		BIT(1) /* Root port timeout */
+#define IGC_PTM_STAT_BAD_PTM_RES	BIT(2) /* PTM Response msg instead of PTM Response Data */
+#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 */
+
+/* PCIe PTM Cycle Control */
+#define IGC_PTM_CYCLE_CTRL_CYC_TIME(msec)	((msec) & 0x3ff) /* PTM Cycle Time (msec) */
+#define IGC_PTM_CYCLE_CTRL_AUTO_CYC_EN		BIT(31) /* PTM Cycle Control */
+
 /* GPY211 - I225 defines */
 #define GPY_MMD_MASK		0xFFFF0000
 #define GPY_MMD_SHIFT		16
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index fa4171860623..e0a76ac1bbbc 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -862,7 +862,9 @@ static void igc_ethtool_get_stats(struct net_device *netdev,
 }
 
 static int igc_ethtool_get_coalesce(struct net_device *netdev,
-				    struct ethtool_coalesce *ec)
+				    struct ethtool_coalesce *ec,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
@@ -882,7 +884,9 @@ static int igc_ethtool_get_coalesce(struct net_device *netdev,
 }
 
 static int igc_ethtool_set_coalesce(struct net_device *netdev,
-				    struct ethtool_coalesce *ec)
+				    struct ethtool_coalesce *ec,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	int i;
@@ -979,6 +983,12 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter,
 		eth_broadcast_addr(fsp->m_u.ether_spec.h_source);
 	}
 
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_USER_DATA) {
+		fsp->flow_type |= FLOW_EXT;
+		memcpy(fsp->h_ext.data, rule->filter.user_data, sizeof(fsp->h_ext.data));
+		memcpy(fsp->m_ext.data, rule->filter.user_mask, sizeof(fsp->m_ext.data));
+	}
+
 	mutex_unlock(&adapter->nfc_rule_lock);
 	return 0;
 
@@ -1215,6 +1225,30 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule,
 		ether_addr_copy(rule->filter.dst_addr,
 				fsp->h_u.ether_spec.h_dest);
 	}
+
+	/* VLAN etype matching */
+	if ((fsp->flow_type & FLOW_EXT) && fsp->h_ext.vlan_etype) {
+		rule->filter.vlan_etype = fsp->h_ext.vlan_etype;
+		rule->filter.match_flags |= IGC_FILTER_FLAG_VLAN_ETYPE;
+	}
+
+	/* Check for user defined data */
+	if ((fsp->flow_type & FLOW_EXT) &&
+	    (fsp->h_ext.data[0] || fsp->h_ext.data[1])) {
+		rule->filter.match_flags |= IGC_FILTER_FLAG_USER_DATA;
+		memcpy(rule->filter.user_data, fsp->h_ext.data, sizeof(fsp->h_ext.data));
+		memcpy(rule->filter.user_mask, fsp->m_ext.data, sizeof(fsp->m_ext.data));
+	}
+
+	/* When multiple filter options or user data or vlan etype is set, use a
+	 * flex filter.
+	 */
+	if ((rule->filter.match_flags & IGC_FILTER_FLAG_USER_DATA) ||
+	    (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) ||
+	    (rule->filter.match_flags & (rule->filter.match_flags - 1)))
+		rule->flex = true;
+	else
+		rule->flex = false;
 }
 
 /**
@@ -1244,11 +1278,6 @@ static int igc_ethtool_check_nfc_rule(struct igc_adapter *adapter,
 		return -EINVAL;
 	}
 
-	if (flags & (flags - 1)) {
-		netdev_dbg(dev, "Rule with multiple matches not supported\n");
-		return -EOPNOTSUPP;
-	}
-
 	list_for_each_entry(tmp, &adapter->nfc_rule_list, list) {
 		if (!memcmp(&rule->filter, &tmp->filter,
 			    sizeof(rule->filter)) &&
@@ -1280,12 +1309,6 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
 		return -EOPNOTSUPP;
 	}
 
-	if ((fsp->flow_type & FLOW_EXT) &&
-	    fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK)) {
-		netdev_dbg(netdev, "VLAN mask not supported\n");
-		return -EOPNOTSUPP;
-	}
-
 	if (fsp->ring_cookie >= adapter->num_rx_queues) {
 		netdev_dbg(netdev, "Invalid action\n");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index ed2d66bc2d6c..b877efae61df 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -12,6 +12,8 @@
 #include <net/pkt_sched.h>
 #include <linux/bpf_trace.h>
 #include <net/xdp_sock_drv.h>
+#include <linux/pci.h>
+
 #include <net/ipv6.h>
 
 #include "igc.h"
@@ -118,7 +120,7 @@ void igc_reset(struct igc_adapter *adapter)
 	igc_ptp_reset(adapter);
 
 	/* Re-enable TSN offloading, where applicable. */
-	igc_tsn_offload_apply(adapter);
+	igc_tsn_reset(adapter);
 
 	igc_get_phy_info(hw);
 }
@@ -3078,11 +3080,320 @@ static void igc_del_etype_filter(struct igc_adapter *adapter, u16 etype)
 		   etype);
 }
 
+static int igc_flex_filter_select(struct igc_adapter *adapter,
+				  struct igc_flex_filter *input,
+				  u32 *fhft)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u8 fhft_index;
+	u32 fhftsl;
+
+	if (input->index >= MAX_FLEX_FILTER) {
+		dev_err(&adapter->pdev->dev, "Wrong Flex Filter index selected!\n");
+		return -EINVAL;
+	}
+
+	/* Indirect table select register */
+	fhftsl = rd32(IGC_FHFTSL);
+	fhftsl &= ~IGC_FHFTSL_FTSL_MASK;
+	switch (input->index) {
+	case 0 ... 7:
+		fhftsl |= 0x00;
+		break;
+	case 8 ... 15:
+		fhftsl |= 0x01;
+		break;
+	case 16 ... 23:
+		fhftsl |= 0x02;
+		break;
+	case 24 ... 31:
+		fhftsl |= 0x03;
+		break;
+	}
+	wr32(IGC_FHFTSL, fhftsl);
+
+	/* Normalize index down to host table register */
+	fhft_index = input->index % 8;
+
+	*fhft = (fhft_index < 4) ? IGC_FHFT(fhft_index) :
+		IGC_FHFT_EXT(fhft_index - 4);
+
+	return 0;
+}
+
+static int igc_write_flex_filter_ll(struct igc_adapter *adapter,
+				    struct igc_flex_filter *input)
+{
+	struct device *dev = &adapter->pdev->dev;
+	struct igc_hw *hw = &adapter->hw;
+	u8 *data = input->data;
+	u8 *mask = input->mask;
+	u32 queuing;
+	u32 fhft;
+	u32 wufc;
+	int ret;
+	int i;
+
+	/* Length has to be aligned to 8. Otherwise the filter will fail. Bail
+	 * out early to avoid surprises later.
+	 */
+	if (input->length % 8 != 0) {
+		dev_err(dev, "The length of a flex filter has to be 8 byte aligned!\n");
+		return -EINVAL;
+	}
+
+	/* Select corresponding flex filter register and get base for host table. */
+	ret = igc_flex_filter_select(adapter, input, &fhft);
+	if (ret)
+		return ret;
+
+	/* When adding a filter globally disable flex filter feature. That is
+	 * recommended within the datasheet.
+	 */
+	wufc = rd32(IGC_WUFC);
+	wufc &= ~IGC_WUFC_FLEX_HQ;
+	wr32(IGC_WUFC, wufc);
+
+	/* Configure filter */
+	queuing = input->length & IGC_FHFT_LENGTH_MASK;
+	queuing |= (input->rx_queue << IGC_FHFT_QUEUE_SHIFT) & IGC_FHFT_QUEUE_MASK;
+	queuing |= (input->prio << IGC_FHFT_PRIO_SHIFT) & IGC_FHFT_PRIO_MASK;
+
+	if (input->immediate_irq)
+		queuing |= IGC_FHFT_IMM_INT;
+
+	if (input->drop)
+		queuing |= IGC_FHFT_DROP;
+
+	wr32(fhft + 0xFC, queuing);
+
+	/* Write data (128 byte) and mask (128 bit) */
+	for (i = 0; i < 16; ++i) {
+		const size_t data_idx = i * 8;
+		const size_t row_idx = i * 16;
+		u32 dw0 =
+			(data[data_idx + 0] << 0) |
+			(data[data_idx + 1] << 8) |
+			(data[data_idx + 2] << 16) |
+			(data[data_idx + 3] << 24);
+		u32 dw1 =
+			(data[data_idx + 4] << 0) |
+			(data[data_idx + 5] << 8) |
+			(data[data_idx + 6] << 16) |
+			(data[data_idx + 7] << 24);
+		u32 tmp;
+
+		/* Write row: dw0, dw1 and mask */
+		wr32(fhft + row_idx, dw0);
+		wr32(fhft + row_idx + 4, dw1);
+
+		/* mask is only valid for MASK(7, 0) */
+		tmp = rd32(fhft + row_idx + 8);
+		tmp &= ~GENMASK(7, 0);
+		tmp |= mask[i];
+		wr32(fhft + row_idx + 8, tmp);
+	}
+
+	/* Enable filter. */
+	wufc |= IGC_WUFC_FLEX_HQ;
+	if (input->index > 8) {
+		/* Filter 0-7 are enabled via WUFC. The other 24 filters are not. */
+		u32 wufc_ext = rd32(IGC_WUFC_EXT);
+
+		wufc_ext |= (IGC_WUFC_EXT_FLX8 << (input->index - 8));
+
+		wr32(IGC_WUFC_EXT, wufc_ext);
+	} else {
+		wufc |= (IGC_WUFC_FLX0 << input->index);
+	}
+	wr32(IGC_WUFC, wufc);
+
+	dev_dbg(&adapter->pdev->dev, "Added flex filter %u to HW.\n",
+		input->index);
+
+	return 0;
+}
+
+static void igc_flex_filter_add_field(struct igc_flex_filter *flex,
+				      const void *src, unsigned int offset,
+				      size_t len, const void *mask)
+{
+	int i;
+
+	/* data */
+	memcpy(&flex->data[offset], src, len);
+
+	/* mask */
+	for (i = 0; i < len; ++i) {
+		const unsigned int idx = i + offset;
+		const u8 *ptr = mask;
+
+		if (mask) {
+			if (ptr[i] & 0xff)
+				flex->mask[idx / 8] |= BIT(idx % 8);
+
+			continue;
+		}
+
+		flex->mask[idx / 8] |= BIT(idx % 8);
+	}
+}
+
+static int igc_find_avail_flex_filter_slot(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 wufc, wufc_ext;
+	int i;
+
+	wufc = rd32(IGC_WUFC);
+	wufc_ext = rd32(IGC_WUFC_EXT);
+
+	for (i = 0; i < MAX_FLEX_FILTER; i++) {
+		if (i < 8) {
+			if (!(wufc & (IGC_WUFC_FLX0 << i)))
+				return i;
+		} else {
+			if (!(wufc_ext & (IGC_WUFC_EXT_FLX8 << (i - 8))))
+				return i;
+		}
+	}
+
+	return -ENOSPC;
+}
+
+static bool igc_flex_filter_in_use(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 wufc, wufc_ext;
+
+	wufc = rd32(IGC_WUFC);
+	wufc_ext = rd32(IGC_WUFC_EXT);
+
+	if (wufc & IGC_WUFC_FILTER_MASK)
+		return true;
+
+	if (wufc_ext & IGC_WUFC_EXT_FILTER_MASK)
+		return true;
+
+	return false;
+}
+
+static int igc_add_flex_filter(struct igc_adapter *adapter,
+			       struct igc_nfc_rule *rule)
+{
+	struct igc_flex_filter flex = { };
+	struct igc_nfc_filter *filter = &rule->filter;
+	unsigned int eth_offset, user_offset;
+	int ret, index;
+	bool vlan;
+
+	index = igc_find_avail_flex_filter_slot(adapter);
+	if (index < 0)
+		return -ENOSPC;
+
+	/* Construct the flex filter:
+	 *  -> dest_mac [6]
+	 *  -> src_mac [6]
+	 *  -> tpid [2]
+	 *  -> vlan tci [2]
+	 *  -> ether type [2]
+	 *  -> user data [8]
+	 *  -> = 26 bytes => 32 length
+	 */
+	flex.index    = index;
+	flex.length   = 32;
+	flex.rx_queue = rule->action;
+
+	vlan = rule->filter.vlan_tci || rule->filter.vlan_etype;
+	eth_offset = vlan ? 16 : 12;
+	user_offset = vlan ? 18 : 14;
+
+	/* Add destination MAC  */
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
+		igc_flex_filter_add_field(&flex, &filter->dst_addr, 0,
+					  ETH_ALEN, NULL);
+
+	/* Add source MAC */
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR)
+		igc_flex_filter_add_field(&flex, &filter->src_addr, 6,
+					  ETH_ALEN, NULL);
+
+	/* Add VLAN etype */
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE)
+		igc_flex_filter_add_field(&flex, &filter->vlan_etype, 12,
+					  sizeof(filter->vlan_etype),
+					  NULL);
+
+	/* Add VLAN TCI */
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI)
+		igc_flex_filter_add_field(&flex, &filter->vlan_tci, 14,
+					  sizeof(filter->vlan_tci), NULL);
+
+	/* Add Ether type */
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
+		__be16 etype = cpu_to_be16(filter->etype);
+
+		igc_flex_filter_add_field(&flex, &etype, eth_offset,
+					  sizeof(etype), NULL);
+	}
+
+	/* Add user data */
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_USER_DATA)
+		igc_flex_filter_add_field(&flex, &filter->user_data,
+					  user_offset,
+					  sizeof(filter->user_data),
+					  filter->user_mask);
+
+	/* Add it down to the hardware and enable it. */
+	ret = igc_write_flex_filter_ll(adapter, &flex);
+	if (ret)
+		return ret;
+
+	filter->flex_index = index;
+
+	return 0;
+}
+
+static void igc_del_flex_filter(struct igc_adapter *adapter,
+				u16 reg_index)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 wufc;
+
+	/* Just disable the filter. The filter table itself is kept
+	 * intact. Another flex_filter_add() should override the "old" data
+	 * then.
+	 */
+	if (reg_index > 8) {
+		u32 wufc_ext = rd32(IGC_WUFC_EXT);
+
+		wufc_ext &= ~(IGC_WUFC_EXT_FLX8 << (reg_index - 8));
+		wr32(IGC_WUFC_EXT, wufc_ext);
+	} else {
+		wufc = rd32(IGC_WUFC);
+
+		wufc &= ~(IGC_WUFC_FLX0 << reg_index);
+		wr32(IGC_WUFC, wufc);
+	}
+
+	if (igc_flex_filter_in_use(adapter))
+		return;
+
+	/* No filters are in use, we may disable flex filters */
+	wufc = rd32(IGC_WUFC);
+	wufc &= ~IGC_WUFC_FLEX_HQ;
+	wr32(IGC_WUFC, wufc);
+}
+
 static int igc_enable_nfc_rule(struct igc_adapter *adapter,
-			       const struct igc_nfc_rule *rule)
+			       struct igc_nfc_rule *rule)
 {
 	int err;
 
+	if (rule->flex) {
+		return igc_add_flex_filter(adapter, rule);
+	}
+
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
 		err = igc_add_etype_filter(adapter, rule->filter.etype,
 					   rule->action);
@@ -3119,6 +3430,11 @@ static int igc_enable_nfc_rule(struct igc_adapter *adapter,
 static void igc_disable_nfc_rule(struct igc_adapter *adapter,
 				 const struct igc_nfc_rule *rule)
 {
+	if (rule->flex) {
+		igc_del_flex_filter(adapter, rule->filter.flex_index);
+		return;
+	}
+
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE)
 		igc_del_etype_filter(adapter, rule->filter.etype);
 
@@ -4817,6 +5133,7 @@ static irqreturn_t igc_msix_ring(int irq, void *data)
  */
 static int igc_request_msix(struct igc_adapter *adapter)
 {
+	unsigned int num_q_vectors = adapter->num_q_vectors;
 	int i = 0, err = 0, vector = 0, free_vector = 0;
 	struct net_device *netdev = adapter->netdev;
 
@@ -4825,7 +5142,13 @@ static int igc_request_msix(struct igc_adapter *adapter)
 	if (err)
 		goto err_out;
 
-	for (i = 0; i < adapter->num_q_vectors; i++) {
+	if (num_q_vectors > MAX_Q_VECTORS) {
+		num_q_vectors = MAX_Q_VECTORS;
+		dev_warn(&adapter->pdev->dev,
+			 "The number of queue vectors (%d) is higher than max allowed (%d)\n",
+			 adapter->num_q_vectors, MAX_Q_VECTORS);
+	}
+	for (i = 0; i < num_q_vectors; i++) {
 		struct igc_q_vector *q_vector = adapter->q_vector[i];
 
 		vector++;
@@ -4904,20 +5227,12 @@ bool igc_has_link(struct igc_adapter *adapter)
 	 * false until the igc_check_for_link establishes link
 	 * for copper adapters ONLY
 	 */
-	switch (hw->phy.media_type) {
-	case igc_media_type_copper:
-		if (!hw->mac.get_link_status)
-			return true;
-		hw->mac.ops.check_for_link(hw);
-		link_active = !hw->mac.get_link_status;
-		break;
-	default:
-	case igc_media_type_unknown:
-		break;
-	}
+	if (!hw->mac.get_link_status)
+		return true;
+	hw->mac.ops.check_for_link(hw);
+	link_active = !hw->mac.get_link_status;
 
-	if (hw->mac.type == igc_i225 &&
-	    hw->phy.id == I225_I_PHY_ID) {
+	if (hw->mac.type == igc_i225) {
 		if (!netif_carrier_ok(adapter->netdev)) {
 			adapter->flags &= ~IGC_FLAG_NEED_LINK_UPDATE;
 		} else if (!(adapter->flags & IGC_FLAG_NEED_LINK_UPDATE)) {
@@ -5005,7 +5320,9 @@ static void igc_watchdog_task(struct work_struct *work)
 				adapter->tx_timeout_factor = 14;
 				break;
 			case SPEED_100:
-				/* maybe add some timeout factor ? */
+			case SPEED_1000:
+			case SPEED_2500:
+				adapter->tx_timeout_factor = 7;
 				break;
 			}
 
@@ -5432,7 +5749,6 @@ static int igc_save_launchtime_params(struct igc_adapter *adapter, int queue,
 				      bool enable)
 {
 	struct igc_ring *ring;
-	int i;
 
 	if (queue < 0 || queue >= adapter->num_tx_queues)
 		return -EINVAL;
@@ -5440,17 +5756,6 @@ static int igc_save_launchtime_params(struct igc_adapter *adapter, int queue,
 	ring = adapter->tx_ring[queue];
 	ring->launchtime_enable = enable;
 
-	if (adapter->base_time)
-		return 0;
-
-	adapter->cycle_time = NSEC_PER_SEC;
-
-	for (i = 0; i < adapter->num_tx_queues; i++) {
-		ring = adapter->tx_ring[i];
-		ring->start_time = 0;
-		ring->end_time = NSEC_PER_SEC;
-	}
-
 	return 0;
 }
 
@@ -5523,16 +5828,31 @@ static int igc_tsn_enable_launchtime(struct igc_adapter *adapter,
 	return igc_tsn_offload_apply(adapter);
 }
 
+static int igc_tsn_clear_schedule(struct igc_adapter *adapter)
+{
+	int i;
+
+	adapter->base_time = 0;
+	adapter->cycle_time = NSEC_PER_SEC;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *ring = adapter->tx_ring[i];
+
+		ring->start_time = 0;
+		ring->end_time = NSEC_PER_SEC;
+	}
+
+	return 0;
+}
+
 static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 				 struct tc_taprio_qopt_offload *qopt)
 {
 	u32 start_time = 0, end_time = 0;
 	size_t n;
 
-	if (!qopt->enable) {
-		adapter->base_time = 0;
-		return 0;
-	}
+	if (!qopt->enable)
+		return igc_tsn_clear_schedule(adapter);
 
 	if (adapter->base_time)
 		return -EALREADY;
@@ -5584,6 +5904,74 @@ static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter,
 	return igc_tsn_offload_apply(adapter);
 }
 
+static int igc_save_cbs_params(struct igc_adapter *adapter, int queue,
+			       bool enable, int idleslope, int sendslope,
+			       int hicredit, int locredit)
+{
+	bool cbs_status[IGC_MAX_SR_QUEUES] = { false };
+	struct net_device *netdev = adapter->netdev;
+	struct igc_ring *ring;
+	int i;
+
+	/* i225 has two sets of credit-based shaper logic.
+	 * Supporting it only on the top two priority queues
+	 */
+	if (queue < 0 || queue > 1)
+		return -EINVAL;
+
+	ring = adapter->tx_ring[queue];
+
+	for (i = 0; i < IGC_MAX_SR_QUEUES; i++)
+		if (adapter->tx_ring[i])
+			cbs_status[i] = adapter->tx_ring[i]->cbs_enable;
+
+	/* CBS should be enabled on the highest priority queue first in order
+	 * for the CBS algorithm to operate as intended.
+	 */
+	if (enable) {
+		if (queue == 1 && !cbs_status[0]) {
+			netdev_err(netdev,
+				   "Enabling CBS on queue1 before queue0\n");
+			return -EINVAL;
+		}
+	} else {
+		if (queue == 0 && cbs_status[1]) {
+			netdev_err(netdev,
+				   "Disabling CBS on queue0 before queue1\n");
+			return -EINVAL;
+		}
+	}
+
+	ring->cbs_enable = enable;
+	ring->idleslope = idleslope;
+	ring->sendslope = sendslope;
+	ring->hicredit = hicredit;
+	ring->locredit = locredit;
+
+	return 0;
+}
+
+static int igc_tsn_enable_cbs(struct igc_adapter *adapter,
+			      struct tc_cbs_qopt_offload *qopt)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int err;
+
+	if (hw->mac.type != igc_i225)
+		return -EOPNOTSUPP;
+
+	if (qopt->queue < 0 || qopt->queue > 1)
+		return -EINVAL;
+
+	err = igc_save_cbs_params(adapter, qopt->queue, qopt->enable,
+				  qopt->idleslope, qopt->sendslope,
+				  qopt->hicredit, qopt->locredit);
+	if (err)
+		return err;
+
+	return igc_tsn_offload_apply(adapter);
+}
+
 static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			void *type_data)
 {
@@ -5596,6 +5984,9 @@ static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	case TC_SETUP_QDISC_ETF:
 		return igc_tsn_enable_launchtime(adapter, type_data);
 
+	case TC_SETUP_QDISC_CBS:
+		return igc_tsn_enable_cbs(adapter, type_data);
+
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5704,7 +6095,7 @@ static const struct net_device_ops igc_netdev_ops = {
 	.ndo_fix_features	= igc_fix_features,
 	.ndo_set_features	= igc_set_features,
 	.ndo_features_check	= igc_features_check,
-	.ndo_do_ioctl		= igc_ioctl,
+	.ndo_eth_ioctl		= igc_ioctl,
 	.ndo_setup_tc		= igc_setup_tc,
 	.ndo_bpf		= igc_bpf,
 	.ndo_xdp_xmit		= igc_xdp_xmit,
@@ -5865,6 +6256,10 @@ static int igc_probe(struct pci_dev *pdev,
 
 	pci_enable_pcie_error_reporting(pdev);
 
+	err = pci_enable_ptm(pdev, NULL);
+	if (err < 0)
+		dev_info(&pdev->dev, "PCIe PTM not supported by PCIe bus/controller\n");
+
 	pci_set_master(pdev);
 
 	err = -ENOMEM;
@@ -6018,6 +6413,8 @@ static int igc_probe(struct pci_dev *pdev,
 
 	igc_ptp_init(adapter);
 
+	igc_tsn_clear_schedule(adapter);
+
 	/* reset the hardware with the new settings */
 	igc_reset(adapter);
 
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c
index 83aeb5e7076f..5cad31c3c7b0 100644
--- a/drivers/net/ethernet/intel/igc/igc_phy.c
+++ b/drivers/net/ethernet/intel/igc/igc_phy.c
@@ -249,8 +249,7 @@ static s32 igc_phy_setup_autoneg(struct igc_hw *hw)
 			return ret_val;
 	}
 
-	if ((phy->autoneg_mask & ADVERTISE_2500_FULL) &&
-	    hw->phy.id == I225_I_PHY_ID) {
+	if (phy->autoneg_mask & ADVERTISE_2500_FULL) {
 		/* Read the MULTI GBT AN Control Register - reg 7.32 */
 		ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK <<
 					    MMD_DEVADDR_SHIFT) |
@@ -390,8 +389,7 @@ static s32 igc_phy_setup_autoneg(struct igc_hw *hw)
 		ret_val = phy->ops.write_reg(hw, PHY_1000T_CTRL,
 					     mii_1000t_ctrl_reg);
 
-	if ((phy->autoneg_mask & ADVERTISE_2500_FULL) &&
-	    hw->phy.id == I225_I_PHY_ID)
+	if (phy->autoneg_mask & ADVERTISE_2500_FULL)
 		ret_val = phy->ops.write_reg(hw,
 					     (STANDARD_AN_REG_MASK <<
 					     MMD_DEVADDR_SHIFT) |
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 4ae19c6a3247..0f021909b430 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -9,6 +9,8 @@
 #include <linux/ptp_classify.h>
 #include <linux/clocksource.h>
 #include <linux/ktime.h>
+#include <linux/delay.h>
+#include <linux/iopoll.h>
 
 #define INCVALUE_MASK		0x7fffffff
 #define ISGN			0x80000000
@@ -16,6 +18,9 @@
 #define IGC_SYSTIM_OVERFLOW_PERIOD	(HZ * 60 * 9)
 #define IGC_PTP_TX_TIMEOUT		(HZ * 15)
 
+#define IGC_PTM_STAT_SLEEP		2
+#define IGC_PTM_STAT_TIMEOUT		100
+
 /* SYSTIM read access for I225 */
 void igc_ptp_read(struct igc_adapter *adapter, struct timespec64 *ts)
 {
@@ -752,6 +757,147 @@ int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr)
 		-EFAULT : 0;
 }
 
+/* The two conditions below must be met for cross timestamping via
+ * PCIe PTM:
+ *
+ * 1. We have an way to convert the timestamps in the PTM messages
+ *    to something related to the system clocks (right now, only
+ *    X86 systems with support for the Always Running Timer allow that);
+ *
+ * 2. We have PTM enabled in the path from the device to the PCIe root port.
+ */
+static bool igc_is_crosststamp_supported(struct igc_adapter *adapter)
+{
+	return IS_ENABLED(CONFIG_X86_TSC) ? pcie_ptm_enabled(adapter->pdev) : false;
+}
+
+static struct system_counterval_t igc_device_tstamp_to_system(u64 tstamp)
+{
+#if IS_ENABLED(CONFIG_X86_TSC)
+	return convert_art_ns_to_tsc(tstamp);
+#else
+	return (struct system_counterval_t) { };
+#endif
+}
+
+static void igc_ptm_log_error(struct igc_adapter *adapter, u32 ptm_stat)
+{
+	struct net_device *netdev = adapter->netdev;
+
+	switch (ptm_stat) {
+	case IGC_PTM_STAT_RET_ERR:
+		netdev_err(netdev, "PTM Error: Root port timeout\n");
+		break;
+	case IGC_PTM_STAT_BAD_PTM_RES:
+		netdev_err(netdev, "PTM Error: Bad response, PTM Response Data expected\n");
+		break;
+	case IGC_PTM_STAT_T4M1_OVFL:
+		netdev_err(netdev, "PTM Error: T4 minus T1 overflow\n");
+		break;
+	case IGC_PTM_STAT_ADJUST_1ST:
+		netdev_err(netdev, "PTM Error: 1588 timer adjusted during first PTM cycle\n");
+		break;
+	case IGC_PTM_STAT_ADJUST_CYC:
+		netdev_err(netdev, "PTM Error: 1588 timer adjusted during non-first PTM cycle\n");
+		break;
+	default:
+		netdev_err(netdev, "PTM Error: Unknown error (%#x)\n", ptm_stat);
+		break;
+	}
+}
+
+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;
+	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);
+
+	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);
+
+		/* 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);
+
+		err = readx_poll_timeout(rd32, IGC_PTM_STAT, stat,
+					 stat, IGC_PTM_STAT_SLEEP,
+					 IGC_PTM_STAT_TIMEOUT);
+		if (err < 0) {
+			netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n");
+			return err;
+		}
+
+		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;
+		}
+	} while (--count);
+
+	if (!count) {
+		netdev_err(adapter->netdev, "Exceeded number of tries for PTM cycle\n");
+		return -ETIMEDOUT;
+	}
+
+	t1 = ktime_set(rd32(IGC_PTM_T1_TIM0_H), rd32(IGC_PTM_T1_TIM0_L));
+
+	t2_curr_l = rd32(IGC_PTM_CURR_T2_L);
+	t2_curr_h = rd32(IGC_PTM_CURR_T2_H);
+
+	/* FIXME: When the register that tells the endianness of the
+	 * PTM registers are implemented, check them here and add the
+	 * appropriate conversion.
+	 */
+	t2_curr_h = swab32(t2_curr_h);
+
+	t2_curr = ((s64)t2_curr_h << 32 | t2_curr_l);
+
+	*device = t1;
+	*system = igc_device_tstamp_to_system(t2_curr);
+
+	return 0;
+}
+
+static int igc_ptp_getcrosststamp(struct ptp_clock_info *ptp,
+				  struct system_device_crosststamp *cts)
+{
+	struct igc_adapter *adapter = container_of(ptp, struct igc_adapter,
+						   ptp_caps);
+
+	return get_device_system_crosststamp(igc_phc_get_syncdevicetime,
+					     adapter, &adapter->snapshot, cts);
+}
+
 /**
  * igc_ptp_init - Initialize PTP functionality
  * @adapter: Board private structure
@@ -788,6 +934,11 @@ void igc_ptp_init(struct igc_adapter *adapter)
 		adapter->ptp_caps.n_per_out = IGC_N_PEROUT;
 		adapter->ptp_caps.n_pins = IGC_N_SDP;
 		adapter->ptp_caps.verify = igc_ptp_verify_pin;
+
+		if (!igc_is_crosststamp_supported(adapter))
+			break;
+
+		adapter->ptp_caps.getcrosststamp = igc_ptp_getcrosststamp;
 		break;
 	default:
 		adapter->ptp_clock = NULL;
@@ -879,7 +1030,9 @@ 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;
 	unsigned long flags;
+	u32 timadj;
 
 	/* reset the tstamp_config */
 	igc_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config);
@@ -888,12 +1041,38 @@ void igc_ptp_reset(struct igc_adapter *adapter)
 
 	switch (adapter->hw.mac.type) {
 	case igc_i225:
+		timadj = rd32(IGC_TIMADJ);
+		timadj |= IGC_TIMADJ_ADJUST_METH;
+		wr32(IGC_TIMADJ, timadj);
+
 		wr32(IGC_TSAUXC, 0x0);
 		wr32(IGC_TSSDP, 0x0);
 		wr32(IGC_TSIM,
 		     IGC_TSICR_INTERRUPTS |
 		     (adapter->pps_sys_wrap_on ? IGC_TSICR_SYS_WRAP : 0));
 		wr32(IGC_IMS, IGC_IMS_TS);
+
+		if (!igc_is_crosststamp_supported(adapter))
+			break;
+
+		wr32(IGC_PCIE_DIG_DELAY, IGC_PCIE_DIG_DELAY_DEFAULT);
+		wr32(IGC_PCIE_PHY_DELAY, IGC_PCIE_PHY_DELAY_DEFAULT);
+
+		cycle_ctrl = IGC_PTM_CYCLE_CTRL_CYC_TIME(IGC_PTM_CYC_TIME_DEFAULT);
+
+		wr32(IGC_PTM_CYCLE_CTRL, cycle_ctrl);
+
+		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;
+
+		wr32(IGC_PTM_CTRL, ctrl);
+
+		/* Force the first cycle to run. */
+		wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID);
+
 		break;
 	default:
 		/* No work to do. */
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 0f82990567d9..e197a33d93a0 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -67,6 +67,9 @@
 
 /* Filtering Registers */
 #define IGC_ETQF(_n)		(0x05CB0 + (4 * (_n))) /* EType Queue Fltr */
+#define IGC_FHFT(_n)		(0x09000 + (256 * (_n))) /* Flexible Host Filter */
+#define IGC_FHFT_EXT(_n)	(0x09A00 + (256 * (_n))) /* Flexible Host Filter Extended */
+#define IGC_FHFTSL		0x05804 /* Flex Filter indirect table select */
 
 /* ETQF register bit definitions */
 #define IGC_ETQF_FILTER_ENABLE	BIT(26)
@@ -75,6 +78,19 @@
 #define IGC_ETQF_QUEUE_MASK	0x00070000
 #define IGC_ETQF_ETYPE_MASK	0x0000FFFF
 
+/* FHFT register bit definitions */
+#define IGC_FHFT_LENGTH_MASK	GENMASK(7, 0)
+#define IGC_FHFT_QUEUE_SHIFT	8
+#define IGC_FHFT_QUEUE_MASK	GENMASK(10, 8)
+#define IGC_FHFT_PRIO_SHIFT	16
+#define IGC_FHFT_PRIO_MASK	GENMASK(18, 16)
+#define IGC_FHFT_IMM_INT	BIT(24)
+#define IGC_FHFT_DROP		BIT(25)
+
+/* FHFTSL register bit definitions */
+#define IGC_FHFTSL_FTSL_SHIFT	0
+#define IGC_FHFTSL_FTSL_MASK	GENMASK(1, 0)
+
 /* Redirection Table - RW Array */
 #define IGC_RETA(_i)		(0x05C00 + ((_i) * 4))
 /* RSS Random Key - RW Array */
@@ -220,6 +236,9 @@
 #define IGC_ENDQT(_n)		(0x3334 + 0x4 * (_n))
 #define IGC_DTXMXPKTSZ		0x355C
 
+#define IGC_TQAVCC(_n)		(0x3004 + ((_n) * 0x40))
+#define IGC_TQAVHC(_n)		(0x300C + ((_n) * 0x40))
+
 /* System Time Registers */
 #define IGC_SYSTIML	0x0B600  /* System time register Low - RO */
 #define IGC_SYSTIMH	0x0B604  /* System time register High - RO */
@@ -229,6 +248,29 @@
 #define IGC_TXSTMPL	0x0B618  /* Tx timestamp value Low - RO */
 #define IGC_TXSTMPH	0x0B61C  /* Tx timestamp value High - RO */
 
+#define IGC_TIMADJ	0x0B60C  /* Time Adjustment Offset Register */
+
+/* PCIe Registers */
+#define IGC_PTM_CTRL		0x12540  /* PTM Control */
+#define IGC_PTM_STAT		0x12544  /* PTM Status */
+#define IGC_PTM_CYCLE_CTRL	0x1254C  /* PTM Cycle Control */
+
+/* PTM Time registers */
+#define IGC_PTM_T1_TIM0_L	0x12558  /* T1 on Timer 0 Low */
+#define IGC_PTM_T1_TIM0_H	0x1255C  /* T1 on Timer 0 High */
+
+#define IGC_PTM_CURR_T2_L	0x1258C  /* Current T2 Low */
+#define IGC_PTM_CURR_T2_H	0x12590  /* Current T2 High */
+#define IGC_PTM_PREV_T2_L	0x12584  /* Previous T2 Low */
+#define IGC_PTM_PREV_T2_H	0x12588  /* Previous T2 High */
+#define IGC_PTM_PREV_T4M1	0x12578  /* T4 Minus T1 on previous PTM Cycle */
+#define IGC_PTM_CURR_T4M1	0x1257C  /* T4 Minus T1 on this PTM Cycle */
+#define IGC_PTM_PREV_T3M2	0x12580  /* T3 Minus T2 on previous PTM Cycle */
+#define IGC_PTM_TDELAY		0x12594  /* PTM PCIe Link Delay */
+
+#define IGC_PCIE_DIG_DELAY	0x12550  /* PCIe Digital Delay */
+#define IGC_PCIE_PHY_DELAY	0x12554  /* PCIe PHY Delay */
+
 /* Management registers */
 #define IGC_MANC	0x05820  /* Management Control - RW */
 
@@ -240,6 +282,7 @@
 #define IGC_WUFC	0x05808  /* Wakeup Filter Control - RW */
 #define IGC_WUS		0x05810  /* Wakeup Status - R/W1C */
 #define IGC_WUPL	0x05900  /* Wakeup Packet Length - RW */
+#define IGC_WUFC_EXT	0x0580C  /* Wakeup Filter Control Register Extended - RW */
 
 /* Wake Up packet memory */
 #define IGC_WUPM_REG(_i)	(0x05A00 + ((_i) * 4))
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c
index 174103c4bea6..0fce22de2ab8 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.c
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.c
@@ -18,8 +18,38 @@ static bool is_any_launchtime(struct igc_adapter *adapter)
 	return false;
 }
 
+static bool is_cbs_enabled(struct igc_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *ring = adapter->tx_ring[i];
+
+		if (ring->cbs_enable)
+			return true;
+	}
+
+	return false;
+}
+
+static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter)
+{
+	unsigned int new_flags = adapter->flags & ~IGC_FLAG_TSN_ANY_ENABLED;
+
+	if (adapter->base_time)
+		new_flags |= IGC_FLAG_TSN_QBV_ENABLED;
+
+	if (is_any_launchtime(adapter))
+		new_flags |= IGC_FLAG_TSN_QBV_ENABLED;
+
+	if (is_cbs_enabled(adapter))
+		new_flags |= IGC_FLAG_TSN_QAV_ENABLED;
+
+	return new_flags;
+}
+
 /* Returns the TSN specific registers to their default values after
- * TSN offloading is disabled.
+ * the adapter is reset.
  */
 static int igc_tsn_disable_offload(struct igc_adapter *adapter)
 {
@@ -27,11 +57,6 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
 	u32 tqavctrl;
 	int i;
 
-	if (!(adapter->flags & IGC_FLAG_TSN_QBV_ENABLED))
-		return 0;
-
-	adapter->cycle_time = 0;
-
 	wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT);
 	wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT);
 
@@ -41,18 +66,12 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
 	wr32(IGC_TQAVCTRL, tqavctrl);
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
-		struct igc_ring *ring = adapter->tx_ring[i];
-
-		ring->start_time = 0;
-		ring->end_time = 0;
-		ring->launchtime_enable = false;
-
 		wr32(IGC_TXQCTL(i), 0);
 		wr32(IGC_STQT(i), 0);
 		wr32(IGC_ENDQT(i), NSEC_PER_SEC);
 	}
 
-	wr32(IGC_QBVCYCLET_S, NSEC_PER_SEC);
+	wr32(IGC_QBVCYCLET_S, 0);
 	wr32(IGC_QBVCYCLET, NSEC_PER_SEC);
 
 	adapter->flags &= ~IGC_FLAG_TSN_QBV_ENABLED;
@@ -68,9 +87,6 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 	ktime_t base_time, systim;
 	int i;
 
-	if (adapter->flags & IGC_FLAG_TSN_QBV_ENABLED)
-		return 0;
-
 	cycle = adapter->cycle_time;
 	base_time = adapter->base_time;
 
@@ -88,6 +104,8 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		struct igc_ring *ring = adapter->tx_ring[i];
 		u32 txqctl = 0;
+		u16 cbs_value;
+		u32 tqavcc;
 
 		wr32(IGC_STQT(i), ring->start_time);
 		wr32(IGC_ENDQT(i), ring->end_time);
@@ -105,6 +123,90 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 		if (ring->launchtime_enable)
 			txqctl |= IGC_TXQCTL_QUEUE_MODE_LAUNCHT;
 
+		/* Skip configuring CBS for Q2 and Q3 */
+		if (i > 1)
+			goto skip_cbs;
+
+		if (ring->cbs_enable) {
+			if (i == 0)
+				txqctl |= IGC_TXQCTL_QAV_SEL_CBS0;
+			else
+				txqctl |= IGC_TXQCTL_QAV_SEL_CBS1;
+
+			/* According to i225 datasheet section 7.5.2.7, we
+			 * should set the 'idleSlope' field from TQAVCC
+			 * register following the equation:
+			 *
+			 * value = link-speed   0x7736 * BW * 0.2
+			 *         ---------- *  -----------------         (E1)
+			 *          100Mbps            2.5
+			 *
+			 * Note that 'link-speed' is in Mbps.
+			 *
+			 * 'BW' is the percentage bandwidth out of full
+			 * link speed which can be found with the
+			 * following equation. Note that idleSlope here
+			 * is the parameter from this function
+			 * which is in kbps.
+			 *
+			 *     BW =     idleSlope
+			 *          -----------------                      (E2)
+			 *          link-speed * 1000
+			 *
+			 * That said, we can come up with a generic
+			 * equation to calculate the value we should set
+			 * it TQAVCC register by replacing 'BW' in E1 by E2.
+			 * The resulting equation is:
+			 *
+			 * value = link-speed * 0x7736 * idleSlope * 0.2
+			 *         -------------------------------------   (E3)
+			 *             100 * 2.5 * link-speed * 1000
+			 *
+			 * 'link-speed' is present in both sides of the
+			 * fraction so it is canceled out. The final
+			 * equation is the following:
+			 *
+			 *     value = idleSlope * 61036
+			 *             -----------------                   (E4)
+			 *                  2500000
+			 *
+			 * NOTE: For i225, given the above, we can see
+			 *       that idleslope is represented in
+			 *       40.959433 kbps units by the value at
+			 *       the TQAVCC register (2.5Gbps / 61036),
+			 *       which reduces the granularity for
+			 *       idleslope increments.
+			 *
+			 * In i225 controller, the sendSlope and loCredit
+			 * parameters from CBS are not configurable
+			 * by software so we don't do any
+			 * 'controller configuration' in respect to
+			 * these parameters.
+			 */
+			cbs_value = DIV_ROUND_UP_ULL(ring->idleslope
+						     * 61036ULL, 2500000);
+
+			tqavcc = rd32(IGC_TQAVCC(i));
+			tqavcc &= ~IGC_TQAVCC_IDLESLOPE_MASK;
+			tqavcc |= cbs_value | IGC_TQAVCC_KEEP_CREDITS;
+			wr32(IGC_TQAVCC(i), tqavcc);
+
+			wr32(IGC_TQAVHC(i),
+			     0x80000000 + ring->hicredit * 0x7735);
+		} else {
+			/* Disable any CBS for the queue */
+			txqctl &= ~(IGC_TXQCTL_QAV_SEL_MASK);
+
+			/* Set idleSlope to zero. */
+			tqavcc = rd32(IGC_TQAVCC(i));
+			tqavcc &= ~(IGC_TQAVCC_IDLESLOPE_MASK |
+				    IGC_TQAVCC_KEEP_CREDITS);
+			wr32(IGC_TQAVCC(i), tqavcc);
+
+			/* Set hiCredit to zero. */
+			wr32(IGC_TQAVHC(i), 0);
+		}
+skip_cbs:
 		wr32(IGC_TXQCTL(i), txqctl);
 	}
 
@@ -125,33 +227,41 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 	wr32(IGC_BASET_H, baset_h);
 	wr32(IGC_BASET_L, baset_l);
 
-	adapter->flags |= IGC_FLAG_TSN_QBV_ENABLED;
-
 	return 0;
 }
 
-int igc_tsn_offload_apply(struct igc_adapter *adapter)
+int igc_tsn_reset(struct igc_adapter *adapter)
 {
-	bool is_any_enabled = adapter->base_time || is_any_launchtime(adapter);
+	unsigned int new_flags;
+	int err = 0;
 
-	if (!(adapter->flags & IGC_FLAG_TSN_QBV_ENABLED) && !is_any_enabled)
-		return 0;
+	new_flags = igc_tsn_new_flags(adapter);
 
-	if (!is_any_enabled) {
-		int err = igc_tsn_disable_offload(adapter);
+	if (!(new_flags & IGC_FLAG_TSN_ANY_ENABLED))
+		return igc_tsn_disable_offload(adapter);
 
-		if (err < 0)
-			return err;
+	err = igc_tsn_enable_offload(adapter);
+	if (err < 0)
+		return err;
 
-		/* The BASET registers aren't cleared when writing
-		 * into them, force a reset if the interface is
-		 * running.
-		 */
-		if (netif_running(adapter->netdev))
-			schedule_work(&adapter->reset_task);
+	adapter->flags = new_flags;
 
+	return err;
+}
+
+int igc_tsn_offload_apply(struct igc_adapter *adapter)
+{
+	int err;
+
+	if (netif_running(adapter->netdev)) {
+		schedule_work(&adapter->reset_task);
 		return 0;
 	}
 
-	return igc_tsn_enable_offload(adapter);
+	err = igc_tsn_enable_offload(adapter);
+	if (err < 0)
+		return err;
+
+	adapter->flags = igc_tsn_new_flags(adapter);
+	return 0;
 }
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h
index f76bc86ddccd..1512307f5a52 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.h
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.h
@@ -5,5 +5,6 @@
 #define _IGC_TSN_H_
 
 int igc_tsn_offload_apply(struct igc_adapter *adapter);
+int igc_tsn_reset(struct igc_adapter *adapter);
 
 #endif /* _IGC_BASE_H */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 4ceaca0f6ce3..fc26e4ddeb0d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -2358,7 +2358,9 @@ static int ixgbe_set_phys_id(struct net_device *netdev,
 }
 
 static int ixgbe_get_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
@@ -2412,7 +2414,9 @@ static bool ixgbe_update_rsc(struct ixgbe_adapter *adapter)
 }
 
 static int ixgbe_set_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_q_vector *q_vector;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 14aea40da50f..24e06ba6f5e9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -10247,7 +10247,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_set_tx_maxrate	= ixgbe_tx_maxrate,
 	.ndo_vlan_rx_add_vid	= ixgbe_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= ixgbe_vlan_rx_kill_vid,
-	.ndo_do_ioctl		= ixgbe_ioctl,
+	.ndo_eth_ioctl		= ixgbe_ioctl,
 	.ndo_set_vf_mac		= ixgbe_ndo_set_vf_mac,
 	.ndo_set_vf_vlan	= ixgbe_ndo_set_vf_vlan,
 	.ndo_set_vf_rate	= ixgbe_ndo_set_vf_bw,
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index e49fb1cd9a99..8380f905e708 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -787,7 +787,9 @@ static int ixgbevf_nway_reset(struct net_device *netdev)
 }
 
 static int ixgbevf_get_coalesce(struct net_device *netdev,
-				struct ethtool_coalesce *ec)
+				struct ethtool_coalesce *ec,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 
@@ -811,7 +813,9 @@ static int ixgbevf_get_coalesce(struct net_device *netdev,
 }
 
 static int ixgbevf_set_coalesce(struct net_device *netdev,
-				struct ethtool_coalesce *ec)
+				struct ethtool_coalesce *ec,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 	struct ixgbevf_q_vector *q_vector;
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index f1b9284e0bea..1bdc4f23e1e5 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -734,17 +734,17 @@ jme_make_new_rx_buf(struct jme_adapter *jme, int i)
 	if (unlikely(!skb))
 		return -ENOMEM;
 
-	mapping = pci_map_page(jme->pdev, virt_to_page(skb->data),
+	mapping = dma_map_page(&jme->pdev->dev, virt_to_page(skb->data),
 			       offset_in_page(skb->data), skb_tailroom(skb),
-			       PCI_DMA_FROMDEVICE);
-	if (unlikely(pci_dma_mapping_error(jme->pdev, mapping))) {
+			       DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(&jme->pdev->dev, mapping))) {
 		dev_kfree_skb(skb);
 		return -ENOMEM;
 	}
 
 	if (likely(rxbi->mapping))
-		pci_unmap_page(jme->pdev, rxbi->mapping,
-			       rxbi->len, PCI_DMA_FROMDEVICE);
+		dma_unmap_page(&jme->pdev->dev, rxbi->mapping, rxbi->len,
+			       DMA_FROM_DEVICE);
 
 	rxbi->skb = skb;
 	rxbi->len = skb_tailroom(skb);
@@ -760,10 +760,8 @@ jme_free_rx_buf(struct jme_adapter *jme, int i)
 	rxbi += i;
 
 	if (rxbi->skb) {
-		pci_unmap_page(jme->pdev,
-				 rxbi->mapping,
-				 rxbi->len,
-				 PCI_DMA_FROMDEVICE);
+		dma_unmap_page(&jme->pdev->dev, rxbi->mapping, rxbi->len,
+			       DMA_FROM_DEVICE);
 		dev_kfree_skb(rxbi->skb);
 		rxbi->skb = NULL;
 		rxbi->mapping = 0;
@@ -1005,16 +1003,12 @@ jme_alloc_and_feed_skb(struct jme_adapter *jme, int idx)
 	rxbi += idx;
 
 	skb = rxbi->skb;
-	pci_dma_sync_single_for_cpu(jme->pdev,
-					rxbi->mapping,
-					rxbi->len,
-					PCI_DMA_FROMDEVICE);
+	dma_sync_single_for_cpu(&jme->pdev->dev, rxbi->mapping, rxbi->len,
+				DMA_FROM_DEVICE);
 
 	if (unlikely(jme_make_new_rx_buf(jme, idx))) {
-		pci_dma_sync_single_for_device(jme->pdev,
-						rxbi->mapping,
-						rxbi->len,
-						PCI_DMA_FROMDEVICE);
+		dma_sync_single_for_device(&jme->pdev->dev, rxbi->mapping,
+					   rxbi->len, DMA_FROM_DEVICE);
 
 		++(NET_STAT(jme).rx_dropped);
 	} else {
@@ -1453,10 +1447,9 @@ static void jme_tx_clean_tasklet(struct tasklet_struct *t)
 				ttxbi = txbi + ((i + j) & (mask));
 				txdesc[(i + j) & (mask)].dw[0] = 0;
 
-				pci_unmap_page(jme->pdev,
-						 ttxbi->mapping,
-						 ttxbi->len,
-						 PCI_DMA_TODEVICE);
+				dma_unmap_page(&jme->pdev->dev,
+					       ttxbi->mapping, ttxbi->len,
+					       DMA_TO_DEVICE);
 
 				ttxbi->mapping = 0;
 				ttxbi->len = 0;
@@ -1966,19 +1959,13 @@ jme_fill_tx_map(struct pci_dev *pdev,
 {
 	dma_addr_t dmaaddr;
 
-	dmaaddr = pci_map_page(pdev,
-				page,
-				page_offset,
-				len,
-				PCI_DMA_TODEVICE);
+	dmaaddr = dma_map_page(&pdev->dev, page, page_offset, len,
+			       DMA_TO_DEVICE);
 
-	if (unlikely(pci_dma_mapping_error(pdev, dmaaddr)))
+	if (unlikely(dma_mapping_error(&pdev->dev, dmaaddr)))
 		return -EINVAL;
 
-	pci_dma_sync_single_for_device(pdev,
-				       dmaaddr,
-				       len,
-				       PCI_DMA_TODEVICE);
+	dma_sync_single_for_device(&pdev->dev, dmaaddr, len, DMA_TO_DEVICE);
 
 	txdesc->dw[0] = 0;
 	txdesc->dw[1] = 0;
@@ -2003,10 +1990,8 @@ static void jme_drop_tx_map(struct jme_adapter *jme, int startidx, int count)
 
 	for (j = 0 ; j < count ; j++) {
 		ctxbi = txbi + ((startidx + j + 2) & (mask));
-		pci_unmap_page(jme->pdev,
-				ctxbi->mapping,
-				ctxbi->len,
-				PCI_DMA_TODEVICE);
+		dma_unmap_page(&jme->pdev->dev, ctxbi->mapping, ctxbi->len,
+			       DMA_TO_DEVICE);
 
 		ctxbi->mapping = 0;
 		ctxbi->len = 0;
@@ -2400,8 +2385,10 @@ jme_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 	mdio_memcpy(jme, p32, JME_PHY_REG_NR);
 }
 
-static int
-jme_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecmd)
+static int jme_get_coalesce(struct net_device *netdev,
+			    struct ethtool_coalesce *ecmd,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct jme_adapter *jme = netdev_priv(netdev);
 
@@ -2437,8 +2424,10 @@ jme_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecmd)
 	return 0;
 }
 
-static int
-jme_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecmd)
+static int jme_set_coalesce(struct net_device *netdev,
+			    struct ethtool_coalesce *ecmd,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct jme_adapter *jme = netdev_priv(netdev);
 	struct dynpcc_info *dpi = &(jme->dpi);
@@ -2859,18 +2848,15 @@ static int
 jme_pci_dma64(struct pci_dev *pdev)
 {
 	if (pdev->device == PCI_DEVICE_ID_JMICRON_JMC250 &&
-	    !pci_set_dma_mask(pdev, DMA_BIT_MASK(64)))
-		if (!pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)))
-			return 1;
+	    !dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)))
+		return 1;
 
 	if (pdev->device == PCI_DEVICE_ID_JMICRON_JMC250 &&
-	    !pci_set_dma_mask(pdev, DMA_BIT_MASK(40)))
-		if (!pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(40)))
-			return 1;
+	    !dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40)))
+		return 1;
 
-	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))
-		if (!pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)))
-			return 0;
+	if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)))
+		return 0;
 
 	return -1;
 }
@@ -2901,7 +2887,7 @@ static const struct net_device_ops jme_netdev_ops = {
 	.ndo_open		= jme_open,
 	.ndo_stop		= jme_close,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= jme_ioctl,
+	.ndo_eth_ioctl		= jme_ioctl,
 	.ndo_start_xmit		= jme_start_xmit,
 	.ndo_set_mac_address	= jme_set_macaddr,
 	.ndo_set_rx_mode	= jme_set_multi,
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index b30a45725374..3e9f324f1061 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -1272,7 +1272,7 @@ static const struct net_device_ops korina_netdev_ops = {
 	.ndo_start_xmit		= korina_send_packet,
 	.ndo_set_rx_mode	= korina_multicast_list,
 	.ndo_tx_timeout		= korina_tx_timeout,
-	.ndo_do_ioctl		= korina_ioctl,
+	.ndo_eth_ioctl		= korina_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 2d0c52f7106b..62f8c5212182 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -609,7 +609,7 @@ static const struct net_device_ops ltq_eth_netdev_ops = {
 	.ndo_stop = ltq_etop_stop,
 	.ndo_start_xmit = ltq_etop_tx,
 	.ndo_change_mtu = ltq_etop_change_mtu,
-	.ndo_do_ioctl = phy_do_ioctl,
+	.ndo_eth_ioctl = phy_do_ioctl,
 	.ndo_set_mac_address = ltq_etop_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_set_rx_mode = ltq_etop_set_multicast_list,
diff --git a/drivers/net/ethernet/litex/Kconfig b/drivers/net/ethernet/litex/Kconfig
new file mode 100644
index 000000000000..63bf01d28f0c
--- /dev/null
+++ b/drivers/net/ethernet/litex/Kconfig
@@ -0,0 +1,28 @@
+#
+# LiteX device configuration
+#
+
+config NET_VENDOR_LITEX
+	bool "LiteX devices"
+	default y
+	help
+	  If you have a network (Ethernet) card belonging to this class, say Y.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about LiteX devices. If you say Y, you will be asked
+	  for your specific card in the following questions.
+
+if NET_VENDOR_LITEX
+
+config LITEX_LITEETH
+	tristate "LiteX Ethernet support"
+	depends on OF_NET
+	help
+	  If you wish to compile a kernel for hardware with a LiteX LiteEth
+	  device then you should answer Y to this.
+
+	  LiteX is a soft system-on-chip that targets FPGAs. LiteETH is a basic
+	  network device that is commonly used in LiteX designs.
+
+endif # NET_VENDOR_LITEX
diff --git a/drivers/net/ethernet/litex/Makefile b/drivers/net/ethernet/litex/Makefile
new file mode 100644
index 000000000000..9343b73b8e49
--- /dev/null
+++ b/drivers/net/ethernet/litex/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the LiteX network device drivers.
+#
+
+obj-$(CONFIG_LITEX_LITEETH) += litex_liteeth.o
diff --git a/drivers/net/ethernet/litex/litex_liteeth.c b/drivers/net/ethernet/litex/litex_liteeth.c
new file mode 100644
index 000000000000..a9bdbf0dcfe1
--- /dev/null
+++ b/drivers/net/ethernet/litex/litex_liteeth.c
@@ -0,0 +1,314 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * LiteX Liteeth Ethernet
+ *
+ * Copyright 2017 Joel Stanley <joel@jms.id.au>
+ *
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/interrupt.h>
+#include <linux/litex.h>
+#include <linux/module.h>
+#include <linux/of_net.h>
+#include <linux/platform_device.h>
+
+#define LITEETH_WRITER_SLOT       0x00
+#define LITEETH_WRITER_LENGTH     0x04
+#define LITEETH_WRITER_ERRORS     0x08
+#define LITEETH_WRITER_EV_STATUS  0x0C
+#define LITEETH_WRITER_EV_PENDING 0x10
+#define LITEETH_WRITER_EV_ENABLE  0x14
+#define LITEETH_READER_START      0x18
+#define LITEETH_READER_READY      0x1C
+#define LITEETH_READER_LEVEL      0x20
+#define LITEETH_READER_SLOT       0x24
+#define LITEETH_READER_LENGTH     0x28
+#define LITEETH_READER_EV_STATUS  0x2C
+#define LITEETH_READER_EV_PENDING 0x30
+#define LITEETH_READER_EV_ENABLE  0x34
+#define LITEETH_PREAMBLE_CRC      0x38
+#define LITEETH_PREAMBLE_ERRORS   0x3C
+#define LITEETH_CRC_ERRORS        0x40
+
+#define LITEETH_PHY_CRG_RESET     0x00
+#define LITEETH_MDIO_W            0x04
+#define LITEETH_MDIO_R            0x0C
+
+#define DRV_NAME	"liteeth"
+
+struct liteeth {
+	void __iomem *base;
+	struct net_device *netdev;
+	struct device *dev;
+	u32 slot_size;
+
+	/* Tx */
+	u32 tx_slot;
+	u32 num_tx_slots;
+	void __iomem *tx_base;
+
+	/* Rx */
+	u32 rx_slot;
+	u32 num_rx_slots;
+	void __iomem *rx_base;
+};
+
+static int liteeth_rx(struct net_device *netdev)
+{
+	struct liteeth *priv = netdev_priv(netdev);
+	struct sk_buff *skb;
+	unsigned char *data;
+	u8 rx_slot;
+	int len;
+
+	rx_slot = litex_read8(priv->base + LITEETH_WRITER_SLOT);
+	len = litex_read32(priv->base + LITEETH_WRITER_LENGTH);
+
+	if (len == 0 || len > 2048)
+		goto rx_drop;
+
+	skb = netdev_alloc_skb_ip_align(netdev, len);
+	if (!skb) {
+		netdev_err(netdev, "couldn't get memory\n");
+		goto rx_drop;
+	}
+
+	data = skb_put(skb, len);
+	memcpy_fromio(data, priv->rx_base + rx_slot * priv->slot_size, len);
+	skb->protocol = eth_type_trans(skb, netdev);
+
+	netdev->stats.rx_packets++;
+	netdev->stats.rx_bytes += len;
+
+	return netif_rx(skb);
+
+rx_drop:
+	netdev->stats.rx_dropped++;
+	netdev->stats.rx_errors++;
+
+	return NET_RX_DROP;
+}
+
+static irqreturn_t liteeth_interrupt(int irq, void *dev_id)
+{
+	struct net_device *netdev = dev_id;
+	struct liteeth *priv = netdev_priv(netdev);
+	u8 reg;
+
+	reg = litex_read8(priv->base + LITEETH_READER_EV_PENDING);
+	if (reg) {
+		if (netif_queue_stopped(netdev))
+			netif_wake_queue(netdev);
+		litex_write8(priv->base + LITEETH_READER_EV_PENDING, reg);
+	}
+
+	reg = litex_read8(priv->base + LITEETH_WRITER_EV_PENDING);
+	if (reg) {
+		liteeth_rx(netdev);
+		litex_write8(priv->base + LITEETH_WRITER_EV_PENDING, reg);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int liteeth_open(struct net_device *netdev)
+{
+	struct liteeth *priv = netdev_priv(netdev);
+	int err;
+
+	/* Clear pending events */
+	litex_write8(priv->base + LITEETH_WRITER_EV_PENDING, 1);
+	litex_write8(priv->base + LITEETH_READER_EV_PENDING, 1);
+
+	err = request_irq(netdev->irq, liteeth_interrupt, 0, netdev->name, netdev);
+	if (err) {
+		netdev_err(netdev, "failed to request irq %d\n", netdev->irq);
+		return err;
+	}
+
+	/* Enable IRQs */
+	litex_write8(priv->base + LITEETH_WRITER_EV_ENABLE, 1);
+	litex_write8(priv->base + LITEETH_READER_EV_ENABLE, 1);
+
+	netif_carrier_on(netdev);
+	netif_start_queue(netdev);
+
+	return 0;
+}
+
+static int liteeth_stop(struct net_device *netdev)
+{
+	struct liteeth *priv = netdev_priv(netdev);
+
+	netif_stop_queue(netdev);
+	netif_carrier_off(netdev);
+
+	litex_write8(priv->base + LITEETH_WRITER_EV_ENABLE, 0);
+	litex_write8(priv->base + LITEETH_READER_EV_ENABLE, 0);
+
+	free_irq(netdev->irq, netdev);
+
+	return 0;
+}
+
+static int liteeth_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct liteeth *priv = netdev_priv(netdev);
+	void __iomem *txbuffer;
+
+	if (!litex_read8(priv->base + LITEETH_READER_READY)) {
+		if (net_ratelimit())
+			netdev_err(netdev, "LITEETH_READER_READY not ready\n");
+
+		netif_stop_queue(netdev);
+
+		return NETDEV_TX_BUSY;
+	}
+
+	/* Reject oversize packets */
+	if (unlikely(skb->len > priv->slot_size)) {
+		if (net_ratelimit())
+			netdev_err(netdev, "tx packet too big\n");
+
+		dev_kfree_skb_any(skb);
+		netdev->stats.tx_dropped++;
+		netdev->stats.tx_errors++;
+
+		return NETDEV_TX_OK;
+	}
+
+	txbuffer = priv->tx_base + priv->tx_slot * priv->slot_size;
+	memcpy_toio(txbuffer, skb->data, skb->len);
+	litex_write8(priv->base + LITEETH_READER_SLOT, priv->tx_slot);
+	litex_write16(priv->base + LITEETH_READER_LENGTH, skb->len);
+	litex_write8(priv->base + LITEETH_READER_START, 1);
+
+	netdev->stats.tx_bytes += skb->len;
+	netdev->stats.tx_packets++;
+
+	priv->tx_slot = (priv->tx_slot + 1) % priv->num_tx_slots;
+	dev_kfree_skb_any(skb);
+
+	return NETDEV_TX_OK;
+}
+
+static const struct net_device_ops liteeth_netdev_ops = {
+	.ndo_open		= liteeth_open,
+	.ndo_stop		= liteeth_stop,
+	.ndo_start_xmit         = liteeth_start_xmit,
+};
+
+static void liteeth_setup_slots(struct liteeth *priv)
+{
+	struct device_node *np = priv->dev->of_node;
+	int err;
+
+	err = of_property_read_u32(np, "litex,rx-slots", &priv->num_rx_slots);
+	if (err) {
+		dev_dbg(priv->dev, "unable to get litex,rx-slots, using 2\n");
+		priv->num_rx_slots = 2;
+	}
+
+	err = of_property_read_u32(np, "litex,tx-slots", &priv->num_tx_slots);
+	if (err) {
+		dev_dbg(priv->dev, "unable to get litex,tx-slots, using 2\n");
+		priv->num_tx_slots = 2;
+	}
+
+	err = of_property_read_u32(np, "litex,slot-size", &priv->slot_size);
+	if (err) {
+		dev_dbg(priv->dev, "unable to get litex,slot-size, using 0x800\n");
+		priv->slot_size = 0x800;
+	}
+}
+
+static int liteeth_probe(struct platform_device *pdev)
+{
+	struct net_device *netdev;
+	void __iomem *buf_base;
+	struct liteeth *priv;
+	int irq, err;
+
+	netdev = devm_alloc_etherdev(&pdev->dev, sizeof(*priv));
+	if (!netdev)
+		return -ENOMEM;
+
+	SET_NETDEV_DEV(netdev, &pdev->dev);
+	platform_set_drvdata(pdev, netdev);
+
+	priv = netdev_priv(netdev);
+	priv->netdev = netdev;
+	priv->dev = &pdev->dev;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "Failed to get IRQ %d\n", irq);
+		return irq;
+	}
+	netdev->irq = irq;
+
+	priv->base = devm_platform_ioremap_resource_byname(pdev, "mac");
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	buf_base = devm_platform_ioremap_resource_byname(pdev, "buffer");
+	if (IS_ERR(buf_base))
+		return PTR_ERR(buf_base);
+
+	liteeth_setup_slots(priv);
+
+	/* Rx slots */
+	priv->rx_base = buf_base;
+	priv->rx_slot = 0;
+
+	/* Tx slots come after Rx slots */
+	priv->tx_base = buf_base + priv->num_rx_slots * priv->slot_size;
+	priv->tx_slot = 0;
+
+	err = of_get_mac_address(pdev->dev.of_node, netdev->dev_addr);
+	if (err)
+		eth_hw_addr_random(netdev);
+
+	netdev->netdev_ops = &liteeth_netdev_ops;
+
+	err = register_netdev(netdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to register netdev %d\n", err);
+		return err;
+	}
+
+	netdev_info(netdev, "irq %d slots: tx %d rx %d size %d\n",
+		    netdev->irq, priv->num_tx_slots, priv->num_rx_slots, priv->slot_size);
+
+	return 0;
+}
+
+static int liteeth_remove(struct platform_device *pdev)
+{
+	struct net_device *netdev = platform_get_drvdata(pdev);
+
+	unregister_netdev(netdev);
+	free_netdev(netdev);
+
+	return 0;
+}
+
+static const struct of_device_id liteeth_of_match[] = {
+	{ .compatible = "litex,liteeth" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, liteeth_of_match);
+
+static struct platform_driver liteeth_driver = {
+	.probe = liteeth_probe,
+	.remove = liteeth_remove,
+	.driver = {
+		.name = DRV_NAME,
+		.of_match_table = liteeth_of_match,
+	},
+};
+module_platform_driver(liteeth_driver);
+
+MODULE_AUTHOR("Joel Stanley <joel@jms.id.au>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index d207bfcaf31d..28d5ad296646 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -1611,8 +1611,10 @@ static void mv643xx_eth_get_drvinfo(struct net_device *dev,
 	strlcpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info));
 }
 
-static int
-mv643xx_eth_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
+static int mv643xx_eth_get_coalesce(struct net_device *dev,
+				    struct ethtool_coalesce *ec,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct mv643xx_eth_private *mp = netdev_priv(dev);
 
@@ -1622,8 +1624,10 @@ mv643xx_eth_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 	return 0;
 }
 
-static int
-mv643xx_eth_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
+static int mv643xx_eth_set_coalesce(struct net_device *dev,
+				    struct ethtool_coalesce *ec,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct mv643xx_eth_private *mp = netdev_priv(dev);
 
@@ -3060,7 +3064,7 @@ static const struct net_device_ops mv643xx_eth_netdev_ops = {
 	.ndo_set_rx_mode	= mv643xx_eth_set_rx_mode,
 	.ndo_set_mac_address	= mv643xx_eth_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= mv643xx_eth_ioctl,
+	.ndo_eth_ioctl		= mv643xx_eth_ioctl,
 	.ndo_change_mtu		= mv643xx_eth_change_mtu,
 	.ndo_set_features	= mv643xx_eth_set_features,
 	.ndo_tx_timeout		= mv643xx_eth_tx_timeout,
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index de32e5b49053..9d460a270601 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2327,7 +2327,7 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
-	skb_mark_for_recycle(skb, virt_to_page(xdp->data), pool);
+	skb_mark_for_recycle(skb);
 
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	skb_put(skb, xdp->data_end - xdp->data);
@@ -2339,10 +2339,6 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 				skb_frag_page(frag), skb_frag_off(frag),
 				skb_frag_size(frag), PAGE_SIZE);
-		/* We don't need to reset pp_recycle here. It's already set, so
-		 * just mark fragments for recycling.
-		 */
-		page_pool_store_mem_info(skb_frag_page(frag), pool);
 	}
 
 	return skb;
@@ -2666,7 +2662,7 @@ static int mvneta_tx_tso(struct sk_buff *skb, struct net_device *dev,
 		return 0;
 
 	if (skb_headlen(skb) < (skb_transport_offset(skb) + tcp_hdrlen(skb))) {
-		pr_info("*** Is this even  possible???!?!?\n");
+		pr_info("*** Is this even possible?\n");
 		return 0;
 	}
 
@@ -3832,12 +3828,20 @@ static void mvneta_validate(struct phylink_config *config,
 	struct mvneta_port *pp = netdev_priv(ndev);
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 
-	/* We only support QSGMII, SGMII, 802.3z and RGMII modes */
-	if (state->interface != PHY_INTERFACE_MODE_NA &&
-	    state->interface != PHY_INTERFACE_MODE_QSGMII &&
-	    state->interface != PHY_INTERFACE_MODE_SGMII &&
-	    !phy_interface_mode_is_8023z(state->interface) &&
-	    !phy_interface_mode_is_rgmii(state->interface)) {
+	/* We only support QSGMII, SGMII, 802.3z and RGMII modes.
+	 * When in 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."
+	 */
+	if (phy_interface_mode_is_8023z(state->interface)) {
+		if (!phylink_test(state->advertising, Autoneg)) {
+			bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
+			return;
+		}
+	} else if (state->interface != PHY_INTERFACE_MODE_NA &&
+		   state->interface != PHY_INTERFACE_MODE_QSGMII &&
+		   state->interface != PHY_INTERFACE_MODE_SGMII &&
+		   !phy_interface_mode_is_rgmii(state->interface)) {
 		bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
 		return;
 	}
@@ -4496,8 +4500,11 @@ static int mvneta_ethtool_nway_reset(struct net_device *dev)
 }
 
 /* Set interrupt coalescing for ethtools */
-static int mvneta_ethtool_set_coalesce(struct net_device *dev,
-				       struct ethtool_coalesce *c)
+static int
+mvneta_ethtool_set_coalesce(struct net_device *dev,
+			    struct ethtool_coalesce *c,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
 	int queue;
@@ -4520,8 +4527,11 @@ static int mvneta_ethtool_set_coalesce(struct net_device *dev,
 }
 
 /* get coalescing for ethtools */
-static int mvneta_ethtool_get_coalesce(struct net_device *dev,
-				       struct ethtool_coalesce *c)
+static int
+mvneta_ethtool_get_coalesce(struct net_device *dev,
+			    struct ethtool_coalesce *c,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
 
@@ -4986,7 +4996,7 @@ static const struct net_device_ops mvneta_netdev_ops = {
 	.ndo_change_mtu      = mvneta_change_mtu,
 	.ndo_fix_features    = mvneta_fix_features,
 	.ndo_get_stats64     = mvneta_get_stats64,
-	.ndo_do_ioctl        = mvneta_ioctl,
+	.ndo_eth_ioctl        = mvneta_ioctl,
 	.ndo_bpf	     = mvneta_xdp,
 	.ndo_xdp_xmit        = mvneta_xdp_xmit,
 	.ndo_setup_tc	     = mvneta_setup_tc,
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 3229bafa2a2c..d5c92e43f89e 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3995,7 +3995,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 		}
 
 		if (pp)
-			skb_mark_for_recycle(skb, page, pp);
+			skb_mark_for_recycle(skb);
 		else
 			dma_unmap_single_attrs(dev->dev.parent, dma_addr,
 					       bm_pool->buf_size, DMA_FROM_DEVICE,
@@ -5367,8 +5367,11 @@ static int mvpp2_ethtool_nway_reset(struct net_device *dev)
 }
 
 /* Set interrupt coalescing for ethtools */
-static int mvpp2_ethtool_set_coalesce(struct net_device *dev,
-				      struct ethtool_coalesce *c)
+static int
+mvpp2_ethtool_set_coalesce(struct net_device *dev,
+			   struct ethtool_coalesce *c,
+			   struct kernel_ethtool_coalesce *kernel_coal,
+			   struct netlink_ext_ack *extack)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
 	int queue;
@@ -5400,8 +5403,11 @@ static int mvpp2_ethtool_set_coalesce(struct net_device *dev,
 }
 
 /* get coalescing for ethtools */
-static int mvpp2_ethtool_get_coalesce(struct net_device *dev,
-				      struct ethtool_coalesce *c)
+static int
+mvpp2_ethtool_get_coalesce(struct net_device *dev,
+			   struct ethtool_coalesce *c,
+			   struct kernel_ethtool_coalesce *kernel_coal,
+			   struct netlink_ext_ack *extack)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
 
@@ -5702,7 +5708,7 @@ static const struct net_device_ops mvpp2_netdev_ops = {
 	.ndo_set_mac_address	= mvpp2_set_mac_address,
 	.ndo_change_mtu		= mvpp2_change_mtu,
 	.ndo_get_stats64	= mvpp2_get_stats64,
-	.ndo_do_ioctl		= mvpp2_ioctl,
+	.ndo_eth_ioctl		= mvpp2_ioctl,
 	.ndo_vlan_rx_add_vid	= mvpp2_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= mvpp2_vlan_rx_kill_vid,
 	.ndo_set_features	= mvpp2_set_features,
@@ -6269,6 +6275,15 @@ static void mvpp2_phylink_validate(struct phylink_config *config,
 		if (!mvpp2_port_supports_rgmii(port))
 			goto empty_set;
 		break;
+	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_2500BASEX:
+		/* When in 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.
+		 */
+		if (!phylink_test(state->advertising, Autoneg))
+			goto empty_set;
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig
index 16caa02095fe..3f982ccf2c85 100644
--- a/drivers/net/ethernet/marvell/octeontx2/Kconfig
+++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 #
-# Marvell OcteonTX2 drivers configuration
+# Marvell RVU Network drivers configuration
 #
 
 config OCTEONTX2_MBOX
@@ -12,6 +12,7 @@ config OCTEONTX2_AF
 	select NET_DEVLINK
 	depends on (64BIT && COMPILE_TEST) || ARM64
 	depends on PCI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  This driver supports Marvell's OcteonTX2 Resource Virtualization
 	  Unit's admin function manager which manages all RVU HW resources
@@ -32,6 +33,7 @@ config OCTEONTX2_PF
 	select OCTEONTX2_MBOX
 	depends on (64BIT && COMPILE_TEST) || ARM64
 	depends on PCI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  This driver supports Marvell's OcteonTX2 NIC physical function.
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
index cc8ac36cf687..7f4a4ca9af78 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 #
-# Makefile for Marvell's OcteonTX2 RVU Admin Function driver
+# Makefile for Marvell's RVU Admin Function driver
 #
 
 ccflags-y += -I$(src)
@@ -10,4 +10,5 @@ obj-$(CONFIG_OCTEONTX2_AF) += rvu_af.o
 rvu_mbox-y := mbox.o rvu_trace.o
 rvu_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \
 		  rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o rvu_npc_fs.o \
-		  rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o rvu_switch.o
+		  rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o rvu_switch.o \
+		  rvu_sdp.o
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 544c96c8fe1d..7f3d01059e19 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Marvell OcteonTx2 CGX driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index 237ba2b56210..ab1e4abdea38 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -1,11 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*  Marvell OcteonTx2 CGX driver
+/* Marvell OcteonTx2 CGX driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #ifndef CGX_H
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
index aa4e42f78f13..f72ec0e2506f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
@@ -1,11 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*  Marvell OcteonTx2 CGX driver
+/* Marvell OcteonTx2 CGX driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #ifndef __CGX_FW_INTF_H__
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index 47f5ed006a93..d9bea13f15b8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -1,11 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*  Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
- *
- * 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.
+ * Copyright (C) 2018 Marvell.
  */
 
 #ifndef COMMON_H
@@ -64,8 +60,8 @@ static inline int qmem_alloc(struct device *dev, struct qmem **q,
 
 	qmem->entry_sz = entry_sz;
 	qmem->alloc_sz = (qsize * entry_sz) + OTX2_ALIGN;
-	qmem->base = dma_alloc_coherent(dev, qmem->alloc_sz,
-					 &qmem->iova, GFP_KERNEL);
+	qmem->base = dma_alloc_attrs(dev, qmem->alloc_sz, &qmem->iova,
+				     GFP_KERNEL, DMA_ATTR_FORCE_CONTIGUOUS);
 	if (!qmem->base)
 		return -ENOMEM;
 
@@ -84,9 +80,10 @@ static inline void qmem_free(struct device *dev, struct qmem *qmem)
 		return;
 
 	if (qmem->base)
-		dma_free_coherent(dev, qmem->alloc_sz,
-				  qmem->base - qmem->align,
-				  qmem->iova - qmem->align);
+		dma_free_attrs(dev, qmem->alloc_sz,
+			       qmem->base - qmem->align,
+			       qmem->iova - qmem->align,
+			       DMA_ATTR_FORCE_CONTIGUOUS);
 	devm_kfree(dev, qmem);
 }
 
@@ -146,10 +143,7 @@ enum nix_scheduler {
 #define TXSCH_RR_QTM_MAX		((1 << 24) - 1)
 #define TXSCH_TL1_DFLT_RR_QTM		TXSCH_RR_QTM_MAX
 #define TXSCH_TL1_DFLT_RR_PRIO		(0x1ull)
-#define MAX_SCHED_WEIGHT		0xFF
-#define DFLT_RR_WEIGHT			71
-#define DFLT_RR_QTM	((DFLT_RR_WEIGHT * TXSCH_RR_QTM_MAX) \
-			 / MAX_SCHED_WEIGHT)
+#define CN10K_MAX_DWRR_WEIGHT          16384 /* Weight is 14bit on CN10K */
 
 /* Min/Max packet sizes, excluding FCS */
 #define	NIC_HW_MIN_FRS			40
@@ -187,15 +181,16 @@ enum nix_scheduler {
 
 #define NIX_INTF_TYPE_CGX		0
 #define NIX_INTF_TYPE_LBK		1
+#define NIX_INTF_TYPE_SDP		2
 
 #define MAX_LMAC_PKIND			12
 #define NIX_LINK_CGX_LMAC(a, b)		(0 + 4 * (a) + (b))
 #define NIX_LINK_LBK(a)			(12 + (a))
 #define NIX_CHAN_CGX_LMAC_CHX(a, b, c)	(0x800 + 0x100 * (a) + 0x10 * (b) + (c))
 #define NIX_CHAN_LBK_CHX(a, b)		(0 + 0x100 * (a) + (b))
-#define NIX_CHAN_SDP_CH_START		(0x700ull)
-
-#define SDP_CHANNELS			256
+#define NIX_CHAN_SDP_CH_START          (0x700ull)
+#define NIX_CHAN_SDP_CHX(a)            (NIX_CHAN_SDP_CH_START + (a))
+#define NIX_CHAN_SDP_NUM_CHANS		256
 
 /* The mask is to extract lower 10-bits of channel number
  * which CPT will pass to X2P.
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h
index a8b7b1c7a1d5..c38306b3384a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h
@@ -1,7 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*  Marvell OcteonTx2 RPM driver
+/* Marvell CN10K RPM driver
  *
  * Copyright (C) 2020 Marvell.
+ *
  */
 
 #ifndef LMAC_COMMON_H
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
index 0a37ca96aab8..2898931d5260 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #include <linux/module.h>
@@ -412,5 +409,5 @@ const char *otx2_mbox_id2name(u16 id)
 }
 EXPORT_SYMBOL(otx2_mbox_id2name);
 
-MODULE_AUTHOR("Marvell International Ltd.");
+MODULE_AUTHOR("Marvell.");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index f5ec39de026a..154877706a0e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -1,11 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*  Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #ifndef MBOX_H
@@ -87,7 +84,7 @@ struct mbox_msghdr {
 #define OTX2_MBOX_REQ_SIG (0xdead)
 #define OTX2_MBOX_RSP_SIG (0xbeef)
 	u16 sig;         /* Signature, for validating corrupted msgs */
-#define OTX2_MBOX_VERSION (0x0007)
+#define OTX2_MBOX_VERSION (0x0009)
 	u16 ver;         /* Version of msg's structure for this ID */
 	u16 next_msgoff; /* Offset of next msg within mailbox region */
 	int rc;          /* Msg process'ed response code */
@@ -130,6 +127,7 @@ static inline struct mbox_msghdr *otx2_mbox_alloc_msg(struct otx2_mbox *mbox,
 M(READY,		0x001, ready, msg_req, ready_msg_rsp)		\
 M(ATTACH_RESOURCES,	0x002, attach_resources, rsrc_attach, msg_rsp)	\
 M(DETACH_RESOURCES,	0x003, detach_resources, rsrc_detach, msg_rsp)	\
+M(FREE_RSRC_CNT,	0x004, free_rsrc_cnt, msg_req, free_rsrcs_rsp)	\
 M(MSIX_OFFSET,		0x005, msix_offset, msg_req, msix_offset_rsp)	\
 M(VF_FLR,		0x006, vf_flr, msg_req, msg_rsp)		\
 M(PTP_OP,		0x007, ptp_op, ptp_req, ptp_rsp)		\
@@ -191,6 +189,9 @@ M(CPT_RD_WR_REGISTER,	0xA02, cpt_rd_wr_register,  cpt_rd_wr_reg_msg,	\
 M(CPT_STATS,            0xA05, cpt_sts, cpt_sts_req, cpt_sts_rsp)	\
 M(CPT_RXC_TIME_CFG,     0xA06, cpt_rxc_time_cfg, cpt_rxc_time_cfg_req,  \
 			       msg_rsp)                                 \
+/* SDP mbox IDs (range 0x1000 - 0x11FF) */				\
+M(SET_SDP_CHAN_INFO, 0x1000, set_sdp_chan_info, sdp_chan_info_msg, msg_rsp) \
+M(GET_SDP_CHAN_INFO, 0x1001, get_sdp_chan_info, msg_req, sdp_get_chan_info_msg) \
 /* NPC mbox IDs (range 0x6000 - 0x7FFF) */				\
 M(NPC_MCAM_ALLOC_ENTRY,	0x6000, npc_mcam_alloc_entry, npc_mcam_alloc_entry_req,\
 				npc_mcam_alloc_entry_rsp)		\
@@ -243,7 +244,8 @@ M(NIX_HWCTX_DISABLE,	0x8003, nix_hwctx_disable,			\
 M(NIX_TXSCH_ALLOC,	0x8004, nix_txsch_alloc,			\
 				 nix_txsch_alloc_req, nix_txsch_alloc_rsp)   \
 M(NIX_TXSCH_FREE,	0x8005, nix_txsch_free, nix_txsch_free_req, msg_rsp) \
-M(NIX_TXSCHQ_CFG,	0x8006, nix_txschq_cfg, nix_txschq_config, msg_rsp)  \
+M(NIX_TXSCHQ_CFG,	0x8006, nix_txschq_cfg, nix_txschq_config,	\
+				nix_txschq_config)			\
 M(NIX_STATS_RST,	0x8007, nix_stats_rst, msg_req, msg_rsp)	\
 M(NIX_VTAG_CFG,		0x8008, nix_vtag_cfg, nix_vtag_config,		\
 				 nix_vtag_config_rsp)			\
@@ -268,13 +270,15 @@ M(NIX_BP_ENABLE,	0x8016, nix_bp_enable, nix_bp_cfg_req,	\
 				nix_bp_cfg_rsp)	\
 M(NIX_BP_DISABLE,	0x8017, nix_bp_disable, nix_bp_cfg_req, msg_rsp) \
 M(NIX_GET_MAC_ADDR, 0x8018, nix_get_mac_addr, msg_req, nix_get_mac_addr_rsp) \
-M(NIX_CN10K_AQ_ENQ,	0x8019, nix_cn10k_aq_enq, nix_cn10k_aq_enq_req, \
+M(NIX_CN10K_AQ_ENQ,	0x801b, nix_cn10k_aq_enq, nix_cn10k_aq_enq_req, \
 				nix_cn10k_aq_enq_rsp)			\
 M(NIX_GET_HW_INFO,	0x801c, nix_get_hw_info, msg_req, nix_hw_info)	\
 M(NIX_BANDPROF_ALLOC,	0x801d, nix_bandprof_alloc, nix_bandprof_alloc_req, \
 				nix_bandprof_alloc_rsp)			    \
 M(NIX_BANDPROF_FREE,	0x801e, nix_bandprof_free, nix_bandprof_free_req,   \
-				msg_rsp)
+				msg_rsp)				    \
+M(NIX_BANDPROF_GET_HWINFO, 0x801f, nix_bandprof_get_hwinfo, msg_req,		\
+				nix_bandprof_get_hwinfo_rsp)
 
 /* Messages initiated by AF (range 0xC00 - 0xDFF) */
 #define MBOX_UP_CGX_MESSAGES						\
@@ -363,6 +367,25 @@ struct rsrc_detach {
 	u8 cptlfs:1;
 };
 
+/* Number of resources available to the caller.
+ * In reply to MBOX_MSG_FREE_RSRC_CNT.
+ */
+struct free_rsrcs_rsp {
+	struct mbox_msghdr hdr;
+	u16 schq[NIX_TXSCH_LVL_CNT];
+	u16  sso;
+	u16  tim;
+	u16  ssow;
+	u16  cpt;
+	u8   npa;
+	u8   nix;
+	u16  schq_nix1[NIX_TXSCH_LVL_CNT];
+	u8   nix1;
+	u8   cpt1;
+	u8   ree0;
+	u8   ree1;
+};
+
 #define MSIX_VECTOR_INVALID	0xFFFF
 #define MAX_RVU_BLKLF_CNT	256
 
@@ -370,16 +393,20 @@ struct msix_offset_rsp {
 	struct mbox_msghdr hdr;
 	u16  npa_msixoff;
 	u16  nix_msixoff;
-	u8   sso;
-	u8   ssow;
-	u8   timlfs;
-	u8   cptlfs;
+	u16  sso;
+	u16  ssow;
+	u16  timlfs;
+	u16  cptlfs;
 	u16  sso_msixoff[MAX_RVU_BLKLF_CNT];
 	u16  ssow_msixoff[MAX_RVU_BLKLF_CNT];
 	u16  timlf_msixoff[MAX_RVU_BLKLF_CNT];
 	u16  cptlf_msixoff[MAX_RVU_BLKLF_CNT];
-	u8   cpt1_lfs;
+	u16  cpt1_lfs;
+	u16  ree0_lfs;
+	u16  ree1_lfs;
 	u16  cpt1_lf_msixoff[MAX_RVU_BLKLF_CNT];
+	u16  ree0_lf_msixoff[MAX_RVU_BLKLF_CNT];
+	u16  ree1_lf_msixoff[MAX_RVU_BLKLF_CNT];
 };
 
 struct get_hw_cap_rsp {
@@ -594,6 +621,7 @@ struct npa_lf_alloc_rsp {
 	u32 stack_pg_ptrs;  /* No of ptrs per stack page */
 	u32 stack_pg_bytes; /* Size of stack page */
 	u16 qints; /* NPA_AF_CONST::QINTS */
+	u8 cache_lines; /*BATCH ALLOC DMA */
 };
 
 /* NPA AQ enqueue msg */
@@ -698,6 +726,9 @@ struct nix_lf_alloc_req {
 	u16 sso_func;
 	u64 rx_cfg;   /* See NIX_AF_LF(0..127)_RX_CFG */
 	u64 way_mask;
+#define NIX_LF_RSS_TAG_LSB_AS_ADDER BIT_ULL(0)
+#define NIX_LF_LBK_BLK_SEL	    BIT_ULL(1)
+	u64 flags;
 };
 
 struct nix_lf_alloc_rsp {
@@ -717,6 +748,7 @@ struct nix_lf_alloc_rsp {
 	u8	cgx_links;  /* No. of CGX links present in HW */
 	u8	lbk_links;  /* No. of LBK links present in HW */
 	u8	sdp_links;  /* No. of SDP links present in HW */
+	u8	tx_link;    /* Transmit channel link number */
 };
 
 struct nix_lf_free_req {
@@ -835,6 +867,7 @@ struct nix_txsch_free_req {
 struct nix_txschq_config {
 	struct mbox_msghdr hdr;
 	u8 lvl;	/* SMQ/MDQ/TL4/TL3/TL2/TL1 */
+	u8 read;
 #define TXSCHQ_IDX_SHIFT	16
 #define TXSCHQ_IDX_MASK		(BIT_ULL(10) - 1)
 #define TXSCHQ_IDX(reg, shift)	(((reg) >> (shift)) & TXSCHQ_IDX_MASK)
@@ -842,6 +875,8 @@ struct nix_txschq_config {
 #define MAX_REGS_PER_MBOX_MSG	20
 	u64 reg[MAX_REGS_PER_MBOX_MSG];
 	u64 regval[MAX_REGS_PER_MBOX_MSG];
+	/* All 0's => overwrite with new value */
+	u64 regval_mask[MAX_REGS_PER_MBOX_MSG];
 };
 
 struct nix_vtag_config {
@@ -1032,8 +1067,12 @@ struct nix_bp_cfg_rsp {
 
 struct nix_hw_info {
 	struct mbox_msghdr hdr;
+	u16 rsvs16;
 	u16 max_mtu;
 	u16 min_mtu;
+	u32 rpm_dwrr_mtu;
+	u32 sdp_dwrr_mtu;
+	u64 rsvd[16]; /* Add reserved fields for future expansion */
 };
 
 struct nix_bandprof_alloc_req {
@@ -1061,6 +1100,12 @@ struct nix_bandprof_free_req {
 	u16 prof_idx[BAND_PROF_NUM_LAYERS][MAX_BANDPROF_PER_PFFUNC];
 };
 
+struct nix_bandprof_get_hwinfo_rsp {
+	struct mbox_msghdr hdr;
+	u16 prof_count[BAND_PROF_NUM_LAYERS];
+	u32 policer_timeunit;
+};
+
 /* NPC mbox message structs */
 
 #define NPC_MCAM_ENTRY_INVALID	0xFFFF
@@ -1074,6 +1119,13 @@ enum npc_af_status {
 	NPC_MCAM_ALLOC_DENIED	= -702,
 	NPC_MCAM_ALLOC_FAILED	= -703,
 	NPC_MCAM_PERM_DENIED	= -704,
+	NPC_FLOW_INTF_INVALID	= -707,
+	NPC_FLOW_CHAN_INVALID	= -708,
+	NPC_FLOW_NO_NIXLF	= -709,
+	NPC_FLOW_NOT_SUPPORTED	= -710,
+	NPC_FLOW_VF_PERM_DENIED	= -711,
+	NPC_FLOW_VF_NOT_INIT	= -712,
+	NPC_FLOW_VF_OVERLAP	= -713,
 };
 
 struct npc_mcam_alloc_entry_req {
@@ -1328,6 +1380,10 @@ struct set_vf_perm  {
 
 struct lmtst_tbl_setup_req {
 	struct mbox_msghdr hdr;
+	u64 dis_sched_early_comp :1;
+	u64 sch_ena		 :1;
+	u64 dis_line_pref	 :1;
+	u64 ssow_pf_func	 :13;
 	u16 base_pcifunc;
 	u8  use_local_lmt_region;
 	u64 lmt_iova;
@@ -1422,4 +1478,34 @@ struct cpt_rxc_time_cfg_req {
 	u16 active_limit;
 };
 
+struct sdp_node_info {
+	/* Node to which this PF belons to */
+	u8 node_id;
+	u8 max_vfs;
+	u8 num_pf_rings;
+	u8 pf_srn;
+#define SDP_MAX_VFS	128
+	u8 vf_rings[SDP_MAX_VFS];
+};
+
+struct sdp_chan_info_msg {
+	struct mbox_msghdr hdr;
+	struct sdp_node_info info;
+};
+
+struct sdp_get_chan_info_msg {
+	struct mbox_msghdr hdr;
+	u16 chan_base;
+	u16 num_chan;
+};
+
+/* CGX mailbox error codes
+ * Range 1101 - 1200.
+ */
+enum cgx_af_status {
+	LMAC_AF_ERR_INVALID_PARAM	= -1101,
+	LMAC_AF_ERR_PF_NOT_MAPPED	= -1102,
+	LMAC_AF_ERR_PERM_DENIED		= -1103,
+};
+
 #endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index 243cf8070e77..3a819b24accc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -1,11 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*  Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #ifndef NPC_H
@@ -172,6 +169,8 @@ enum key_fields {
 	NPC_DMAC,
 	NPC_SMAC,
 	NPC_ETYPE,
+	NPC_VLAN_ETYPE_CTAG, /* 0x8100 */
+	NPC_VLAN_ETYPE_STAG, /* 0x88A8 */
 	NPC_OUTER_VID,
 	NPC_TOS,
 	NPC_SIP_IPV4,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
index fee655cc7523..588822a0cf21 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
@@ -1,11 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*  Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #ifndef NPC_PROFILE_H
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
index 1ee37853f338..9b8e59f4c206 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Marvell PTP driver
  *
- * Copyright (C) 2020 Marvell International Ltd.
+ * Copyright (C) 2020 Marvell.
+ *
  */
 
 #include <linux/bitfield.h>
@@ -19,12 +20,11 @@
 #define PCI_SUBSYS_DEVID_OCTX2_98xx_PTP		0xB100
 #define PCI_SUBSYS_DEVID_OCTX2_96XX_PTP		0xB200
 #define PCI_SUBSYS_DEVID_OCTX2_95XX_PTP		0xB300
-#define PCI_SUBSYS_DEVID_OCTX2_LOKI_PTP		0xB400
+#define PCI_SUBSYS_DEVID_OCTX2_95XXN_PTP	0xB400
 #define PCI_SUBSYS_DEVID_OCTX2_95MM_PTP		0xB500
-#define PCI_SUBSYS_DEVID_CN10K_A_PTP		0xB900
-#define PCI_SUBSYS_DEVID_CNF10K_A_PTP		0xBA00
-#define PCI_SUBSYS_DEVID_CNF10K_B_PTP		0xBC00
+#define PCI_SUBSYS_DEVID_OCTX2_95XXO_PTP	0xB600
 #define PCI_DEVID_OCTEONTX2_RST			0xA085
+#define PCI_DEVID_CN10K_PTP			0xA09E
 
 #define PCI_PTP_BAR_NO				0
 #define PCI_RST_BAR_NO				0
@@ -39,6 +39,9 @@
 #define RST_MUL_BITS				GENMASK_ULL(38, 33)
 #define CLOCK_BASE_RATE				50000000ULL
 
+static struct ptp *first_ptp_block;
+static const struct pci_device_id ptp_id_table[];
+
 static u64 get_clock_rate(void)
 {
 	u64 cfg, ret = CLOCK_BASE_RATE * 16;
@@ -74,23 +77,14 @@ error:
 
 struct ptp *ptp_get(void)
 {
-	struct pci_dev *pdev;
-	struct ptp *ptp;
+	struct ptp *ptp = first_ptp_block;
 
-	/* If the PTP pci device is found on the system and ptp
-	 * driver is bound to it then the PTP pci device is returned
-	 * to the caller(rvu driver).
-	 */
-	pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM,
-			      PCI_DEVID_OCTEONTX2_PTP, NULL);
-	if (!pdev)
+	/* Check PTP block is present in hardware */
+	if (!pci_dev_present(ptp_id_table))
 		return ERR_PTR(-ENODEV);
-
-	ptp = pci_get_drvdata(pdev);
+	/* Check driver is bound to PTP block */
 	if (!ptp)
 		ptp = ERR_PTR(-EPROBE_DEFER);
-	if (IS_ERR(ptp))
-		pci_dev_put(pdev);
 
 	return ptp;
 }
@@ -190,6 +184,8 @@ static int ptp_probe(struct pci_dev *pdev,
 	writeq(clock_comp, ptp->reg_base + PTP_CLOCK_COMP);
 
 	pci_set_drvdata(pdev, ptp);
+	if (!first_ptp_block)
+		first_ptp_block = ptp;
 
 	return 0;
 
@@ -204,6 +200,9 @@ error:
 	 * `dev->driver_data`.
 	 */
 	pci_set_drvdata(pdev, ERR_PTR(err));
+	if (!first_ptp_block)
+		first_ptp_block = ERR_PTR(err);
+
 	return 0;
 }
 
@@ -233,19 +232,14 @@ static const struct pci_device_id ptp_id_table[] = {
 			 PCI_SUBSYS_DEVID_OCTX2_95XX_PTP) },
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP,
 			 PCI_VENDOR_ID_CAVIUM,
-			 PCI_SUBSYS_DEVID_OCTX2_LOKI_PTP) },
+			 PCI_SUBSYS_DEVID_OCTX2_95XXN_PTP) },
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP,
 			 PCI_VENDOR_ID_CAVIUM,
 			 PCI_SUBSYS_DEVID_OCTX2_95MM_PTP) },
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP,
 			 PCI_VENDOR_ID_CAVIUM,
-			 PCI_SUBSYS_DEVID_CN10K_A_PTP) },
-	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP,
-			 PCI_VENDOR_ID_CAVIUM,
-			 PCI_SUBSYS_DEVID_CNF10K_A_PTP) },
-	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP,
-			 PCI_VENDOR_ID_CAVIUM,
-			 PCI_SUBSYS_DEVID_CNF10K_B_PTP) },
+			 PCI_SUBSYS_DEVID_OCTX2_95XXO_PTP) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_PTP) },
 	{ 0, }
 };
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.h b/drivers/net/ethernet/marvell/octeontx2/af/ptp.h
index 878bc395d28f..76d404b24552 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/ptp.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.h
@@ -1,7 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Marvell PTP driver
  *
- * Copyright (C) 2020 Marvell International Ltd.
+ * Copyright (C) 2020 Marvell.
+ *
  */
 
 #ifndef PTP_H
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index a91ccdc59403..07b0eafccad8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/*  Marvell OcteonTx2 RPM driver
+/* Marvell CN10K RPM driver
  *
  * Copyright (C) 2020 Marvell.
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
index d32e74bd5964..f0b069442dcc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*  Marvell OcteonTx2 RPM driver
+/* Marvell CN10K RPM driver
  *
  * Copyright (C) 2020 Marvell.
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 5fe277e354f7..ce647e037f4d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #include <linux/module.h>
@@ -70,18 +67,21 @@ static void rvu_setup_hw_capabilities(struct rvu *rvu)
 	hw->cap.nix_shaping = true;
 	hw->cap.nix_tx_link_bp = true;
 	hw->cap.nix_rx_multicast = true;
+	hw->cap.nix_shaper_toggle_wait = false;
 	hw->rvu = rvu;
 
-	if (is_rvu_96xx_B0(rvu)) {
+	if (is_rvu_pre_96xx_C0(rvu)) {
 		hw->cap.nix_fixed_txschq_mapping = true;
 		hw->cap.nix_txsch_per_cgx_lmac = 4;
 		hw->cap.nix_txsch_per_lbk_lmac = 132;
 		hw->cap.nix_txsch_per_sdp_lmac = 76;
 		hw->cap.nix_shaping = false;
 		hw->cap.nix_tx_link_bp = false;
-		if (is_rvu_96xx_A0(rvu))
+		if (is_rvu_96xx_A0(rvu) || is_rvu_95xx_A0(rvu))
 			hw->cap.nix_rx_multicast = false;
 	}
+	if (!is_rvu_pre_96xx_C0(rvu))
+		hw->cap.nix_shaper_toggle_wait = true;
 
 	if (!is_rvu_otx2(rvu))
 		hw->cap.per_pf_mbox_regs = true;
@@ -498,12 +498,15 @@ int rvu_lf_reset(struct rvu *rvu, struct rvu_block *block, int lf)
 static void rvu_block_reset(struct rvu *rvu, int blkaddr, u64 rst_reg)
 {
 	struct rvu_block *block = &rvu->hw->block[blkaddr];
+	int err;
 
 	if (!block->implemented)
 		return;
 
 	rvu_write64(rvu, blkaddr, rst_reg, BIT_ULL(0));
-	rvu_poll_reg(rvu, blkaddr, rst_reg, BIT_ULL(63), true);
+	err = rvu_poll_reg(rvu, blkaddr, rst_reg, BIT_ULL(63), true);
+	if (err)
+		dev_err(rvu->dev, "HW block:%d reset failed\n", blkaddr);
 }
 
 static void rvu_reset_all_blocks(struct rvu *rvu)
@@ -924,16 +927,26 @@ static int rvu_setup_hw_resources(struct rvu *rvu)
 	block->lfreset_reg = NPA_AF_LF_RST;
 	sprintf(block->name, "NPA");
 	err = rvu_alloc_bitmap(&block->lf);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev,
+			"%s: Failed to allocate NPA LF bitmap\n", __func__);
 		return err;
+	}
 
 nix:
 	err = rvu_setup_nix_hw_resource(rvu, BLKADDR_NIX0);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev,
+			"%s: Failed to allocate NIX0 LFs bitmap\n", __func__);
 		return err;
+	}
+
 	err = rvu_setup_nix_hw_resource(rvu, BLKADDR_NIX1);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev,
+			"%s: Failed to allocate NIX1 LFs bitmap\n", __func__);
 		return err;
+	}
 
 	/* Init SSO group's bitmap */
 	block = &hw->block[BLKADDR_SSO];
@@ -953,8 +966,11 @@ nix:
 	block->lfreset_reg = SSO_AF_LF_HWGRP_RST;
 	sprintf(block->name, "SSO GROUP");
 	err = rvu_alloc_bitmap(&block->lf);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev,
+			"%s: Failed to allocate SSO LF bitmap\n", __func__);
 		return err;
+	}
 
 ssow:
 	/* Init SSO workslot's bitmap */
@@ -974,8 +990,11 @@ ssow:
 	block->lfreset_reg = SSOW_AF_LF_HWS_RST;
 	sprintf(block->name, "SSOWS");
 	err = rvu_alloc_bitmap(&block->lf);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev,
+			"%s: Failed to allocate SSOW LF bitmap\n", __func__);
 		return err;
+	}
 
 tim:
 	/* Init TIM LF's bitmap */
@@ -996,35 +1015,53 @@ tim:
 	block->lfreset_reg = TIM_AF_LF_RST;
 	sprintf(block->name, "TIM");
 	err = rvu_alloc_bitmap(&block->lf);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev,
+			"%s: Failed to allocate TIM LF bitmap\n", __func__);
 		return err;
+	}
 
 cpt:
 	err = rvu_setup_cpt_hw_resource(rvu, BLKADDR_CPT0);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev,
+			"%s: Failed to allocate CPT0 LF bitmap\n", __func__);
 		return err;
+	}
 	err = rvu_setup_cpt_hw_resource(rvu, BLKADDR_CPT1);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev,
+			"%s: Failed to allocate CPT1 LF bitmap\n", __func__);
 		return err;
+	}
 
 	/* Allocate memory for PFVF data */
 	rvu->pf = devm_kcalloc(rvu->dev, hw->total_pfs,
 			       sizeof(struct rvu_pfvf), GFP_KERNEL);
-	if (!rvu->pf)
+	if (!rvu->pf) {
+		dev_err(rvu->dev,
+			"%s: Failed to allocate memory for PF's rvu_pfvf struct\n", __func__);
 		return -ENOMEM;
+	}
 
 	rvu->hwvf = devm_kcalloc(rvu->dev, hw->total_vfs,
 				 sizeof(struct rvu_pfvf), GFP_KERNEL);
-	if (!rvu->hwvf)
+	if (!rvu->hwvf) {
+		dev_err(rvu->dev,
+			"%s: Failed to allocate memory for VF's rvu_pfvf struct\n", __func__);
 		return -ENOMEM;
+	}
 
 	mutex_init(&rvu->rsrc_lock);
 
 	rvu_fwdata_init(rvu);
 
 	err = rvu_setup_msix_resources(rvu);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev,
+			"%s: Failed to setup MSIX resources\n", __func__);
 		return err;
+	}
 
 	for (blkid = 0; blkid < BLK_COUNT; blkid++) {
 		block = &hw->block[blkid];
@@ -1050,25 +1087,39 @@ cpt:
 		goto msix_err;
 
 	err = rvu_npc_init(rvu);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev, "%s: Failed to initialize npc\n", __func__);
 		goto npc_err;
+	}
 
 	err = rvu_cgx_init(rvu);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev, "%s: Failed to initialize cgx\n", __func__);
 		goto cgx_err;
+	}
 
 	/* Assign MACs for CGX mapped functions */
 	rvu_setup_pfvf_macaddress(rvu);
 
 	err = rvu_npa_init(rvu);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev, "%s: Failed to initialize npa\n", __func__);
 		goto npa_err;
+	}
 
 	rvu_get_lbk_bufsize(rvu);
 
 	err = rvu_nix_init(rvu);
-	if (err)
+	if (err) {
+		dev_err(rvu->dev, "%s: Failed to initialize nix\n", __func__);
 		goto nix_err;
+	}
+
+	err = rvu_sdp_init(rvu);
+	if (err) {
+		dev_err(rvu->dev, "%s: Failed to initialize sdp\n", __func__);
+		goto nix_err;
+	}
 
 	rvu_program_channels(rvu);
 
@@ -1322,9 +1373,10 @@ int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
 	int blkaddr = BLKADDR_NIX0, vf;
 	struct rvu_pfvf *pf;
 
+	pf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK);
+
 	/* All CGX mapped PFs are set with assigned NIX block during init */
 	if (is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) {
-		pf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK);
 		blkaddr = pf->nix_blkaddr;
 	} else if (is_afvf(pcifunc)) {
 		vf = pcifunc - 1;
@@ -1337,6 +1389,10 @@ int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
 			blkaddr = BLKADDR_NIX0;
 	}
 
+	/* if SDP1 then the blkaddr is NIX1 */
+	if (is_sdp_pfvf(pcifunc) && pf->sdp_info->node_id == 1)
+		blkaddr = BLKADDR_NIX1;
+
 	switch (blkaddr) {
 	case BLKADDR_NIX1:
 		pfvf->nix_blkaddr = BLKADDR_NIX1;
@@ -1737,6 +1793,99 @@ int rvu_mbox_handler_msix_offset(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
+int rvu_mbox_handler_free_rsrc_cnt(struct rvu *rvu, struct msg_req *req,
+				   struct free_rsrcs_rsp *rsp)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	struct rvu_block *block;
+	struct nix_txsch *txsch;
+	struct nix_hw *nix_hw;
+
+	mutex_lock(&rvu->rsrc_lock);
+
+	block = &hw->block[BLKADDR_NPA];
+	rsp->npa = rvu_rsrc_free_count(&block->lf);
+
+	block = &hw->block[BLKADDR_NIX0];
+	rsp->nix = rvu_rsrc_free_count(&block->lf);
+
+	block = &hw->block[BLKADDR_NIX1];
+	rsp->nix1 = rvu_rsrc_free_count(&block->lf);
+
+	block = &hw->block[BLKADDR_SSO];
+	rsp->sso = rvu_rsrc_free_count(&block->lf);
+
+	block = &hw->block[BLKADDR_SSOW];
+	rsp->ssow = rvu_rsrc_free_count(&block->lf);
+
+	block = &hw->block[BLKADDR_TIM];
+	rsp->tim = rvu_rsrc_free_count(&block->lf);
+
+	block = &hw->block[BLKADDR_CPT0];
+	rsp->cpt = rvu_rsrc_free_count(&block->lf);
+
+	block = &hw->block[BLKADDR_CPT1];
+	rsp->cpt1 = rvu_rsrc_free_count(&block->lf);
+
+	if (rvu->hw->cap.nix_fixed_txschq_mapping) {
+		rsp->schq[NIX_TXSCH_LVL_SMQ] = 1;
+		rsp->schq[NIX_TXSCH_LVL_TL4] = 1;
+		rsp->schq[NIX_TXSCH_LVL_TL3] = 1;
+		rsp->schq[NIX_TXSCH_LVL_TL2] = 1;
+		/* NIX1 */
+		if (!is_block_implemented(rvu->hw, BLKADDR_NIX1))
+			goto out;
+		rsp->schq_nix1[NIX_TXSCH_LVL_SMQ] = 1;
+		rsp->schq_nix1[NIX_TXSCH_LVL_TL4] = 1;
+		rsp->schq_nix1[NIX_TXSCH_LVL_TL3] = 1;
+		rsp->schq_nix1[NIX_TXSCH_LVL_TL2] = 1;
+	} else {
+		nix_hw = get_nix_hw(hw, BLKADDR_NIX0);
+		txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ];
+		rsp->schq[NIX_TXSCH_LVL_SMQ] =
+				rvu_rsrc_free_count(&txsch->schq);
+
+		txsch = &nix_hw->txsch[NIX_TXSCH_LVL_TL4];
+		rsp->schq[NIX_TXSCH_LVL_TL4] =
+				rvu_rsrc_free_count(&txsch->schq);
+
+		txsch = &nix_hw->txsch[NIX_TXSCH_LVL_TL3];
+		rsp->schq[NIX_TXSCH_LVL_TL3] =
+				rvu_rsrc_free_count(&txsch->schq);
+
+		txsch = &nix_hw->txsch[NIX_TXSCH_LVL_TL2];
+		rsp->schq[NIX_TXSCH_LVL_TL2] =
+				rvu_rsrc_free_count(&txsch->schq);
+
+		if (!is_block_implemented(rvu->hw, BLKADDR_NIX1))
+			goto out;
+
+		nix_hw = get_nix_hw(hw, BLKADDR_NIX1);
+		txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ];
+		rsp->schq_nix1[NIX_TXSCH_LVL_SMQ] =
+				rvu_rsrc_free_count(&txsch->schq);
+
+		txsch = &nix_hw->txsch[NIX_TXSCH_LVL_TL4];
+		rsp->schq_nix1[NIX_TXSCH_LVL_TL4] =
+				rvu_rsrc_free_count(&txsch->schq);
+
+		txsch = &nix_hw->txsch[NIX_TXSCH_LVL_TL3];
+		rsp->schq_nix1[NIX_TXSCH_LVL_TL3] =
+				rvu_rsrc_free_count(&txsch->schq);
+
+		txsch = &nix_hw->txsch[NIX_TXSCH_LVL_TL2];
+		rsp->schq_nix1[NIX_TXSCH_LVL_TL2] =
+				rvu_rsrc_free_count(&txsch->schq);
+	}
+
+	rsp->schq_nix1[NIX_TXSCH_LVL_TL1] = 1;
+out:
+	rsp->schq[NIX_TXSCH_LVL_TL1] = 1;
+	mutex_unlock(&rvu->rsrc_lock);
+
+	return 0;
+}
+
 int rvu_mbox_handler_vf_flr(struct rvu *rvu, struct msg_req *req,
 			    struct msg_rsp *rsp)
 {
@@ -2402,11 +2551,12 @@ static void rvu_afvf_queue_flr_work(struct rvu *rvu, int start_vf, int numvfs)
 	for (vf = 0; vf < numvfs; vf++) {
 		if (!(intr & BIT_ULL(vf)))
 			continue;
-		dev = vf + start_vf + rvu->hw->total_pfs;
-		queue_work(rvu->flr_wq, &rvu->flr_wrk[dev].work);
 		/* Clear and disable the interrupt */
 		rvupf_write64(rvu, RVU_PF_VFFLR_INTX(reg), BIT_ULL(vf));
 		rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(reg), BIT_ULL(vf));
+
+		dev = vf + start_vf + rvu->hw->total_pfs;
+		queue_work(rvu->flr_wq, &rvu->flr_wrk[dev].work);
 	}
 }
 
@@ -2422,14 +2572,14 @@ static irqreturn_t rvu_flr_intr_handler(int irq, void *rvu_irq)
 
 	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
 		if (intr & (1ULL << pf)) {
-			/* PF is already dead do only AF related operations */
-			queue_work(rvu->flr_wq, &rvu->flr_wrk[pf].work);
 			/* clear interrupt */
 			rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT,
 				    BIT_ULL(pf));
 			/* Disable the interrupt */
 			rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1C,
 				    BIT_ULL(pf));
+			/* PF is already dead do only AF related operations */
+			queue_work(rvu->flr_wq, &rvu->flr_wrk[pf].work);
 		}
 	}
 
@@ -2984,27 +3134,37 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = rvu_mbox_init(rvu, &rvu->afpf_wq_info, TYPE_AFPF,
 			    rvu->hw->total_pfs, rvu_afpf_mbox_handler,
 			    rvu_afpf_mbox_up_handler);
-	if (err)
+	if (err) {
+		dev_err(dev, "%s: Failed to initialize mbox\n", __func__);
 		goto err_hwsetup;
+	}
 
 	err = rvu_flr_init(rvu);
-	if (err)
+	if (err) {
+		dev_err(dev, "%s: Failed to initialize flr\n", __func__);
 		goto err_mbox;
+	}
 
 	err = rvu_register_interrupts(rvu);
-	if (err)
+	if (err) {
+		dev_err(dev, "%s: Failed to register interrupts\n", __func__);
 		goto err_flr;
+	}
 
 	err = rvu_register_dl(rvu);
-	if (err)
+	if (err) {
+		dev_err(dev, "%s: Failed to register devlink\n", __func__);
 		goto err_irq;
+	}
 
 	rvu_setup_rvum_blk_revid(rvu);
 
 	/* Enable AF's VFs (if any) */
 	err = rvu_enable_sriov(rvu);
-	if (err)
+	if (err) {
+		dev_err(dev, "%s: Failed to enable sriov\n", __func__);
 		goto err_dl;
+	}
 
 	/* Initialize debugfs */
 	rvu_dbg_init(rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 91503fb2762c..d38e5c980c30 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -1,11 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*  Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #ifndef RVU_H
@@ -243,8 +240,11 @@ struct rvu_pfvf {
 	u8	nix_blkaddr; /* BLKADDR_NIX0/1 assigned to this PF */
 	u8	nix_rx_intf; /* NIX0_RX/NIX1_RX interface to NPC */
 	u8	nix_tx_intf; /* NIX0_TX/NIX1_TX interface to NPC */
+	u8	lbkid;	     /* NIX0/1 lbk link ID */
 	u64     lmt_base_addr; /* Preseving the pcifunc's lmtst base addr*/
+	u64     lmt_map_ent_w1; /* Preseving the word1 of lmtst map table entry*/
 	unsigned long flags;
+	struct  sdp_node_info *sdp_info;
 };
 
 enum rvu_pfvf_flags {
@@ -314,6 +314,7 @@ struct nix_hw {
 	struct nix_lso lso;
 	struct nix_txvlan txvlan;
 	struct nix_ipolicer *ipolicer;
+	u64    *tx_credits;
 };
 
 /* RVU block's capabilities or functionality,
@@ -327,8 +328,10 @@ struct hw_cap {
 	u16	nix_txsch_per_sdp_lmac; /* Max Q's transmitting to SDP LMAC */
 	bool	nix_fixed_txschq_mapping; /* Schq mapping fixed or flexible */
 	bool	nix_shaping;		 /* Is shaping and coloring supported */
+	bool    nix_shaper_toggle_wait; /* Shaping toggle needs poll/wait */
 	bool	nix_tx_link_bp;		 /* Can link backpressure TL queues ? */
 	bool	nix_rx_multicast;	 /* Rx packet replication support */
+	bool	nix_common_dwrr_mtu;	 /* Common DWRR MTU for quantum config */
 	bool	per_pf_mbox_regs; /* PF mbox specified in per PF registers ? */
 	bool	programmable_chans; /* Channels programmable ? */
 	bool	ipolicer;
@@ -355,6 +358,7 @@ struct rvu_hwinfo {
 	u16	npc_counters;	   /* No of match stats counters */
 	u32	lbk_bufsize;	   /* FIFO size supported by LBK */
 	bool	npc_ext_set;	   /* Extended register set */
+	u64     npc_stat_ena;      /* Match stats enable bit */
 
 	struct hw_cap    cap;
 	struct rvu_block block[BLK_COUNT]; /* Block info */
@@ -514,20 +518,34 @@ static inline u64 rvupf_read64(struct rvu *rvu, u64 offset)
 }
 
 /* Silicon revisions */
+static inline bool is_rvu_pre_96xx_C0(struct rvu *rvu)
+{
+	struct pci_dev *pdev = rvu->pdev;
+	/* 96XX A0/B0, 95XX A0/A1/B0 chips */
+	return ((pdev->revision == 0x00) || (pdev->revision == 0x01) ||
+		(pdev->revision == 0x10) || (pdev->revision == 0x11) ||
+		(pdev->revision == 0x14));
+}
+
 static inline bool is_rvu_96xx_A0(struct rvu *rvu)
 {
 	struct pci_dev *pdev = rvu->pdev;
 
-	return (pdev->revision == 0x00) &&
-		(pdev->subsystem_device == PCI_SUBSYS_DEVID_96XX);
+	return (pdev->revision == 0x00);
 }
 
 static inline bool is_rvu_96xx_B0(struct rvu *rvu)
 {
 	struct pci_dev *pdev = rvu->pdev;
 
-	return ((pdev->revision == 0x00) || (pdev->revision == 0x01)) &&
-		(pdev->subsystem_device == PCI_SUBSYS_DEVID_96XX);
+	return (pdev->revision == 0x00) || (pdev->revision == 0x01);
+}
+
+static inline bool is_rvu_95xx_A0(struct rvu *rvu)
+{
+	struct pci_dev *pdev = rvu->pdev;
+
+	return (pdev->revision == 0x10) || (pdev->revision == 0x11);
 }
 
 /* REVID for PCIe devices.
@@ -536,9 +554,10 @@ static inline bool is_rvu_96xx_B0(struct rvu *rvu)
  */
 #define PCI_REVISION_ID_96XX		0x00
 #define PCI_REVISION_ID_95XX		0x10
-#define PCI_REVISION_ID_LOKI		0x20
+#define PCI_REVISION_ID_95XXN		0x20
 #define PCI_REVISION_ID_98XX		0x30
 #define PCI_REVISION_ID_95XXMM		0x40
+#define PCI_REVISION_ID_95XXO		0xE0
 
 static inline bool is_rvu_otx2(struct rvu *rvu)
 {
@@ -547,8 +566,8 @@ static inline bool is_rvu_otx2(struct rvu *rvu)
 	u8 midr = pdev->revision & 0xF0;
 
 	return (midr == PCI_REVISION_ID_96XX || midr == PCI_REVISION_ID_95XX ||
-		midr == PCI_REVISION_ID_LOKI || midr == PCI_REVISION_ID_98XX ||
-		midr == PCI_REVISION_ID_95XXMM);
+		midr == PCI_REVISION_ID_95XXN || midr == PCI_REVISION_ID_98XX ||
+		midr == PCI_REVISION_ID_95XXMM || midr == PCI_REVISION_ID_95XXO);
 }
 
 static inline u16 rvu_nix_chan_cgx(struct rvu *rvu, u8 cgxid,
@@ -578,6 +597,16 @@ static inline u16 rvu_nix_chan_lbk(struct rvu *rvu, u8 lbkid,
 	return rvu->hw->lbk_chan_base + lbkid * lbk_chans + chan;
 }
 
+static inline u16 rvu_nix_chan_sdp(struct rvu *rvu, u8 chan)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+
+	if (!hw->cap.programmable_chans)
+		return NIX_CHAN_SDP_CHX(chan);
+
+	return hw->sdp_chan_base + chan;
+}
+
 static inline u16 rvu_nix_chan_cpt(struct rvu *rvu, u8 chan)
 {
 	return rvu->hw->cpt_chan_base + chan;
@@ -640,10 +669,17 @@ int rvu_aq_alloc(struct rvu *rvu, struct admin_queue **ad_queue,
 		 int qsize, int inst_size, int res_size);
 void rvu_aq_free(struct rvu *rvu, struct admin_queue *aq);
 
+/* SDP APIs */
+int rvu_sdp_init(struct rvu *rvu);
+bool is_sdp_pfvf(u16 pcifunc);
+bool is_sdp_pf(u16 pcifunc);
+bool is_sdp_vf(u16 pcifunc);
+
 /* CGX APIs */
 static inline bool is_pf_cgxmapped(struct rvu *rvu, u8 pf)
 {
-	return (pf >= PF_CGXMAP_BASE && pf <= rvu->cgx_mapped_pfs);
+	return (pf >= PF_CGXMAP_BASE && pf <= rvu->cgx_mapped_pfs) &&
+		!is_sdp_pf(pf << RVU_PFVF_PF_SHIFT);
 }
 
 static inline void rvu_get_cgx_lmac_id(u8 map, u8 *cgx_id, u8 *lmac_id)
@@ -706,6 +742,8 @@ int nix_aq_context_read(struct rvu *rvu, struct nix_hw *nix_hw,
 			struct nix_cn10k_aq_enq_rsp *aq_rsp,
 			u16 pcifunc, u8 ctype, u32 qidx);
 int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc);
+u32 convert_dwrr_mtu_to_bytes(u8 dwrr_mtu);
+u32 convert_bytes_to_dwrr_mtu(u32 bytes);
 
 /* NPC APIs */
 int rvu_npc_init(struct rvu *rvu);
@@ -745,7 +783,6 @@ bool is_npc_intf_tx(u8 intf);
 bool is_npc_intf_rx(u8 intf);
 bool is_npc_interface_valid(struct rvu *rvu, u8 intf);
 int rvu_npc_get_tx_nibble_cfg(struct rvu *rvu, u64 nibble_ena);
-int npc_mcam_verify_channel(struct rvu *rvu, u16 pcifunc, u8 intf, u16 channel);
 int npc_flow_steering_init(struct rvu *rvu, int blkaddr);
 const char *npc_get_field_name(u8 hdr);
 int npc_get_bank(struct npc_mcam *mcam, int index);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index fe99ac4a4dd8..81e8ea9ee30e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #include <linux/types.h>
@@ -448,7 +445,7 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start)
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, pcifunc))
-		return -EPERM;
+		return LMAC_AF_ERR_PERM_DENIED;
 
 	rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
 
@@ -507,7 +504,7 @@ static int rvu_lmac_get_stats(struct rvu *rvu, struct msg_req *req,
 	void *cgxd;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
-		return -ENODEV;
+		return LMAC_AF_ERR_PERM_DENIED;
 
 	rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_idx, &lmac);
 	cgxd = rvu_cgx_pdata(cgx_idx, rvu);
@@ -561,7 +558,7 @@ int rvu_mbox_handler_cgx_fec_stats(struct rvu *rvu,
 	void *cgxd;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
-		return -EPERM;
+		return LMAC_AF_ERR_PERM_DENIED;
 	rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_idx, &lmac);
 
 	cgxd = rvu_cgx_pdata(cgx_idx, rvu);
@@ -888,7 +885,7 @@ int rvu_mbox_handler_cgx_get_phy_fec_stats(struct rvu *rvu, struct msg_req *req,
 	u8 cgx_id, lmac_id;
 
 	if (!is_pf_cgxmapped(rvu, pf))
-		return -EPERM;
+		return LMAC_AF_ERR_PF_NOT_MAPPED;
 
 	rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
 	return cgx_get_phy_fec_stats(rvu_cgx_pdata(cgx_id, rvu), lmac_id);
@@ -1046,7 +1043,7 @@ int rvu_mbox_handler_cgx_mac_addr_reset(struct rvu *rvu, struct msg_req *req,
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
-		return -EPERM;
+		return LMAC_AF_ERR_PERM_DENIED;
 
 	rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
 	return cgx_lmac_addr_reset(cgx_id, lmac_id);
@@ -1060,7 +1057,7 @@ int rvu_mbox_handler_cgx_mac_addr_update(struct rvu *rvu,
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
-		return -EPERM;
+		return LMAC_AF_ERR_PERM_DENIED;
 
 	rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
 	return cgx_lmac_addr_update(cgx_id, lmac_id, req->mac_addr, req->index);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
index 8d48b64485c6..46a41cfff575 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/*  Marvell RPM CN10K driver
+/* Marvell RPM CN10K driver
  *
  * Copyright (C) 2020 Marvell.
  */
@@ -49,6 +49,7 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 	return 0;
 }
 
+#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) +
@@ -82,10 +83,10 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc,
 		dev_err(rvu->dev, "%s LMTLINE iova transulation failed err:%llx\n", __func__, val);
 		return -EIO;
 	}
-	/* PA[51:12] = RVU_AF_SMMU_TLN_FLIT1[60:21]
+	/* PA[51:12] = RVU_AF_SMMU_TLN_FLIT0[57:18]
 	 * PA[11:0] = IOVA[11:0]
 	 */
-	pa = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TLN_FLIT1) >> 21;
+	pa = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TLN_FLIT0) >> 18;
 	pa &= GENMASK_ULL(39, 0);
 	*lmt_addr = (pa << 12) | (iova  & 0xFFF);
 
@@ -131,9 +132,11 @@ int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu,
 				     struct lmtst_tbl_setup_req *req,
 				     struct msg_rsp *rsp)
 {
-	u64 lmt_addr, val;
-	u32 pri_tbl_idx;
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc);
+	u32 pri_tbl_idx, tbl_idx;
+	u64 lmt_addr;
 	int err = 0;
+	u64 val;
 
 	/* Check if PF_FUNC wants to use it's own local memory as LMTLINE
 	 * region, if so, convert that IOVA to physical address and
@@ -170,7 +173,7 @@ int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu,
 			dev_err(rvu->dev,
 				"Failed to read LMT map table: index 0x%x err %d\n",
 				pri_tbl_idx, err);
-			return err;
+			goto error;
 		}
 
 		/* Update the base lmt addr of secondary with primary's base
@@ -181,7 +184,53 @@ int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu,
 			return err;
 	}
 
-	return 0;
+	/* This mailbox can also be used to update word1 of APR_LMT_MAP_ENTRY_S
+	 * like enabling scheduled LMTST, disable LMTLINE prefetch, disable
+	 * early completion for ordered LMTST.
+	 */
+	if (req->sch_ena || req->dis_sched_early_comp || req->dis_line_pref) {
+		tbl_idx = rvu_get_lmtst_tbl_index(rvu, req->hdr.pcifunc);
+		err = lmtst_map_table_ops(rvu, tbl_idx + LMT_MAP_TBL_W1_OFF,
+					  &val, LMT_TBL_OP_READ);
+		if (err) {
+			dev_err(rvu->dev,
+				"Failed to read LMT map table: index 0x%x err %d\n",
+				tbl_idx + LMT_MAP_TBL_W1_OFF, err);
+			goto error;
+		}
+
+		/* Storing lmt map table entry word1 default value as this needs
+		 * to be reverted in FLR. Also making sure this default value
+		 * doesn't get overwritten on multiple calls to this mailbox.
+		 */
+		if (!pfvf->lmt_map_ent_w1)
+			pfvf->lmt_map_ent_w1 = val;
+
+		/* Disable early completion for Ordered LMTSTs. */
+		if (req->dis_sched_early_comp)
+			val |= (req->dis_sched_early_comp <<
+				APR_LMT_MAP_ENT_DIS_SCH_CMP_SHIFT);
+		/* Enable scheduled LMTST */
+		if (req->sch_ena)
+			val |= (req->sch_ena << APR_LMT_MAP_ENT_SCH_ENA_SHIFT) |
+				req->ssow_pf_func;
+		/* Disables LMTLINE prefetch before receiving store data. */
+		if (req->dis_line_pref)
+			val |= (req->dis_line_pref <<
+				APR_LMT_MAP_ENT_DIS_LINE_PREF_SHIFT);
+
+		err = lmtst_map_table_ops(rvu, tbl_idx + LMT_MAP_TBL_W1_OFF,
+					  &val, LMT_TBL_OP_WRITE);
+		if (err) {
+			dev_err(rvu->dev,
+				"Failed to update LMT map table: index 0x%x err %d\n",
+				tbl_idx + LMT_MAP_TBL_W1_OFF, err);
+			goto error;
+		}
+	}
+
+error:
+	return err;
 }
 
 /* Resetting the lmtst map table to original base addresses */
@@ -194,27 +243,45 @@ void rvu_reset_lmt_map_tbl(struct rvu *rvu, u16 pcifunc)
 	if (is_rvu_otx2(rvu))
 		return;
 
-	if (pfvf->lmt_base_addr) {
+	if (pfvf->lmt_base_addr || pfvf->lmt_map_ent_w1) {
 		/* This corresponds to lmt map table index */
 		tbl_idx = rvu_get_lmtst_tbl_index(rvu, pcifunc);
 		/* Reverting back original lmt base addr for respective
 		 * pcifunc.
 		 */
-		err = lmtst_map_table_ops(rvu, tbl_idx, &pfvf->lmt_base_addr,
-					  LMT_TBL_OP_WRITE);
-		if (err)
-			dev_err(rvu->dev,
-				"Failed to update LMT map table: index 0x%x err %d\n",
-				tbl_idx, err);
-		pfvf->lmt_base_addr = 0;
+		if (pfvf->lmt_base_addr) {
+			err = lmtst_map_table_ops(rvu, tbl_idx,
+						  &pfvf->lmt_base_addr,
+						  LMT_TBL_OP_WRITE);
+			if (err)
+				dev_err(rvu->dev,
+					"Failed to update LMT map table: index 0x%x err %d\n",
+					tbl_idx, err);
+			pfvf->lmt_base_addr = 0;
+		}
+		/* Reverting back to orginal word1 val of lmtst map table entry
+		 * which underwent changes.
+		 */
+		if (pfvf->lmt_map_ent_w1) {
+			err = lmtst_map_table_ops(rvu,
+						  tbl_idx + LMT_MAP_TBL_W1_OFF,
+						  &pfvf->lmt_map_ent_w1,
+						  LMT_TBL_OP_WRITE);
+			if (err)
+				dev_err(rvu->dev,
+					"Failed to update LMT map table: index 0x%x err %d\n",
+					tbl_idx + LMT_MAP_TBL_W1_OFF, err);
+			pfvf->lmt_map_ent_w1 = 0;
+		}
 	}
 }
 
 int rvu_set_channels_base(struct rvu *rvu)
 {
+	u16 nr_lbk_chans, nr_sdp_chans, nr_cgx_chans, nr_cpt_chans;
+	u16 sdp_chan_base, cgx_chan_base, cpt_chan_base;
 	struct rvu_hwinfo *hw = rvu->hw;
-	u16 cpt_chan_base;
-	u64 nix_const;
+	u64 nix_const, nix_const1;
 	int blkaddr;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, 0);
@@ -222,6 +289,7 @@ int rvu_set_channels_base(struct rvu *rvu)
 		return blkaddr;
 
 	nix_const = rvu_read64(rvu, blkaddr, NIX_AF_CONST);
+	nix_const1 = rvu_read64(rvu, blkaddr, NIX_AF_CONST1);
 
 	hw->cgx = (nix_const >> 12) & 0xFULL;
 	hw->lmac_per_cgx = (nix_const >> 8) & 0xFULL;
@@ -244,14 +312,24 @@ int rvu_set_channels_base(struct rvu *rvu)
 	 * channels such that all channel numbers are contiguous
 	 * leaving no holes. This way the new CPT channels can be
 	 * accomodated. The order of channel numbers assigned is
-	 * LBK, SDP, CGX and CPT.
+	 * LBK, SDP, CGX and CPT. Also the base channel number
+	 * of a block must be multiple of number of channels
+	 * of the block.
 	 */
-	hw->sdp_chan_base = hw->lbk_chan_base + hw->lbk_links *
-				((nix_const >> 16) & 0xFFULL);
-	hw->cgx_chan_base = hw->sdp_chan_base + hw->sdp_links * SDP_CHANNELS;
+	nr_lbk_chans = (nix_const >> 16) & 0xFFULL;
+	nr_sdp_chans = nix_const1 & 0xFFFULL;
+	nr_cgx_chans = nix_const & 0xFFULL;
+	nr_cpt_chans = (nix_const >> 32) & 0xFFFULL;
+
+	sdp_chan_base = hw->lbk_chan_base + hw->lbk_links * nr_lbk_chans;
+	/* Round up base channel to multiple of number of channels */
+	hw->sdp_chan_base = ALIGN(sdp_chan_base, nr_sdp_chans);
+
+	cgx_chan_base = hw->sdp_chan_base + hw->sdp_links * nr_sdp_chans;
+	hw->cgx_chan_base = ALIGN(cgx_chan_base, nr_cgx_chans);
 
-	cpt_chan_base = hw->cgx_chan_base + hw->cgx_links *
-				(nix_const & 0xFFULL);
+	cpt_chan_base = hw->cgx_chan_base + hw->cgx_links * nr_cgx_chans;
+	hw->cpt_chan_base = ALIGN(cpt_chan_base, nr_cpt_chans);
 
 	/* Out of 4096 channels start CPT from 2048 so
 	 * that MSB for CPT channels is always set
@@ -355,6 +433,7 @@ err_put:
 
 static void __rvu_nix_set_channels(struct rvu *rvu, int blkaddr)
 {
+	u64 nix_const1 = rvu_read64(rvu, blkaddr, NIX_AF_CONST1);
 	u64 nix_const = rvu_read64(rvu, blkaddr, NIX_AF_CONST);
 	u16 cgx_chans, lbk_chans, sdp_chans, cpt_chans;
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -364,7 +443,7 @@ static void __rvu_nix_set_channels(struct rvu *rvu, int blkaddr)
 
 	cgx_chans = nix_const & 0xFFULL;
 	lbk_chans = (nix_const >> 16) & 0xFFULL;
-	sdp_chans = SDP_CHANNELS;
+	sdp_chans = nix_const1 & 0xFFFULL;
 	cpt_chans = (nix_const >> 32) & 0xFFFULL;
 
 	start = hw->cgx_chan_base;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index 89253f7bdadb..1f90a7403392 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -1,5 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/* Copyright (C) 2020 Marvell. */
+/* Marvell RVU Admin Function driver
+ *
+ * Copyright (C) 2020 Marvell.
+ *
+ */
 
 #include <linux/bitfield.h>
 #include <linux/pci.h>
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 9b2dfbf90e51..9338765da048 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2019 Marvell International Ltd.
+ * Copyright (C) 2019 Marvell.
  *
- * 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.
  */
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index 2688186066d9..274d3abe30eb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Devlink
+/* Marvell RVU Admin Function Devlink
  *
  * Copyright (C) 2020 Marvell.
  *
@@ -1364,6 +1364,89 @@ static void rvu_health_reporters_destroy(struct rvu *rvu)
 	rvu_nix_health_reporters_destroy(rvu_dl);
 }
 
+/* Devlink Params APIs */
+static int rvu_af_dl_dwrr_mtu_validate(struct devlink *devlink, u32 id,
+				       union devlink_param_value val,
+				       struct netlink_ext_ack *extack)
+{
+	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+	struct rvu *rvu = rvu_dl->rvu;
+	int dwrr_mtu = val.vu32;
+	struct nix_txsch *txsch;
+	struct nix_hw *nix_hw;
+
+	if (!rvu->hw->cap.nix_common_dwrr_mtu) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Setting DWRR_MTU is not supported on this silicon");
+		return -EOPNOTSUPP;
+	}
+
+	if ((dwrr_mtu > 65536 || !is_power_of_2(dwrr_mtu)) &&
+	    (dwrr_mtu != 9728 && dwrr_mtu != 10240)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Invalid, supported MTUs are 0,2,4,8.16,32,64....4K,8K,32K,64K and 9728, 10240");
+		return -EINVAL;
+	}
+
+	nix_hw = get_nix_hw(rvu->hw, BLKADDR_NIX0);
+	if (!nix_hw)
+		return -ENODEV;
+
+	txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ];
+	if (rvu_rsrc_free_count(&txsch->schq) != txsch->schq.max) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Changing DWRR MTU is not supported when there are active NIXLFs");
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Make sure none of the PF/VF interfaces are initialized and retry");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int rvu_af_dl_dwrr_mtu_set(struct devlink *devlink, u32 id,
+				  struct devlink_param_gset_ctx *ctx)
+{
+	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+	struct rvu *rvu = rvu_dl->rvu;
+	u64 dwrr_mtu;
+
+	dwrr_mtu = convert_bytes_to_dwrr_mtu(ctx->val.vu32);
+	rvu_write64(rvu, BLKADDR_NIX0, NIX_AF_DWRR_RPM_MTU, dwrr_mtu);
+
+	return 0;
+}
+
+static int rvu_af_dl_dwrr_mtu_get(struct devlink *devlink, u32 id,
+				  struct devlink_param_gset_ctx *ctx)
+{
+	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+	struct rvu *rvu = rvu_dl->rvu;
+	u64 dwrr_mtu;
+
+	if (!rvu->hw->cap.nix_common_dwrr_mtu)
+		return -EOPNOTSUPP;
+
+	dwrr_mtu = rvu_read64(rvu, BLKADDR_NIX0, NIX_AF_DWRR_RPM_MTU);
+	ctx->val.vu32 = convert_dwrr_mtu_to_bytes(dwrr_mtu);
+
+	return 0;
+}
+
+enum rvu_af_dl_param_id {
+	RVU_AF_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	RVU_AF_DEVLINK_PARAM_ID_DWRR_MTU,
+};
+
+static const struct devlink_param rvu_af_dl_params[] = {
+	DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_DWRR_MTU,
+			     "dwrr_mtu", DEVLINK_PARAM_TYPE_U32,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     rvu_af_dl_dwrr_mtu_get, rvu_af_dl_dwrr_mtu_set,
+			     rvu_af_dl_dwrr_mtu_validate),
+};
+
+/* Devlink switch mode */
 static int rvu_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
@@ -1420,13 +1503,14 @@ int rvu_register_dl(struct rvu *rvu)
 	struct devlink *dl;
 	int err;
 
-	dl = devlink_alloc(&rvu_devlink_ops, sizeof(struct rvu_devlink));
+	dl = devlink_alloc(&rvu_devlink_ops, sizeof(struct rvu_devlink),
+			   rvu->dev);
 	if (!dl) {
 		dev_warn(rvu->dev, "devlink_alloc failed\n");
 		return -ENOMEM;
 	}
 
-	err = devlink_register(dl, rvu->dev);
+	err = devlink_register(dl);
 	if (err) {
 		dev_err(rvu->dev, "devlink register failed with error %d\n", err);
 		devlink_free(dl);
@@ -1438,7 +1522,30 @@ int rvu_register_dl(struct rvu *rvu)
 	rvu_dl->rvu = rvu;
 	rvu->rvu_dl = rvu_dl;
 
-	return rvu_health_reporters_create(rvu);
+	err = rvu_health_reporters_create(rvu);
+	if (err) {
+		dev_err(rvu->dev,
+			"devlink health reporter creation failed with error %d\n", err);
+		goto err_dl_health;
+	}
+
+	err = devlink_params_register(dl, rvu_af_dl_params,
+				      ARRAY_SIZE(rvu_af_dl_params));
+	if (err) {
+		dev_err(rvu->dev,
+			"devlink params register failed with error %d", err);
+		goto err_dl_health;
+	}
+
+	devlink_params_publish(dl);
+
+	return 0;
+
+err_dl_health:
+	rvu_health_reporters_destroy(rvu);
+	devlink_unregister(dl);
+	devlink_free(dl);
+	return err;
 }
 
 void rvu_unregister_dl(struct rvu *rvu)
@@ -1449,6 +1556,8 @@ void rvu_unregister_dl(struct rvu *rvu)
 	if (!dl)
 		return;
 
+	devlink_params_unregister(dl, rvu_af_dl_params,
+				  ARRAY_SIZE(rvu_af_dl_params));
 	rvu_health_reporters_destroy(rvu);
 	devlink_unregister(dl);
 	devlink_free(dl);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.h
index 471e57dedb20..51efe88dce11 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*  Marvell OcteonTx2 RVU Devlink
+/* Marvell RVU Admin Function Devlink
  *
  * Copyright (C) 2020 Marvell.
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 4bfbbdf38770..9ef4e942e31e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #include <linux/module.h>
@@ -25,7 +22,7 @@ static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc,
 			       int type, bool add);
 static int nix_setup_ipolicers(struct rvu *rvu,
 			       struct nix_hw *nix_hw, int blkaddr);
-static void nix_ipolicer_freemem(struct nix_hw *nix_hw);
+static void nix_ipolicer_freemem(struct rvu *rvu, struct nix_hw *nix_hw);
 static int nix_verify_bandprof(struct nix_cn10k_aq_enq_req *req,
 			       struct nix_hw *nix_hw, u16 pcifunc);
 static int nix_free_all_bandprof(struct rvu *rvu, u16 pcifunc);
@@ -192,6 +189,47 @@ struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr)
 	return NULL;
 }
 
+u32 convert_dwrr_mtu_to_bytes(u8 dwrr_mtu)
+{
+	dwrr_mtu &= 0x1FULL;
+
+	/* MTU used for DWRR calculation is in power of 2 up until 64K bytes.
+	 * Value of 4 is reserved for MTU value of 9728 bytes.
+	 * Value of 5 is reserved for MTU value of 10240 bytes.
+	 */
+	switch (dwrr_mtu) {
+	case 4:
+		return 9728;
+	case 5:
+		return 10240;
+	default:
+		return BIT_ULL(dwrr_mtu);
+	}
+
+	return 0;
+}
+
+u32 convert_bytes_to_dwrr_mtu(u32 bytes)
+{
+	/* MTU used for DWRR calculation is in power of 2 up until 64K bytes.
+	 * Value of 4 is reserved for MTU value of 9728 bytes.
+	 * Value of 5 is reserved for MTU value of 10240 bytes.
+	 */
+	if (bytes > BIT_ULL(16))
+		return 0;
+
+	switch (bytes) {
+	case 9728:
+		return 4;
+	case 10240:
+		return 5;
+	default:
+		return ilog2(bytes);
+	}
+
+	return 0;
+}
+
 static void nix_rx_sync(struct rvu *rvu, int blkaddr)
 {
 	int err;
@@ -249,16 +287,22 @@ static bool is_valid_txschq(struct rvu *rvu, int blkaddr,
 	return true;
 }
 
-static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
+static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf,
+			      struct nix_lf_alloc_rsp *rsp, bool loop)
 {
-	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+	struct rvu_pfvf *parent_pf, *pfvf = rvu_get_pfvf(rvu, pcifunc);
+	u16 req_chan_base, req_chan_end, req_chan_cnt;
+	struct rvu_hwinfo *hw = rvu->hw;
+	struct sdp_node_info *sdp_info;
+	int pkind, pf, vf, lbkid, vfid;
 	struct mac_ops *mac_ops;
-	int pkind, pf, vf, lbkid;
 	u8 cgx_id, lmac_id;
+	bool from_vf;
 	int err;
 
 	pf = rvu_get_pf(pcifunc);
-	if (!is_pf_cgxmapped(rvu, pf) && type != NIX_INTF_TYPE_LBK)
+	if (!is_pf_cgxmapped(rvu, pf) && type != NIX_INTF_TYPE_LBK &&
+	    type != NIX_INTF_TYPE_SDP)
 		return 0;
 
 	switch (type) {
@@ -276,10 +320,13 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
 		pfvf->tx_chan_base = pfvf->rx_chan_base;
 		pfvf->rx_chan_cnt = 1;
 		pfvf->tx_chan_cnt = 1;
+		rsp->tx_link = cgx_id * hw->lmac_per_cgx + lmac_id;
+
 		cgx_set_pkind(rvu_cgx_pdata(cgx_id, rvu), lmac_id, pkind);
 		rvu_npc_set_pkind(rvu, pkind, pfvf);
 
 		mac_ops = get_mac_ops(rvu_cgx_pdata(cgx_id, rvu));
+
 		/* By default we enable pause frames */
 		if ((pcifunc & RVU_PFVF_FUNC_MASK) == 0)
 			mac_ops->mac_enadis_pause_frm(rvu_cgx_pdata(cgx_id,
@@ -299,6 +346,25 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
 		if (rvu->hw->lbk_links > 1)
 			lbkid = vf & 0x1 ? 0 : 1;
 
+		/* By default NIX0 is configured to send packet on lbk link 1
+		 * (which corresponds to LBK1), same packet will receive on
+		 * NIX1 over lbk link 0. If NIX1 sends packet on lbk link 0
+		 * (which corresponds to LBK2) packet will receive on NIX0 lbk
+		 * link 1.
+		 * But if lbk links for NIX0 and NIX1 are negated, i.e NIX0
+		 * transmits and receives on lbk link 0, whick corresponds
+		 * to LBK1 block, back to back connectivity between NIX and
+		 * LBK can be achieved (which is similar to 96xx)
+		 *
+		 *			RX		TX
+		 * NIX0 lbk link	1 (LBK2)	1 (LBK1)
+		 * NIX0 lbk link	0 (LBK0)	0 (LBK0)
+		 * NIX1 lbk link	0 (LBK1)	0 (LBK2)
+		 * NIX1 lbk link	1 (LBK3)	1 (LBK3)
+		 */
+		if (loop)
+			lbkid = !lbkid;
+
 		/* Note that AF's VFs work in pairs and talk over consecutive
 		 * loopback channels.Therefore if odd number of AF VFs are
 		 * enabled then the last VF remains with no pair.
@@ -309,10 +375,51 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
 					rvu_nix_chan_lbk(rvu, lbkid, vf + 1);
 		pfvf->rx_chan_cnt = 1;
 		pfvf->tx_chan_cnt = 1;
+		rsp->tx_link = hw->cgx_links + lbkid;
+		pfvf->lbkid = lbkid;
 		rvu_npc_set_pkind(rvu, NPC_RX_LBK_PKIND, pfvf);
 		rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
 					      pfvf->rx_chan_base,
 					      pfvf->rx_chan_cnt);
+
+		break;
+	case NIX_INTF_TYPE_SDP:
+		from_vf = !!(pcifunc & RVU_PFVF_FUNC_MASK);
+		parent_pf = &rvu->pf[rvu_get_pf(pcifunc)];
+		sdp_info = parent_pf->sdp_info;
+		if (!sdp_info) {
+			dev_err(rvu->dev, "Invalid sdp_info pointer\n");
+			return -EINVAL;
+		}
+		if (from_vf) {
+			req_chan_base = rvu_nix_chan_sdp(rvu, 0) + sdp_info->pf_srn +
+				sdp_info->num_pf_rings;
+			vf = (pcifunc & RVU_PFVF_FUNC_MASK) - 1;
+			for (vfid = 0; vfid < vf; vfid++)
+				req_chan_base += sdp_info->vf_rings[vfid];
+			req_chan_cnt = sdp_info->vf_rings[vf];
+			req_chan_end = req_chan_base + req_chan_cnt - 1;
+			if (req_chan_base < rvu_nix_chan_sdp(rvu, 0) ||
+			    req_chan_end > rvu_nix_chan_sdp(rvu, 255)) {
+				dev_err(rvu->dev,
+					"PF_Func 0x%x: Invalid channel base and count\n",
+					pcifunc);
+				return -EINVAL;
+			}
+		} else {
+			req_chan_base = rvu_nix_chan_sdp(rvu, 0) + sdp_info->pf_srn;
+			req_chan_cnt = sdp_info->num_pf_rings;
+		}
+
+		pfvf->rx_chan_base = req_chan_base;
+		pfvf->rx_chan_cnt = req_chan_cnt;
+		pfvf->tx_chan_base = pfvf->rx_chan_base;
+		pfvf->tx_chan_cnt = pfvf->rx_chan_cnt;
+
+		rsp->tx_link = hw->cgx_links + hw->lbk_links;
+		rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
+					      pfvf->rx_chan_base,
+					      pfvf->rx_chan_cnt);
 		break;
 	}
 
@@ -393,9 +500,9 @@ int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu,
 static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req,
 			    int type, int chan_id)
 {
-	int bpid, blkaddr, lmac_chan_cnt;
+	int bpid, blkaddr, lmac_chan_cnt, sdp_chan_cnt;
+	u16 cgx_bpid_cnt, lbk_bpid_cnt, sdp_bpid_cnt;
 	struct rvu_hwinfo *hw = rvu->hw;
-	u16 cgx_bpid_cnt, lbk_bpid_cnt;
 	struct rvu_pfvf *pfvf;
 	u8 cgx_id, lmac_id;
 	u64 cfg;
@@ -404,8 +511,12 @@ static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req,
 	cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST);
 	lmac_chan_cnt = cfg & 0xFF;
 
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST1);
+	sdp_chan_cnt = cfg & 0xFFF;
+
 	cgx_bpid_cnt = hw->cgx_links * lmac_chan_cnt;
 	lbk_bpid_cnt = hw->lbk_links * ((cfg >> 16) & 0xFF);
+	sdp_bpid_cnt = hw->sdp_links * sdp_chan_cnt;
 
 	pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc);
 
@@ -443,6 +554,17 @@ static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req,
 		if (bpid > (cgx_bpid_cnt + lbk_bpid_cnt))
 			return -EINVAL;
 		break;
+	case NIX_INTF_TYPE_SDP:
+		if ((req->chan_base + req->chan_cnt) > 255)
+			return -EINVAL;
+
+		bpid = sdp_bpid_cnt + req->chan_base;
+		if (req->bpid_per_chan)
+			bpid += chan_id;
+
+		if (bpid > (cgx_bpid_cnt + lbk_bpid_cnt + sdp_bpid_cnt))
+			return -EINVAL;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -462,9 +584,12 @@ int rvu_mbox_handler_nix_bp_enable(struct rvu *rvu,
 
 	pf = rvu_get_pf(pcifunc);
 	type = is_afvf(pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
+	if (is_sdp_pfvf(pcifunc))
+		type = NIX_INTF_TYPE_SDP;
 
-	/* Enable backpressure only for CGX mapped PFs and LBK interface */
-	if (!is_pf_cgxmapped(rvu, pf) && type != NIX_INTF_TYPE_LBK)
+	/* Enable backpressure only for CGX mapped PFs and LBK/SDP interface */
+	if (!is_pf_cgxmapped(rvu, pf) && type != NIX_INTF_TYPE_LBK &&
+	    type != NIX_INTF_TYPE_SDP)
 		return 0;
 
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
@@ -481,8 +606,9 @@ int rvu_mbox_handler_nix_bp_enable(struct rvu *rvu,
 		}
 
 		cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan));
+		cfg &= ~GENMASK_ULL(8, 0);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan),
-			    cfg | (bpid & 0xFF) | BIT_ULL(16));
+			    cfg | (bpid & GENMASK_ULL(8, 0)) | BIT_ULL(16));
 		chan_id++;
 		bpid = rvu_nix_get_bpid(rvu, req, type, chan_id);
 	}
@@ -630,9 +756,10 @@ static void nix_ctx_free(struct rvu *rvu, struct rvu_pfvf *pfvf)
 static int nixlf_rss_ctx_init(struct rvu *rvu, int blkaddr,
 			      struct rvu_pfvf *pfvf, int nixlf,
 			      int rss_sz, int rss_grps, int hwctx_size,
-			      u64 way_mask)
+			      u64 way_mask, bool tag_lsb_as_adder)
 {
 	int err, grp, num_indices;
+	u64 val;
 
 	/* RSS is not requested for this NIXLF */
 	if (!rss_sz)
@@ -648,10 +775,13 @@ static int nixlf_rss_ctx_init(struct rvu *rvu, int blkaddr,
 		    (u64)pfvf->rss_ctx->iova);
 
 	/* Config full RSS table size, enable RSS and caching */
-	rvu_write64(rvu, blkaddr, NIX_AF_LFX_RSS_CFG(nixlf),
-		    BIT_ULL(36) | BIT_ULL(4) |
-		    ilog2(num_indices / MAX_RSS_INDIR_TBL_SIZE) |
-		    way_mask << 20);
+	val = BIT_ULL(36) | BIT_ULL(4) | way_mask << 20 |
+			ilog2(num_indices / MAX_RSS_INDIR_TBL_SIZE);
+
+	if (tag_lsb_as_adder)
+		val |= BIT_ULL(5);
+
+	rvu_write64(rvu, blkaddr, NIX_AF_LFX_RSS_CFG(nixlf), val);
 	/* Config RSS group offset and sizes */
 	for (grp = 0; grp < rss_grps; grp++)
 		rvu_write64(rvu, blkaddr, NIX_AF_LFX_RSS_GRPX(nixlf, grp),
@@ -943,7 +1073,7 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
 
 	nix_hw =  get_nix_hw(rvu->hw, blkaddr);
 	if (!nix_hw)
-		return -EINVAL;
+		return NIX_AF_ERR_INVALID_NIXBLK;
 
 	return rvu_nix_blk_aq_enq_inst(rvu, nix_hw, req, rsp);
 }
@@ -1200,7 +1330,8 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 	/* Initialize receive side scaling (RSS) */
 	hwctx_size = 1UL << ((ctx_cfg >> 12) & 0xF);
 	err = nixlf_rss_ctx_init(rvu, blkaddr, pfvf, nixlf, req->rss_sz,
-				 req->rss_grps, hwctx_size, req->way_mask);
+				 req->rss_grps, hwctx_size, req->way_mask,
+				 !!(req->flags & NIX_LF_RSS_TAG_LSB_AS_ADDER));
 	if (err)
 		goto free_mem;
 
@@ -1258,7 +1389,11 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 	rvu_write64(rvu, blkaddr, NIX_AF_LFX_TX_PARSE_CFG(nixlf), cfg);
 
 	intf = is_afvf(pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
-	err = nix_interface_init(rvu, pcifunc, intf, nixlf);
+	if (is_sdp_pfvf(pcifunc))
+		intf = NIX_INTF_TYPE_SDP;
+
+	err = nix_interface_init(rvu, pcifunc, intf, nixlf, rsp,
+				 !!(req->flags & NIX_LF_LBK_BLK_SEL));
 	if (err)
 		goto free_mem;
 
@@ -1364,7 +1499,7 @@ int rvu_mbox_handler_nix_mark_format_cfg(struct rvu *rvu,
 
 	nix_hw = get_nix_hw(rvu->hw, blkaddr);
 	if (!nix_hw)
-		return -EINVAL;
+		return NIX_AF_ERR_INVALID_NIXBLK;
 
 	cfg = (((u32)req->offset & 0x7) << 16) |
 	      (((u32)req->y_mask & 0xF) << 12) |
@@ -1382,12 +1517,104 @@ int rvu_mbox_handler_nix_mark_format_cfg(struct rvu *rvu,
 	return 0;
 }
 
+/* Handle shaper update specially for few revisions */
+static bool
+handle_txschq_shaper_update(struct rvu *rvu, int blkaddr, int nixlf,
+			    int lvl, u64 reg, u64 regval)
+{
+	u64 regbase, oldval, sw_xoff = 0;
+	u64 dbgval, md_debug0 = 0;
+	unsigned long poll_tmo;
+	bool rate_reg = 0;
+	u32 schq;
+
+	regbase = reg & 0xFFFF;
+	schq = TXSCHQ_IDX(reg, TXSCHQ_IDX_SHIFT);
+
+	/* Check for rate register */
+	switch (lvl) {
+	case NIX_TXSCH_LVL_TL1:
+		md_debug0 = NIX_AF_TL1X_MD_DEBUG0(schq);
+		sw_xoff = NIX_AF_TL1X_SW_XOFF(schq);
+
+		rate_reg = !!(regbase == NIX_AF_TL1X_CIR(0));
+		break;
+	case NIX_TXSCH_LVL_TL2:
+		md_debug0 = NIX_AF_TL2X_MD_DEBUG0(schq);
+		sw_xoff = NIX_AF_TL2X_SW_XOFF(schq);
+
+		rate_reg = (regbase == NIX_AF_TL2X_CIR(0) ||
+			    regbase == NIX_AF_TL2X_PIR(0));
+		break;
+	case NIX_TXSCH_LVL_TL3:
+		md_debug0 = NIX_AF_TL3X_MD_DEBUG0(schq);
+		sw_xoff = NIX_AF_TL3X_SW_XOFF(schq);
+
+		rate_reg = (regbase == NIX_AF_TL3X_CIR(0) ||
+			    regbase == NIX_AF_TL3X_PIR(0));
+		break;
+	case NIX_TXSCH_LVL_TL4:
+		md_debug0 = NIX_AF_TL4X_MD_DEBUG0(schq);
+		sw_xoff = NIX_AF_TL4X_SW_XOFF(schq);
+
+		rate_reg = (regbase == NIX_AF_TL4X_CIR(0) ||
+			    regbase == NIX_AF_TL4X_PIR(0));
+		break;
+	case NIX_TXSCH_LVL_MDQ:
+		sw_xoff = NIX_AF_MDQX_SW_XOFF(schq);
+		rate_reg = (regbase == NIX_AF_MDQX_CIR(0) ||
+			    regbase == NIX_AF_MDQX_PIR(0));
+		break;
+	}
+
+	if (!rate_reg)
+		return false;
+
+	/* Nothing special to do when state is not toggled */
+	oldval = rvu_read64(rvu, blkaddr, reg);
+	if ((oldval & 0x1) == (regval & 0x1)) {
+		rvu_write64(rvu, blkaddr, reg, regval);
+		return true;
+	}
+
+	/* PIR/CIR disable */
+	if (!(regval & 0x1)) {
+		rvu_write64(rvu, blkaddr, sw_xoff, 1);
+		rvu_write64(rvu, blkaddr, reg, 0);
+		udelay(4);
+		rvu_write64(rvu, blkaddr, sw_xoff, 0);
+		return true;
+	}
+
+	/* PIR/CIR enable */
+	rvu_write64(rvu, blkaddr, sw_xoff, 1);
+	if (md_debug0) {
+		poll_tmo = jiffies + usecs_to_jiffies(10000);
+		/* Wait until VLD(bit32) == 1 or C_CON(bit48) == 0 */
+		do {
+			if (time_after(jiffies, poll_tmo)) {
+				dev_err(rvu->dev,
+					"NIXLF%d: TLX%u(lvl %u) CIR/PIR enable failed\n",
+					nixlf, schq, lvl);
+				goto exit;
+			}
+			usleep_range(1, 5);
+			dbgval = rvu_read64(rvu, blkaddr, md_debug0);
+		} while (!(dbgval & BIT_ULL(32)) && (dbgval & BIT_ULL(48)));
+	}
+	rvu_write64(rvu, blkaddr, reg, regval);
+exit:
+	rvu_write64(rvu, blkaddr, sw_xoff, 0);
+	return true;
+}
+
 /* Disable shaping of pkts by a scheduler queue
  * at a given scheduler level.
  */
 static void nix_reset_tx_shaping(struct rvu *rvu, int blkaddr,
-				 int lvl, int schq)
+				 int nixlf, int lvl, int schq)
 {
+	struct rvu_hwinfo *hw = rvu->hw;
 	u64  cir_reg = 0, pir_reg = 0;
 	u64  cfg;
 
@@ -1408,6 +1635,21 @@ static void nix_reset_tx_shaping(struct rvu *rvu, int blkaddr,
 		cir_reg = NIX_AF_TL4X_CIR(schq);
 		pir_reg = NIX_AF_TL4X_PIR(schq);
 		break;
+	case NIX_TXSCH_LVL_MDQ:
+		cir_reg = NIX_AF_MDQX_CIR(schq);
+		pir_reg = NIX_AF_MDQX_PIR(schq);
+		break;
+	}
+
+	/* Shaper state toggle needs wait/poll */
+	if (hw->cap.nix_shaper_toggle_wait) {
+		if (cir_reg)
+			handle_txschq_shaper_update(rvu, blkaddr, nixlf,
+						    lvl, cir_reg, 0);
+		if (pir_reg)
+			handle_txschq_shaper_update(rvu, blkaddr, nixlf,
+						    lvl, pir_reg, 0);
+		return;
 	}
 
 	if (!cir_reg)
@@ -1425,6 +1667,7 @@ static void nix_reset_tx_linkcfg(struct rvu *rvu, int blkaddr,
 				 int lvl, int schq)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
+	int link_level;
 	int link;
 
 	if (lvl >= hw->cap.nix_tx_aggr_lvl)
@@ -1434,7 +1677,9 @@ static void nix_reset_tx_linkcfg(struct rvu *rvu, int blkaddr,
 	if (lvl == NIX_TXSCH_LVL_TL4)
 		rvu_write64(rvu, blkaddr, NIX_AF_TL4X_SDP_LINK_CFG(schq), 0x00);
 
-	if (lvl != NIX_TXSCH_LVL_TL2)
+	link_level = rvu_read64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL) & 0x01 ?
+			NIX_TXSCH_LVL_TL3 : NIX_TXSCH_LVL_TL2;
+	if (lvl != link_level)
 		return;
 
 	/* Reset TL2's CGX or LBK link config */
@@ -1443,6 +1688,40 @@ static void nix_reset_tx_linkcfg(struct rvu *rvu, int blkaddr,
 			    NIX_AF_TL3_TL2X_LINKX_CFG(schq, link), 0x00);
 }
 
+static void nix_clear_tx_xoff(struct rvu *rvu, int blkaddr,
+			      int lvl, int schq)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	u64 reg;
+
+	/* Skip this if shaping is not supported */
+	if (!hw->cap.nix_shaping)
+		return;
+
+	/* Clear level specific SW_XOFF */
+	switch (lvl) {
+	case NIX_TXSCH_LVL_TL1:
+		reg = NIX_AF_TL1X_SW_XOFF(schq);
+		break;
+	case NIX_TXSCH_LVL_TL2:
+		reg = NIX_AF_TL2X_SW_XOFF(schq);
+		break;
+	case NIX_TXSCH_LVL_TL3:
+		reg = NIX_AF_TL3X_SW_XOFF(schq);
+		break;
+	case NIX_TXSCH_LVL_TL4:
+		reg = NIX_AF_TL4X_SW_XOFF(schq);
+		break;
+	case NIX_TXSCH_LVL_MDQ:
+		reg = NIX_AF_MDQX_SW_XOFF(schq);
+		break;
+	default:
+		return;
+	}
+
+	rvu_write64(rvu, blkaddr, reg, 0x0);
+}
+
 static int nix_get_tx_link(struct rvu *rvu, u16 pcifunc)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -1620,19 +1899,18 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 	int link, blkaddr, rc = 0;
 	int lvl, idx, start, end;
 	struct nix_txsch *txsch;
-	struct rvu_pfvf *pfvf;
 	struct nix_hw *nix_hw;
 	u32 *pfvf_map;
+	int nixlf;
 	u16 schq;
 
-	pfvf = rvu_get_pfvf(rvu, pcifunc);
-	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
-	if (!pfvf->nixlf || blkaddr < 0)
-		return NIX_AF_ERR_AF_LF_INVALID;
+	rc = nix_get_nixlf(rvu, pcifunc, &nixlf, &blkaddr);
+	if (rc)
+		return rc;
 
 	nix_hw = get_nix_hw(rvu->hw, blkaddr);
 	if (!nix_hw)
-		return -EINVAL;
+		return NIX_AF_ERR_INVALID_NIXBLK;
 
 	mutex_lock(&rvu->rsrc_lock);
 
@@ -1677,7 +1955,7 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 			    NIX_TXSCHQ_CFG_DONE))
 				pfvf_map[schq] = TXSCH_MAP(pcifunc, 0);
 			nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq);
-			nix_reset_tx_shaping(rvu, blkaddr, lvl, schq);
+			nix_reset_tx_shaping(rvu, blkaddr, nixlf, lvl, schq);
 		}
 
 		for (idx = 0; idx < req->schq[lvl]; idx++) {
@@ -1686,7 +1964,7 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 			    NIX_TXSCHQ_CFG_DONE))
 				pfvf_map[schq] = TXSCH_MAP(pcifunc, 0);
 			nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq);
-			nix_reset_tx_shaping(rvu, blkaddr, lvl, schq);
+			nix_reset_tx_shaping(rvu, blkaddr, nixlf, lvl, schq);
 		}
 	}
 
@@ -1703,8 +1981,8 @@ exit:
 	return rc;
 }
 
-static void nix_smq_flush(struct rvu *rvu, int blkaddr,
-			  int smq, u16 pcifunc, int nixlf)
+static int nix_smq_flush(struct rvu *rvu, int blkaddr,
+			 int smq, u16 pcifunc, int nixlf)
 {
 	int pf = rvu_get_pf(pcifunc);
 	u8 cgx_id = 0, lmac_id = 0;
@@ -1739,6 +2017,7 @@ static void nix_smq_flush(struct rvu *rvu, int blkaddr,
 	/* restore cgx tx state */
 	if (restore_tx_en)
 		cgx_lmac_tx_enable(rvu_cgx_pdata(cgx_id, rvu), lmac_id, false);
+	return err;
 }
 
 static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
@@ -1747,6 +2026,7 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 	struct rvu_hwinfo *hw = rvu->hw;
 	struct nix_txsch *txsch;
 	struct nix_hw *nix_hw;
+	u16 map_func;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
 	if (blkaddr < 0)
@@ -1754,25 +2034,42 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 
 	nix_hw = get_nix_hw(rvu->hw, blkaddr);
 	if (!nix_hw)
-		return -EINVAL;
+		return NIX_AF_ERR_INVALID_NIXBLK;
 
 	nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0);
 	if (nixlf < 0)
 		return NIX_AF_ERR_AF_LF_INVALID;
 
-	/* Disable TL2/3 queue links before SMQ flush*/
+	/* Disable TL2/3 queue links and all XOFF's before SMQ flush*/
 	mutex_lock(&rvu->rsrc_lock);
-	for (lvl = NIX_TXSCH_LVL_TL4; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
-		if (lvl != NIX_TXSCH_LVL_TL2 && lvl != NIX_TXSCH_LVL_TL4)
+	for (lvl = NIX_TXSCH_LVL_MDQ; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
+		txsch = &nix_hw->txsch[lvl];
+
+		if (lvl >= hw->cap.nix_tx_aggr_lvl)
 			continue;
 
-		txsch = &nix_hw->txsch[lvl];
 		for (schq = 0; schq < txsch->schq.max; schq++) {
 			if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
 				continue;
 			nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq);
+			nix_clear_tx_xoff(rvu, blkaddr, lvl, schq);
 		}
 	}
+	nix_clear_tx_xoff(rvu, blkaddr, NIX_TXSCH_LVL_TL1,
+			  nix_get_tx_link(rvu, pcifunc));
+
+	/* On PF cleanup, clear cfg done flag as
+	 * PF would have changed default config.
+	 */
+	if (!(pcifunc & RVU_PFVF_FUNC_MASK)) {
+		txsch = &nix_hw->txsch[NIX_TXSCH_LVL_TL1];
+		schq = nix_get_tx_link(rvu, pcifunc);
+		/* Do not clear pcifunc in txsch->pfvf_map[schq] because
+		 * VF might be using this TL1 queue
+		 */
+		map_func = TXSCH_MAP_FUNC(txsch->pfvf_map[schq]);
+		txsch->pfvf_map[schq] = TXSCH_SET_FLAG(map_func, 0x0);
+	}
 
 	/* Flush SMQs */
 	txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ];
@@ -1818,6 +2115,7 @@ static int nix_txschq_free_one(struct rvu *rvu,
 	struct nix_txsch *txsch;
 	struct nix_hw *nix_hw;
 	u32 *pfvf_map;
+	int rc;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
 	if (blkaddr < 0)
@@ -1825,7 +2123,7 @@ static int nix_txschq_free_one(struct rvu *rvu,
 
 	nix_hw = get_nix_hw(rvu->hw, blkaddr);
 	if (!nix_hw)
-		return -EINVAL;
+		return NIX_AF_ERR_INVALID_NIXBLK;
 
 	nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0);
 	if (nixlf < 0)
@@ -1842,15 +2140,24 @@ static int nix_txschq_free_one(struct rvu *rvu,
 	mutex_lock(&rvu->rsrc_lock);
 
 	if (TXSCH_MAP_FUNC(pfvf_map[schq]) != pcifunc) {
-		mutex_unlock(&rvu->rsrc_lock);
+		rc = NIX_AF_ERR_TLX_INVALID;
 		goto err;
 	}
 
+	/* Clear SW_XOFF of this resource only.
+	 * For SMQ level, all path XOFF's
+	 * need to be made clear by user
+	 */
+	nix_clear_tx_xoff(rvu, blkaddr, lvl, schq);
+
 	/* Flush if it is a SMQ. Onus of disabling
 	 * TL2/3 queue links before SMQ flush is on user
 	 */
-	if (lvl == NIX_TXSCH_LVL_SMQ)
-		nix_smq_flush(rvu, blkaddr, schq, pcifunc, nixlf);
+	if (lvl == NIX_TXSCH_LVL_SMQ &&
+	    nix_smq_flush(rvu, blkaddr, schq, pcifunc, nixlf)) {
+		rc = NIX_AF_SMQ_FLUSH_FAILED;
+		goto err;
+	}
 
 	/* Free the resource */
 	rvu_free_rsrc(&txsch->schq, schq);
@@ -1858,7 +2165,8 @@ static int nix_txschq_free_one(struct rvu *rvu,
 	mutex_unlock(&rvu->rsrc_lock);
 	return 0;
 err:
-	return NIX_AF_ERR_TLX_INVALID;
+	mutex_unlock(&rvu->rsrc_lock);
+	return rc;
 }
 
 int rvu_mbox_handler_nix_txsch_free(struct rvu *rvu,
@@ -1941,6 +2249,11 @@ static bool is_txschq_shaping_valid(struct rvu_hwinfo *hw, int lvl, u64 reg)
 		    regbase == NIX_AF_TL4X_PIR(0))
 			return false;
 		break;
+	case NIX_TXSCH_LVL_MDQ:
+		if (regbase == NIX_AF_MDQX_CIR(0) ||
+		    regbase == NIX_AF_MDQX_PIR(0))
+			return false;
+		break;
 	}
 	return true;
 }
@@ -1958,12 +2271,48 @@ static void nix_tl1_default_cfg(struct rvu *rvu, struct nix_hw *nix_hw,
 		return;
 	rvu_write64(rvu, blkaddr, NIX_AF_TL1X_TOPOLOGY(schq),
 		    (TXSCH_TL1_DFLT_RR_PRIO << 1));
-	rvu_write64(rvu, blkaddr, NIX_AF_TL1X_SCHEDULE(schq),
-		    TXSCH_TL1_DFLT_RR_QTM);
+
+	/* On OcteonTx2 the config was in bytes and newer silcons
+	 * it's changed to weight.
+	 */
+	if (!rvu->hw->cap.nix_common_dwrr_mtu)
+		rvu_write64(rvu, blkaddr, NIX_AF_TL1X_SCHEDULE(schq),
+			    TXSCH_TL1_DFLT_RR_QTM);
+	else
+		rvu_write64(rvu, blkaddr, NIX_AF_TL1X_SCHEDULE(schq),
+			    CN10K_MAX_DWRR_WEIGHT);
+
 	rvu_write64(rvu, blkaddr, NIX_AF_TL1X_CIR(schq), 0x00);
 	pfvf_map[schq] = TXSCH_SET_FLAG(pfvf_map[schq], NIX_TXSCHQ_CFG_DONE);
 }
 
+/* Register offset - [15:0]
+ * Scheduler Queue number - [25:16]
+ */
+#define NIX_TX_SCHQ_MASK	GENMASK_ULL(25, 0)
+
+static int nix_txschq_cfg_read(struct rvu *rvu, struct nix_hw *nix_hw,
+			       int blkaddr, struct nix_txschq_config *req,
+			       struct nix_txschq_config *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	int idx, schq;
+	u64 reg;
+
+	for (idx = 0; idx < req->num_regs; idx++) {
+		reg = req->reg[idx];
+		reg &= NIX_TX_SCHQ_MASK;
+		schq = TXSCHQ_IDX(reg, TXSCHQ_IDX_SHIFT);
+		if (!rvu_check_valid_reg(TXSCHQ_HWREGMAP, req->lvl, reg) ||
+		    !is_valid_txschq(rvu, blkaddr, req->lvl, pcifunc, schq))
+			return NIX_AF_INVAL_TXSCHQ_CFG;
+		rsp->regval[idx] = rvu_read64(rvu, blkaddr, reg);
+	}
+	rsp->lvl = req->lvl;
+	rsp->num_regs = req->num_regs;
+	return 0;
+}
+
 static void rvu_nix_tx_tl2_cfg(struct rvu *rvu, int blkaddr,
 			       u16 pcifunc, struct nix_txsch *txsch)
 {
@@ -1995,11 +2344,11 @@ static void rvu_nix_tx_tl2_cfg(struct rvu *rvu, int blkaddr,
 
 int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 				    struct nix_txschq_config *req,
-				    struct msg_rsp *rsp)
+				    struct nix_txschq_config *rsp)
 {
+	u64 reg, val, regval, schq_regbase, val_mask;
 	struct rvu_hwinfo *hw = rvu->hw;
 	u16 pcifunc = req->hdr.pcifunc;
-	u64 reg, regval, schq_regbase;
 	struct nix_txsch *txsch;
 	struct nix_hw *nix_hw;
 	int blkaddr, idx, err;
@@ -2016,7 +2365,10 @@ int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 
 	nix_hw = get_nix_hw(rvu->hw, blkaddr);
 	if (!nix_hw)
-		return -EINVAL;
+		return NIX_AF_ERR_INVALID_NIXBLK;
+
+	if (req->read)
+		return nix_txschq_cfg_read(rvu, nix_hw, blkaddr, req, rsp);
 
 	txsch = &nix_hw->txsch[req->lvl];
 	pfvf_map = txsch->pfvf_map;
@@ -2032,8 +2384,10 @@ int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 
 	for (idx = 0; idx < req->num_regs; idx++) {
 		reg = req->reg[idx];
+		reg &= NIX_TX_SCHQ_MASK;
 		regval = req->regval[idx];
 		schq_regbase = reg & 0xFFFF;
+		val_mask = req->regval_mask[idx];
 
 		if (!is_txschq_hierarchy_valid(rvu, pcifunc, blkaddr,
 					       txsch->lvl, reg, regval))
@@ -2043,6 +2397,15 @@ int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 		if (!is_txschq_shaping_valid(hw, req->lvl, reg))
 			continue;
 
+		val = rvu_read64(rvu, blkaddr, reg);
+		regval = (val & val_mask) | (regval & ~val_mask);
+
+		/* Handle shaping state toggle specially */
+		if (hw->cap.nix_shaper_toggle_wait &&
+		    handle_txschq_shaper_update(rvu, blkaddr, nixlf,
+						req->lvl, reg, regval))
+			continue;
+
 		/* Replace PF/VF visible NIXLF slot with HW NIXLF id */
 		if (schq_regbase == NIX_AF_SMQX_CFG(0)) {
 			nixlf = rvu_get_lf(rvu, &hw->block[blkaddr],
@@ -2083,7 +2446,6 @@ int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 
 	rvu_nix_tx_tl2_cfg(rvu, blkaddr, pcifunc,
 			   &nix_hw->txsch[NIX_TXSCH_LVL_TL2]);
-
 	return 0;
 }
 
@@ -2114,8 +2476,12 @@ static int nix_tx_vtag_free(struct rvu *rvu, int blkaddr,
 			    u16 pcifunc, int index)
 {
 	struct nix_hw *nix_hw = get_nix_hw(rvu->hw, blkaddr);
-	struct nix_txvlan *vlan = &nix_hw->txvlan;
+	struct nix_txvlan *vlan;
+
+	if (!nix_hw)
+		return NIX_AF_ERR_INVALID_NIXBLK;
 
+	vlan = &nix_hw->txvlan;
 	if (vlan->entry2pfvf_map[index] != pcifunc)
 		return NIX_AF_ERR_PARAM;
 
@@ -2156,10 +2522,15 @@ static int nix_tx_vtag_alloc(struct rvu *rvu, int blkaddr,
 			     u64 vtag, u8 size)
 {
 	struct nix_hw *nix_hw = get_nix_hw(rvu->hw, blkaddr);
-	struct nix_txvlan *vlan = &nix_hw->txvlan;
+	struct nix_txvlan *vlan;
 	u64 regval;
 	int index;
 
+	if (!nix_hw)
+		return NIX_AF_ERR_INVALID_NIXBLK;
+
+	vlan = &nix_hw->txvlan;
+
 	mutex_lock(&vlan->rsrc_lock);
 
 	index = rvu_alloc_rsrc(&vlan->rsrc);
@@ -2184,12 +2555,16 @@ static int nix_tx_vtag_decfg(struct rvu *rvu, int blkaddr,
 			     struct nix_vtag_config *req)
 {
 	struct nix_hw *nix_hw = get_nix_hw(rvu->hw, blkaddr);
-	struct nix_txvlan *vlan = &nix_hw->txvlan;
 	u16 pcifunc = req->hdr.pcifunc;
 	int idx0 = req->tx.vtag0_idx;
 	int idx1 = req->tx.vtag1_idx;
+	struct nix_txvlan *vlan;
 	int err = 0;
 
+	if (!nix_hw)
+		return NIX_AF_ERR_INVALID_NIXBLK;
+
+	vlan = &nix_hw->txvlan;
 	if (req->tx.free_vtag0 && req->tx.free_vtag1)
 		if (vlan->entry2pfvf_map[idx0] != pcifunc ||
 		    vlan->entry2pfvf_map[idx1] != pcifunc)
@@ -2216,9 +2591,13 @@ static int nix_tx_vtag_cfg(struct rvu *rvu, int blkaddr,
 			   struct nix_vtag_config_rsp *rsp)
 {
 	struct nix_hw *nix_hw = get_nix_hw(rvu->hw, blkaddr);
-	struct nix_txvlan *vlan = &nix_hw->txvlan;
+	struct nix_txvlan *vlan;
 	u16 pcifunc = req->hdr.pcifunc;
 
+	if (!nix_hw)
+		return NIX_AF_ERR_INVALID_NIXBLK;
+
+	vlan = &nix_hw->txvlan;
 	if (req->tx.cfg_vtag0) {
 		rsp->vtag0_idx =
 			nix_tx_vtag_alloc(rvu, blkaddr,
@@ -2456,14 +2835,19 @@ static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc,
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	struct rvu_hwinfo *hw = rvu->hw;
 	struct nix_mce_list *mce_list;
+	int pf;
 
-	/* skip multicast pkt replication for AF's VFs */
-	if (is_afvf(pcifunc))
+	/* skip multicast pkt replication for AF's VFs & SDP links */
+	if (is_afvf(pcifunc) || is_sdp_pfvf(pcifunc))
 		return 0;
 
 	if (!hw->cap.nix_rx_multicast)
 		return 0;
 
+	pf = rvu_get_pf(pcifunc);
+	if (!is_pf_cgxmapped(rvu, pf))
+		return 0;
+
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
 	if (blkaddr < 0)
 		return -EINVAL;
@@ -2667,6 +3051,15 @@ static int nix_setup_txschq(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 		for (schq = 0; schq < txsch->schq.max; schq++)
 			txsch->pfvf_map[schq] = TXSCH_MAP(0, NIX_TXSCHQ_FREE);
 	}
+
+	/* Setup a default value of 8192 as DWRR MTU */
+	if (rvu->hw->cap.nix_common_dwrr_mtu) {
+		rvu_write64(rvu, blkaddr, NIX_AF_DWRR_RPM_MTU,
+			    convert_bytes_to_dwrr_mtu(8192));
+		rvu_write64(rvu, blkaddr, NIX_AF_DWRR_SDP_MTU,
+			    convert_bytes_to_dwrr_mtu(8192));
+	}
+
 	return 0;
 }
 
@@ -2743,6 +3136,7 @@ int rvu_mbox_handler_nix_get_hw_info(struct rvu *rvu, struct msg_req *req,
 				     struct nix_hw_info *rsp)
 {
 	u16 pcifunc = req->hdr.pcifunc;
+	u64 dwrr_mtu;
 	int blkaddr;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
@@ -2755,6 +3149,20 @@ int rvu_mbox_handler_nix_get_hw_info(struct rvu *rvu, struct msg_req *req,
 		rvu_get_lmac_link_max_frs(rvu, &rsp->max_mtu);
 
 	rsp->min_mtu = NIC_HW_MIN_FRS;
+
+	if (!rvu->hw->cap.nix_common_dwrr_mtu) {
+		/* Return '1' on OTx2 */
+		rsp->rpm_dwrr_mtu = 1;
+		rsp->sdp_dwrr_mtu = 1;
+		return 0;
+	}
+
+	dwrr_mtu = rvu_read64(rvu, BLKADDR_NIX0, NIX_AF_DWRR_RPM_MTU);
+	rsp->rpm_dwrr_mtu = convert_dwrr_mtu_to_bytes(dwrr_mtu);
+
+	dwrr_mtu = rvu_read64(rvu, BLKADDR_NIX0, NIX_AF_DWRR_SDP_MTU);
+	rsp->sdp_dwrr_mtu = convert_dwrr_mtu_to_bytes(dwrr_mtu);
+
 	return 0;
 }
 
@@ -3068,7 +3476,7 @@ static int reserve_flowkey_alg_idx(struct rvu *rvu, int blkaddr, u32 flow_cfg)
 
 	hw = get_nix_hw(rvu->hw, blkaddr);
 	if (!hw)
-		return -EINVAL;
+		return NIX_AF_ERR_INVALID_NIXBLK;
 
 	/* No room to add new flow hash algoritham */
 	if (hw->flowkey.in_use >= NIX_FLOW_KEY_ALG_MAX)
@@ -3108,7 +3516,7 @@ int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu,
 
 	nix_hw = get_nix_hw(rvu->hw, blkaddr);
 	if (!nix_hw)
-		return -EINVAL;
+		return NIX_AF_ERR_INVALID_NIXBLK;
 
 	alg_idx = get_flowkey_alg_idx(nix_hw, req->flowkey_cfg);
 	/* Failed to get algo index from the exiting list, reserve new  */
@@ -3366,6 +3774,77 @@ static void nix_find_link_frs(struct rvu *rvu,
 		req->minlen = minlen;
 }
 
+static int
+nix_config_link_credits(struct rvu *rvu, int blkaddr, int link,
+			u16 pcifunc, u64 tx_credits)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	int pf = rvu_get_pf(pcifunc);
+	u8 cgx_id = 0, lmac_id = 0;
+	unsigned long poll_tmo;
+	bool restore_tx_en = 0;
+	struct nix_hw *nix_hw;
+	u64 cfg, sw_xoff = 0;
+	u32 schq = 0;
+	u32 credits;
+	int rc;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return NIX_AF_ERR_INVALID_NIXBLK;
+
+	if (tx_credits == nix_hw->tx_credits[link])
+		return 0;
+
+	/* Enable cgx tx if disabled for credits to be back */
+	if (is_pf_cgxmapped(rvu, pf)) {
+		rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+		restore_tx_en = !cgx_lmac_tx_enable(rvu_cgx_pdata(cgx_id, rvu),
+						    lmac_id, true);
+	}
+
+	mutex_lock(&rvu->rsrc_lock);
+	/* Disable new traffic to link */
+	if (hw->cap.nix_shaping) {
+		schq = nix_get_tx_link(rvu, pcifunc);
+		sw_xoff = rvu_read64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq));
+		rvu_write64(rvu, blkaddr,
+			    NIX_AF_TL1X_SW_XOFF(schq), BIT_ULL(0));
+	}
+
+	rc = -EBUSY;
+	poll_tmo = jiffies + usecs_to_jiffies(10000);
+	/* Wait for credits to return */
+	do {
+		if (time_after(jiffies, poll_tmo))
+			goto exit;
+		usleep_range(100, 200);
+
+		cfg = rvu_read64(rvu, blkaddr,
+				 NIX_AF_TX_LINKX_NORM_CREDIT(link));
+		credits = (cfg >> 12) & 0xFFFFFULL;
+	} while (credits != nix_hw->tx_credits[link]);
+
+	cfg &= ~(0xFFFFFULL << 12);
+	cfg |= (tx_credits << 12);
+	rvu_write64(rvu, blkaddr, NIX_AF_TX_LINKX_NORM_CREDIT(link), cfg);
+	rc = 0;
+
+	nix_hw->tx_credits[link] = tx_credits;
+
+exit:
+	/* Enable traffic back */
+	if (hw->cap.nix_shaping && !sw_xoff)
+		rvu_write64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq), 0);
+
+	/* Restore state of cgx tx */
+	if (restore_tx_en)
+		cgx_lmac_tx_enable(rvu_cgx_pdata(cgx_id, rvu), lmac_id, false);
+
+	mutex_unlock(&rvu->rsrc_lock);
+	return rc;
+}
+
 int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
 				    struct msg_rsp *rsp)
 {
@@ -3376,6 +3855,7 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
 	struct nix_txsch *txsch;
 	u64 cfg, lmac_fifo_len;
 	struct nix_hw *nix_hw;
+	struct rvu_pfvf *pfvf;
 	u8 cgx = 0, lmac = 0;
 	u16 max_mtu;
 
@@ -3385,7 +3865,7 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
 
 	nix_hw = get_nix_hw(rvu->hw, blkaddr);
 	if (!nix_hw)
-		return -EINVAL;
+		return NIX_AF_ERR_INVALID_NIXBLK;
 
 	if (is_afvf(pcifunc))
 		rvu_get_lbk_link_max_frs(rvu, &max_mtu);
@@ -3432,7 +3912,8 @@ rx_frscfg:
 		link = (cgx * hw->lmac_per_cgx) + lmac;
 	} else if (pf == 0) {
 		/* For VFs of PF0 ingress is LBK port, so config LBK link */
-		link = hw->cgx_links;
+		pfvf = rvu_get_pfvf(rvu, pcifunc);
+		link = hw->cgx_links + pfvf->lbkid;
 	}
 
 	if (link < 0)
@@ -3454,11 +3935,8 @@ linkcfg:
 	lmac_fifo_len =
 		rvu_cgx_get_fifolen(rvu) /
 		cgx_get_lmac_cnt(rvu_cgx_pdata(cgx, rvu));
-	cfg = rvu_read64(rvu, blkaddr, NIX_AF_TX_LINKX_NORM_CREDIT(link));
-	cfg &= ~(0xFFFFFULL << 12);
-	cfg |=  ((lmac_fifo_len - req->maxlen) / 16) << 12;
-	rvu_write64(rvu, blkaddr, NIX_AF_TX_LINKX_NORM_CREDIT(link), cfg);
-	return 0;
+	return nix_config_link_credits(rvu, blkaddr, link, pcifunc,
+				       (lmac_fifo_len - req->maxlen) / 16);
 }
 
 int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req,
@@ -3502,12 +3980,13 @@ static u64 rvu_get_lbk_link_credits(struct rvu *rvu, u16 lbk_max_frs)
 	return 1600; /* 16 * max LBK datarate = 16 * 100Gbps */
 }
 
-static void nix_link_config(struct rvu *rvu, int blkaddr)
+static void nix_link_config(struct rvu *rvu, int blkaddr,
+			    struct nix_hw *nix_hw)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
 	int cgx, lmac_cnt, slink, link;
 	u16 lbk_max_frs, lmac_max_frs;
-	u64 tx_credits;
+	u64 tx_credits, cfg;
 
 	rvu_get_lbk_link_max_frs(rvu, &lbk_max_frs);
 	rvu_get_lmac_link_max_frs(rvu, &lmac_max_frs);
@@ -3538,15 +4017,18 @@ static void nix_link_config(struct rvu *rvu, int blkaddr)
 	 */
 	for (cgx = 0; cgx < hw->cgx; cgx++) {
 		lmac_cnt = cgx_get_lmac_cnt(rvu_cgx_pdata(cgx, rvu));
+		/* Skip when cgx is not available or lmac cnt is zero */
+		if (lmac_cnt <= 0)
+			continue;
 		tx_credits = ((rvu_cgx_get_fifolen(rvu) / lmac_cnt) -
 			       lmac_max_frs) / 16;
 		/* Enable credits and set credit pkt count to max allowed */
-		tx_credits =  (tx_credits << 12) | (0x1FF << 2) | BIT_ULL(1);
+		cfg =  (tx_credits << 12) | (0x1FF << 2) | BIT_ULL(1);
 		slink = cgx * hw->lmac_per_cgx;
 		for (link = slink; link < (slink + lmac_cnt); link++) {
+			nix_hw->tx_credits[link] = tx_credits;
 			rvu_write64(rvu, blkaddr,
-				    NIX_AF_TX_LINKX_NORM_CREDIT(link),
-				    tx_credits);
+				    NIX_AF_TX_LINKX_NORM_CREDIT(link), cfg);
 		}
 	}
 
@@ -3554,6 +4036,7 @@ static void nix_link_config(struct rvu *rvu, int blkaddr)
 	slink = hw->cgx_links;
 	for (link = slink; link < (slink + hw->lbk_links); link++) {
 		tx_credits = rvu_get_lbk_link_credits(rvu, lbk_max_frs);
+		nix_hw->tx_credits[link] = tx_credits;
 		/* Enable credits and set credit pkt count to max allowed */
 		tx_credits =  (tx_credits << 12) | (0x1FF << 2) | BIT_ULL(1);
 		rvu_write64(rvu, blkaddr,
@@ -3647,6 +4130,28 @@ static int nix_aq_init(struct rvu *rvu, struct rvu_block *block)
 	return 0;
 }
 
+static void rvu_nix_setup_capabilities(struct rvu *rvu, int blkaddr)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	u64 hw_const;
+
+	hw_const = rvu_read64(rvu, blkaddr, NIX_AF_CONST1);
+
+	/* On OcteonTx2 DWRR quantum is directly configured into each of
+	 * the transmit scheduler queues. And PF/VF drivers were free to
+	 * config any value upto 2^24.
+	 * On CN10K, HW is modified, the quantum configuration at scheduler
+	 * queues is in terms of weight. And SW needs to setup a base DWRR MTU
+	 * at NIX_AF_DWRR_RPM_MTU / NIX_AF_DWRR_SDP_MTU. HW will do
+	 * 'DWRR MTU * weight' to get the quantum.
+	 *
+	 * Check if HW uses a common MTU for all DWRR quantum configs.
+	 * On OcteonTx2 this register field is '0'.
+	 */
+	if (((hw_const >> 56) & 0x10) == 0x10)
+		hw->cap.nix_common_dwrr_mtu = true;
+}
+
 static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw)
 {
 	const struct npc_lt_def_cfg *ltdefs;
@@ -3684,6 +4189,9 @@ static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw)
 	if (err)
 		return err;
 
+	/* Setup capabilities of the NIX block */
+	rvu_nix_setup_capabilities(rvu, blkaddr);
+
 	/* Initialize admin queue */
 	err = nix_aq_init(rvu, block);
 	if (err)
@@ -3692,6 +4200,9 @@ static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw)
 	/* Restore CINT timer delay to HW reset values */
 	rvu_write64(rvu, blkaddr, NIX_AF_CINT_DELAY, 0x0ULL);
 
+	/* For better performance use NDC TX instead of NDC RX for SQ's SQEs" */
+	rvu_write64(rvu, blkaddr, NIX_AF_SEB_CFG, 0x1ULL);
+
 	if (is_block_implemented(hw, blkaddr)) {
 		err = nix_setup_txschq(rvu, nix_hw, blkaddr);
 		if (err)
@@ -3792,8 +4303,13 @@ static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw)
 		if (err)
 			return err;
 
+		nix_hw->tx_credits = kcalloc(hw->cgx_links + hw->lbk_links,
+					     sizeof(u64), GFP_KERNEL);
+		if (!nix_hw->tx_credits)
+			return -ENOMEM;
+
 		/* Initialize CGX/LBK/SDP link credits, min/max pkt lengths */
-		nix_link_config(rvu, blkaddr);
+		nix_link_config(rvu, blkaddr, nix_hw);
 
 		/* Enable Channel backpressure */
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_CFG, BIT_ULL(0));
@@ -3849,7 +4365,9 @@ static void rvu_nix_block_freemem(struct rvu *rvu, int blkaddr,
 			kfree(txsch->schq.bmap);
 		}
 
-		nix_ipolicer_freemem(nix_hw);
+		kfree(nix_hw->tx_credits);
+
+		nix_ipolicer_freemem(rvu, nix_hw);
 
 		vlan = &nix_hw->txvlan;
 		kfree(vlan->rsrc.bmap);
@@ -4027,7 +4545,7 @@ int rvu_mbox_handler_nix_lso_format_cfg(struct rvu *rvu,
 
 	nix_hw = get_nix_hw(rvu->hw, blkaddr);
 	if (!nix_hw)
-		return -EINVAL;
+		return NIX_AF_ERR_INVALID_NIXBLK;
 
 	/* Find existing matching LSO format, if any */
 	for (idx = 0; idx < nix_hw->lso.in_use; idx++) {
@@ -4225,11 +4743,14 @@ static int nix_setup_ipolicers(struct rvu *rvu,
 	return 0;
 }
 
-static void nix_ipolicer_freemem(struct nix_hw *nix_hw)
+static void nix_ipolicer_freemem(struct rvu *rvu, struct nix_hw *nix_hw)
 {
 	struct nix_ipolicer *ipolicer;
 	int layer;
 
+	if (!rvu->hw->cap.ipolicer)
+		return;
+
 	for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
 		ipolicer = &nix_hw->ipolicer[layer];
 
@@ -4652,3 +5173,36 @@ static void nix_clear_ratelimit_aggr(struct rvu *rvu, struct nix_hw *nix_hw,
 		rvu_free_rsrc(&ipolicer->band_prof, mid_prof);
 	}
 }
+
+int rvu_mbox_handler_nix_bandprof_get_hwinfo(struct rvu *rvu, struct msg_req *req,
+					     struct nix_bandprof_get_hwinfo_rsp *rsp)
+{
+	struct nix_ipolicer *ipolicer;
+	int blkaddr, layer, err;
+	struct nix_hw *nix_hw;
+	u64 tu;
+
+	if (!rvu->hw->cap.ipolicer)
+		return NIX_AF_ERR_IPOLICER_NOTSUPP;
+
+	err = nix_get_struct_ptrs(rvu, req->hdr.pcifunc, &nix_hw, &blkaddr);
+	if (err)
+		return err;
+
+	/* Return number of bandwidth profiles free at each layer */
+	mutex_lock(&rvu->rsrc_lock);
+	for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
+		if (layer == BAND_PROF_INVAL_LAYER)
+			continue;
+
+		ipolicer = &nix_hw->ipolicer[layer];
+		rsp->prof_count[layer] = rvu_rsrc_free_count(&ipolicer->band_prof);
+	}
+	mutex_unlock(&rvu->rsrc_lock);
+
+	/* Set the policer timeunit in nanosec */
+	tu = rvu_read64(rvu, blkaddr, NIX_AF_PL_TS) & GENMASK_ULL(9, 0);
+	rsp->policer_timeunit = (tu + 1) * 100;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
index 24c2bfdfec4e..70bd036ed76e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #include <linux/module.h>
@@ -419,6 +416,10 @@ exit:
 	rsp->stack_pg_ptrs = (cfg >> 8) & 0xFF;
 	rsp->stack_pg_bytes = cfg & 0xFF;
 	rsp->qints = (cfg >> 28) & 0xFFF;
+	if (!is_rvu_otx2(rvu)) {
+		cfg = rvu_read64(rvu, block->addr, NPA_AF_BATCH_CTL);
+		rsp->cache_lines = (cfg >> 1) & 0x3F;
+	}
 	return rc;
 }
 
@@ -478,6 +479,13 @@ static int npa_aq_init(struct rvu *rvu, struct rvu_block *block)
 #endif
 	rvu_write64(rvu, block->addr, NPA_AF_NDC_CFG, cfg);
 
+	/* For CN10K NPA BATCH DMA set 35 cache lines */
+	if (!is_rvu_otx2(rvu)) {
+		cfg = rvu_read64(rvu, block->addr, NPA_AF_BATCH_CTL);
+		cfg &= ~0x7EULL;
+		cfg |= BIT_ULL(6) | BIT_ULL(2) | BIT_ULL(1);
+		rvu_write64(rvu, block->addr, NPA_AF_BATCH_CTL, cfg);
+	}
 	/* Result structure can be followed by Aura/Pool context at
 	 * RES + 128bytes and a write mask at RES + 256 bytes, depending on
 	 * operation type. Alloc sufficient result memory for all operations.
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 52b255426c22..5efb4174e82d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #include <linux/bitfield.h>
@@ -23,7 +20,7 @@
 #define RSVD_MCAM_ENTRIES_PER_NIXLF	1 /* Ucast for LFs */
 
 #define NPC_PARSE_RESULT_DMAC_OFFSET	8
-#define NPC_HW_TSTAMP_OFFSET		8
+#define NPC_HW_TSTAMP_OFFSET		8ULL
 #define NPC_KEX_CHAN_MASK		0xFFFULL
 #define NPC_KEX_PF_FUNC_MASK		0xFFFFULL
 
@@ -85,36 +82,6 @@ static int npc_mcam_verify_pf_func(struct rvu *rvu,
 	return 0;
 }
 
-int npc_mcam_verify_channel(struct rvu *rvu, u16 pcifunc, u8 intf, u16 channel)
-{
-	int pf = rvu_get_pf(pcifunc);
-	u8 cgx_id, lmac_id;
-	int base = 0, end;
-
-	if (is_npc_intf_tx(intf))
-		return 0;
-
-	/* return in case of AF installed rules */
-	if (is_pffunc_af(pcifunc))
-		return 0;
-
-	if (is_afvf(pcifunc)) {
-		end = rvu_get_num_lbk_chans();
-		if (end < 0)
-			return -EINVAL;
-	} else {
-		rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
-		base = rvu_nix_chan_cgx(rvu, cgx_id, lmac_id, 0x0);
-		/* CGX mapped functions has maximum of 16 channels */
-		end = rvu_nix_chan_cgx(rvu, cgx_id, lmac_id, 0xF);
-	}
-
-	if (channel < base || channel > end)
-		return -EINVAL;
-
-	return 0;
-}
-
 void rvu_npc_set_pkind(struct rvu *rvu, int pkind, struct rvu_pfvf *pfvf)
 {
 	int blkaddr;
@@ -634,8 +601,8 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 	struct nix_rx_action action;
 	int blkaddr, index;
 
-	/* AF's VFs work in promiscuous mode */
-	if (is_afvf(pcifunc))
+	/* AF's and SDP VFs work in promiscuous mode */
+	if (is_afvf(pcifunc) || is_sdp_vf(pcifunc))
 		return;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
@@ -724,7 +691,17 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 		action.index = pfvf->promisc_mce_idx;
 	}
 
-	req.chan_mask = 0xFFFU;
+	/* For cn10k the upper two bits of the channel number are
+	 * cpt channel number. with masking out these bits in the
+	 * mcam entry, same entry used for NIX will allow packets
+	 * received from cpt for parsing.
+	 */
+	if (!is_rvu_otx2(rvu)) {
+		req.chan_mask = NIX_CHAN_CPT_X2P_MASK;
+	} else {
+		req.chan_mask = 0xFFFU;
+	}
+
 	if (chan_cnt > 1) {
 		if (!is_power_of_2(chan_cnt)) {
 			dev_err(rvu->dev,
@@ -853,7 +830,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 	u16 vf_func;
 
 	/* Only CGX PF/VF can add allmulticast entry */
-	if (is_afvf(pcifunc))
+	if (is_afvf(pcifunc) && is_sdp_vf(pcifunc))
 		return;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
@@ -938,7 +915,7 @@ void rvu_npc_enable_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 static void npc_update_vf_flow_entry(struct rvu *rvu, struct npc_mcam *mcam,
 				     int blkaddr, u16 pcifunc, u64 rx_action)
 {
-	int actindex, index, bank;
+	int actindex, index, bank, entry;
 	bool enable;
 
 	if (!(pcifunc & RVU_PFVF_FUNC_MASK))
@@ -949,7 +926,7 @@ static void npc_update_vf_flow_entry(struct rvu *rvu, struct npc_mcam *mcam,
 		if (mcam->entry2target_pffunc[index] == pcifunc) {
 			bank = npc_get_bank(mcam, index);
 			actindex = index;
-			index &= (mcam->banksize - 1);
+			entry = index & (mcam->banksize - 1);
 
 			/* read vf flow entry enable status */
 			enable = is_mcam_entry_enabled(rvu, mcam, blkaddr,
@@ -959,7 +936,7 @@ static void npc_update_vf_flow_entry(struct rvu *rvu, struct npc_mcam *mcam,
 					      false);
 			/* update 'action' */
 			rvu_write64(rvu, blkaddr,
-				    NPC_AF_MCAMEX_BANKX_ACTION(index, bank),
+				    NPC_AF_MCAMEX_BANKX_ACTION(entry, bank),
 				    rx_action);
 			if (enable)
 				npc_enable_mcam_entry(rvu, mcam, blkaddr,
@@ -1898,9 +1875,22 @@ static void rvu_npc_hw_init(struct rvu *rvu, int blkaddr)
 
 	mcam->banks = (npc_const >> 44) & 0xFULL;
 	mcam->banksize = (npc_const >> 28) & 0xFFFFULL;
+	hw->npc_stat_ena = BIT_ULL(9);
 	/* Extended set */
 	if (npc_const2) {
 		hw->npc_ext_set = true;
+		/* 96xx supports only match_stats and npc_counters
+		 * reflected in NPC_AF_CONST reg.
+		 * STAT_SEL and ENA are at [0:8] and 9 bit positions.
+		 * 98xx has both match_stat and ext and npc_counter
+		 * reflected in NPC_AF_CONST2
+		 * STAT_SEL_EXT added at [12:14] bit position.
+		 * cn10k supports only ext and hence npc_counters in
+		 * NPC_AF_CONST is 0 and npc_counters reflected in NPC_AF_CONST2.
+		 * STAT_SEL bitpos incremented from [0:8] to [0:11] and ENA bit moved to 63
+		 */
+		if (!hw->npc_counters)
+			hw->npc_stat_ena = BIT_ULL(63);
 		hw->npc_counters = (npc_const2 >> 16) & 0xFFFFULL;
 		mcam->banksize = npc_const2 & 0xFFFFULL;
 	}
@@ -1955,7 +1945,7 @@ static void rvu_npc_setup_interfaces(struct rvu *rvu, int blkaddr)
 		rvu_write64(rvu, blkaddr,
 			    NPC_AF_INTFX_MISS_STAT_ACT(intf),
 			    ((mcam->rx_miss_act_cntr >> 9) << 12) |
-			    BIT_ULL(9) | mcam->rx_miss_act_cntr);
+			    hw->npc_stat_ena | mcam->rx_miss_act_cntr);
 	}
 
 	/* Configure TX interfaces */
@@ -2030,14 +2020,15 @@ int rvu_npc_init(struct rvu *rvu)
 
 	/* Enable below for Rx pkts.
 	 * - Outer IPv4 header checksum validation.
-	 * - Detect outer L2 broadcast address and set NPC_RESULT_S[L2M].
+	 * - Detect outer L2 broadcast address and set NPC_RESULT_S[L2B].
+	 * - Detect outer L2 multicast address and set NPC_RESULT_S[L2M].
 	 * - Inner IPv4 header checksum validation.
 	 * - Set non zero checksum error code value
 	 */
 	rvu_write64(rvu, blkaddr, NPC_AF_PCK_CFG,
 		    rvu_read64(rvu, blkaddr, NPC_AF_PCK_CFG) |
-		    BIT_ULL(32) | BIT_ULL(24) | BIT_ULL(6) |
-		    BIT_ULL(2) | BIT_ULL(1));
+		    ((u64)NPC_EC_OIP4_CSUM << 32) | (NPC_EC_IIP4_CSUM << 24) |
+		    BIT_ULL(7) | BIT_ULL(6) | BIT_ULL(2) | BIT_ULL(1));
 
 	rvu_npc_setup_interfaces(rvu, blkaddr);
 
@@ -2147,18 +2138,16 @@ static void npc_map_mcam_entry_and_cntr(struct rvu *rvu, struct npc_mcam *mcam,
 					int blkaddr, u16 entry, u16 cntr)
 {
 	u16 index = entry & (mcam->banksize - 1);
-	u16 bank = npc_get_bank(mcam, entry);
+	u32 bank = npc_get_bank(mcam, entry);
+	struct rvu_hwinfo *hw = rvu->hw;
 
 	/* Set mapping and increment counter's refcnt */
 	mcam->entry2cntr_map[entry] = cntr;
 	mcam->cntr_refcnt[cntr]++;
-	/* Enable stats
-	 * NPC_AF_MCAMEX_BANKX_STAT_ACT[14:12] - counter[11:9]
-	 * NPC_AF_MCAMEX_BANKX_STAT_ACT[8:0] - counter[8:0]
-	 */
+	/* Enable stats */
 	rvu_write64(rvu, blkaddr,
 		    NPC_AF_MCAMEX_BANKX_STAT_ACT(index, bank),
-		    ((cntr >> 9) << 12) | BIT_ULL(9) | cntr);
+		    ((cntr >> 9) << 12) | hw->npc_stat_ena | cntr);
 }
 
 static void npc_unmap_mcam_entry_and_cntr(struct rvu *rvu,
@@ -2166,7 +2155,7 @@ static void npc_unmap_mcam_entry_and_cntr(struct rvu *rvu,
 					  int blkaddr, u16 entry, u16 cntr)
 {
 	u16 index = entry & (mcam->banksize - 1);
-	u16 bank = npc_get_bank(mcam, entry);
+	u32 bank = npc_get_bank(mcam, entry);
 
 	/* Remove mapping and reduce counter's refcnt */
 	mcam->entry2cntr_map[entry] = NPC_MCAM_INVALID_MAP;
@@ -2414,6 +2403,17 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc,
 		goto alloc;
 	}
 
+	/* For a VF base MCAM match rule is set by its PF. And all the
+	 * further MCAM rules installed by VF on its own are
+	 * concatenated with the base rule set by its PF. Hence PF entries
+	 * should be at lower priority compared to VF entries. Otherwise
+	 * base rule is hit always and rules installed by VF will be of
+	 * no use. Hence if the request is from PF and NOT a priority
+	 * allocation request then allocate low priority entries.
+	 */
+	if (!(pcifunc & RVU_PFVF_FUNC_MASK))
+		goto lprio_alloc;
+
 	/* Find out the search range for non-priority allocation request
 	 *
 	 * Get MCAM free entry count in middle zone.
@@ -2439,6 +2439,7 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc,
 		/* Not enough free entries, search all entries in reverse,
 		 * so that low priority ones will get used up.
 		 */
+lprio_alloc:
 		reverse = true;
 		start = 0;
 		end = mcam->bmap_entries;
@@ -2673,7 +2674,6 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
 	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc);
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	u16 pcifunc = req->hdr.pcifunc;
-	u16 channel, chan_mask;
 	int blkaddr, rc;
 	u8 nix_intf;
 
@@ -2681,10 +2681,6 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
 	if (blkaddr < 0)
 		return NPC_MCAM_INVALID_REQ;
 
-	chan_mask = req->entry_data.kw_mask[0] & NPC_KEX_CHAN_MASK;
-	channel = req->entry_data.kw[0] & NPC_KEX_CHAN_MASK;
-	channel &= chan_mask;
-
 	mutex_lock(&mcam->lock);
 	rc = npc_mcam_verify_entry(mcam, pcifunc, req->entry);
 	if (rc)
@@ -2707,12 +2703,6 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
 		nix_intf = pfvf->nix_rx_intf;
 
 	if (!is_pffunc_af(pcifunc) &&
-	    npc_mcam_verify_channel(rvu, pcifunc, req->intf, channel)) {
-		rc = NPC_MCAM_INVALID_REQ;
-		goto exit;
-	}
-
-	if (!is_pffunc_af(pcifunc) &&
 	    npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf, pcifunc)) {
 		rc = NPC_MCAM_INVALID_REQ;
 		goto exit;
@@ -2788,8 +2778,8 @@ int rvu_mbox_handler_npc_mcam_shift_entry(struct rvu *rvu,
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	u16 pcifunc = req->hdr.pcifunc;
 	u16 old_entry, new_entry;
+	int blkaddr, rc = 0;
 	u16 index, cntr;
-	int blkaddr, rc;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0)
@@ -2990,10 +2980,11 @@ int rvu_mbox_handler_npc_mcam_unmap_counter(struct rvu *rvu,
 		index = find_next_bit(mcam->bmap, mcam->bmap_entries, entry);
 		if (index >= mcam->bmap_entries)
 			break;
+		entry = index + 1;
+
 		if (mcam->entry2cntr_map[index] != req->cntr)
 			continue;
 
-		entry = index + 1;
 		npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
 					      index, req->cntr);
 	}
@@ -3058,7 +3049,6 @@ int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu,
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	u16 entry = NPC_MCAM_ENTRY_INVALID;
 	u16 cntr = NPC_MCAM_ENTRY_INVALID;
-	u16 channel, chan_mask;
 	int blkaddr, rc;
 	u8 nix_intf;
 
@@ -3069,13 +3059,6 @@ int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu,
 	if (!is_npc_interface_valid(rvu, req->intf))
 		return NPC_MCAM_INVALID_REQ;
 
-	chan_mask = req->entry_data.kw_mask[0] & NPC_KEX_CHAN_MASK;
-	channel = req->entry_data.kw[0] & NPC_KEX_CHAN_MASK;
-	channel &= chan_mask;
-
-	if (npc_mcam_verify_channel(rvu, req->hdr.pcifunc, req->intf, channel))
-		return NPC_MCAM_INVALID_REQ;
-
 	if (npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf,
 				    req->hdr.pcifunc))
 		return NPC_MCAM_INVALID_REQ;
@@ -3252,7 +3235,7 @@ int rvu_mbox_handler_npc_mcam_entry_stats(struct rvu *rvu,
 	/* read MCAM entry STAT_ACT register */
 	regval = rvu_read64(rvu, blkaddr, NPC_AF_MCAMEX_BANKX_STAT_ACT(index, bank));
 
-	if (!(regval & BIT_ULL(9))) {
+	if (!(regval & rvu->hw->npc_stat_ena)) {
 		rsp->stat_ena = 0;
 		mutex_unlock(&mcam->lock);
 		return 0;
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 5c01cf4a9c5b..51ddc7b81d0b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
  * Copyright (C) 2020 Marvell.
  */
@@ -20,6 +20,8 @@ static const char * const npc_flow_names[] = {
 	[NPC_DMAC]	= "dmac",
 	[NPC_SMAC]	= "smac",
 	[NPC_ETYPE]	= "ether type",
+	[NPC_VLAN_ETYPE_CTAG] = "vlan ether type ctag",
+	[NPC_VLAN_ETYPE_STAG] = "vlan ether type stag",
 	[NPC_OUTER_VID]	= "outer vlan id",
 	[NPC_TOS]	= "tos",
 	[NPC_SIP_IPV4]	= "ipv4 source ip",
@@ -492,6 +494,11 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf)
 	if (*features & BIT_ULL(NPC_OUTER_VID))
 		if (!npc_check_field(rvu, blkaddr, NPC_LB, intf))
 			*features &= ~BIT_ULL(NPC_OUTER_VID);
+
+	/* for vlan ethertypes corresponding layer type should be in the key */
+	if (npc_check_field(rvu, blkaddr, NPC_LB, intf))
+		*features |= BIT_ULL(NPC_VLAN_ETYPE_CTAG) |
+			     BIT_ULL(NPC_VLAN_ETYPE_STAG);
 }
 
 /* Scan key extraction profile and record how fields of our interest
@@ -600,7 +607,7 @@ static int npc_check_unsupported_flows(struct rvu *rvu, u64 features, u8 intf)
 		dev_info(rvu->dev, "Unsupported flow(s):\n");
 		for_each_set_bit(bit, (unsigned long *)&unsupported, 64)
 			dev_info(rvu->dev, "%s ", npc_get_field_name(bit));
-		return NIX_AF_ERR_NPC_KEY_NOT_SUPP;
+		return -EOPNOTSUPP;
 	}
 
 	return 0;
@@ -747,6 +754,28 @@ static void npc_update_ipv6_flow(struct rvu *rvu, struct mcam_entry *entry,
 	}
 }
 
+static void npc_update_vlan_features(struct rvu *rvu, struct mcam_entry *entry,
+				     u64 features, u8 intf)
+{
+	bool ctag = !!(features & BIT_ULL(NPC_VLAN_ETYPE_CTAG));
+	bool stag = !!(features & BIT_ULL(NPC_VLAN_ETYPE_STAG));
+	bool vid = !!(features & BIT_ULL(NPC_OUTER_VID));
+
+	/* If only VLAN id is given then always match outer VLAN id */
+	if (vid && !ctag && !stag) {
+		npc_update_entry(rvu, NPC_LB, entry,
+				 NPC_LT_LB_STAG_QINQ | NPC_LT_LB_CTAG, 0,
+				 NPC_LT_LB_STAG_QINQ & NPC_LT_LB_CTAG, 0, intf);
+		return;
+	}
+	if (ctag)
+		npc_update_entry(rvu, NPC_LB, entry, NPC_LT_LB_CTAG, 0,
+				 ~0ULL, 0, intf);
+	if (stag)
+		npc_update_entry(rvu, NPC_LB, entry, NPC_LT_LB_STAG_QINQ, 0,
+				 ~0ULL, 0, intf);
+}
+
 static void npc_update_flow(struct rvu *rvu, struct mcam_entry *entry,
 			    u64 features, struct flow_msg *pkt,
 			    struct flow_msg *mask,
@@ -779,11 +808,6 @@ static void npc_update_flow(struct rvu *rvu, struct mcam_entry *entry,
 		npc_update_entry(rvu, NPC_LD, entry, NPC_LT_LD_ICMP6,
 				 0, ~0ULL, 0, intf);
 
-	if (features & BIT_ULL(NPC_OUTER_VID))
-		npc_update_entry(rvu, NPC_LB, entry,
-				 NPC_LT_LB_STAG_QINQ | NPC_LT_LB_CTAG, 0,
-				 NPC_LT_LB_STAG_QINQ & NPC_LT_LB_CTAG, 0, intf);
-
 	/* For AH, LTYPE should be present in entry */
 	if (features & BIT_ULL(NPC_IPPROTO_AH))
 		npc_update_entry(rvu, NPC_LD, entry, NPC_LT_LD_AH,
@@ -829,6 +853,7 @@ do {									      \
 		       ntohs(mask->vlan_tci), 0);
 
 	npc_update_ipv6_flow(rvu, entry, features, pkt, mask, output, intf);
+	npc_update_vlan_features(rvu, entry, features, intf);
 }
 
 static struct rvu_npc_mcam_rule *rvu_mcam_find_rule(struct npc_mcam *mcam,
@@ -995,13 +1020,11 @@ static int npc_install_flow(struct rvu *rvu, int blkaddr, u16 target,
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	struct rvu_npc_mcam_rule dummy = { 0 };
 	struct rvu_npc_mcam_rule *rule;
-	bool new = false, msg_from_vf;
 	u16 owner = req->hdr.pcifunc;
 	struct msg_rsp write_rsp;
 	struct mcam_entry *entry;
 	int entry_index, err;
-
-	msg_from_vf = !!(owner & RVU_PFVF_FUNC_MASK);
+	bool new = false;
 
 	installed_features = req->features;
 	features = req->features;
@@ -1027,7 +1050,7 @@ static int npc_install_flow(struct rvu *rvu, int blkaddr, u16 target,
 	}
 
 	/* update mcam entry with default unicast rule attributes */
-	if (def_ucast_rule && (msg_from_vf || (req->default_rule && req->append))) {
+	if (def_ucast_rule && (req->default_rule && req->append)) {
 		missing_features = (def_ucast_rule->features ^ features) &
 					def_ucast_rule->features;
 		if (missing_features)
@@ -1130,6 +1153,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 				      struct npc_install_flow_rsp *rsp)
 {
 	bool from_vf = !!(req->hdr.pcifunc & RVU_PFVF_FUNC_MASK);
+	struct rvu_switch *rswitch = &rvu->rswitch;
 	int blkaddr, nixlf, err;
 	struct rvu_pfvf *pfvf;
 	bool pf_set_vfs_mac = false;
@@ -1139,14 +1163,14 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0) {
 		dev_err(rvu->dev, "%s: NPC block not implemented\n", __func__);
-		return -ENODEV;
+		return NPC_MCAM_INVALID_REQ;
 	}
 
 	if (!is_npc_interface_valid(rvu, req->intf))
-		return -EINVAL;
+		return NPC_FLOW_INTF_INVALID;
 
 	if (from_vf && req->default_rule)
-		return NPC_MCAM_PERM_DENIED;
+		return NPC_FLOW_VF_PERM_DENIED;
 
 	/* Each PF/VF info is maintained in struct rvu_pfvf.
 	 * rvu_pfvf for the target PF/VF needs to be retrieved
@@ -1172,12 +1196,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 
 	err = npc_check_unsupported_flows(rvu, req->features, req->intf);
 	if (err)
-		return err;
-
-	/* Skip channel validation if AF is installing */
-	if (!is_pffunc_af(req->hdr.pcifunc) &&
-	    npc_mcam_verify_channel(rvu, target, req->intf, req->channel))
-		return -EINVAL;
+		return NPC_FLOW_NOT_SUPPORTED;
 
 	pfvf = rvu_get_pfvf(rvu, target);
 
@@ -1195,7 +1214,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 	/* Proceed if NIXLF is attached or not for TX rules */
 	err = nix_get_nixlf(rvu, target, &nixlf, NULL);
 	if (err && is_npc_intf_rx(req->intf) && !pf_set_vfs_mac)
-		return -EINVAL;
+		return NPC_FLOW_NO_NIXLF;
 
 	/* don't enable rule when nixlf not attached or initialized */
 	if (!(is_nixlf_attached(rvu, target) &&
@@ -1211,7 +1230,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 
 	/* Do not allow requests from uninitialized VFs */
 	if (from_vf && !enable)
-		return -EINVAL;
+		return NPC_FLOW_VF_NOT_INIT;
 
 	/* PF sets VF mac & VF NIXLF is not attached, update the mac addr */
 	if (pf_set_vfs_mac && !enable) {
@@ -1221,15 +1240,12 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 		return 0;
 	}
 
-	/* If message is from VF then its flow should not overlap with
-	 * reserved unicast flow.
-	 */
-	if (from_vf && pfvf->def_ucast_rule && is_npc_intf_rx(req->intf) &&
-	    pfvf->def_ucast_rule->features & req->features)
-		return -EINVAL;
+	mutex_lock(&rswitch->switch_lock);
+	err = npc_install_flow(rvu, blkaddr, target, nixlf, pfvf,
+			       req, rsp, enable, pf_set_vfs_mac);
+	mutex_unlock(&rswitch->switch_lock);
 
-	return npc_install_flow(rvu, blkaddr, target, nixlf, pfvf, req, rsp,
-				enable, pf_set_vfs_mac);
+	return err;
 }
 
 static int npc_delete_flow(struct rvu *rvu, struct rvu_npc_mcam_rule *rule,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c
index e266f0c49559..b3150f053291 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #include <linux/module.h>
@@ -33,8 +30,8 @@ static struct hw_reg_map txsch_reg_map[NIX_TXSCH_LVL_CNT] = {
 	{NIX_TXSCH_LVL_SMQ, 2, 0xFFFF, {{0x0700, 0x0708}, {0x1400, 0x14C8} } },
 	{NIX_TXSCH_LVL_TL4, 3, 0xFFFF, {{0x0B00, 0x0B08}, {0x0B10, 0x0B18},
 			      {0x1200, 0x12E0} } },
-	{NIX_TXSCH_LVL_TL3, 3, 0xFFFF, {{0x1000, 0x10E0}, {0x1600, 0x1608},
-			      {0x1610, 0x1618} } },
+	{NIX_TXSCH_LVL_TL3, 4, 0xFFFF, {{0x1000, 0x10E0}, {0x1600, 0x1608},
+			      {0x1610, 0x1618}, {0x1700, 0x17B0} } },
 	{NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x17B0} } },
 	{NIX_TXSCH_LVL_TL1, 1, 0xFFFF, {{0x0C00, 0x0D98} } },
 };
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index 8b01ef6e2c99..21f1ed4e222f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -1,11 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*  Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #ifndef RVU_REG_H
@@ -53,7 +50,7 @@
 #define RVU_AF_SMMU_TXN_REQ		    (0x6008)
 #define RVU_AF_SMMU_ADDR_RSP_STS	    (0x6010)
 #define RVU_AF_SMMU_ADDR_TLN		    (0x6018)
-#define RVU_AF_SMMU_TLN_FLIT1		    (0x6030)
+#define RVU_AF_SMMU_TLN_FLIT0		    (0x6020)
 
 /* Admin function's privileged PF/VF registers */
 #define RVU_PRIV_CONST                      (0x8000000)
@@ -156,6 +153,7 @@
 #define NPA_AF_AQ_DONE_INT_W1S          (0x0688)
 #define NPA_AF_AQ_DONE_ENA_W1S          (0x0690)
 #define NPA_AF_AQ_DONE_ENA_W1C          (0x0698)
+#define NPA_AF_BATCH_CTL		(0x06a0)
 #define NPA_AF_LFX_AURAS_CFG(a)         (0x4000 | (a) << 18)
 #define NPA_AF_LFX_LOC_AURAS_BASE(a)    (0x4010 | (a) << 18)
 #define NPA_AF_LFX_QINTS_CFG(a)         (0x4100 | (a) << 18)
@@ -265,10 +263,13 @@
 #define NIX_AF_SDP_TX_FIFO_STATUS	(0x0640)
 #define NIX_AF_TX_NPC_CAPTURE_CONFIG	(0x0660)
 #define NIX_AF_TX_NPC_CAPTURE_INFO	(0x0670)
+#define NIX_AF_SEB_CFG			(0x05F0)
 
 #define NIX_AF_DEBUG_NPC_RESP_DATAX(a)          (0x680 | (a) << 3)
 #define NIX_AF_SMQX_CFG(a)                      (0x700 | (a) << 16)
 #define NIX_AF_SQM_DBG_CTL_STATUS               (0x750)
+#define NIX_AF_DWRR_SDP_MTU                     (0x790)
+#define NIX_AF_DWRR_RPM_MTU                     (0x7A0)
 #define NIX_AF_PSE_CHANNEL_LEVEL                (0x800)
 #define NIX_AF_PSE_SHAPER_CFG                   (0x810)
 #define NIX_AF_TX_EXPR_CREDIT			(0x830)
@@ -701,5 +702,8 @@
 #define	APR_AF_LMT_CFG			(0x000ull)
 #define	APR_AF_LMT_MAP_BASE		(0x008ull)
 #define	APR_AF_LMT_CTL			(0x010ull)
+#define APR_LMT_MAP_ENT_DIS_SCH_CMP_SHIFT	23
+#define APR_LMT_MAP_ENT_SCH_ENA_SHIFT		22
+#define APR_LMT_MAP_ENT_DIS_LINE_PREF_SHIFT	21
 
 #endif /* RVU_REG_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c
new file mode 100644
index 000000000000..b04fb226f708
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell RVU Admin Function driver
+ *
+ * Copyright (C) 2021 Marvell.
+ *
+ */
+
+#include <linux/pci.h>
+#include "rvu.h"
+
+/* SDP PF device id */
+#define PCI_DEVID_OTX2_SDP_PF   0xA0F6
+
+/* Maximum SDP blocks in a chip */
+#define MAX_SDP		2
+
+/* SDP PF number */
+static int sdp_pf_num[MAX_SDP] = {-1, -1};
+
+bool is_sdp_pfvf(u16 pcifunc)
+{
+	u16 pf = rvu_get_pf(pcifunc);
+	u32 found = 0, i = 0;
+
+	while (i < MAX_SDP) {
+		if (pf == sdp_pf_num[i])
+			found = 1;
+		i++;
+	}
+
+	if (!found)
+		return false;
+
+	return true;
+}
+
+bool is_sdp_pf(u16 pcifunc)
+{
+	return (is_sdp_pfvf(pcifunc) &&
+		!(pcifunc & RVU_PFVF_FUNC_MASK));
+}
+
+bool is_sdp_vf(u16 pcifunc)
+{
+	return (is_sdp_pfvf(pcifunc) &&
+		!!(pcifunc & RVU_PFVF_FUNC_MASK));
+}
+
+int rvu_sdp_init(struct rvu *rvu)
+{
+	struct pci_dev *pdev = NULL;
+	struct rvu_pfvf *pfvf;
+	u32 i = 0;
+
+	while ((i < MAX_SDP) && (pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM,
+						       PCI_DEVID_OTX2_SDP_PF,
+						       pdev)) != NULL) {
+		/* The RVU PF number is one less than bus number */
+		sdp_pf_num[i] = pdev->bus->number - 1;
+		pfvf = &rvu->pf[sdp_pf_num[i]];
+
+		pfvf->sdp_info = devm_kzalloc(rvu->dev,
+					      sizeof(struct sdp_node_info),
+					      GFP_KERNEL);
+		if (!pfvf->sdp_info)
+			return -ENOMEM;
+
+		dev_info(rvu->dev, "SDP PF number:%d\n", sdp_pf_num[i]);
+
+		put_device(&pdev->dev);
+		i++;
+	}
+
+	return 0;
+}
+
+int
+rvu_mbox_handler_set_sdp_chan_info(struct rvu *rvu,
+				   struct sdp_chan_info_msg *req,
+				   struct msg_rsp *rsp)
+{
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc);
+
+	memcpy(pfvf->sdp_info, &req->info, sizeof(struct sdp_node_info));
+	dev_info(rvu->dev, "AF: SDP%d max_vfs %d num_pf_rings %d pf_srn %d\n",
+		 req->info.node_id, req->info.max_vfs, req->info.num_pf_rings,
+		 req->info.pf_srn);
+	return 0;
+}
+
+int
+rvu_mbox_handler_get_sdp_chan_info(struct rvu *rvu, struct msg_req *req,
+				   struct sdp_get_chan_info_msg *rsp)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	int blkaddr;
+
+	if (!hw->cap.programmable_chans) {
+		rsp->chan_base = NIX_CHAN_SDP_CH_START;
+		rsp->num_chan = NIX_CHAN_SDP_NUM_CHANS;
+	} else {
+		blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, 0);
+		rsp->chan_base = hw->sdp_chan_base;
+		rsp->num_chan = rvu_read64(rvu, blkaddr, NIX_AF_CONST1) & 0xFFFUL;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
index 5bbe6727d11d..77ac96693f04 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
@@ -1,11 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*  Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
- * Copyright (C) 2018 Marvell International Ltd.
+ * Copyright (C) 2018 Marvell.
  *
- * 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.
  */
 
 #ifndef RVU_STRUCT_H
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
index 820adf390b8e..3392487f6b47 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Admin Function driver
+/* Marvell RVU Admin Function driver
  *
  * Copyright (C) 2021 Marvell.
+ *
  */
 
 #include <linux/bitfield.h>
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
index 56f90cf9c4c0..775fd4c35794 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Admin Function driver tracepoints
+/* Marvell RVU Admin Function driver
+ *
+ * Copyright (C) 2020 Marvell.
  *
- * Copyright (C) 2020 Marvell International Ltd.
  */
 
 #define CREATE_TRACE_POINTS
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
index 64aa7d350df1..28984d0e848a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
@@ -1,7 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Marvell OcteonTx2 RVU Admin Function driver tracepoints
+/* Marvell RVU Admin Function driver
+ *
+ * Copyright (C) 2020 Marvell.
  *
- * Copyright (C) 2020 Marvell International Ltd.
  */
 
 #undef TRACE_SYSTEM
@@ -14,6 +15,8 @@
 #include <linux/tracepoint.h>
 #include <linux/pci.h>
 
+#include "mbox.h"
+
 TRACE_EVENT(otx2_msg_alloc,
 	    TP_PROTO(const struct pci_dev *pdev, u16 id, u64 size),
 	    TP_ARGS(pdev, id, size),
@@ -25,8 +28,8 @@ TRACE_EVENT(otx2_msg_alloc,
 			   __entry->id = id;
 			   __entry->size = size;
 	    ),
-	    TP_printk("[%s] msg:(0x%x) size:%lld\n", __get_str(dev),
-		      __entry->id, __entry->size)
+	    TP_printk("[%s] msg:(%s) size:%lld\n", __get_str(dev),
+		      otx2_mbox_id2name(__entry->id), __entry->size)
 );
 
 TRACE_EVENT(otx2_msg_send,
@@ -88,8 +91,8 @@ TRACE_EVENT(otx2_msg_process,
 			   __entry->id = id;
 			   __entry->err = err;
 	    ),
-	    TP_printk("[%s] msg:(0x%x) error:%d\n", __get_str(dev),
-		      __entry->id, __entry->err)
+	    TP_printk("[%s] msg:(%s) error:%d\n", __get_str(dev),
+		      otx2_mbox_id2name(__entry->id), __entry->err)
 );
 
 #endif /* __RVU_TRACE_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
index 3254b02205ca..b92c267628b8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
@@ -1,13 +1,14 @@
 # SPDX-License-Identifier: GPL-2.0
 #
-# Makefile for Marvell's OcteonTX2 ethernet device drivers
+# Makefile for Marvell's RVU Ethernet device drivers
 #
 
 obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o
 obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o
 
 rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \
-               otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o
-rvu_nicvf-y := otx2_vf.o
+               otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \
+               otx2_devlink.o
+rvu_nicvf-y := otx2_vf.o otx2_devlink.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 184de9466286..3cc76f14d2fd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Physcial Function ethernet driver
+/* Marvell RVU Ethernet driver
+ *
+ * Copyright (C) 2021 Marvell.
  *
- * Copyright (C) 2020 Marvell.
  */
 
 #include "cn10k.h"
@@ -92,8 +93,7 @@ int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura)
 	aq->sq.ena = 1;
 	/* Only one SMQ is allocated, map all SQ's to that SMQ  */
 	aq->sq.smq = pfvf->hw.txschq_list[NIX_TXSCH_LVL_SMQ][0];
-	/* FIXME: set based on NIX_AF_DWRR_RPM_MTU*/
-	aq->sq.smq_rr_weight = pfvf->netdev->mtu;
+	aq->sq.smq_rr_weight = mtu_to_dwrr_weight(pfvf, pfvf->max_frs);
 	aq->sq.default_chan = pfvf->hw.tx_chan_base;
 	aq->sq.sqe_stype = NIX_STYPE_STF; /* Cache SQB */
 	aq->sq.sqb_aura = sqb_aura;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
index 1a1ae334477d..8ae96815865e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
@@ -1,7 +1,8 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Marvell OcteonTx2 RVU Ethernet driver
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell RVU Ethernet driver
+ *
+ * Copyright (C) 2021 Marvell.
  *
- * Copyright (C) 2020 Marvell.
  */
 
 #ifndef CN10K_H
@@ -9,6 +10,20 @@
 
 #include "otx2_common.h"
 
+static inline int mtu_to_dwrr_weight(struct otx2_nic *pfvf, int mtu)
+{
+	u32 weight;
+
+	/* On OTx2, since AF returns DWRR_MTU as '1', this logic
+	 * will work on those silicons as well.
+	 */
+	weight = mtu / pfvf->hw.dwrr_mtu;
+	if (mtu % pfvf->hw.dwrr_mtu)
+		weight += 1;
+
+	return weight;
+}
+
 void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
 void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx);
 int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 70fcc1fd962f..ce25c2744435 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Ethernet driver
+/* Marvell RVU Ethernet driver
  *
- * Copyright (C) 2020 Marvell International Ltd.
+ * Copyright (C) 2020 Marvell.
  *
- * 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.
  */
 
 #include <linux/interrupt.h>
@@ -208,7 +205,8 @@ int otx2_set_mac_address(struct net_device *netdev, void *p)
 	if (!otx2_hw_set_mac_addr(pfvf, addr->sa_data)) {
 		memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
 		/* update dmac field in vlan offload rule */
-		if (pfvf->flags & OTX2_FLAG_RX_VLAN_SUPPORT)
+		if (netif_running(netdev) &&
+		    pfvf->flags & OTX2_FLAG_RX_VLAN_SUPPORT)
 			otx2_install_rxvlan_offload_flow(pfvf);
 		/* update dmac address in ntuple and DMAC filter list */
 		if (pfvf->flags & OTX2_FLAG_DMACFLTR_SUPPORT)
@@ -268,6 +266,7 @@ unlock:
 int otx2_set_flowkey_cfg(struct otx2_nic *pfvf)
 {
 	struct otx2_rss_info *rss = &pfvf->hw.rss_info;
+	struct nix_rss_flowkey_cfg_rsp *rsp;
 	struct nix_rss_flowkey_cfg *req;
 	int err;
 
@@ -282,6 +281,18 @@ int otx2_set_flowkey_cfg(struct otx2_nic *pfvf)
 	req->group = DEFAULT_RSS_CONTEXT_GROUP;
 
 	err = otx2_sync_mbox_msg(&pfvf->mbox);
+	if (err)
+		goto fail;
+
+	rsp = (struct nix_rss_flowkey_cfg_rsp *)
+			otx2_mbox_get_rsp(&pfvf->mbox.mbox, 0, &req->hdr);
+	if (IS_ERR(rsp)) {
+		err = PTR_ERR(rsp);
+		goto fail;
+	}
+
+	pfvf->hw.flowkey_alg_idx = rsp->alg_idx;
+fail:
 	mutex_unlock(&pfvf->mbox.lock);
 	return err;
 }
@@ -572,30 +583,14 @@ void otx2_get_mac_from_af(struct net_device *netdev)
 }
 EXPORT_SYMBOL(otx2_get_mac_from_af);
 
-static int otx2_get_link(struct otx2_nic *pfvf)
-{
-	int link = 0;
-	u16 map;
-
-	/* cgx lmac link */
-	if (pfvf->hw.tx_chan_base >= CGX_CHAN_BASE) {
-		map = pfvf->hw.tx_chan_base & 0x7FF;
-		link = 4 * ((map >> 8) & 0xF) + ((map >> 4) & 0xF);
-	}
-	/* LBK channel */
-	if (pfvf->hw.tx_chan_base < SDP_CHAN_BASE) {
-		map = pfvf->hw.tx_chan_base & 0x7FF;
-		link = pfvf->hw.cgx_links | ((map >> 8) & 0xF);
-	}
-
-	return link;
-}
-
 int otx2_txschq_config(struct otx2_nic *pfvf, int lvl)
 {
 	struct otx2_hw *hw = &pfvf->hw;
 	struct nix_txschq_config *req;
 	u64 schq, parent;
+	u64 dwrr_val;
+
+	dwrr_val = mtu_to_dwrr_weight(pfvf, pfvf->max_frs);
 
 	req = otx2_mbox_alloc_msg_nix_txschq_cfg(&pfvf->mbox);
 	if (!req)
@@ -621,21 +616,21 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl)
 		req->num_regs++;
 		/* Set DWRR quantum */
 		req->reg[2] = NIX_AF_MDQX_SCHEDULE(schq);
-		req->regval[2] =  DFLT_RR_QTM;
+		req->regval[2] =  dwrr_val;
 	} else if (lvl == NIX_TXSCH_LVL_TL4) {
 		parent =  hw->txschq_list[NIX_TXSCH_LVL_TL3][0];
 		req->reg[0] = NIX_AF_TL4X_PARENT(schq);
 		req->regval[0] = parent << 16;
 		req->num_regs++;
 		req->reg[1] = NIX_AF_TL4X_SCHEDULE(schq);
-		req->regval[1] = DFLT_RR_QTM;
+		req->regval[1] = dwrr_val;
 	} else if (lvl == NIX_TXSCH_LVL_TL3) {
 		parent = hw->txschq_list[NIX_TXSCH_LVL_TL2][0];
 		req->reg[0] = NIX_AF_TL3X_PARENT(schq);
 		req->regval[0] = parent << 16;
 		req->num_regs++;
 		req->reg[1] = NIX_AF_TL3X_SCHEDULE(schq);
-		req->regval[1] = DFLT_RR_QTM;
+		req->regval[1] = dwrr_val;
 	} else if (lvl == NIX_TXSCH_LVL_TL2) {
 		parent =  hw->txschq_list[NIX_TXSCH_LVL_TL1][0];
 		req->reg[0] = NIX_AF_TL2X_PARENT(schq);
@@ -643,11 +638,10 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl)
 
 		req->num_regs++;
 		req->reg[1] = NIX_AF_TL2X_SCHEDULE(schq);
-		req->regval[1] = TXSCH_TL1_DFLT_RR_PRIO << 24 | DFLT_RR_QTM;
+		req->regval[1] = TXSCH_TL1_DFLT_RR_PRIO << 24 | dwrr_val;
 
 		req->num_regs++;
-		req->reg[2] = NIX_AF_TL3_TL2X_LINKX_CFG(schq,
-							otx2_get_link(pfvf));
+		req->reg[2] = NIX_AF_TL3_TL2X_LINKX_CFG(schq, hw->tx_link);
 		/* Enable this queue and backpressure */
 		req->regval[2] = BIT_ULL(13) | BIT_ULL(12);
 
@@ -656,7 +650,10 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl)
 		 * For VF this is always ignored.
 		 */
 
-		/* Set DWRR quantum */
+		/* On CN10K, if RR_WEIGHT is greater than 16384, HW will
+		 * clip it to 16384, so configuring a 24bit max value
+		 * will work on both OTx2 and CN10K.
+		 */
 		req->reg[0] = NIX_AF_TL1X_SCHEDULE(schq);
 		req->regval[0] = TXSCH_TL1_DFLT_RR_QTM;
 
@@ -803,7 +800,7 @@ int otx2_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura)
 	aq->sq.ena = 1;
 	/* Only one SMQ is allocated, map all SQ's to that SMQ  */
 	aq->sq.smq = pfvf->hw.txschq_list[NIX_TXSCH_LVL_SMQ][0];
-	aq->sq.smq_rr_quantum = DFLT_RR_QTM;
+	aq->sq.smq_rr_quantum = mtu_to_dwrr_weight(pfvf, pfvf->max_frs);
 	aq->sq.default_chan = pfvf->hw.tx_chan_base;
 	aq->sq.sqe_stype = NIX_STYPE_STF; /* Cache SQB */
 	aq->sq.sqb_aura = sqb_aura;
@@ -1190,7 +1187,22 @@ static int otx2_aura_init(struct otx2_nic *pfvf, int aura_id,
 	/* Enable backpressure for RQ aura */
 	if (aura_id < pfvf->hw.rqpool_cnt && !is_otx2_lbkvf(pfvf->pdev)) {
 		aq->aura.bp_ena = 0;
+		/* If NIX1 LF is attached then specify NIX1_RX.
+		 *
+		 * Below NPA_AURA_S[BP_ENA] is set according to the
+		 * NPA_BPINTF_E enumeration given as:
+		 * 0x0 + a*0x1 where 'a' is 0 for NIX0_RX and 1 for NIX1_RX so
+		 * NIX0_RX is 0x0 + 0*0x1 = 0
+		 * NIX1_RX is 0x0 + 1*0x1 = 1
+		 * But in HRM it is given that
+		 * "NPA_AURA_S[BP_ENA](w1[33:32]) - Enable aura backpressure to
+		 * NIX-RX based on [BP] level. One bit per NIX-RX; index
+		 * enumerated by NPA_BPINTF_E."
+		 */
+		if (pfvf->nix_blkaddr == BLKADDR_NIX1)
+			aq->aura.bp_ena = 1;
 		aq->aura.nix0_bpid = pfvf->bpid[0];
+
 		/* Set backpressure level for RQ's Aura */
 		aq->aura.bp = RQ_BP_LVL_AURA;
 	}
@@ -1577,6 +1589,7 @@ void mbox_handler_nix_lf_alloc(struct otx2_nic *pfvf,
 	pfvf->hw.lso_tsov6_idx = rsp->lso_tsov6_idx;
 	pfvf->hw.cgx_links = rsp->cgx_links;
 	pfvf->hw.lbk_links = rsp->lbk_links;
+	pfvf->hw.tx_link = rsp->tx_link;
 }
 EXPORT_SYMBOL(mbox_handler_nix_lf_alloc);
 
@@ -1668,6 +1681,11 @@ u16 otx2_get_max_mtu(struct otx2_nic *pfvf)
 		 * SMQ errors
 		 */
 		max_mtu = rsp->max_mtu - 8 - OTX2_ETH_HLEN;
+
+		/* Also save DWRR MTU, needed for DWRR weight calculation */
+		pfvf->hw.dwrr_mtu = rsp->rpm_dwrr_mtu;
+		if (!pfvf->hw.dwrr_mtu)
+			pfvf->hw.dwrr_mtu = 1;
 	}
 
 out:
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 8fd58cd07f50..48227cec06ee 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -1,11 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Marvell OcteonTx2 RVU Ethernet driver
+/* Marvell RVU Ethernet driver
  *
- * Copyright (C) 2020 Marvell International Ltd.
+ * Copyright (C) 2020 Marvell.
  *
- * 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.
  */
 
 #ifndef OTX2_COMMON_H
@@ -19,11 +16,13 @@
 #include <linux/timecounter.h>
 #include <linux/soc/marvell/octeontx2/asm.h>
 #include <net/pkt_cls.h>
+#include <net/devlink.h>
 
 #include <mbox.h>
 #include <npc.h>
 #include "otx2_reg.h"
 #include "otx2_txrx.h"
+#include "otx2_devlink.h"
 #include <rvu_trace.h>
 
 /* PCI device IDs */
@@ -181,6 +180,7 @@ struct otx2_hw {
 	/* NIX */
 	u16		txschq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC];
 	u16			matchall_ipolicer;
+	u32			dwrr_mtu;
 
 	/* HW settings, coalescing etc */
 	u16			rx_chan_base;
@@ -196,6 +196,9 @@ struct otx2_hw {
 	u8			lso_udpv4_idx;
 	u8			lso_udpv6_idx;
 
+	/* RSS */
+	u8			flowkey_alg_idx;
+
 	/* MSI-X */
 	u8			cint_cnt; /* CQ interrupt count */
 	u16			npa_msixoff; /* Offset of NPA vectors */
@@ -212,6 +215,7 @@ struct otx2_hw {
 	u64			cgx_fec_uncorr_blks;
 	u8			cgx_links;  /* No. of CGX links present in HW */
 	u8			lbk_links;  /* No. of LBK links present in HW */
+	u8			tx_link;    /* Transmit channel link number */
 #define HW_TSO			0
 #define CN10K_MBOX		1
 #define CN10K_LMTST		2
@@ -267,7 +271,6 @@ struct otx2_mac_table {
 };
 
 struct otx2_flow_config {
-	u16			entry[NPC_MAX_NONCONTIG_ENTRIES];
 	u16			*flow_ent;
 	u16			*def_ent;
 	u16			nr_flows;
@@ -278,16 +281,13 @@ struct otx2_flow_config {
 #define OTX2_MCAM_COUNT		(OTX2_DEFAULT_FLOWCOUNT + \
 				 OTX2_MAX_UNICAST_FLOWS + \
 				 OTX2_MAX_VLAN_FLOWS)
-	u16			ntuple_offset;
 	u16			unicast_offset;
 	u16			rx_vlan_offset;
 	u16			vf_vlan_offset;
 #define OTX2_PER_VF_VLAN_FLOWS	2 /* Rx + Tx per VF */
 #define OTX2_VF_VLAN_RX_INDEX	0
 #define OTX2_VF_VLAN_TX_INDEX	1
-	u16			tc_flower_offset;
-	u16                     ntuple_max_flows;
-	u16			tc_max_flows;
+	u16			max_flows;
 	u8			dmacflt_max_flows;
 	u8			*bmap_to_dmacindex;
 	unsigned long		dmacflt_bmap;
@@ -298,8 +298,7 @@ struct otx2_tc_info {
 	/* hash table to store TC offloaded flows */
 	struct rhashtable		flow_table;
 	struct rhashtable_params	flow_ht_params;
-	DECLARE_BITMAP(tc_entries_bitmap, OTX2_MAX_TC_FLOWS);
-	unsigned long			num_entries;
+	unsigned long			*tc_entries_bitmap;
 };
 
 struct dev_hw_ops {
@@ -352,6 +351,11 @@ struct otx2_nic {
 	struct otx2_vf_config	*vf_configs;
 	struct cgx_link_user_info linfo;
 
+	/* NPC MCAM */
+	struct otx2_flow_config	*flow_cfg;
+	struct otx2_mac_table	*mac_table;
+	struct otx2_tc_info	tc_info;
+
 	u64			reset_count;
 	struct work_struct	reset_task;
 	struct workqueue_struct	*flr_wq;
@@ -359,7 +363,6 @@ struct otx2_nic {
 	struct refill_work	*refill_wrk;
 	struct workqueue_struct	*otx2_wq;
 	struct work_struct	rx_mode_work;
-	struct otx2_mac_table	*mac_table;
 
 	/* Ethtool stuff */
 	u32			msg_enable;
@@ -375,9 +378,10 @@ struct otx2_nic {
 	struct otx2_ptp		*ptp;
 	struct hwtstamp_config	tstamp;
 
-	struct otx2_flow_config	*flow_cfg;
-	struct otx2_tc_info	tc_info;
 	unsigned long		rq_bmap;
+
+	/* Devlink */
+	struct otx2_devlink	*dl;
 };
 
 static inline bool is_otx2_lbkvf(struct pci_dev *pdev)
@@ -709,6 +713,11 @@ MBOX_UP_CGX_MESSAGES
 #define	RVU_PFVF_FUNC_SHIFT	0
 #define	RVU_PFVF_FUNC_MASK	0x3FF
 
+static inline bool is_otx2_vf(u16 pcifunc)
+{
+	return !!(pcifunc & RVU_PFVF_FUNC_MASK);
+}
+
 static inline int rvu_get_pf(u16 pcifunc)
 {
 	return (pcifunc >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK;
@@ -814,7 +823,8 @@ int otx2_set_real_num_queues(struct net_device *netdev,
 			     int tx_queues, int rx_queues);
 /* MCAM filter related APIs */
 int otx2_mcam_flow_init(struct otx2_nic *pf);
-int otx2_alloc_mcam_entries(struct otx2_nic *pfvf);
+int otx2vf_mcam_flow_init(struct otx2_nic *pfvf);
+int otx2_alloc_mcam_entries(struct otx2_nic *pfvf, u16 count);
 void otx2_mcam_flow_del(struct otx2_nic *pf);
 int otx2_destroy_ntuple_flows(struct otx2_nic *pf);
 int otx2_destroy_mcam_flows(struct otx2_nic *pfvf);
@@ -825,8 +835,7 @@ int otx2_get_all_flows(struct otx2_nic *pfvf,
 int otx2_add_flow(struct otx2_nic *pfvf,
 		  struct ethtool_rxnfc *nfc);
 int otx2_remove_flow(struct otx2_nic *pfvf, u32 location);
-int otx2_prepare_flow_request(struct ethtool_rx_flow_spec *fsp,
-			      struct npc_install_flow_req *req);
+int otx2_get_maxflows(struct otx2_flow_config *flow_cfg);
 void otx2_rss_ctx_flow_del(struct otx2_nic *pfvf, int ctx_id);
 int otx2_del_macfilter(struct net_device *netdev, const u8 *mac);
 int otx2_add_macfilter(struct net_device *netdev, const u8 *mac);
@@ -838,6 +847,7 @@ int otx2_init_tc(struct otx2_nic *nic);
 void otx2_shutdown_tc(struct otx2_nic *nic);
 int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 		  void *type_data);
+int otx2_tc_alloc_ent_bitmap(struct otx2_nic *nic);
 /* CGX/RPM DMAC filters support */
 int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf);
 int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u8 bit_pos);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
new file mode 100644
index 000000000000..7ac3ef2fa06a
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell RVU PF/VF Netdev Devlink
+ *
+ * Copyright (C) 2021 Marvell.
+ */
+
+#include "otx2_common.h"
+
+/* Devlink Params APIs */
+static int otx2_dl_mcam_count_validate(struct devlink *devlink, u32 id,
+				       union devlink_param_value val,
+				       struct netlink_ext_ack *extack)
+{
+	struct otx2_devlink *otx2_dl = devlink_priv(devlink);
+	struct otx2_nic *pfvf = otx2_dl->pfvf;
+	struct otx2_flow_config *flow_cfg;
+
+	if (!pfvf->flow_cfg) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "pfvf->flow_cfg not initialized");
+		return -EINVAL;
+	}
+
+	flow_cfg = pfvf->flow_cfg;
+	if (flow_cfg && flow_cfg->nr_flows) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot modify count when there are active rules");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int otx2_dl_mcam_count_set(struct devlink *devlink, u32 id,
+				  struct devlink_param_gset_ctx *ctx)
+{
+	struct otx2_devlink *otx2_dl = devlink_priv(devlink);
+	struct otx2_nic *pfvf = otx2_dl->pfvf;
+
+	if (!pfvf->flow_cfg)
+		return 0;
+
+	otx2_alloc_mcam_entries(pfvf, ctx->val.vu16);
+	otx2_tc_alloc_ent_bitmap(pfvf);
+
+	return 0;
+}
+
+static int otx2_dl_mcam_count_get(struct devlink *devlink, u32 id,
+				  struct devlink_param_gset_ctx *ctx)
+{
+	struct otx2_devlink *otx2_dl = devlink_priv(devlink);
+	struct otx2_nic *pfvf = otx2_dl->pfvf;
+	struct otx2_flow_config *flow_cfg;
+
+	if (!pfvf->flow_cfg) {
+		ctx->val.vu16 = 0;
+		return 0;
+	}
+
+	flow_cfg = pfvf->flow_cfg;
+	ctx->val.vu16 = flow_cfg->max_flows;
+
+	return 0;
+}
+
+enum otx2_dl_param_id {
+	OTX2_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	OTX2_DEVLINK_PARAM_ID_MCAM_COUNT,
+};
+
+static const struct devlink_param otx2_dl_params[] = {
+	DEVLINK_PARAM_DRIVER(OTX2_DEVLINK_PARAM_ID_MCAM_COUNT,
+			     "mcam_count", DEVLINK_PARAM_TYPE_U16,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     otx2_dl_mcam_count_get, otx2_dl_mcam_count_set,
+			     otx2_dl_mcam_count_validate),
+};
+
+/* Devlink OPs */
+static int otx2_devlink_info_get(struct devlink *devlink,
+				 struct devlink_info_req *req,
+				 struct netlink_ext_ack *extack)
+{
+	struct otx2_devlink *otx2_dl = devlink_priv(devlink);
+	struct otx2_nic *pfvf = otx2_dl->pfvf;
+
+	if (is_otx2_vf(pfvf->pcifunc))
+		return devlink_info_driver_name_put(req, "rvu_nicvf");
+
+	return devlink_info_driver_name_put(req, "rvu_nicpf");
+}
+
+static const struct devlink_ops otx2_devlink_ops = {
+	.info_get = otx2_devlink_info_get,
+};
+
+int otx2_register_dl(struct otx2_nic *pfvf)
+{
+	struct otx2_devlink *otx2_dl;
+	struct devlink *dl;
+	int err;
+
+	dl = devlink_alloc(&otx2_devlink_ops,
+			   sizeof(struct otx2_devlink), pfvf->dev);
+	if (!dl) {
+		dev_warn(pfvf->dev, "devlink_alloc failed\n");
+		return -ENOMEM;
+	}
+
+	err = devlink_register(dl);
+	if (err) {
+		dev_err(pfvf->dev, "devlink register failed with error %d\n", err);
+		devlink_free(dl);
+		return err;
+	}
+
+	otx2_dl = devlink_priv(dl);
+	otx2_dl->dl = dl;
+	otx2_dl->pfvf = pfvf;
+	pfvf->dl = otx2_dl;
+
+	err = devlink_params_register(dl, otx2_dl_params,
+				      ARRAY_SIZE(otx2_dl_params));
+	if (err) {
+		dev_err(pfvf->dev,
+			"devlink params register failed with error %d", err);
+		goto err_dl;
+	}
+
+	devlink_params_publish(dl);
+
+	return 0;
+
+err_dl:
+	devlink_unregister(dl);
+	devlink_free(dl);
+	return err;
+}
+
+void otx2_unregister_dl(struct otx2_nic *pfvf)
+{
+	struct otx2_devlink *otx2_dl = pfvf->dl;
+	struct devlink *dl;
+
+	if (!otx2_dl || !otx2_dl->dl)
+		return;
+
+	dl = otx2_dl->dl;
+
+	devlink_params_unregister(dl, otx2_dl_params,
+				  ARRAY_SIZE(otx2_dl_params));
+
+	devlink_unregister(dl);
+	devlink_free(dl);
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.h
new file mode 100644
index 000000000000..c7bd4f3c6c6b
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell RVU PF/VF Netdev Devlink
+ *
+ * Copyright (C) 2021 Marvell.
+ *
+ */
+
+#ifndef	OTX2_DEVLINK_H
+#define	OTX2_DEVLINK_H
+
+struct otx2_devlink {
+	struct devlink *dl;
+	struct otx2_nic *pfvf;
+};
+
+/* Devlink APIs */
+int otx2_register_dl(struct otx2_nic *pfvf);
+void otx2_unregister_dl(struct otx2_nic *pfvf);
+
+#endif /* RVU_DEVLINK_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c
index 383a6b5cb698..2ec800f741d8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Physcial Function ethernet driver
+/* Marvell RVU Ethernet driver
  *
  * Copyright (C) 2021 Marvell.
+ *
  */
 
 #include "otx2_common.h"
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index b906a0eb6e0d..799486c72177 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Ethernet driver
+/* Marvell RVU Ethernet driver
  *
- * Copyright (C) 2020 Marvell International Ltd.
+ * Copyright (C) 2020 Marvell.
  *
- * 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.
  */
 
 #include <linux/pci.h>
@@ -33,9 +30,6 @@ struct otx2_stat {
 	.index = offsetof(struct otx2_dev_stats, stat) / sizeof(u64), \
 }
 
-/* Physical link config */
-#define OTX2_ETHTOOL_SUPPORTED_MODES 0x638CCBF //110001110001100110010111111
-
 enum link_mode {
 	OTX2_MODE_SUPPORTED,
 	OTX2_MODE_ADVERTISED
@@ -415,7 +409,9 @@ static int otx2_set_ringparam(struct net_device *netdev,
 }
 
 static int otx2_get_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *cmd)
+			     struct ethtool_coalesce *cmd,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 	struct otx2_hw *hw = &pfvf->hw;
@@ -429,7 +425,9 @@ static int otx2_get_coalesce(struct net_device *netdev,
 }
 
 static int otx2_set_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *ec)
+			     struct ethtool_coalesce *ec,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 	struct otx2_hw *hw = &pfvf->hw;
@@ -645,6 +643,7 @@ static int otx2_set_rss_hash_opts(struct otx2_nic *pfvf,
 static int otx2_get_rxnfc(struct net_device *dev,
 			  struct ethtool_rxnfc *nfc, u32 *rules)
 {
+	bool ntuple = !!(dev->features & NETIF_F_NTUPLE);
 	struct otx2_nic *pfvf = netdev_priv(dev);
 	int ret = -EOPNOTSUPP;
 
@@ -654,14 +653,18 @@ static int otx2_get_rxnfc(struct net_device *dev,
 		ret = 0;
 		break;
 	case ETHTOOL_GRXCLSRLCNT:
-		nfc->rule_cnt = pfvf->flow_cfg->nr_flows;
-		ret = 0;
+		if (netif_running(dev) && ntuple) {
+			nfc->rule_cnt = pfvf->flow_cfg->nr_flows;
+			ret = 0;
+		}
 		break;
 	case ETHTOOL_GRXCLSRULE:
-		ret = otx2_get_flow(pfvf, nfc,  nfc->fs.location);
+		if (netif_running(dev) && ntuple)
+			ret = otx2_get_flow(pfvf, nfc,  nfc->fs.location);
 		break;
 	case ETHTOOL_GRXCLSRLALL:
-		ret = otx2_get_all_flows(pfvf, nfc, rules);
+		if (netif_running(dev) && ntuple)
+			ret = otx2_get_all_flows(pfvf, nfc, rules);
 		break;
 	case ETHTOOL_GRXFH:
 		return otx2_get_rss_hash_opts(pfvf, nfc);
@@ -696,41 +699,6 @@ static int otx2_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc)
 	return ret;
 }
 
-static int otx2vf_get_rxnfc(struct net_device *dev,
-			    struct ethtool_rxnfc *nfc, u32 *rules)
-{
-	struct otx2_nic *pfvf = netdev_priv(dev);
-	int ret = -EOPNOTSUPP;
-
-	switch (nfc->cmd) {
-	case ETHTOOL_GRXRINGS:
-		nfc->data = pfvf->hw.rx_queues;
-		ret = 0;
-		break;
-	case ETHTOOL_GRXFH:
-		return otx2_get_rss_hash_opts(pfvf, nfc);
-	default:
-		break;
-	}
-	return ret;
-}
-
-static int otx2vf_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc)
-{
-	struct otx2_nic *pfvf = netdev_priv(dev);
-	int ret = -EOPNOTSUPP;
-
-	switch (nfc->cmd) {
-	case ETHTOOL_SRXFH:
-		ret = otx2_set_rss_hash_opts(pfvf, nfc);
-		break;
-	default:
-		break;
-	}
-
-	return ret;
-}
-
 static u32 otx2_get_rxfh_key_size(struct net_device *netdev)
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
@@ -1116,8 +1084,6 @@ static void otx2_get_link_mode_info(u64 link_mode_bmap,
 	};
 	u8 bit;
 
-	link_mode_bmap = link_mode_bmap & OTX2_ETHTOOL_SUPPORTED_MODES;
-
 	for_each_set_bit(bit, (unsigned long *)&link_mode_bmap, 27) {
 		/* SGMII mode is set */
 		if (bit == 0)
@@ -1357,8 +1323,8 @@ static const struct ethtool_ops otx2vf_ethtool_ops = {
 	.get_sset_count		= otx2vf_get_sset_count,
 	.set_channels		= otx2_set_channels,
 	.get_channels		= otx2_get_channels,
-	.get_rxnfc		= otx2vf_get_rxnfc,
-	.set_rxnfc              = otx2vf_set_rxnfc,
+	.get_rxnfc		= otx2_get_rxnfc,
+	.set_rxnfc              = otx2_set_rxnfc,
 	.get_rxfh_key_size	= otx2_get_rxfh_key_size,
 	.get_rxfh_indir_size	= otx2_get_rxfh_indir_size,
 	.get_rxfh		= otx2_get_rxfh,
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 4d9de525802d..77a13fb555fb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -1,15 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Physical Function ethernet driver
+/* Marvell RVU Ethernet driver
  *
  * Copyright (C) 2020 Marvell.
+ *
  */
 
 #include <net/ipv6.h>
+#include <linux/sort.h>
 
 #include "otx2_common.h"
 
 #define OTX2_DEFAULT_ACTION	0x1
 
+static int otx2_mcam_entry_init(struct otx2_nic *pfvf);
+
 struct otx2_flow {
 	struct ethtool_rx_flow_spec flow_spec;
 	struct list_head list;
@@ -30,8 +34,7 @@ static void otx2_clear_ntuple_flow_info(struct otx2_nic *pfvf, struct otx2_flow_
 {
 	devm_kfree(pfvf->dev, flow_cfg->flow_ent);
 	flow_cfg->flow_ent = NULL;
-	flow_cfg->ntuple_max_flows = 0;
-	flow_cfg->tc_max_flows = 0;
+	flow_cfg->max_flows = 0;
 }
 
 static int otx2_free_ntuple_mcam_entries(struct otx2_nic *pfvf)
@@ -40,11 +43,11 @@ static int otx2_free_ntuple_mcam_entries(struct otx2_nic *pfvf)
 	struct npc_mcam_free_entry_req *req;
 	int ent, err;
 
-	if (!flow_cfg->ntuple_max_flows)
+	if (!flow_cfg->max_flows)
 		return 0;
 
 	mutex_lock(&pfvf->mbox.lock);
-	for (ent = 0; ent < flow_cfg->ntuple_max_flows; ent++) {
+	for (ent = 0; ent < flow_cfg->max_flows; ent++) {
 		req = otx2_mbox_alloc_msg_npc_mcam_free_entry(&pfvf->mbox);
 		if (!req)
 			break;
@@ -61,7 +64,12 @@ static int otx2_free_ntuple_mcam_entries(struct otx2_nic *pfvf)
 	return 0;
 }
 
-static int otx2_alloc_ntuple_mcam_entries(struct otx2_nic *pfvf, u16 count)
+static int mcam_entry_cmp(const void *a, const void *b)
+{
+	return *(u16 *)a - *(u16 *)b;
+}
+
+int otx2_alloc_mcam_entries(struct otx2_nic *pfvf, u16 count)
 {
 	struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
 	struct npc_mcam_alloc_entry_req *req;
@@ -76,8 +84,12 @@ static int otx2_alloc_ntuple_mcam_entries(struct otx2_nic *pfvf, u16 count)
 
 	flow_cfg->flow_ent = devm_kmalloc_array(pfvf->dev, count,
 						sizeof(u16), GFP_KERNEL);
-	if (!flow_cfg->flow_ent)
+	if (!flow_cfg->flow_ent) {
+		netdev_err(pfvf->netdev,
+			   "%s: Unable to allocate memory for flow entries\n",
+			    __func__);
 		return -ENOMEM;
+	}
 
 	mutex_lock(&pfvf->mbox.lock);
 
@@ -92,8 +104,14 @@ static int otx2_alloc_ntuple_mcam_entries(struct otx2_nic *pfvf, u16 count)
 		req->contig = false;
 		req->count = (count - allocated) > NPC_MAX_NONCONTIG_ENTRIES ?
 				NPC_MAX_NONCONTIG_ENTRIES : count - allocated;
-		req->priority = NPC_MCAM_HIGHER_PRIO;
-		req->ref_entry = flow_cfg->def_ent[0];
+
+		/* Allocate higher priority entries for PFs, so that VF's entries
+		 * will be on top of PF.
+		 */
+		if (!is_otx2_vf(pfvf->pcifunc)) {
+			req->priority = NPC_MCAM_HIGHER_PRIO;
+			req->ref_entry = flow_cfg->def_ent[0];
+		}
 
 		/* Send message to AF */
 		if (otx2_sync_mbox_msg(&pfvf->mbox))
@@ -114,22 +132,34 @@ static int otx2_alloc_ntuple_mcam_entries(struct otx2_nic *pfvf, u16 count)
 			break;
 	}
 
+	/* Multiple MCAM entry alloc requests could result in non-sequential
+	 * MCAM entries in the flow_ent[] array. Sort them in an ascending order,
+	 * otherwise user installed ntuple filter index and MCAM entry index will
+	 * not be in sync.
+	 */
+	if (allocated)
+		sort(&flow_cfg->flow_ent[0], allocated,
+		     sizeof(flow_cfg->flow_ent[0]), mcam_entry_cmp, NULL);
+
 exit:
 	mutex_unlock(&pfvf->mbox.lock);
 
-	flow_cfg->ntuple_offset = 0;
-	flow_cfg->ntuple_max_flows = allocated;
-	flow_cfg->tc_max_flows = allocated;
+	flow_cfg->max_flows = allocated;
+
+	if (allocated) {
+		pfvf->flags |= OTX2_FLAG_MCAM_ENTRIES_ALLOC;
+		pfvf->flags |= OTX2_FLAG_NTUPLE_SUPPORT;
+	}
 
 	if (allocated != count)
 		netdev_info(pfvf->netdev,
-			    "Unable to allocate %d MCAM entries for ntuple, got %d\n",
+			    "Unable to allocate %d MCAM entries, got only %d\n",
 			    count, allocated);
-
 	return allocated;
 }
+EXPORT_SYMBOL(otx2_alloc_mcam_entries);
 
-int otx2_alloc_mcam_entries(struct otx2_nic *pfvf)
+static int otx2_mcam_entry_init(struct otx2_nic *pfvf)
 {
 	struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
 	struct npc_mcam_alloc_entry_req *req;
@@ -189,18 +219,35 @@ int otx2_alloc_mcam_entries(struct otx2_nic *pfvf)
 	mutex_unlock(&pfvf->mbox.lock);
 
 	/* Allocate entries for Ntuple filters */
-	count = otx2_alloc_ntuple_mcam_entries(pfvf, OTX2_DEFAULT_FLOWCOUNT);
+	count = otx2_alloc_mcam_entries(pfvf, OTX2_DEFAULT_FLOWCOUNT);
 	if (count <= 0) {
 		otx2_clear_ntuple_flow_info(pfvf, flow_cfg);
 		return 0;
 	}
 
-	pfvf->flags |= OTX2_FLAG_NTUPLE_SUPPORT;
 	pfvf->flags |= OTX2_FLAG_TC_FLOWER_SUPPORT;
 
 	return 0;
 }
 
+int otx2vf_mcam_flow_init(struct otx2_nic *pfvf)
+{
+	struct otx2_flow_config *flow_cfg;
+
+	pfvf->flow_cfg = devm_kzalloc(pfvf->dev,
+				      sizeof(struct otx2_flow_config),
+				      GFP_KERNEL);
+	if (!pfvf->flow_cfg)
+		return -ENOMEM;
+
+	flow_cfg = pfvf->flow_cfg;
+	INIT_LIST_HEAD(&flow_cfg->flow_list);
+	flow_cfg->max_flows = 0;
+
+	return 0;
+}
+EXPORT_SYMBOL(otx2vf_mcam_flow_init);
+
 int otx2_mcam_flow_init(struct otx2_nic *pf)
 {
 	int err;
@@ -212,7 +259,10 @@ int otx2_mcam_flow_init(struct otx2_nic *pf)
 
 	INIT_LIST_HEAD(&pf->flow_cfg->flow_list);
 
-	err = otx2_alloc_mcam_entries(pf);
+	/* Allocate bare minimum number of MCAM entries needed for
+	 * unicast and ntuple filters.
+	 */
+	err = otx2_mcam_entry_init(pf);
 	if (err)
 		return err;
 
@@ -248,6 +298,7 @@ void otx2_mcam_flow_del(struct otx2_nic *pf)
 {
 	otx2_destroy_mcam_flows(pf);
 }
+EXPORT_SYMBOL(otx2_mcam_flow_del);
 
 /*  On success adds mcam entry
  *  On failure enable promisous mode
@@ -379,15 +430,19 @@ static void otx2_add_flow_to_list(struct otx2_nic *pfvf, struct otx2_flow *flow)
 	list_add(&flow->list, head);
 }
 
-static int otx2_get_maxflows(struct otx2_flow_config *flow_cfg)
+int otx2_get_maxflows(struct otx2_flow_config *flow_cfg)
 {
-	if (flow_cfg->nr_flows == flow_cfg->ntuple_max_flows ||
+	if (!flow_cfg)
+		return 0;
+
+	if (flow_cfg->nr_flows == flow_cfg->max_flows ||
 	    bitmap_weight(&flow_cfg->dmacflt_bmap,
 			  flow_cfg->dmacflt_max_flows))
-		return flow_cfg->ntuple_max_flows + flow_cfg->dmacflt_max_flows;
+		return flow_cfg->max_flows + flow_cfg->dmacflt_max_flows;
 	else
-		return flow_cfg->ntuple_max_flows;
+		return flow_cfg->max_flows;
 }
+EXPORT_SYMBOL(otx2_get_maxflows);
 
 int otx2_get_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc,
 		  u32 location)
@@ -708,7 +763,7 @@ static int otx2_prepare_ipv6_flow(struct ethtool_rx_flow_spec *fsp,
 	return 0;
 }
 
-int otx2_prepare_flow_request(struct ethtool_rx_flow_spec *fsp,
+static int otx2_prepare_flow_request(struct ethtool_rx_flow_spec *fsp,
 			      struct npc_install_flow_req *req)
 {
 	struct ethhdr *eth_mask = &fsp->m_u.ether_spec;
@@ -732,7 +787,7 @@ int otx2_prepare_flow_request(struct ethtool_rx_flow_spec *fsp,
 			ether_addr_copy(pmask->dmac, eth_mask->h_dest);
 			req->features |= BIT_ULL(NPC_DMAC);
 		}
-		if (eth_mask->h_proto) {
+		if (eth_hdr->h_proto) {
 			memcpy(&pkt->etype, &eth_hdr->h_proto,
 			       sizeof(pkt->etype));
 			memcpy(&pmask->etype, &eth_mask->h_proto,
@@ -764,14 +819,31 @@ int otx2_prepare_flow_request(struct ethtool_rx_flow_spec *fsp,
 		return -EOPNOTSUPP;
 	}
 	if (fsp->flow_type & FLOW_EXT) {
-		if (fsp->m_ext.vlan_etype)
-			return -EINVAL;
-		if (fsp->m_ext.vlan_tci) {
-			if (fsp->m_ext.vlan_tci != cpu_to_be16(VLAN_VID_MASK))
+		u16 vlan_etype;
+
+		if (fsp->m_ext.vlan_etype) {
+			/* Partial masks not supported */
+			if (be16_to_cpu(fsp->m_ext.vlan_etype) != 0xFFFF)
 				return -EINVAL;
-			if (be16_to_cpu(fsp->h_ext.vlan_tci) >= VLAN_N_VID)
+
+			vlan_etype = be16_to_cpu(fsp->h_ext.vlan_etype);
+			/* Only ETH_P_8021Q and ETH_P_802AD types supported */
+			if (vlan_etype != ETH_P_8021Q &&
+			    vlan_etype != ETH_P_8021AD)
 				return -EINVAL;
 
+			memcpy(&pkt->vlan_etype, &fsp->h_ext.vlan_etype,
+			       sizeof(pkt->vlan_etype));
+			memcpy(&pmask->vlan_etype, &fsp->m_ext.vlan_etype,
+			       sizeof(pmask->vlan_etype));
+
+			if (vlan_etype == ETH_P_8021Q)
+				req->features |= BIT_ULL(NPC_VLAN_ETYPE_CTAG);
+			else
+				req->features |= BIT_ULL(NPC_VLAN_ETYPE_STAG);
+		}
+
+		if (fsp->m_ext.vlan_tci) {
 			memcpy(&pkt->vlan_tci, &fsp->h_ext.vlan_tci,
 			       sizeof(pkt->vlan_tci));
 			memcpy(&pmask->vlan_tci, &fsp->m_ext.vlan_tci,
@@ -858,6 +930,7 @@ static int otx2_add_flow_msg(struct otx2_nic *pfvf, struct otx2_flow *flow)
 		if (flow->flow_spec.flow_type & FLOW_RSS) {
 			req->op = NIX_RX_ACTIONOP_RSS;
 			req->index = flow->rss_ctx_id;
+			req->flow_key_alg = pfvf->hw.flowkey_alg_idx;
 		} else {
 			req->op = NIX_RX_ACTIONOP_UCAST;
 			req->index = ethtool_get_flow_spec_ring(ring_cookie);
@@ -894,7 +967,7 @@ static int otx2_add_flow_with_pfmac(struct otx2_nic *pfvf,
 
 	pf_mac->entry = 0;
 	pf_mac->dmac_filter = true;
-	pf_mac->location = pfvf->flow_cfg->ntuple_max_flows;
+	pf_mac->location = pfvf->flow_cfg->max_flows;
 	memcpy(&pf_mac->flow_spec, &flow->flow_spec,
 	       sizeof(struct ethtool_rx_flow_spec));
 	pf_mac->flow_spec.location = pf_mac->location;
@@ -923,6 +996,12 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
 	int err = 0;
 	u32 ring;
 
+	if (!flow_cfg->max_flows) {
+		netdev_err(pfvf->netdev,
+			   "Ntuple rule count is 0, allocate and retry\n");
+		return -EINVAL;
+	}
+
 	ring = ethtool_get_flow_spec_ring(fsp->ring_cookie);
 	if (!(pfvf->flags & OTX2_FLAG_NTUPLE_SUPPORT))
 		return -ENOMEM;
@@ -939,6 +1018,7 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
 		if (!flow)
 			return -ENOMEM;
 		flow->location = fsp->location;
+		flow->entry = flow_cfg->flow_ent[flow->location];
 		new = true;
 	}
 	/* struct copy */
@@ -975,7 +1055,7 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
 		flow->dmac_filter = true;
 		flow->entry = find_first_zero_bit(&flow_cfg->dmacflt_bmap,
 						  flow_cfg->dmacflt_max_flows);
-		fsp->location = flow_cfg->ntuple_max_flows + flow->entry;
+		fsp->location = flow_cfg->max_flows + flow->entry;
 		flow->flow_spec.location = fsp->location;
 		flow->location = fsp->location;
 
@@ -983,19 +1063,20 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
 		otx2_dmacflt_add(pfvf, eth_hdr->h_dest, flow->entry);
 
 	} else {
-		if (flow->location >= pfvf->flow_cfg->ntuple_max_flows) {
+		if (flow->location >= pfvf->flow_cfg->max_flows) {
 			netdev_warn(pfvf->netdev,
 				    "Can't insert non dmac ntuple rule at %d, allowed range %d-0\n",
 				    flow->location,
-				    flow_cfg->ntuple_max_flows - 1);
+				    flow_cfg->max_flows - 1);
 			err = -EINVAL;
 		} else {
-			flow->entry = flow_cfg->flow_ent[flow->location];
 			err = otx2_add_flow_msg(pfvf, flow);
 		}
 	}
 
 	if (err) {
+		if (err == MBOX_MSG_INVALID)
+			err = -EINVAL;
 		if (new)
 			kfree(flow);
 		return err;
@@ -1132,6 +1213,9 @@ int otx2_destroy_ntuple_flows(struct otx2_nic *pfvf)
 	if (!(pfvf->flags & OTX2_FLAG_NTUPLE_SUPPORT))
 		return 0;
 
+	if (!flow_cfg->max_flows)
+		return 0;
+
 	mutex_lock(&pfvf->mbox.lock);
 	req = otx2_mbox_alloc_msg_npc_delete_flow(&pfvf->mbox);
 	if (!req) {
@@ -1140,7 +1224,7 @@ int otx2_destroy_ntuple_flows(struct otx2_nic *pfvf)
 	}
 
 	req->start = flow_cfg->flow_ent[0];
-	req->end   = flow_cfg->flow_ent[flow_cfg->ntuple_max_flows - 1];
+	req->end   = flow_cfg->flow_ent[flow_cfg->max_flows - 1];
 	err = otx2_sync_mbox_msg(&pfvf->mbox);
 	mutex_unlock(&pfvf->mbox.lock);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 2c24944a4dba..2f2e8a3d7924 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Physical Function ethernet driver
+/* Marvell RVU Physical Function ethernet driver
  *
- * Copyright (C) 2020 Marvell International Ltd.
+ * Copyright (C) 2020 Marvell.
  *
- * 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.
  */
 
 #include <linux/module.h>
@@ -1787,17 +1784,10 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev)
 static netdev_features_t otx2_fix_features(struct net_device *dev,
 					   netdev_features_t features)
 {
-	/* check if n-tuple filters are ON */
-	if ((features & NETIF_F_HW_TC) && (dev->features & NETIF_F_NTUPLE)) {
-		netdev_info(dev, "Disabling n-tuple filters\n");
-		features &= ~NETIF_F_NTUPLE;
-	}
-
-	/* check if tc hw offload is ON */
-	if ((features & NETIF_F_NTUPLE) && (dev->features & NETIF_F_HW_TC)) {
-		netdev_info(dev, "Disabling TC hardware offload\n");
-		features &= ~NETIF_F_HW_TC;
-	}
+	if (features & NETIF_F_HW_VLAN_CTAG_RX)
+		features |= NETIF_F_HW_VLAN_STAG_RX;
+	else
+		features &= ~NETIF_F_HW_VLAN_STAG_RX;
 
 	return features;
 }
@@ -1854,6 +1844,7 @@ static int otx2_set_features(struct net_device *netdev,
 	netdev_features_t changed = features ^ netdev->features;
 	bool ntuple = !!(features & NETIF_F_NTUPLE);
 	struct otx2_nic *pf = netdev_priv(netdev);
+	bool tc = !!(features & NETIF_F_HW_TC);
 
 	if ((changed & NETIF_F_LOOPBACK) && netif_running(netdev))
 		return otx2_cgx_config_loopback(pf,
@@ -1866,12 +1857,42 @@ static int otx2_set_features(struct net_device *netdev,
 	if ((changed & NETIF_F_NTUPLE) && !ntuple)
 		otx2_destroy_ntuple_flows(pf);
 
-	if ((netdev->features & NETIF_F_HW_TC) > (features & NETIF_F_HW_TC) &&
-	    pf->tc_info.num_entries) {
+	if ((changed & NETIF_F_NTUPLE) && ntuple) {
+		if (!pf->flow_cfg->max_flows) {
+			netdev_err(netdev,
+				   "Can't enable NTUPLE, MCAM entries not allocated\n");
+			return -EINVAL;
+		}
+	}
+
+	if ((changed & NETIF_F_HW_TC) && tc) {
+		if (!pf->flow_cfg->max_flows) {
+			netdev_err(netdev,
+				   "Can't enable TC, MCAM entries not allocated\n");
+			return -EINVAL;
+		}
+	}
+
+	if ((changed & NETIF_F_HW_TC) && !tc &&
+	    pf->flow_cfg && pf->flow_cfg->nr_flows) {
 		netdev_err(netdev, "Can't disable TC hardware offload while flows are active\n");
 		return -EBUSY;
 	}
 
+	if ((changed & NETIF_F_NTUPLE) && ntuple &&
+	    (netdev->features & NETIF_F_HW_TC) && !(changed & NETIF_F_HW_TC)) {
+		netdev_err(netdev,
+			   "Can't enable NTUPLE when TC is active, disable TC and retry\n");
+		return -EINVAL;
+	}
+
+	if ((changed & NETIF_F_HW_TC) && tc &&
+	    (netdev->features & NETIF_F_NTUPLE) && !(changed & NETIF_F_NTUPLE)) {
+		netdev_err(netdev,
+			   "Can't enable TC when NTUPLE is active, disable NTUPLE and retry\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -2331,7 +2352,7 @@ static const struct net_device_ops otx2_netdev_ops = {
 	.ndo_set_features	= otx2_set_features,
 	.ndo_tx_timeout		= otx2_tx_timeout,
 	.ndo_get_stats64	= otx2_get_stats64,
-	.ndo_do_ioctl		= otx2_ioctl,
+	.ndo_eth_ioctl		= otx2_ioctl,
 	.ndo_set_vf_mac		= otx2_set_vf_mac,
 	.ndo_set_vf_vlan	= otx2_set_vf_vlan,
 	.ndo_get_vf_config	= otx2_get_vf_config,
@@ -2569,8 +2590,6 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 			       NETIF_F_GSO_UDP_L4);
 	netdev->features |= netdev->hw_features;
 
-	netdev->hw_features |= NETIF_F_LOOPBACK | NETIF_F_RXALL;
-
 	err = otx2_mcam_flow_init(pf);
 	if (err)
 		goto err_ptp_destroy;
@@ -2594,12 +2613,13 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (pf->flags & OTX2_FLAG_TC_FLOWER_SUPPORT)
 		netdev->hw_features |= NETIF_F_HW_TC;
 
+	netdev->hw_features |= NETIF_F_LOOPBACK | NETIF_F_RXALL;
+
 	netdev->gso_max_segs = OTX2_MAX_GSO_SEGS;
 	netdev->watchdog_timeo = OTX2_TX_TIMEOUT;
 
 	netdev->netdev_ops = &otx2_netdev_ops;
 
-	/* MTU range: 64 - 9190 */
 	netdev->min_mtu = OTX2_MIN_MTU;
 	netdev->max_mtu = otx2_get_max_mtu(pf);
 
@@ -2619,6 +2639,10 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_mcam_flow_del;
 
+	err = otx2_register_dl(pf);
+	if (err)
+		goto err_mcam_flow_del;
+
 	/* Initialize SR-IOV resources */
 	err = otx2_sriov_vfcfg_init(pf);
 	if (err)
@@ -2776,6 +2800,7 @@ static void otx2_remove(struct pci_dev *pdev)
 	/* Disable link notifications */
 	otx2_cgx_config_linkevents(pf, false);
 
+	otx2_unregister_dl(pf);
 	unregister_netdev(netdev);
 	otx2_sriov_disable(pf->pdev);
 	otx2_sriov_vfcfg_cleanup(pf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
index 56390a664517..ec9e49985c2c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 PTP support for ethernet driver
+/* Marvell RVU Ethernet driver
+ *
+ * Copyright (C) 2020 Marvell.
  *
- * Copyright (C) 2020 Marvell International Ltd.
  */
 
 #include "otx2_common.h"
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.h
index 706d63a43ae1..6ff284211d7b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.h
@@ -1,5 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Marvell OcteonTx2 PTP support for ethernet driver */
+/* Marvell RVU Ethernet driver
+ *
+ * Copyright (C) 2020 Marvell.
+ *
+ */
 
 #ifndef OTX2_PTP_H
 #define OTX2_PTP_H
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h
index f4fd72ee9a25..1b967eaf948b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h
@@ -1,11 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Marvell OcteonTx2 RVU Ethernet driver
+/* Marvell RVU Ethernet driver
  *
- * Copyright (C) 2020 Marvell International Ltd.
+ * Copyright (C) 2020 Marvell.
  *
- * 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.
  */
 
 #ifndef OTX2_REG_H
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h
index 1f49b3caf5d4..4bbd12ff26e6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h
@@ -1,11 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Marvell OcteonTx2 RVU Ethernet driver
+/* Marvell RVU Ethernet driver
  *
- * Copyright (C) 2020 Marvell International Ltd.
+ * Copyright (C) 2020 Marvell.
  *
- * 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.
  */
 
 #ifndef OTX2_STRUCT_H
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 972b202b9884..626961a41089 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Physcial Function ethernet driver
+/* Marvell RVU Ethernet driver
  *
  * Copyright (C) 2021 Marvell.
+ *
  */
+
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/inetdevice.h>
@@ -52,6 +54,29 @@ struct otx2_tc_flow {
 	bool				is_act_police;
 };
 
+int otx2_tc_alloc_ent_bitmap(struct otx2_nic *nic)
+{
+	struct otx2_tc_info *tc = &nic->tc_info;
+
+	if (!nic->flow_cfg->max_flows || is_otx2_vf(nic->pcifunc))
+		return 0;
+
+	/* Max flows changed, free the existing bitmap */
+	kfree(tc->tc_entries_bitmap);
+
+	tc->tc_entries_bitmap =
+			kcalloc(BITS_TO_LONGS(nic->flow_cfg->max_flows),
+				sizeof(long), GFP_KERNEL);
+	if (!tc->tc_entries_bitmap) {
+		netdev_err(nic->netdev,
+			   "Unable to alloc TC flow entries bitmap\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(otx2_tc_alloc_ent_bitmap);
+
 static void otx2_get_egress_burst_cfg(u32 burst, u32 *burst_exp,
 				      u32 *burst_mantissa)
 {
@@ -485,8 +510,8 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 				   match.key->vlan_priority << 13;
 
 			vlan_tci_mask = match.mask->vlan_id |
-					match.key->vlan_dei << 12 |
-					match.key->vlan_priority << 13;
+					match.mask->vlan_dei << 12 |
+					match.mask->vlan_priority << 13;
 
 			flow_spec->vlan_tci = htons(vlan_tci);
 			flow_mask->vlan_tci = htons(vlan_tci_mask);
@@ -596,6 +621,7 @@ static int otx2_del_mcam_flow_entry(struct otx2_nic *nic, u16 entry)
 static int otx2_tc_del_flow(struct otx2_nic *nic,
 			    struct flow_cls_offload *tc_flow_cmd)
 {
+	struct otx2_flow_config *flow_cfg = nic->flow_cfg;
 	struct otx2_tc_info *tc_info = &nic->tc_info;
 	struct otx2_tc_flow *flow_node;
 	int err;
@@ -638,7 +664,7 @@ static int otx2_tc_del_flow(struct otx2_nic *nic,
 	kfree_rcu(flow_node, rcu);
 
 	clear_bit(flow_node->bitpos, tc_info->tc_entries_bitmap);
-	tc_info->num_entries--;
+	flow_cfg->nr_flows--;
 
 	return 0;
 }
@@ -647,6 +673,7 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 			    struct flow_cls_offload *tc_flow_cmd)
 {
 	struct netlink_ext_ack *extack = tc_flow_cmd->common.extack;
+	struct otx2_flow_config *flow_cfg = nic->flow_cfg;
 	struct otx2_tc_info *tc_info = &nic->tc_info;
 	struct otx2_tc_flow *new_node, *old_node;
 	struct npc_install_flow_req *req, dummy;
@@ -655,9 +682,9 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 	if (!(nic->flags & OTX2_FLAG_TC_FLOWER_SUPPORT))
 		return -ENOMEM;
 
-	if (bitmap_full(tc_info->tc_entries_bitmap, nic->flow_cfg->tc_max_flows)) {
+	if (bitmap_full(tc_info->tc_entries_bitmap, flow_cfg->max_flows)) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "Not enough MCAM space to add the flow");
+				   "Free MCAM entry not available to add the flow");
 		return -ENOMEM;
 	}
 
@@ -695,10 +722,9 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 	memcpy(req, &dummy, sizeof(struct npc_install_flow_req));
 
 	new_node->bitpos = find_first_zero_bit(tc_info->tc_entries_bitmap,
-					       nic->flow_cfg->tc_max_flows);
+					       flow_cfg->max_flows);
 	req->channel = nic->hw.rx_chan_base;
-	req->entry = nic->flow_cfg->flow_ent[nic->flow_cfg->tc_flower_offset +
-				nic->flow_cfg->tc_max_flows - new_node->bitpos];
+	req->entry = flow_cfg->flow_ent[flow_cfg->max_flows - new_node->bitpos - 1];
 	req->intf = NIX_INTF_RX;
 	req->set_cntr = 1;
 	new_node->entry = req->entry;
@@ -723,7 +749,7 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 	}
 
 	set_bit(new_node->bitpos, tc_info->tc_entries_bitmap);
-	tc_info->num_entries++;
+	flow_cfg->nr_flows++;
 
 	return 0;
 
@@ -1008,10 +1034,21 @@ static const struct rhashtable_params tc_flow_ht_params = {
 int otx2_init_tc(struct otx2_nic *nic)
 {
 	struct otx2_tc_info *tc = &nic->tc_info;
+	int err;
 
 	/* Exclude receive queue 0 being used for police action */
 	set_bit(0, &nic->rq_bmap);
 
+	if (!nic->flow_cfg) {
+		netdev_err(nic->netdev,
+			   "Can't init TC, nic->flow_cfg is not setup\n");
+		return -EINVAL;
+	}
+
+	err = otx2_tc_alloc_ent_bitmap(nic);
+	if (err)
+		return err;
+
 	tc->flow_ht_params = tc_flow_ht_params;
 	return rhashtable_init(&tc->flow_table, &tc->flow_ht_params);
 }
@@ -1020,5 +1057,6 @@ void otx2_shutdown_tc(struct otx2_nic *nic)
 {
 	struct otx2_tc_info *tc = &nic->tc_info;
 
+	kfree(tc->tc_entries_bitmap);
 	rhashtable_destroy(&tc->flow_table);
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 22ec03a618b1..f42b1d4e0c67 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -1,11 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Ethernet driver
+/* Marvell RVU Ethernet driver
  *
- * Copyright (C) 2020 Marvell International Ltd.
+ * Copyright (C) 2020 Marvell.
  *
- * 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.
  */
 
 #include <linux/etherdevice.h>
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
index 2f144e2cf436..869de5f59e73 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
@@ -1,11 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Marvell OcteonTx2 RVU Ethernet driver
+/* Marvell RVU Ethernet driver
  *
- * Copyright (C) 2020 Marvell International Ltd.
+ * Copyright (C) 2020 Marvell.
  *
- * 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.
  */
 
 #ifndef OTX2_TXRX_H
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index a8bee5aefec1..03b4ec630432 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -1,5 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Marvell OcteonTx2 RVU Virtual Function ethernet driver */
+/* Marvell RVU Virtual Function ethernet driver
+ *
+ * Copyright (C) 2020 Marvell.
+ *
+ */
 
 #include <linux/etherdevice.h>
 #include <linux/module.h>
@@ -464,6 +468,28 @@ static void otx2vf_reset_task(struct work_struct *work)
 	rtnl_unlock();
 }
 
+static int otx2vf_set_features(struct net_device *netdev,
+			       netdev_features_t features)
+{
+	netdev_features_t changed = features ^ netdev->features;
+	bool ntuple_enabled = !!(features & NETIF_F_NTUPLE);
+	struct otx2_nic *vf = netdev_priv(netdev);
+
+	if (changed & NETIF_F_NTUPLE) {
+		if (!ntuple_enabled) {
+			otx2_mcam_flow_del(vf);
+			return 0;
+		}
+
+		if (!otx2_get_maxflows(vf->flow_cfg)) {
+			netdev_err(netdev,
+				   "Can't enable NTUPLE, MCAM entries not allocated\n");
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
 static const struct net_device_ops otx2vf_netdev_ops = {
 	.ndo_open = otx2vf_open,
 	.ndo_stop = otx2vf_stop,
@@ -471,6 +497,7 @@ static const struct net_device_ops otx2vf_netdev_ops = {
 	.ndo_set_rx_mode = otx2vf_set_rx_mode,
 	.ndo_set_mac_address = otx2_set_mac_address,
 	.ndo_change_mtu = otx2vf_change_mtu,
+	.ndo_set_features = otx2vf_set_features,
 	.ndo_get_stats64 = otx2_get_stats64,
 	.ndo_tx_timeout = otx2_tx_timeout,
 };
@@ -627,12 +654,14 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 				NETIF_F_HW_VLAN_STAG_TX;
 	netdev->features |= netdev->hw_features;
 
+	netdev->hw_features |= NETIF_F_NTUPLE;
+	netdev->hw_features |= NETIF_F_RXALL;
+
 	netdev->gso_max_segs = OTX2_MAX_GSO_SEGS;
 	netdev->watchdog_timeo = OTX2_TX_TIMEOUT;
 
 	netdev->netdev_ops = &otx2vf_netdev_ops;
 
-	/* MTU range: 68 - 9190 */
 	netdev->min_mtu = OTX2_MIN_MTU;
 	netdev->max_mtu = otx2_get_max_mtu(vf);
 
@@ -658,6 +687,14 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	otx2vf_set_ethtool_ops(netdev);
 
+	err = otx2vf_mcam_flow_init(vf);
+	if (err)
+		goto err_unreg_netdev;
+
+	err = otx2_register_dl(vf);
+	if (err)
+		goto err_unreg_netdev;
+
 	/* Enable pause frames by default */
 	vf->flags |= OTX2_FLAG_RX_PAUSE_ENABLED;
 	vf->flags |= OTX2_FLAG_TX_PAUSE_ENABLED;
@@ -695,6 +732,7 @@ static void otx2vf_remove(struct pci_dev *pdev)
 	vf = netdev_priv(netdev);
 
 	cancel_work_sync(&vf->reset_task);
+	otx2_unregister_dl(vf);
 	unregister_netdev(netdev);
 	if (vf->otx2_wq)
 		destroy_workqueue(vf->otx2_wq);
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c
index fa7a0682ad1e..68b442eb6d69 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c
@@ -390,11 +390,12 @@ static const struct devlink_ops prestera_dl_ops = {
 	.trap_drop_counter_get = prestera_drop_counter_get,
 };
 
-struct prestera_switch *prestera_devlink_alloc(void)
+struct prestera_switch *prestera_devlink_alloc(struct prestera_device *dev)
 {
 	struct devlink *dl;
 
-	dl = devlink_alloc(&prestera_dl_ops, sizeof(struct prestera_switch));
+	dl = devlink_alloc(&prestera_dl_ops, sizeof(struct prestera_switch),
+			   dev->dev);
 
 	return devlink_priv(dl);
 }
@@ -411,7 +412,7 @@ int prestera_devlink_register(struct prestera_switch *sw)
 	struct devlink *dl = priv_to_devlink(sw);
 	int err;
 
-	err = devlink_register(dl, sw->dev->dev);
+	err = devlink_register(dl);
 	if (err) {
 		dev_err(prestera_dev(sw), "devlink_register failed: %d\n", err);
 		return err;
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h
index 5d73aa9db897..cc34c3db13a2 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h
+++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h
@@ -6,7 +6,7 @@
 
 #include "prestera.h"
 
-struct prestera_switch *prestera_devlink_alloc(void);
+struct prestera_switch *prestera_devlink_alloc(struct prestera_device *dev);
 void prestera_devlink_free(struct prestera_switch *sw);
 
 int prestera_devlink_register(struct prestera_switch *sw);
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index 226f4ff29f6e..44c670807fb3 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -746,7 +746,8 @@ static int prestera_netdev_port_event(struct net_device *lower,
 	case NETDEV_CHANGEUPPER:
 		if (netif_is_bridge_master(upper)) {
 			if (info->linking)
-				return prestera_bridge_port_join(upper, port);
+				return prestera_bridge_port_join(upper, port,
+								 extack);
 			else
 				prestera_bridge_port_leave(upper, port);
 		} else if (netif_is_lag_master(upper)) {
@@ -904,7 +905,7 @@ int prestera_device_register(struct prestera_device *dev)
 	struct prestera_switch *sw;
 	int err;
 
-	sw = prestera_devlink_alloc();
+	sw = prestera_devlink_alloc(dev);
 	if (!sw)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c
index 9a309169dbae..3ce6ccd0f539 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c
@@ -480,7 +480,8 @@ err_port_flood_set:
 }
 
 int prestera_bridge_port_join(struct net_device *br_dev,
-			      struct prestera_port *port)
+			      struct prestera_port *port,
+			      struct netlink_ext_ack *extack)
 {
 	struct prestera_switchdev *swdev = port->sw->swdev;
 	struct prestera_bridge_port *br_port;
@@ -500,6 +501,11 @@ int prestera_bridge_port_join(struct net_device *br_dev,
 		goto err_brport_create;
 	}
 
+	err = switchdev_bridge_port_offload(br_port->dev, port->dev, NULL,
+					    NULL, NULL, false, extack);
+	if (err)
+		goto err_switchdev_offload;
+
 	if (bridge->vlan_enabled)
 		return 0;
 
@@ -510,6 +516,8 @@ int prestera_bridge_port_join(struct net_device *br_dev,
 	return 0;
 
 err_port_join:
+	switchdev_bridge_port_unoffload(br_port->dev, NULL, NULL, NULL);
+err_switchdev_offload:
 	prestera_bridge_port_put(br_port);
 err_brport_create:
 	prestera_bridge_put(bridge);
@@ -584,6 +592,8 @@ void prestera_bridge_port_leave(struct net_device *br_dev,
 	else
 		prestera_bridge_1d_port_leave(br_port);
 
+	switchdev_bridge_port_unoffload(br_port->dev, NULL, NULL, NULL);
+
 	prestera_hw_port_learning_set(port, false);
 	prestera_hw_port_flood_set(port, BR_FLOOD | BR_MCAST_FLOOD, 0);
 	prestera_port_vid_stp_set(port, PRESTERA_VID_ALL, BR_STATE_FORWARDING);
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h
index a91bc35d235f..0e93fda3d9a5 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h
+++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h
@@ -8,7 +8,8 @@ int prestera_switchdev_init(struct prestera_switch *sw);
 void prestera_switchdev_fini(struct prestera_switch *sw);
 
 int prestera_bridge_port_join(struct net_device *br_dev,
-			      struct prestera_port *port);
+			      struct prestera_port *port,
+			      struct netlink_ext_ack *extack);
 
 void prestera_bridge_port_leave(struct net_device *br_dev,
 				struct prestera_port *port);
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index 9b48ae4bac39..fab53c9b8380 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1377,7 +1377,7 @@ static const struct net_device_ops pxa168_eth_netdev_ops = {
 	.ndo_set_rx_mode	= pxa168_eth_set_rx_mode,
 	.ndo_set_mac_address	= pxa168_eth_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= phy_do_ioctl,
+	.ndo_eth_ioctl		= phy_do_ioctl,
 	.ndo_change_mtu		= pxa168_eth_change_mtu,
 	.ndo_tx_timeout		= pxa168_eth_tx_timeout,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index d4bb27ba1419..051dd3fb5b03 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -615,7 +615,9 @@ static inline u32 skge_usecs2clk(const struct skge_hw *hw, u32 usec)
 }
 
 static int skge_get_coalesce(struct net_device *dev,
-			     struct ethtool_coalesce *ecmd)
+			     struct ethtool_coalesce *ecmd,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct skge_port *skge = netdev_priv(dev);
 	struct skge_hw *hw = skge->hw;
@@ -639,7 +641,9 @@ static int skge_get_coalesce(struct net_device *dev,
 
 /* Note: interrupt timer is per board, but can turn on/off per port */
 static int skge_set_coalesce(struct net_device *dev,
-			     struct ethtool_coalesce *ecmd)
+			     struct ethtool_coalesce *ecmd,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct skge_port *skge = netdev_priv(dev);
 	struct skge_hw *hw = skge->hw;
@@ -3787,7 +3791,7 @@ static const struct net_device_ops skge_netdev_ops = {
 	.ndo_open		= skge_up,
 	.ndo_stop		= skge_down,
 	.ndo_start_xmit		= skge_xmit_frame,
-	.ndo_do_ioctl		= skge_ioctl,
+	.ndo_eth_ioctl		= skge_ioctl,
 	.ndo_get_stats		= skge_get_stats,
 	.ndo_tx_timeout		= skge_tx_timeout,
 	.ndo_change_mtu		= skge_change_mtu,
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 8b8bff59c8fe..e9fc74e54b22 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -4052,7 +4052,9 @@ static int sky2_set_pauseparam(struct net_device *dev,
 }
 
 static int sky2_get_coalesce(struct net_device *dev,
-			     struct ethtool_coalesce *ecmd)
+			     struct ethtool_coalesce *ecmd,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct sky2_port *sky2 = netdev_priv(dev);
 	struct sky2_hw *hw = sky2->hw;
@@ -4087,7 +4089,9 @@ static int sky2_get_coalesce(struct net_device *dev,
 
 /* Note: this affect both ports */
 static int sky2_set_coalesce(struct net_device *dev,
-			     struct ethtool_coalesce *ecmd)
+			     struct ethtool_coalesce *ecmd,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct sky2_port *sky2 = netdev_priv(dev);
 	struct sky2_hw *hw = sky2->hw;
@@ -4693,7 +4697,7 @@ static const struct net_device_ops sky2_netdev_ops[2] = {
 	.ndo_open		= sky2_open,
 	.ndo_stop		= sky2_close,
 	.ndo_start_xmit		= sky2_xmit_frame,
-	.ndo_do_ioctl		= sky2_ioctl,
+	.ndo_eth_ioctl		= sky2_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= sky2_set_mac_address,
 	.ndo_set_rx_mode	= sky2_set_multicast,
@@ -4710,7 +4714,7 @@ static const struct net_device_ops sky2_netdev_ops[2] = {
 	.ndo_open		= sky2_open,
 	.ndo_stop		= sky2_close,
 	.ndo_start_xmit		= sky2_xmit_frame,
-	.ndo_do_ioctl		= sky2_ioctl,
+	.ndo_eth_ioctl		= sky2_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= sky2_set_mac_address,
 	.ndo_set_rx_mode	= sky2_set_multicast,
@@ -4884,7 +4888,7 @@ static int sky2_test_msi(struct sky2_hw *hw)
 /* This driver supports yukon2 chipset only */
 static const char *sky2_name(u8 chipid, char *buf, int sz)
 {
-	const char *name[] = {
+	static const char *const name[] = {
 		"XL",		/* 0xb3 */
 		"EC Ultra", 	/* 0xb4 */
 		"Extreme",	/* 0xb5 */
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 64adfd24e134..398c23cec815 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -2933,7 +2933,7 @@ static const struct net_device_ops mtk_netdev_ops = {
 	.ndo_start_xmit		= mtk_start_xmit,
 	.ndo_set_mac_address	= mtk_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= mtk_do_ioctl,
+	.ndo_eth_ioctl		= mtk_do_ioctl,
 	.ndo_change_mtu		= mtk_change_mtu,
 	.ndo_tx_timeout		= mtk_tx_timeout,
 	.ndo_get_stats64        = mtk_get_stats64,
diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 96d2891f1675..1d5dd2015453 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1162,7 +1162,7 @@ static const struct net_device_ops mtk_star_netdev_ops = {
 	.ndo_start_xmit		= mtk_star_netdev_start_xmit,
 	.ndo_get_stats64	= mtk_star_netdev_get_stats64,
 	.ndo_set_rx_mode	= mtk_star_set_rx_mode,
-	.ndo_do_ioctl		= mtk_star_netdev_ioctl,
+	.ndo_eth_ioctl		= mtk_star_netdev_ioctl,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig
index 400e611ba041..1b4b1f642317 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig
@@ -6,8 +6,8 @@
 config MLX4_EN
 	tristate "Mellanox Technologies 1/10/40Gbit Ethernet support"
 	depends on PCI && NETDEVICES && ETHERNET && INET
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select MLX4_CORE
-	imply PTP_1588_CLOCK
 	help
 	  This driver supports Mellanox Technologies ConnectX Ethernet
 	  devices.
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 3616b77caa0a..ef518b1040f7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -998,7 +998,9 @@ mlx4_en_set_link_ksettings(struct net_device *dev,
 }
 
 static int mlx4_en_get_coalesce(struct net_device *dev,
-			      struct ethtool_coalesce *coal)
+				struct ethtool_coalesce *coal,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
@@ -1020,7 +1022,9 @@ static int mlx4_en_get_coalesce(struct net_device *dev,
 }
 
 static int mlx4_en_set_coalesce(struct net_device *dev,
-			      struct ethtool_coalesce *coal)
+				struct ethtool_coalesce *coal,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 5d0c9c62382d..a2f61a87cef8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2828,7 +2828,7 @@ static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_set_mac_address	= mlx4_en_set_mac,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= mlx4_en_change_mtu,
-	.ndo_do_ioctl		= mlx4_en_ioctl,
+	.ndo_eth_ioctl		= mlx4_en_ioctl,
 	.ndo_tx_timeout		= mlx4_en_tx_timeout,
 	.ndo_vlan_rx_add_vid	= mlx4_en_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= mlx4_en_vlan_rx_kill_vid,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 442991d91c15..7f6d3b82c29b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -991,7 +991,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
 		 * expense of more costly truesize accounting
 		 */
 		priv->frag_info[0].frag_stride = PAGE_SIZE;
-		priv->dma_dir = PCI_DMA_BIDIRECTIONAL;
+		priv->dma_dir = DMA_BIDIRECTIONAL;
 		priv->rx_headroom = XDP_PACKET_HEADROOM;
 		i = 1;
 	} else {
@@ -1021,7 +1021,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
 			buf_size += frag_size;
 			i++;
 		}
-		priv->dma_dir = PCI_DMA_FROMDEVICE;
+		priv->dma_dir = DMA_FROM_DEVICE;
 		priv->rx_headroom = 0;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 31b74bddb7cd..c56b9dba4c71 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -297,12 +297,12 @@ u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 			dma_unmap_single(priv->ddev,
 					 tx_info->map0_dma,
 					 tx_info->map0_byte_count,
-					 PCI_DMA_TODEVICE);
+					 DMA_TO_DEVICE);
 		else
 			dma_unmap_page(priv->ddev,
 				       tx_info->map0_dma,
 				       tx_info->map0_byte_count,
-				       PCI_DMA_TODEVICE);
+				       DMA_TO_DEVICE);
 		/* Optimize the common case when there are no wraparounds */
 		if (likely((void *)tx_desc +
 			   (tx_info->nr_txbb << LOG_TXBB_SIZE) <= end)) {
@@ -311,7 +311,7 @@ u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 				dma_unmap_page(priv->ddev,
 					(dma_addr_t)be64_to_cpu(data->addr),
 					be32_to_cpu(data->byte_count),
-					PCI_DMA_TODEVICE);
+					DMA_TO_DEVICE);
 			}
 		} else {
 			if ((void *)data >= end)
@@ -325,7 +325,7 @@ u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 				dma_unmap_page(priv->ddev,
 					(dma_addr_t)be64_to_cpu(data->addr),
 					be32_to_cpu(data->byte_count),
-					PCI_DMA_TODEVICE);
+					DMA_TO_DEVICE);
 			}
 		}
 	}
@@ -831,7 +831,7 @@ static bool mlx4_en_build_dma_wqe(struct mlx4_en_priv *priv,
 
 		dma = dma_map_single(ddev, skb->data +
 				     lso_header_size, byte_count,
-				     PCI_DMA_TODEVICE);
+				     DMA_TO_DEVICE);
 		if (dma_mapping_error(ddev, dma))
 			goto tx_drop_unmap;
 
@@ -853,7 +853,7 @@ tx_drop_unmap:
 		++data;
 		dma_unmap_page(ddev, (dma_addr_t)be64_to_cpu(data->addr),
 			       be32_to_cpu(data->byte_count),
-			       PCI_DMA_TODEVICE);
+			       DMA_TO_DEVICE);
 	}
 
 	return false;
@@ -1170,7 +1170,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 	tx_info->nr_bytes = max_t(unsigned int, length, ETH_ZLEN);
 
 	dma_sync_single_range_for_device(priv->ddev, dma, frame->page_offset,
-					 length, PCI_DMA_TODEVICE);
+					 length, DMA_TO_DEVICE);
 
 	data->addr = cpu_to_be64(dma + frame->page_offset);
 	dma_wmb();
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 28ac4693da3c..5a6b0fcaf7f8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3806,24 +3806,15 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
 
 	pci_set_master(pdev);
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (err) {
 		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask\n");
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
 			dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting\n");
 			goto err_release_regions;
 		}
 	}
-	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (err) {
-		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit consistent PCI DMA mask\n");
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (err) {
-			dev_err(&pdev->dev, "Can't set consistent PCI DMA mask, aborting\n");
-			goto err_release_regions;
-		}
-	}
 
 	/* Allow large DMA segments, up to the firmware limit of 1 GB */
 	dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024);
@@ -4005,7 +3996,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	printk_once(KERN_INFO "%s", mlx4_version);
 
-	devlink = devlink_alloc(&mlx4_devlink_ops, sizeof(*priv));
+	devlink = devlink_alloc(&mlx4_devlink_ops, sizeof(*priv), &pdev->dev);
 	if (!devlink)
 		return -ENOMEM;
 	priv = devlink_priv(devlink);
@@ -4024,7 +4015,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	mutex_init(&dev->persist->interface_state_mutex);
 	mutex_init(&dev->persist->pci_status_mutex);
 
-	ret = devlink_register(devlink, &pdev->dev);
+	ret = devlink_register(devlink);
 	if (ret)
 		goto err_persist_free;
 	ret = devlink_params_register(devlink, mlx4_devlink_params,
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 427e7a31862c..b149e601f673 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -739,7 +739,7 @@ static void mlx4_cleanup_qp_zones(struct mlx4_dev *dev)
 		int i;
 
 		for (i = 0;
-		     i < sizeof(qp_table->zones_uids)/sizeof(qp_table->zones_uids[0]);
+		     i < ARRAY_SIZE(qp_table->zones_uids);
 		     i++) {
 			struct mlx4_bitmap *bitmap =
 				mlx4_zone_get_bitmap(qp_table->zones,
@@ -917,7 +917,7 @@ int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 {
 	int err;
 	int i;
-	enum mlx4_qp_state states[] = {
+	static const enum mlx4_qp_state states[] = {
 		MLX4_QP_STATE_RST,
 		MLX4_QP_STATE_INIT,
 		MLX4_QP_STATE_RTR,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index e1a5a79e27c7..92056452a9e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -10,7 +10,7 @@ config MLX5_CORE
 	select NET_DEVLINK
 	depends on VXLAN || !VXLAN
 	depends on MLXFW || !MLXFW
-	depends on PTP_1588_CLOCK || !PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	depends on PCI_HYPERV_INTERFACE || !PCI_HYPERV_INTERFACE
 	help
 	  Core driver for low level functionality of the ConnectX-4 and
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index b5072a3a2585..63032cd6efb1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -15,14 +15,15 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o alloc.o port.o mr.o pd.o \
 		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
 		fs_counters.o fs_ft_pool.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
-		lib/devcom.o lib/pci_vsc.o lib/dm.o diag/fs_tracepoint.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 \
 		fw_reset.o qos.o
 
 #
 # Netdev basic
 #
-mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
+mlx5_core-$(CONFIG_MLX5_CORE_EN) += en/rqt.o en/tir.o en/rss.o en/rx_res.o \
+		en/channels.o en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
 		en_selftest.o en/port.o en/monitor_stats.o en/health.o \
 		en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \
@@ -43,19 +44,22 @@ mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en_tc.o en/rep/tc.o en/rep/neigh.o \
 					lib/fs_chains.o en/tc_tun.o \
 					esw/indir_table.o en/tc_tun_encap.o \
 					en/tc_tun_vxlan.o en/tc_tun_gre.o en/tc_tun_geneve.o \
-					en/tc_tun_mplsoudp.o diag/en_tc_tracepoint.o
+					en/tc_tun_mplsoudp.o diag/en_tc_tracepoint.o \
+					en/tc/post_act.o
 mlx5_core-$(CONFIG_MLX5_TC_CT)	     += en/tc_ct.o
+mlx5_core-$(CONFIG_MLX5_TC_SAMPLE)   += en/tc/sample.o
 
 #
 # Core extra
 #
 mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o eswitch_offloads_termtbl.o \
-				      ecpf.o rdma.o esw/legacy.o
+				      ecpf.o rdma.o esw/legacy.o \
+				      esw/devlink_port.o esw/vporttbl.o esw/qos.o
+
 mlx5_core-$(CONFIG_MLX5_ESWITCH)   += esw/acl/helper.o \
 				      esw/acl/egress_lgcy.o esw/acl/egress_ofld.o \
-				      esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o \
-				      esw/devlink_port.o esw/vporttbl.o
-mlx5_core-$(CONFIG_MLX5_TC_SAMPLE) += esw/sample.o
+				      esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o
+
 mlx5_core-$(CONFIG_MLX5_BRIDGE)    += esw/bridge.o en/rep/bridge.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 9d79c5ec31e9..db5dfff585c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -877,7 +877,7 @@ static void cb_timeout_handler(struct work_struct *work)
 	ent->ret = -ETIMEDOUT;
 	mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n",
 		       ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
-	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+	mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true);
 
 out:
 	cmd_ent_put(ent); /* for the cmd_ent_get() took on schedule delayed work */
@@ -994,7 +994,7 @@ static void cmd_work_handler(struct work_struct *work)
 		MLX5_SET(mbox_out, ent->out, status, status);
 		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
 
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+		mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true);
 		return;
 	}
 
@@ -1008,7 +1008,7 @@ static void cmd_work_handler(struct work_struct *work)
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, (ent->ret == -ETIMEDOUT));
+		mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, (ent->ret == -ETIMEDOUT));
 	}
 }
 
@@ -1068,7 +1068,7 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev,
 		       mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
 
 	ent->ret = -ETIMEDOUT;
-	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+	mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true);
 }
 
 static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 360e093874d4..cf97985628ab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -89,7 +89,8 @@ static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq,
 int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 			u32 *in, int inlen, u32 *out, int outlen)
 {
-	int eqn = MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), c_eqn);
+	int eqn = MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context),
+			   c_eqn_or_apu_element);
 	u32 din[MLX5_ST_SZ_DW(destroy_cq_in)] = {};
 	struct mlx5_eq_comp *eq;
 	int err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index def2156e50ee..e8093c4e09d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -53,7 +53,7 @@ static bool is_eth_rep_supported(struct mlx5_core_dev *dev)
 	return true;
 }
 
-static bool is_eth_supported(struct mlx5_core_dev *dev)
+bool mlx5_eth_supported(struct mlx5_core_dev *dev)
 {
 	if (!IS_ENABLED(CONFIG_MLX5_CORE_EN))
 		return false;
@@ -105,7 +105,18 @@ static bool is_eth_supported(struct mlx5_core_dev *dev)
 	return true;
 }
 
-static bool is_vnet_supported(struct mlx5_core_dev *dev)
+static bool is_eth_enabled(struct mlx5_core_dev *dev)
+{
+	union devlink_param_value val;
+	int err;
+
+	err = devlink_param_driverinit_value_get(priv_to_devlink(dev),
+						 DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH,
+						 &val);
+	return err ? false : val.vbool;
+}
+
+bool mlx5_vnet_supported(struct mlx5_core_dev *dev)
 {
 	if (!IS_ENABLED(CONFIG_MLX5_VDPA_NET))
 		return false;
@@ -127,6 +138,17 @@ static bool is_vnet_supported(struct mlx5_core_dev *dev)
 	return true;
 }
 
+static bool is_vnet_enabled(struct mlx5_core_dev *dev)
+{
+	union devlink_param_value val;
+	int err;
+
+	err = devlink_param_driverinit_value_get(priv_to_devlink(dev),
+						 DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET,
+						 &val);
+	return err ? false : val.vbool;
+}
+
 static bool is_ib_rep_supported(struct mlx5_core_dev *dev)
 {
 	if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND))
@@ -170,7 +192,7 @@ static bool is_mp_supported(struct mlx5_core_dev *dev)
 	return true;
 }
 
-static bool is_ib_supported(struct mlx5_core_dev *dev)
+bool mlx5_rdma_supported(struct mlx5_core_dev *dev)
 {
 	if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND))
 		return false;
@@ -187,6 +209,17 @@ static bool is_ib_supported(struct mlx5_core_dev *dev)
 	return true;
 }
 
+static bool is_ib_enabled(struct mlx5_core_dev *dev)
+{
+	union devlink_param_value val;
+	int err;
+
+	err = devlink_param_driverinit_value_get(priv_to_devlink(dev),
+						 DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA,
+						 &val);
+	return err ? false : val.vbool;
+}
+
 enum {
 	MLX5_INTERFACE_PROTOCOL_ETH,
 	MLX5_INTERFACE_PROTOCOL_ETH_REP,
@@ -201,13 +234,17 @@ enum {
 static const struct mlx5_adev_device {
 	const char *suffix;
 	bool (*is_supported)(struct mlx5_core_dev *dev);
+	bool (*is_enabled)(struct mlx5_core_dev *dev);
 } mlx5_adev_devices[] = {
 	[MLX5_INTERFACE_PROTOCOL_VNET] = { .suffix = "vnet",
-					   .is_supported = &is_vnet_supported },
+					   .is_supported = &mlx5_vnet_supported,
+					   .is_enabled = &is_vnet_enabled },
 	[MLX5_INTERFACE_PROTOCOL_IB] = { .suffix = "rdma",
-					 .is_supported = &is_ib_supported },
+					 .is_supported = &mlx5_rdma_supported,
+					 .is_enabled = &is_ib_enabled },
 	[MLX5_INTERFACE_PROTOCOL_ETH] = { .suffix = "eth",
-					  .is_supported = &is_eth_supported },
+					  .is_supported = &mlx5_eth_supported,
+					  .is_enabled = &is_eth_enabled },
 	[MLX5_INTERFACE_PROTOCOL_ETH_REP] = { .suffix = "eth-rep",
 					   .is_supported = &is_eth_rep_supported },
 	[MLX5_INTERFACE_PROTOCOL_IB_REP] = { .suffix = "rdma-rep",
@@ -308,6 +345,14 @@ int mlx5_attach_device(struct mlx5_core_dev *dev)
 		if (!priv->adev[i]) {
 			bool is_supported = false;
 
+			if (mlx5_adev_devices[i].is_enabled) {
+				bool enabled;
+
+				enabled = mlx5_adev_devices[i].is_enabled(dev);
+				if (!enabled)
+					continue;
+			}
+
 			if (mlx5_adev_devices[i].is_supported)
 				is_supported = mlx5_adev_devices[i].is_supported(dev);
 
@@ -360,6 +405,14 @@ void mlx5_detach_device(struct mlx5_core_dev *dev)
 		if (!priv->adev[i])
 			continue;
 
+		if (mlx5_adev_devices[i].is_enabled) {
+			bool enabled;
+
+			enabled = mlx5_adev_devices[i].is_enabled(dev);
+			if (!enabled)
+				goto skip_suspend;
+		}
+
 		adev = &priv->adev[i]->adev;
 		/* Auxiliary driver was unbind manually through sysfs */
 		if (!adev->dev.driver)
@@ -397,7 +450,7 @@ int mlx5_register_device(struct mlx5_core_dev *dev)
 void mlx5_unregister_device(struct mlx5_core_dev *dev)
 {
 	mutex_lock(&mlx5_intf_mutex);
-	dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV;
+	dev->priv.flags = MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV;
 	mlx5_rescan_drivers_locked(dev);
 	mutex_unlock(&mlx5_intf_mutex);
 }
@@ -447,12 +500,21 @@ static void delete_drivers(struct mlx5_core_dev *dev)
 		if (!priv->adev[i])
 			continue;
 
+		if (mlx5_adev_devices[i].is_enabled) {
+			bool enabled;
+
+			enabled = mlx5_adev_devices[i].is_enabled(dev);
+			if (!enabled)
+				goto del_adev;
+		}
+
 		if (mlx5_adev_devices[i].is_supported && !delete_all)
 			is_supported = mlx5_adev_devices[i].is_supported(dev);
 
 		if (is_supported)
 			continue;
 
+del_adev:
 		del_adev(&priv->adev[i]->adev);
 		priv->adev[i] = NULL;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index d791d351b489..e84287ffc7ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -7,6 +7,7 @@
 #include "fw_reset.h"
 #include "fs_core.h"
 #include "eswitch.h"
+#include "esw/qos.h"
 #include "sf/dev/dev.h"
 #include "sf/sf.h"
 
@@ -292,6 +293,13 @@ static const struct devlink_ops mlx5_devlink_ops = {
 	.eswitch_encap_mode_get = mlx5_devlink_eswitch_encap_mode_get,
 	.port_function_hw_addr_get = mlx5_devlink_port_function_hw_addr_get,
 	.port_function_hw_addr_set = mlx5_devlink_port_function_hw_addr_set,
+	.rate_leaf_tx_share_set = mlx5_esw_devlink_rate_leaf_tx_share_set,
+	.rate_leaf_tx_max_set = mlx5_esw_devlink_rate_leaf_tx_max_set,
+	.rate_node_tx_share_set = mlx5_esw_devlink_rate_node_tx_share_set,
+	.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,
 #endif
 #ifdef CONFIG_MLX5_SF_MANAGER
 	.port_new = mlx5_devlink_sf_port_new,
@@ -359,9 +367,10 @@ int mlx5_devlink_traps_get_action(struct mlx5_core_dev *dev, int trap_id,
 	return 0;
 }
 
-struct devlink *mlx5_devlink_alloc(void)
+struct devlink *mlx5_devlink_alloc(struct device *dev)
 {
-	return devlink_alloc(&mlx5_devlink_ops, sizeof(struct mlx5_core_dev));
+	return devlink_alloc(&mlx5_devlink_ops, sizeof(struct mlx5_core_dev),
+			     dev);
 }
 
 void mlx5_devlink_free(struct devlink *devlink)
@@ -595,6 +604,157 @@ static void mlx5_devlink_set_params_init_values(struct devlink *devlink)
 #endif
 }
 
+static const struct devlink_param enable_eth_param =
+	DEVLINK_PARAM_GENERIC(ENABLE_ETH, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, NULL);
+
+static int mlx5_devlink_eth_param_register(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	union devlink_param_value value;
+	int err;
+
+	if (!mlx5_eth_supported(dev))
+		return 0;
+
+	err = devlink_param_register(devlink, &enable_eth_param);
+	if (err)
+		return err;
+
+	value.vbool = true;
+	devlink_param_driverinit_value_set(devlink,
+					   DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH,
+					   value);
+	devlink_param_publish(devlink, &enable_eth_param);
+	return 0;
+}
+
+static void mlx5_devlink_eth_param_unregister(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	if (!mlx5_eth_supported(dev))
+		return;
+
+	devlink_param_unpublish(devlink, &enable_eth_param);
+	devlink_param_unregister(devlink, &enable_eth_param);
+}
+
+static int mlx5_devlink_enable_rdma_validate(struct devlink *devlink, u32 id,
+					     union devlink_param_value val,
+					     struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	bool new_state = val.vbool;
+
+	if (new_state && !mlx5_rdma_supported(dev))
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static const struct devlink_param enable_rdma_param =
+	DEVLINK_PARAM_GENERIC(ENABLE_RDMA, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, mlx5_devlink_enable_rdma_validate);
+
+static int mlx5_devlink_rdma_param_register(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	union devlink_param_value value;
+	int err;
+
+	if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND) || MLX5_ESWITCH_MANAGER(dev))
+		return 0;
+
+	err = devlink_param_register(devlink, &enable_rdma_param);
+	if (err)
+		return err;
+
+	value.vbool = true;
+	devlink_param_driverinit_value_set(devlink,
+					   DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA,
+					   value);
+	devlink_param_publish(devlink, &enable_rdma_param);
+	return 0;
+}
+
+static void mlx5_devlink_rdma_param_unregister(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND) || MLX5_ESWITCH_MANAGER(dev))
+		return;
+
+	devlink_param_unpublish(devlink, &enable_rdma_param);
+	devlink_param_unregister(devlink, &enable_rdma_param);
+}
+
+static const struct devlink_param enable_vnet_param =
+	DEVLINK_PARAM_GENERIC(ENABLE_VNET, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, NULL);
+
+static int mlx5_devlink_vnet_param_register(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	union devlink_param_value value;
+	int err;
+
+	if (!mlx5_vnet_supported(dev))
+		return 0;
+
+	err = devlink_param_register(devlink, &enable_vnet_param);
+	if (err)
+		return err;
+
+	value.vbool = true;
+	devlink_param_driverinit_value_set(devlink,
+					   DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET,
+					   value);
+	devlink_param_publish(devlink, &enable_rdma_param);
+	return 0;
+}
+
+static void mlx5_devlink_vnet_param_unregister(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	if (!mlx5_vnet_supported(dev))
+		return;
+
+	devlink_param_unpublish(devlink, &enable_vnet_param);
+	devlink_param_unregister(devlink, &enable_vnet_param);
+}
+
+static int mlx5_devlink_auxdev_params_register(struct devlink *devlink)
+{
+	int err;
+
+	err = mlx5_devlink_eth_param_register(devlink);
+	if (err)
+		return err;
+
+	err = mlx5_devlink_rdma_param_register(devlink);
+	if (err)
+		goto rdma_err;
+
+	err = mlx5_devlink_vnet_param_register(devlink);
+	if (err)
+		goto vnet_err;
+	return 0;
+
+vnet_err:
+	mlx5_devlink_rdma_param_unregister(devlink);
+rdma_err:
+	mlx5_devlink_eth_param_unregister(devlink);
+	return err;
+}
+
+static void mlx5_devlink_auxdev_params_unregister(struct devlink *devlink)
+{
+	mlx5_devlink_vnet_param_unregister(devlink);
+	mlx5_devlink_rdma_param_unregister(devlink);
+	mlx5_devlink_eth_param_unregister(devlink);
+}
+
 #define MLX5_TRAP_DROP(_id, _group_id)					\
 	DEVLINK_TRAP_GENERIC(DROP, DROP, _id,				\
 			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \
@@ -638,11 +798,11 @@ static void mlx5_devlink_traps_unregister(struct devlink *devlink)
 				       ARRAY_SIZE(mlx5_trap_groups_arr));
 }
 
-int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
+int mlx5_devlink_register(struct devlink *devlink)
 {
 	int err;
 
-	err = devlink_register(devlink, dev);
+	err = devlink_register(devlink);
 	if (err)
 		return err;
 
@@ -653,6 +813,10 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 	mlx5_devlink_set_params_init_values(devlink);
 	devlink_params_publish(devlink);
 
+	err = mlx5_devlink_auxdev_params_register(devlink);
+	if (err)
+		goto auxdev_reg_err;
+
 	err = mlx5_devlink_traps_register(devlink);
 	if (err)
 		goto traps_reg_err;
@@ -660,6 +824,8 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 	return 0;
 
 traps_reg_err:
+	mlx5_devlink_auxdev_params_unregister(devlink);
+auxdev_reg_err:
 	devlink_params_unregister(devlink, mlx5_devlink_params,
 				  ARRAY_SIZE(mlx5_devlink_params));
 params_reg_err:
@@ -670,6 +836,8 @@ params_reg_err:
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
 	mlx5_devlink_traps_unregister(devlink);
+	mlx5_devlink_auxdev_params_unregister(devlink);
+	devlink_params_unpublish(devlink);
 	devlink_params_unregister(devlink, mlx5_devlink_params,
 				  ARRAY_SIZE(mlx5_devlink_params));
 	devlink_unregister(devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
index 7318d44b774b..30bf4882779b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
@@ -31,9 +31,9 @@ int mlx5_devlink_trap_get_num_active(struct mlx5_core_dev *dev);
 int mlx5_devlink_traps_get_action(struct mlx5_core_dev *dev, int trap_id,
 				  enum devlink_trap_action *action);
 
-struct devlink *mlx5_devlink_alloc(void);
+struct devlink *mlx5_devlink_alloc(struct device *dev);
 void mlx5_devlink_free(struct devlink *devlink);
-int mlx5_devlink_register(struct devlink *devlink, struct device *dev);
+int mlx5_devlink_register(struct devlink *devlink);
 void mlx5_devlink_unregister(struct devlink *devlink);
 
 #endif /* __MLX5_DEVLINK_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index b1b51bbba054..669a75f3537a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -58,6 +58,7 @@
 #include "en/qos.h"
 #include "lib/hv_vhca.h"
 #include "lib/clock.h"
+#include "en/rx_res.h"
 
 extern const struct net_device_ops mlx5e_netdev_ops;
 struct page_pool;
@@ -65,14 +66,13 @@ struct page_pool;
 #define MLX5E_METADATA_ETHER_TYPE (0x8CE4)
 #define MLX5E_METADATA_ETHER_LEN 8
 
-#define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v)
-
 #define MLX5E_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
 
 #define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu))
 #define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu))
 
 #define MLX5E_MAX_NUM_TC	8
+#define MLX5E_MAX_NUM_MQPRIO_CH_TC TC_QOPT_MAX_QUEUE
 
 #define MLX5_RX_HEADROOM NET_SKB_PAD
 #define MLX5_SKB_FRAG_SZ(len)	(SKB_DATA_ALIGN(len) +	\
@@ -126,7 +126,6 @@ struct page_pool;
 
 #define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW            0x2
 
-#define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (64 * 1024)
 #define MLX5E_DEFAULT_LRO_TIMEOUT                       32
 #define MLX5E_LRO_TIMEOUT_ARR_SIZE                      4
 
@@ -139,8 +138,6 @@ struct page_pool;
 #define MLX5E_PARAMS_DEFAULT_MIN_RX_WQES                0x80
 #define MLX5E_PARAMS_DEFAULT_MIN_RX_WQES_MPW            0x2
 
-#define MLX5E_LOG_INDIR_RQT_SIZE       0x8
-#define MLX5E_INDIR_RQT_SIZE           BIT(MLX5E_LOG_INDIR_RQT_SIZE)
 #define MLX5E_MIN_NUM_CHANNELS         0x1
 #define MLX5E_MAX_NUM_CHANNELS         (MLX5E_INDIR_RQT_SIZE / 2)
 #define MLX5E_MAX_NUM_SQS              (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
@@ -252,7 +249,10 @@ struct mlx5e_params {
 	u8  rq_wq_type;
 	u8  log_rq_mtu_frames;
 	u16 num_channels;
-	u8  num_tc;
+	struct {
+		u16 mode;
+		u8 num_tc;
+	} mqprio;
 	bool rx_cqe_compress_def;
 	bool tunneled_offload_en;
 	struct dim_cq_moder rx_cq_moderation;
@@ -272,6 +272,12 @@ struct mlx5e_params {
 	bool ptp_rx;
 };
 
+static inline u8 mlx5e_get_dcb_num_tc(struct mlx5e_params *params)
+{
+	return params->mqprio.mode == TC_MQPRIO_MODE_DCB ?
+		params->mqprio.num_tc : 1;
+}
+
 enum {
 	MLX5E_RQ_STATE_ENABLED,
 	MLX5E_RQ_STATE_RECOVERING,
@@ -745,29 +751,11 @@ enum {
 	MLX5E_STATE_XDP_ACTIVE,
 };
 
-struct mlx5e_rqt {
-	u32              rqtn;
-	bool		 enabled;
-};
-
-struct mlx5e_tir {
-	u32		  tirn;
-	struct mlx5e_rqt  rqt;
-	struct list_head  list;
-};
-
 enum {
 	MLX5E_TC_PRIO = 0,
 	MLX5E_NIC_PRIO
 };
 
-struct mlx5e_rss_params {
-	u32	indirection_rqt[MLX5E_INDIR_RQT_SIZE];
-	u32	rx_hash_fields[MLX5E_NUM_INDIR_TIRS];
-	u8	toeplitz_hash_key[40];
-	u8	hfunc;
-};
-
 struct mlx5e_modify_sq_param {
 	int curr_state;
 	int next_state;
@@ -837,13 +825,7 @@ struct mlx5e_priv {
 
 	struct mlx5e_channels      channels;
 	u32                        tisn[MLX5_MAX_PORTS][MLX5E_MAX_NUM_TC];
-	struct mlx5e_rqt           indir_rqt;
-	struct mlx5e_tir           indir_tir[MLX5E_NUM_INDIR_TIRS];
-	struct mlx5e_tir           inner_indir_tir[MLX5E_NUM_INDIR_TIRS];
-	struct mlx5e_tir           direct_tir[MLX5E_MAX_NUM_CHANNELS];
-	struct mlx5e_tir           xsk_tir[MLX5E_MAX_NUM_CHANNELS];
-	struct mlx5e_tir           ptp_tir;
-	struct mlx5e_rss_params    rss_params;
+	struct mlx5e_rx_res       *rx_res;
 	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
 
 	struct mlx5e_flow_steering fs;
@@ -948,25 +930,6 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
 			   u16 vid);
 void mlx5e_timestamp_init(struct mlx5e_priv *priv);
 
-struct mlx5e_redirect_rqt_param {
-	bool is_rss;
-	union {
-		u32 rqn; /* Direct RQN (Non-RSS) */
-		struct {
-			u8 hfunc;
-			struct mlx5e_channels *channels;
-		} rss; /* RSS data */
-	};
-};
-
-int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
-		       struct mlx5e_redirect_rqt_param rrp);
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params,
-				    const struct mlx5e_tirc_config *ttconfig,
-				    void *tirc, bool inner);
-void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in);
-struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt);
-
 struct mlx5e_xsk_param;
 
 struct mlx5e_rq_param;
@@ -1028,9 +991,6 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv);
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv);
 int mlx5e_ptp_rx_manage_fs_ctx(struct mlx5e_priv *priv, void *ctx);
 
-void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len,
-				   int num_channels);
-
 int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state);
 void mlx5e_activate_rq(struct mlx5e_rq *rq);
 void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
@@ -1065,10 +1025,6 @@ static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev)
 
 extern const struct ethtool_ops mlx5e_ethtool_ops;
 
-int mlx5e_create_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir,
-		     u32 *in);
-void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
-		       struct mlx5e_tir *tir);
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
 int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
@@ -1084,17 +1040,6 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq);
 int mlx5e_init_di_list(struct mlx5e_rq *rq, int wq_sz, int node);
 void mlx5e_free_di_list(struct mlx5e_rq *rq);
 
-int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv);
-
-int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
-void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv);
-
-int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n);
-void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n);
-int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n);
-void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n);
-void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
-
 int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn);
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
 
@@ -1106,7 +1051,6 @@ int mlx5e_close(struct net_device *netdev);
 int mlx5e_open(struct net_device *netdev);
 
 void mlx5e_queue_update_stats(struct mlx5e_priv *priv);
-int mlx5e_bits_invert(unsigned long a, int size);
 
 int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv);
 int mlx5e_set_dev_port_mtu_ctx(struct mlx5e_priv *priv, void *context);
@@ -1183,8 +1127,6 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv,
 void mlx5e_netdev_attach_nic_profile(struct mlx5e_priv *priv);
 void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv);
 void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu);
-void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
-			    u16 num_channels);
 void mlx5e_rx_dim_work(struct work_struct *work);
 void mlx5e_tx_dim_work(struct work_struct *work);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
new file mode 100644
index 000000000000..e7c14c0de0a7
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */
+
+#include "channels.h"
+#include "en.h"
+#include "en/ptp.h"
+
+unsigned int mlx5e_channels_get_num(struct mlx5e_channels *chs)
+{
+	return chs->num;
+}
+
+void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn)
+{
+	struct mlx5e_channel *c;
+
+	WARN_ON(ix >= mlx5e_channels_get_num(chs));
+	c = chs->c[ix];
+
+	*rqn = c->rq.rqn;
+}
+
+bool mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn)
+{
+	struct mlx5e_channel *c;
+
+	WARN_ON(ix >= mlx5e_channels_get_num(chs));
+	c = chs->c[ix];
+
+	if (!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+		return false;
+
+	*rqn = c->xskrq.rqn;
+	return true;
+}
+
+bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn)
+{
+	struct mlx5e_ptp *c = chs->ptp;
+
+	if (!c || !test_bit(MLX5E_PTP_STATE_RX, c->state))
+		return false;
+
+	*rqn = c->rq.rqn;
+	return true;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
new file mode 100644
index 000000000000..ca00cbc827cb
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */
+
+#ifndef __MLX5_EN_CHANNELS_H__
+#define __MLX5_EN_CHANNELS_H__
+
+#include <linux/kernel.h>
+
+struct mlx5e_channels;
+
+unsigned int mlx5e_channels_get_num(struct mlx5e_channels *chs);
+void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn);
+bool mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn);
+bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn);
+
+#endif /* __MLX5_EN_CHANNELS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
index bc33eaada3b9..86e079310ac3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
@@ -55,19 +55,15 @@ void mlx5e_devlink_port_unregister(struct mlx5e_priv *priv)
 {
 	struct devlink_port *dl_port = mlx5e_devlink_get_dl_port(priv);
 
-	if (dl_port->registered)
-		devlink_port_unregister(dl_port);
+	devlink_port_unregister(dl_port);
 }
 
 struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct devlink_port *port;
 
 	if (!netif_device_present(dev))
 		return NULL;
-	port = mlx5e_devlink_get_dl_port(priv);
-	if (port->registered)
-		return port;
-	return NULL;
+
+	return mlx5e_devlink_get_dl_port(priv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 1d5ce07b83f4..41684a6c44e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -5,6 +5,9 @@
 #define __MLX5E_FLOW_STEER_H__
 
 #include "mod_hdr.h"
+#include "lib/fs_ttc.h"
+
+struct mlx5e_post_act;
 
 enum {
 	MLX5E_TC_FT_LEVEL = 0,
@@ -18,6 +21,7 @@ struct mlx5e_tc_table {
 	struct mutex			t_lock;
 	struct mlx5_flow_table		*t;
 	struct mlx5_fs_chains           *chains;
+	struct mlx5e_post_act		*post_act;
 
 	struct rhashtable               ht;
 
@@ -67,27 +71,7 @@ struct mlx5e_l2_table {
 	bool                       promisc_enabled;
 };
 
-enum mlx5e_traffic_types {
-	MLX5E_TT_IPV4_TCP,
-	MLX5E_TT_IPV6_TCP,
-	MLX5E_TT_IPV4_UDP,
-	MLX5E_TT_IPV6_UDP,
-	MLX5E_TT_IPV4_IPSEC_AH,
-	MLX5E_TT_IPV6_IPSEC_AH,
-	MLX5E_TT_IPV4_IPSEC_ESP,
-	MLX5E_TT_IPV6_IPSEC_ESP,
-	MLX5E_TT_IPV4,
-	MLX5E_TT_IPV6,
-	MLX5E_TT_ANY,
-	MLX5E_NUM_TT,
-	MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY,
-};
-
-struct mlx5e_tirc_config {
-	u8 l3_prot_type;
-	u8 l4_prot_type;
-	u32 rx_hash_fields;
-};
+#define MLX5E_NUM_INDIR_TIRS (MLX5_NUM_TT - 1)
 
 #define MLX5_HASH_IP		(MLX5_HASH_FIELD_SEL_SRC_IP   |\
 				 MLX5_HASH_FIELD_SEL_DST_IP)
@@ -99,30 +83,6 @@ struct mlx5e_tirc_config {
 				 MLX5_HASH_FIELD_SEL_DST_IP   |\
 				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
 
-enum mlx5e_tunnel_types {
-	MLX5E_TT_IPV4_GRE,
-	MLX5E_TT_IPV6_GRE,
-	MLX5E_TT_IPV4_IPIP,
-	MLX5E_TT_IPV6_IPIP,
-	MLX5E_TT_IPV4_IPV6,
-	MLX5E_TT_IPV6_IPV6,
-	MLX5E_NUM_TUNNEL_TT,
-};
-
-bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev);
-
-struct mlx5e_ttc_rule {
-	struct mlx5_flow_handle *rule;
-	struct mlx5_flow_destination default_dest;
-};
-
-/* L3/L4 traffic type classifier */
-struct mlx5e_ttc_table {
-	struct mlx5e_flow_table ft;
-	struct mlx5e_ttc_rule rules[MLX5E_NUM_TT];
-	struct mlx5_flow_handle *tunnel_rules[MLX5E_NUM_TUNNEL_TT];
-};
-
 /* NIC prio FTS */
 enum {
 	MLX5E_PROMISC_FT_LEVEL,
@@ -144,21 +104,7 @@ enum {
 #endif
 };
 
-#define MLX5E_TTC_NUM_GROUPS	3
-#define MLX5E_TTC_GROUP1_SIZE	(BIT(3) + MLX5E_NUM_TUNNEL_TT)
-#define MLX5E_TTC_GROUP2_SIZE	 BIT(1)
-#define MLX5E_TTC_GROUP3_SIZE	 BIT(0)
-#define MLX5E_TTC_TABLE_SIZE	(MLX5E_TTC_GROUP1_SIZE +\
-				 MLX5E_TTC_GROUP2_SIZE +\
-				 MLX5E_TTC_GROUP3_SIZE)
-
-#define MLX5E_INNER_TTC_NUM_GROUPS	3
-#define MLX5E_INNER_TTC_GROUP1_SIZE	BIT(3)
-#define MLX5E_INNER_TTC_GROUP2_SIZE	BIT(1)
-#define MLX5E_INNER_TTC_GROUP3_SIZE	BIT(0)
-#define MLX5E_INNER_TTC_TABLE_SIZE	(MLX5E_INNER_TTC_GROUP1_SIZE +\
-					 MLX5E_INNER_TTC_GROUP2_SIZE +\
-					 MLX5E_INNER_TTC_GROUP3_SIZE)
+struct mlx5e_priv;
 
 #ifdef CONFIG_MLX5_EN_RXNFC
 
@@ -226,8 +172,8 @@ struct mlx5e_flow_steering {
 	struct mlx5e_promisc_table      promisc;
 	struct mlx5e_vlan_table         *vlan;
 	struct mlx5e_l2_table           l2;
-	struct mlx5e_ttc_table          ttc;
-	struct mlx5e_ttc_table          inner_ttc;
+	struct mlx5_ttc_table           *ttc;
+	struct mlx5_ttc_table           *inner_ttc;
 #ifdef CONFIG_MLX5_EN_ARFS
 	struct mlx5e_arfs_tables       *arfs;
 #endif
@@ -239,33 +185,13 @@ struct mlx5e_flow_steering {
 	struct mlx5e_ptp_fs            *ptp_fs;
 };
 
-struct ttc_params {
-	struct mlx5_flow_table_attr ft_attr;
-	u32 any_tt_tirn;
-	u32 indir_tirn[MLX5E_NUM_INDIR_TIRS];
-	struct mlx5e_ttc_table *inner_ttc;
-};
-
-void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params);
-void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params);
-void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params);
-
-int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
-			   struct mlx5e_ttc_table *ttc);
-void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv,
-			     struct mlx5e_ttc_table *ttc);
+void mlx5e_set_ttc_params(struct mlx5e_priv *priv,
+			  struct ttc_params *ttc_params, bool tunnel);
 
-int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
-				 struct mlx5e_ttc_table *ttc);
-void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv,
-				   struct mlx5e_ttc_table *ttc);
+void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv);
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv);
 
 void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
-int mlx5e_ttc_fwd_dest(struct mlx5e_priv *priv, enum mlx5e_traffic_types type,
-		       struct mlx5_flow_destination *new_dest);
-struct mlx5_flow_destination
-mlx5e_ttc_get_default_dest(struct mlx5e_priv *priv, enum mlx5e_traffic_types type);
-int mlx5e_ttc_fwd_default_dest(struct mlx5e_priv *priv, enum mlx5e_traffic_types type);
 
 void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv);
 void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
@@ -273,7 +199,6 @@ void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
 int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
 void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
 
-u8 mlx5e_get_proto_by_tunnel_type(enum mlx5e_tunnel_types tt);
 int mlx5e_add_vlan_trap(struct mlx5e_priv *priv, int  trap_id, int tir_num);
 void mlx5e_remove_vlan_trap(struct mlx5e_priv *priv);
 int mlx5e_add_mac_trap(struct mlx5e_priv *priv, int  trap_id, int tir_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
index 909faa6c89d7..7aa25a5e29d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
@@ -33,22 +33,22 @@ static char *fs_udp_type2str(enum fs_udp_type i)
 	}
 }
 
-static enum mlx5e_traffic_types fs_udp2tt(enum fs_udp_type i)
+static enum mlx5_traffic_types fs_udp2tt(enum fs_udp_type i)
 {
 	switch (i) {
 	case FS_IPV4_UDP:
-		return MLX5E_TT_IPV4_UDP;
+		return MLX5_TT_IPV4_UDP;
 	default: /* FS_IPV6_UDP */
-		return MLX5E_TT_IPV6_UDP;
+		return MLX5_TT_IPV6_UDP;
 	}
 }
 
-static enum fs_udp_type tt2fs_udp(enum mlx5e_traffic_types i)
+static enum fs_udp_type tt2fs_udp(enum mlx5_traffic_types i)
 {
 	switch (i) {
-	case MLX5E_TT_IPV4_UDP:
+	case MLX5_TT_IPV4_UDP:
 		return FS_IPV4_UDP;
-	case MLX5E_TT_IPV6_UDP:
+	case MLX5_TT_IPV6_UDP:
 		return FS_IPV6_UDP;
 	default:
 		return FS_UDP_NUM_TYPES;
@@ -75,7 +75,7 @@ static void fs_udp_set_dport_flow(struct mlx5_flow_spec *spec, enum fs_udp_type
 
 struct mlx5_flow_handle *
 mlx5e_fs_tt_redirect_udp_add_rule(struct mlx5e_priv *priv,
-				  enum mlx5e_traffic_types ttc_type,
+				  enum mlx5_traffic_types ttc_type,
 				  u32 tir_num, u16 d_port)
 {
 	enum fs_udp_type type = tt2fs_udp(ttc_type);
@@ -124,7 +124,7 @@ static int fs_udp_add_default_rule(struct mlx5e_priv *priv, enum fs_udp_type typ
 	fs_udp = priv->fs.udp;
 	fs_udp_t = &fs_udp->tables[type];
 
-	dest = mlx5e_ttc_get_default_dest(priv, fs_udp2tt(type));
+	dest = mlx5_ttc_get_default_dest(priv->fs.ttc, fs_udp2tt(type));
 	rule = mlx5_add_flow_rules(fs_udp_t->t, NULL, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -259,7 +259,7 @@ static int fs_udp_disable(struct mlx5e_priv *priv)
 
 	for (i = 0; i < FS_UDP_NUM_TYPES; i++) {
 		/* Modify ttc rules destination to point back to the indir TIRs */
-		err = mlx5e_ttc_fwd_default_dest(priv, fs_udp2tt(i));
+		err = mlx5_ttc_fwd_default_dest(priv->fs.ttc, fs_udp2tt(i));
 		if (err) {
 			netdev_err(priv->netdev,
 				   "%s: modify ttc[%d] default destination failed, err(%d)\n",
@@ -281,7 +281,7 @@ static int fs_udp_enable(struct mlx5e_priv *priv)
 		dest.ft = priv->fs.udp->tables[i].t;
 
 		/* Modify ttc rules destination to point on the accel_fs FTs */
-		err = mlx5e_ttc_fwd_dest(priv, fs_udp2tt(i), &dest);
+		err = mlx5_ttc_fwd_dest(priv->fs.ttc, fs_udp2tt(i), &dest);
 		if (err) {
 			netdev_err(priv->netdev,
 				   "%s: modify ttc[%d] destination to accel failed, err(%d)\n",
@@ -401,7 +401,7 @@ static int fs_any_add_default_rule(struct mlx5e_priv *priv)
 	fs_any = priv->fs.any;
 	fs_any_t = &fs_any->table;
 
-	dest = mlx5e_ttc_get_default_dest(priv, MLX5E_TT_ANY);
+	dest = mlx5_ttc_get_default_dest(priv->fs.ttc, MLX5_TT_ANY);
 	rule = mlx5_add_flow_rules(fs_any_t->t, NULL, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -514,11 +514,11 @@ static int fs_any_disable(struct mlx5e_priv *priv)
 	int err;
 
 	/* Modify ttc rules destination to point back to the indir TIRs */
-	err = mlx5e_ttc_fwd_default_dest(priv, MLX5E_TT_ANY);
+	err = mlx5_ttc_fwd_default_dest(priv->fs.ttc, MLX5_TT_ANY);
 	if (err) {
 		netdev_err(priv->netdev,
 			   "%s: modify ttc[%d] default destination failed, err(%d)\n",
-			   __func__, MLX5E_TT_ANY, err);
+			   __func__, MLX5_TT_ANY, err);
 		return err;
 	}
 	return 0;
@@ -533,11 +533,11 @@ static int fs_any_enable(struct mlx5e_priv *priv)
 	dest.ft = priv->fs.any->table.t;
 
 	/* Modify ttc rules destination to point on the accel_fs FTs */
-	err = mlx5e_ttc_fwd_dest(priv, MLX5E_TT_ANY, &dest);
+	err = mlx5_ttc_fwd_dest(priv->fs.ttc, MLX5_TT_ANY, &dest);
 	if (err) {
 		netdev_err(priv->netdev,
 			   "%s: modify ttc[%d] destination to accel failed, err(%d)\n",
-			   __func__, MLX5E_TT_ANY, err);
+			   __func__, MLX5_TT_ANY, err);
 		return err;
 	}
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.h
index 8385df24eb99..7a70c4f38fda 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.h
@@ -12,7 +12,7 @@ void mlx5e_fs_tt_redirect_del_rule(struct mlx5_flow_handle *rule);
 /* UDP traffic type redirect */
 struct mlx5_flow_handle *
 mlx5e_fs_tt_redirect_udp_add_rule(struct mlx5e_priv *priv,
-				  enum mlx5e_traffic_types ttc_type,
+				  enum mlx5_traffic_types ttc_type,
 				  u32 tir_num, u16 d_port);
 void mlx5e_fs_tt_redirect_udp_destroy(struct mlx5e_priv *priv);
 int mlx5e_fs_tt_redirect_udp_create(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c
index ea321e528749..4e72ca8070e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c
@@ -5,11 +5,15 @@
 #include <linux/slab.h>
 #include <linux/xarray.h>
 #include <linux/hashtable.h>
+#include <linux/refcount.h>
 
 #include "mapping.h"
 
 #define MAPPING_GRACE_PERIOD 2000
 
+static LIST_HEAD(shared_ctx_list);
+static DEFINE_MUTEX(shared_ctx_lock);
+
 struct mapping_ctx {
 	struct xarray xarray;
 	DECLARE_HASHTABLE(ht, 8);
@@ -20,6 +24,10 @@ struct mapping_ctx {
 	struct delayed_work dwork;
 	struct list_head pending_list;
 	spinlock_t pending_list_lock; /* Guards pending list */
+	u64 id;
+	u8 type;
+	struct list_head list;
+	refcount_t refcount;
 };
 
 struct mapping_item {
@@ -205,11 +213,48 @@ mapping_create(size_t data_size, u32 max_id, bool delayed_removal)
 	mutex_init(&ctx->lock);
 	xa_init_flags(&ctx->xarray, XA_FLAGS_ALLOC1);
 
+	refcount_set(&ctx->refcount, 1);
+	INIT_LIST_HEAD(&ctx->list);
+
+	return ctx;
+}
+
+struct mapping_ctx *
+mapping_create_for_id(u64 id, u8 type, size_t data_size, u32 max_id, bool delayed_removal)
+{
+	struct mapping_ctx *ctx;
+
+	mutex_lock(&shared_ctx_lock);
+	list_for_each_entry(ctx, &shared_ctx_list, list) {
+		if (ctx->id == id && ctx->type == type) {
+			if (refcount_inc_not_zero(&ctx->refcount))
+				goto unlock;
+			break;
+		}
+	}
+
+	ctx = mapping_create(data_size, max_id, delayed_removal);
+	if (IS_ERR(ctx))
+		goto unlock;
+
+	ctx->id = id;
+	ctx->type = type;
+	list_add(&ctx->list, &shared_ctx_list);
+
+unlock:
+	mutex_unlock(&shared_ctx_lock);
 	return ctx;
 }
 
 void mapping_destroy(struct mapping_ctx *ctx)
 {
+	if (!refcount_dec_and_test(&ctx->refcount))
+		return;
+
+	mutex_lock(&shared_ctx_lock);
+	list_del(&ctx->list);
+	mutex_unlock(&shared_ctx_lock);
+
 	mapping_flush_work(ctx);
 	xa_destroy(&ctx->xarray);
 	mutex_destroy(&ctx->lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h
index 285525cc5470..4e2119f0f4c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h
@@ -24,4 +24,9 @@ struct mapping_ctx *mapping_create(size_t data_size, u32 max_id,
 				   bool delayed_removal);
 void mapping_destroy(struct mapping_ctx *ctx);
 
+/* adds mapping with an id or get an existing mapping with the same id
+ */
+struct mapping_ctx *
+mapping_create_for_id(u64 id, u8 type, size_t data_size, u32 max_id, bool delayed_removal);
+
 #endif /* __MLX5_MAPPING_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 2cbf18c967f7..3cbb596821e8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -167,6 +167,18 @@ u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
 	return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0;
 }
 
+struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params)
+{
+	struct mlx5e_lro_param lro_param;
+
+	lro_param = (struct mlx5e_lro_param) {
+		.enabled = params->lro_en,
+		.timeout = params->lro_timeout,
+	};
+
+	return lro_param;
+}
+
 u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
 {
 	bool is_mpwqe = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index e9593f5f0661..879ad46d754e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -11,6 +11,11 @@ struct mlx5e_xsk_param {
 	u16 chunk_size;
 };
 
+struct mlx5e_lro_param {
+	bool enabled;
+	u32 timeout;
+};
+
 struct mlx5e_cq_param {
 	u32                        cqc[MLX5_ST_SZ_DW(cqc)];
 	struct mlx5_wq_param       wq;
@@ -120,6 +125,7 @@ u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
 u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
 			  struct mlx5e_params *params,
 			  struct mlx5e_xsk_param *xsk);
+struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params);
 
 /* Build queue parameters */
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index efef4adce086..ee688dec67a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -326,13 +326,14 @@ static int mlx5e_ptp_open_txqsqs(struct mlx5e_ptp *c,
 				 struct mlx5e_ptp_params *cparams)
 {
 	struct mlx5e_params *params = &cparams->params;
+	u8 num_tc = mlx5e_get_dcb_num_tc(params);
 	int ix_base;
 	int err;
 	int tc;
 
-	ix_base = params->num_tc * params->num_channels;
+	ix_base = num_tc * params->num_channels;
 
-	for (tc = 0; tc < params->num_tc; tc++) {
+	for (tc = 0; tc < num_tc; tc++) {
 		int txq_ix = ix_base + tc;
 
 		err = mlx5e_ptp_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix,
@@ -365,9 +366,12 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c,
 	struct mlx5e_create_cq_param ccp = {};
 	struct dim_cq_moder ptp_moder = {};
 	struct mlx5e_cq_param *cq_param;
+	u8 num_tc;
 	int err;
 	int tc;
 
+	num_tc = mlx5e_get_dcb_num_tc(params);
+
 	ccp.node     = dev_to_node(mlx5_core_dma_dev(c->mdev));
 	ccp.ch_stats = c->stats;
 	ccp.napi     = &c->napi;
@@ -375,7 +379,7 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c,
 
 	cq_param = &cparams->txq_sq_param.cqp;
 
-	for (tc = 0; tc < params->num_tc; tc++) {
+	for (tc = 0; tc < num_tc; tc++) {
 		struct mlx5e_cq *cq = &c->ptpsq[tc].txqsq.cq;
 
 		err = mlx5e_open_cq(c->priv, ptp_moder, cq_param, &ccp, cq);
@@ -383,7 +387,7 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c,
 			goto out_err_txqsq_cq;
 	}
 
-	for (tc = 0; tc < params->num_tc; tc++) {
+	for (tc = 0; tc < num_tc; tc++) {
 		struct mlx5e_cq *cq = &c->ptpsq[tc].ts_cq;
 		struct mlx5e_ptpsq *ptpsq = &c->ptpsq[tc];
 
@@ -399,7 +403,7 @@ static int mlx5e_ptp_open_tx_cqs(struct mlx5e_ptp *c,
 out_err_ts_cq:
 	for (--tc; tc >= 0; tc--)
 		mlx5e_close_cq(&c->ptpsq[tc].ts_cq);
-	tc = params->num_tc;
+	tc = num_tc;
 out_err_txqsq_cq:
 	for (--tc; tc >= 0; tc--)
 		mlx5e_close_cq(&c->ptpsq[tc].txqsq.cq);
@@ -475,7 +479,7 @@ static void mlx5e_ptp_build_params(struct mlx5e_ptp *c,
 	params->num_channels = orig->num_channels;
 	params->hard_mtu = orig->hard_mtu;
 	params->sw_mtu = orig->sw_mtu;
-	params->num_tc = orig->num_tc;
+	params->mqprio = orig->mqprio;
 
 	/* SQ */
 	if (test_bit(MLX5E_PTP_STATE_TX, c->state)) {
@@ -605,9 +609,9 @@ static void mlx5e_ptp_rx_unset_fs(struct mlx5e_priv *priv)
 
 static int mlx5e_ptp_rx_set_fs(struct mlx5e_priv *priv)
 {
+	u32 tirn = mlx5e_rx_res_get_tirn_ptp(priv->rx_res);
 	struct mlx5e_ptp_fs *ptp_fs = priv->fs.ptp_fs;
 	struct mlx5_flow_handle *rule;
-	u32 tirn = priv->ptp_tir.tirn;
 	int err;
 
 	if (ptp_fs->valid)
@@ -617,7 +621,7 @@ static int mlx5e_ptp_rx_set_fs(struct mlx5e_priv *priv)
 	if (err)
 		goto out_free;
 
-	rule = mlx5e_fs_tt_redirect_udp_add_rule(priv, MLX5E_TT_IPV4_UDP,
+	rule = mlx5e_fs_tt_redirect_udp_add_rule(priv, MLX5_TT_IPV4_UDP,
 						 tirn, PTP_EV_PORT);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -625,7 +629,7 @@ static int mlx5e_ptp_rx_set_fs(struct mlx5e_priv *priv)
 	}
 	ptp_fs->udp_v4_rule = rule;
 
-	rule = mlx5e_fs_tt_redirect_udp_add_rule(priv, MLX5E_TT_IPV6_UDP,
+	rule = mlx5e_fs_tt_redirect_udp_add_rule(priv, MLX5_TT_IPV6_UDP,
 						 tirn, PTP_EV_PORT);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -680,7 +684,7 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	c->pdev     = mlx5_core_dma_dev(priv->mdev);
 	c->netdev   = priv->netdev;
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key);
-	c->num_tc   = params->num_tc;
+	c->num_tc   = mlx5e_get_dcb_num_tc(params);
 	c->stats    = &priv->ptp_stats.ch;
 	c->lag_port = lag_port;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
index 5efe3278b0f6..e8a8d78e3e4d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
@@ -132,7 +132,7 @@ static u16 mlx5e_qid_from_qos(struct mlx5e_channels *chs, u16 qid)
 	 */
 	bool is_ptp = MLX5E_GET_PFLAG(&chs->params, MLX5E_PFLAG_TX_PORT_TS);
 
-	return (chs->params.num_channels + is_ptp) * chs->params.num_tc + qid;
+	return (chs->params.num_channels + is_ptp) * mlx5e_get_dcb_num_tc(&chs->params) + qid;
 }
 
 int mlx5e_get_txq_by_classid(struct mlx5e_priv *priv, u16 classid)
@@ -733,8 +733,8 @@ static void mlx5e_reset_qdisc(struct net_device *dev, u16 qid)
 	spin_unlock_bh(qdisc_lock(qdisc));
 }
 
-int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 classid, u16 *old_qid,
-		       u16 *new_qid, struct netlink_ext_ack *extack)
+int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 *classid,
+		       struct netlink_ext_ack *extack)
 {
 	struct mlx5e_qos_node *node;
 	struct netdev_queue *txq;
@@ -742,11 +742,9 @@ int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 classid, u16 *old_qid,
 	bool opened;
 	int err;
 
-	qos_dbg(priv->mdev, "TC_HTB_LEAF_DEL classid %04x\n", classid);
-
-	*old_qid = *new_qid = 0;
+	qos_dbg(priv->mdev, "TC_HTB_LEAF_DEL classid %04x\n", *classid);
 
-	node = mlx5e_sw_node_find(priv, classid);
+	node = mlx5e_sw_node_find(priv, *classid);
 	if (!node)
 		return -ENOENT;
 
@@ -764,7 +762,7 @@ int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 classid, u16 *old_qid,
 	err = mlx5_qos_destroy_node(priv->mdev, node->hw_id);
 	if (err) /* Not fatal. */
 		qos_warn(priv->mdev, "Failed to destroy leaf node %u (class %04x), err = %d\n",
-			 node->hw_id, classid, err);
+			 node->hw_id, *classid, err);
 
 	mlx5e_sw_node_delete(priv, node);
 
@@ -826,8 +824,7 @@ int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 classid, u16 *old_qid,
 	if (opened)
 		mlx5e_reactivate_qos_sq(priv, moved_qid, txq);
 
-	*old_qid = mlx5e_qid_from_qos(&priv->channels, moved_qid);
-	*new_qid = mlx5e_qid_from_qos(&priv->channels, qid);
+	*classid = node->classid;
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.h
index 5af7991fcd19..757682b7c0e0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.h
@@ -34,8 +34,8 @@ int mlx5e_htb_leaf_alloc_queue(struct mlx5e_priv *priv, u16 classid,
 			       struct netlink_ext_ack *extack);
 int mlx5e_htb_leaf_to_inner(struct mlx5e_priv *priv, u16 classid, u16 child_classid,
 			    u64 rate, u64 ceil, struct netlink_ext_ack *extack);
-int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 classid, u16 *old_qid,
-		       u16 *new_qid, struct netlink_ext_ack *extack);
+int mlx5e_htb_leaf_del(struct mlx5e_priv *priv, u16 *classid,
+		       struct netlink_ext_ack *extack);
 int mlx5e_htb_leaf_del_last(struct mlx5e_priv *priv, u16 classid, bool force,
 			    struct netlink_ext_ack *extack);
 int mlx5e_htb_node_modify(struct mlx5e_priv *priv, u16 classid, u64 rate, u64 ceil,
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 3c0032c9647c..0c38c2e319be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
@@ -15,9 +15,116 @@ struct mlx5_bridge_switchdev_fdb_work {
 	struct work_struct work;
 	struct switchdev_notifier_fdb_info fdb_info;
 	struct net_device *dev;
+	struct mlx5_esw_bridge_offloads *br_offloads;
 	bool add;
 };
 
+static bool mlx5_esw_bridge_dev_same_esw(struct net_device *dev, struct mlx5_eswitch *esw)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	return esw == priv->mdev->priv.eswitch;
+}
+
+static bool mlx5_esw_bridge_dev_same_hw(struct net_device *dev, struct mlx5_eswitch *esw)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev, *esw_mdev;
+	u64 system_guid, esw_system_guid;
+
+	mdev = priv->mdev;
+	esw_mdev = esw->dev;
+
+	system_guid = mlx5_query_nic_system_image_guid(mdev);
+	esw_system_guid = mlx5_query_nic_system_image_guid(esw_mdev);
+
+	return system_guid == esw_system_guid;
+}
+
+static struct net_device *
+mlx5_esw_bridge_lag_rep_get(struct net_device *dev, struct mlx5_eswitch *esw)
+{
+	struct net_device *lower;
+	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))
+			return lower;
+	}
+
+	return NULL;
+}
+
+static struct net_device *
+mlx5_esw_bridge_rep_vport_num_vhca_id_get(struct net_device *dev, struct mlx5_eswitch *esw,
+					  u16 *vport_num, u16 *esw_owner_vhca_id)
+{
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5e_priv *priv;
+
+	if (netif_is_lag_master(dev))
+		dev = mlx5_esw_bridge_lag_rep_get(dev, esw);
+
+	if (!dev || !mlx5e_eswitch_rep(dev) || !mlx5_esw_bridge_dev_same_hw(dev, esw))
+		return NULL;
+
+	priv = netdev_priv(dev);
+	rpriv = priv->ppriv;
+	*vport_num = rpriv->rep->vport;
+	*esw_owner_vhca_id = MLX5_CAP_GEN(priv->mdev, vhca_id);
+	return dev;
+}
+
+static struct net_device *
+mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get(struct net_device *dev, struct mlx5_eswitch *esw,
+						u16 *vport_num, u16 *esw_owner_vhca_id)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+
+	if (netif_is_lag_master(dev) || mlx5e_eswitch_rep(dev))
+		return mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, esw, vport_num,
+								 esw_owner_vhca_id);
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		struct net_device *rep;
+
+		if (netif_is_bridge_master(lower_dev))
+			continue;
+
+		rep = mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get(lower_dev, esw, vport_num,
+								      esw_owner_vhca_id);
+		if (rep)
+			return rep;
+	}
+
+	return NULL;
+}
+
+static bool mlx5_esw_bridge_is_local(struct net_device *dev, struct net_device *rep,
+				     struct mlx5_eswitch *esw)
+{
+	struct mlx5_core_dev *mdev;
+	struct mlx5e_priv *priv;
+
+	if (!mlx5_esw_bridge_dev_same_esw(rep, esw))
+		return false;
+
+	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 true;
+}
+
 static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr)
 {
 	struct mlx5_esw_bridge_offloads *br_offloads = container_of(nb,
@@ -25,37 +132,36 @@ static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr
 								    netdev_nb);
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct netdev_notifier_changeupper_info *info = ptr;
+	struct net_device *upper = info->upper_dev, *rep;
+	struct mlx5_eswitch *esw = br_offloads->esw;
+	u16 vport_num, esw_owner_vhca_id;
 	struct netlink_ext_ack *extack;
-	struct mlx5e_rep_priv *rpriv;
-	struct mlx5_eswitch *esw;
-	struct mlx5_vport *vport;
-	struct net_device *upper;
-	struct mlx5e_priv *priv;
-	u16 vport_num;
-
-	if (!mlx5e_eswitch_rep(dev))
-		return 0;
+	int ifindex = upper->ifindex;
+	int err;
 
-	upper = info->upper_dev;
 	if (!netif_is_bridge_master(upper))
 		return 0;
 
-	esw = br_offloads->esw;
-	priv = netdev_priv(dev);
-	if (esw != priv->mdev->priv.eswitch)
+	rep = mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, esw, &vport_num, &esw_owner_vhca_id);
+	if (!rep)
 		return 0;
 
-	rpriv = priv->ppriv;
-	vport_num = rpriv->rep->vport;
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return PTR_ERR(vport);
-
 	extack = netdev_notifier_info_to_extack(&info->info);
 
-	return info->linking ?
-		mlx5_esw_bridge_vport_link(upper->ifindex, br_offloads, vport, extack) :
-		mlx5_esw_bridge_vport_unlink(upper->ifindex, br_offloads, vport, extack);
+	if (mlx5_esw_bridge_is_local(dev, rep, esw))
+		err = info->linking ?
+			mlx5_esw_bridge_vport_link(ifindex, vport_num, esw_owner_vhca_id,
+						   br_offloads, extack) :
+			mlx5_esw_bridge_vport_unlink(ifindex, vport_num, esw_owner_vhca_id,
+						     br_offloads, extack);
+	else if (mlx5_esw_bridge_dev_same_hw(rep, esw))
+		err = info->linking ?
+			mlx5_esw_bridge_vport_peer_link(ifindex, vport_num, esw_owner_vhca_id,
+							br_offloads, extack) :
+			mlx5_esw_bridge_vport_peer_unlink(ifindex, vport_num, esw_owner_vhca_id,
+							  br_offloads, extack);
+
+	return err;
 }
 
 static int mlx5_esw_bridge_switchdev_port_event(struct notifier_block *nb,
@@ -75,31 +181,28 @@ static int mlx5_esw_bridge_switchdev_port_event(struct notifier_block *nb,
 	return notifier_from_errno(err);
 }
 
-static int mlx5_esw_bridge_port_obj_add(struct net_device *dev,
-					const void *ctx,
-					const struct switchdev_obj *obj,
-					struct netlink_ext_ack *extack)
+static int
+mlx5_esw_bridge_port_obj_add(struct net_device *dev,
+			     struct switchdev_notifier_port_obj_info *port_obj_info,
+			     struct mlx5_esw_bridge_offloads *br_offloads)
 {
+	struct netlink_ext_ack *extack = switchdev_notifier_info_to_extack(&port_obj_info->info);
+	const struct switchdev_obj *obj = port_obj_info->obj;
 	const struct switchdev_obj_port_vlan *vlan;
-	struct mlx5e_rep_priv *rpriv;
-	struct mlx5_eswitch *esw;
-	struct mlx5_vport *vport;
-	struct mlx5e_priv *priv;
-	u16 vport_num;
-	int err = 0;
+	u16 vport_num, esw_owner_vhca_id;
+	int err;
 
-	priv = netdev_priv(dev);
-	rpriv = priv->ppriv;
-	vport_num = rpriv->rep->vport;
-	esw = priv->mdev->priv.eswitch;
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return PTR_ERR(vport);
+	if (!mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num,
+						       &esw_owner_vhca_id))
+		return 0;
+
+	port_obj_info->handled = true;
 
 	switch (obj->id) {
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
 		vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
-		err = mlx5_esw_bridge_port_vlan_add(vlan->vid, vlan->flags, esw, vport, extack);
+		err = mlx5_esw_bridge_port_vlan_add(vport_num, esw_owner_vhca_id, vlan->vid,
+						    vlan->flags, br_offloads, extack);
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -107,29 +210,25 @@ static int mlx5_esw_bridge_port_obj_add(struct net_device *dev,
 	return err;
 }
 
-static int mlx5_esw_bridge_port_obj_del(struct net_device *dev,
-					const void *ctx,
-					const struct switchdev_obj *obj)
+static int
+mlx5_esw_bridge_port_obj_del(struct net_device *dev,
+			     struct switchdev_notifier_port_obj_info *port_obj_info,
+			     struct mlx5_esw_bridge_offloads *br_offloads)
 {
+	const struct switchdev_obj *obj = port_obj_info->obj;
 	const struct switchdev_obj_port_vlan *vlan;
-	struct mlx5e_rep_priv *rpriv;
-	struct mlx5_eswitch *esw;
-	struct mlx5_vport *vport;
-	struct mlx5e_priv *priv;
-	u16 vport_num;
+	u16 vport_num, esw_owner_vhca_id;
 
-	priv = netdev_priv(dev);
-	rpriv = priv->ppriv;
-	vport_num = rpriv->rep->vport;
-	esw = priv->mdev->priv.eswitch;
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return PTR_ERR(vport);
+	if (!mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num,
+						       &esw_owner_vhca_id))
+		return 0;
+
+	port_obj_info->handled = true;
 
 	switch (obj->id) {
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
 		vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
-		mlx5_esw_bridge_port_vlan_del(vlan->vid, esw, vport);
+		mlx5_esw_bridge_port_vlan_del(vport_num, esw_owner_vhca_id, vlan->vid, br_offloads);
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -137,25 +236,21 @@ static int mlx5_esw_bridge_port_obj_del(struct net_device *dev,
 	return 0;
 }
 
-static int mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev,
-					     const void *ctx,
-					     const struct switchdev_attr *attr,
-					     struct netlink_ext_ack *extack)
+static int
+mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev,
+				  struct switchdev_notifier_port_attr_info *port_attr_info,
+				  struct mlx5_esw_bridge_offloads *br_offloads)
 {
-	struct mlx5e_rep_priv *rpriv;
-	struct mlx5_eswitch *esw;
-	struct mlx5_vport *vport;
-	struct mlx5e_priv *priv;
-	u16 vport_num;
-	int err = 0;
+	struct netlink_ext_ack *extack = switchdev_notifier_info_to_extack(&port_attr_info->info);
+	const struct switchdev_attr *attr = port_attr_info->attr;
+	u16 vport_num, esw_owner_vhca_id;
+	int err;
 
-	priv = netdev_priv(dev);
-	rpriv = priv->ppriv;
-	vport_num = rpriv->rep->vport;
-	esw = priv->mdev->priv.eswitch;
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return PTR_ERR(vport);
+	if (!mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num,
+							     &esw_owner_vhca_id))
+		return 0;
+
+	port_attr_info->handled = true;
 
 	switch (attr->id) {
 	case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
@@ -167,10 +262,12 @@ static int mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev,
 	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME:
-		err = mlx5_esw_bridge_ageing_time_set(attr->u.ageing_time, esw, vport);
+		err = mlx5_esw_bridge_ageing_time_set(vport_num, esw_owner_vhca_id,
+						      attr->u.ageing_time, br_offloads);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
-		err = mlx5_esw_bridge_vlan_filtering_set(attr->u.vlan_filtering, esw, vport);
+		err = mlx5_esw_bridge_vlan_filtering_set(vport_num, esw_owner_vhca_id,
+							 attr->u.vlan_filtering, br_offloads);
 		break;
 	default:
 		err = -EOPNOTSUPP;
@@ -179,27 +276,24 @@ static int mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev,
 	return err;
 }
 
-static int mlx5_esw_bridge_event_blocking(struct notifier_block *unused,
+static int mlx5_esw_bridge_event_blocking(struct notifier_block *nb,
 					  unsigned long event, void *ptr)
 {
+	struct mlx5_esw_bridge_offloads *br_offloads = container_of(nb,
+								    struct mlx5_esw_bridge_offloads,
+								    nb_blk);
 	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
 	int err;
 
 	switch (event) {
 	case SWITCHDEV_PORT_OBJ_ADD:
-		err = switchdev_handle_port_obj_add(dev, ptr,
-						    mlx5e_eswitch_rep,
-						    mlx5_esw_bridge_port_obj_add);
+		err = mlx5_esw_bridge_port_obj_add(dev, ptr, br_offloads);
 		break;
 	case SWITCHDEV_PORT_OBJ_DEL:
-		err = switchdev_handle_port_obj_del(dev, ptr,
-						    mlx5e_eswitch_rep,
-						    mlx5_esw_bridge_port_obj_del);
+		err = mlx5_esw_bridge_port_obj_del(dev, ptr, br_offloads);
 		break;
 	case SWITCHDEV_PORT_ATTR_SET:
-		err = switchdev_handle_port_attr_set(dev, ptr,
-						     mlx5e_eswitch_rep,
-						     mlx5_esw_bridge_port_obj_attr_set);
+		err = mlx5_esw_bridge_port_obj_attr_set(dev, ptr, br_offloads);
 		break;
 	default:
 		err = 0;
@@ -222,27 +316,23 @@ static void mlx5_esw_bridge_switchdev_fdb_event_work(struct work_struct *work)
 		container_of(work, struct mlx5_bridge_switchdev_fdb_work, work);
 	struct switchdev_notifier_fdb_info *fdb_info =
 		&fdb_work->fdb_info;
+	struct mlx5_esw_bridge_offloads *br_offloads =
+		fdb_work->br_offloads;
 	struct net_device *dev = fdb_work->dev;
-	struct mlx5e_rep_priv *rpriv;
-	struct mlx5_eswitch *esw;
-	struct mlx5_vport *vport;
-	struct mlx5e_priv *priv;
-	u16 vport_num;
+	u16 vport_num, esw_owner_vhca_id;
 
 	rtnl_lock();
 
-	priv = netdev_priv(dev);
-	rpriv = priv->ppriv;
-	vport_num = rpriv->rep->vport;
-	esw = priv->mdev->priv.eswitch;
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
+	if (!mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num,
+						       &esw_owner_vhca_id))
 		goto out;
 
 	if (fdb_work->add)
-		mlx5_esw_bridge_fdb_create(dev, esw, vport, fdb_info);
+		mlx5_esw_bridge_fdb_create(dev, vport_num, esw_owner_vhca_id, br_offloads,
+					   fdb_info);
 	else
-		mlx5_esw_bridge_fdb_remove(dev, esw, vport, fdb_info);
+		mlx5_esw_bridge_fdb_remove(dev, vport_num, esw_owner_vhca_id, br_offloads,
+					   fdb_info);
 
 out:
 	rtnl_unlock();
@@ -251,7 +341,8 @@ out:
 
 static struct mlx5_bridge_switchdev_fdb_work *
 mlx5_esw_bridge_init_switchdev_fdb_work(struct net_device *dev, bool add,
-					struct switchdev_notifier_fdb_info *fdb_info)
+					struct switchdev_notifier_fdb_info *fdb_info,
+					struct mlx5_esw_bridge_offloads *br_offloads)
 {
 	struct mlx5_bridge_switchdev_fdb_work *work;
 	u8 *addr;
@@ -273,6 +364,7 @@ mlx5_esw_bridge_init_switchdev_fdb_work(struct net_device *dev, bool add,
 
 	dev_hold(dev);
 	work->dev = dev;
+	work->br_offloads = br_offloads;
 	work->add = add;
 	return work;
 }
@@ -286,20 +378,14 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
 	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
 	struct switchdev_notifier_fdb_info *fdb_info;
 	struct mlx5_bridge_switchdev_fdb_work *work;
+	struct mlx5_eswitch *esw = br_offloads->esw;
 	struct switchdev_notifier_info *info = ptr;
-	struct net_device *upper;
-	struct mlx5e_priv *priv;
-
-	if (!mlx5e_eswitch_rep(dev))
-		return NOTIFY_DONE;
-	priv = netdev_priv(dev);
-	if (priv->mdev->priv.eswitch != br_offloads->esw)
-		return NOTIFY_DONE;
+	u16 vport_num, esw_owner_vhca_id;
+	struct net_device *upper, *rep;
 
 	if (event == SWITCHDEV_PORT_ATTR_SET) {
-		int err = switchdev_handle_port_attr_set(dev, ptr,
-							 mlx5e_eswitch_rep,
-							 mlx5_esw_bridge_port_obj_attr_set);
+		int err = mlx5_esw_bridge_port_obj_attr_set(dev, ptr, br_offloads);
+
 		return notifier_from_errno(err);
 	}
 
@@ -309,7 +395,27 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
 	if (!netif_is_bridge_master(upper))
 		return NOTIFY_DONE;
 
+	rep = mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, esw, &vport_num, &esw_owner_vhca_id);
+	if (!rep)
+		return NOTIFY_DONE;
+
 	switch (event) {
+	case SWITCHDEV_FDB_ADD_TO_BRIDGE:
+		/* only handle the event on native eswtich of representor */
+		if (!mlx5_esw_bridge_is_local(dev, rep, esw))
+			break;
+
+		fdb_info = container_of(info,
+					struct switchdev_notifier_fdb_info,
+					info);
+		mlx5_esw_bridge_fdb_update_used(dev, vport_num, esw_owner_vhca_id, br_offloads,
+						fdb_info);
+		break;
+	case SWITCHDEV_FDB_DEL_TO_BRIDGE:
+		/* only handle the event on peers */
+		if (mlx5_esw_bridge_is_local(dev, rep, esw))
+			break;
+		fallthrough;
 	case SWITCHDEV_FDB_ADD_TO_DEVICE:
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:
 		fdb_info = container_of(info,
@@ -318,7 +424,8 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
 
 		work = mlx5_esw_bridge_init_switchdev_fdb_work(dev,
 							       event == SWITCHDEV_FDB_ADD_TO_DEVICE,
-							       fdb_info);
+							       fdb_info,
+							       br_offloads);
 		if (IS_ERR(work)) {
 			WARN_ONCE(1, "Failed to init switchdev work, err=%ld",
 				  PTR_ERR(work));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index 059799e4f483..51a4d80f7fa3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -17,7 +17,7 @@
 #include "en/mapping.h"
 #include "en/tc_tun.h"
 #include "lib/port_tun.h"
-#include "esw/sample.h"
+#include "en/tc/sample.h"
 
 struct mlx5e_rep_indr_block_priv {
 	struct net_device *netdev;
@@ -516,7 +516,6 @@ void mlx5e_rep_tc_netdevice_event_unregister(struct mlx5e_rep_priv *rpriv)
 				 mlx5e_rep_indr_block_unbind);
 }
 
-#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
 static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb,
 				 struct mlx5e_tc_update_priv *tc_priv,
 				 u32 tunnel_id)
@@ -609,12 +608,13 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb,
 	return true;
 }
 
-static bool mlx5e_restore_skb(struct sk_buff *skb, u32 chain, u32 reg_c1,
-			      struct mlx5e_tc_update_priv *tc_priv)
+static bool mlx5e_restore_skb_chain(struct sk_buff *skb, u32 chain, u32 reg_c1,
+				    struct mlx5e_tc_update_priv *tc_priv)
 {
 	struct mlx5e_priv *priv = netdev_priv(skb->dev);
 	u32 tunnel_id = (reg_c1 >> ESW_TUN_OFFSET) & TUNNEL_ID_MASK;
 
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
 	if (chain) {
 		struct mlx5_rep_uplink_priv *uplink_priv;
 		struct mlx5e_rep_priv *uplink_rpriv;
@@ -636,9 +636,25 @@ static bool mlx5e_restore_skb(struct sk_buff *skb, u32 chain, u32 reg_c1,
 					      zone_restore_id))
 			return false;
 	}
+#endif /* CONFIG_NET_TC_SKB_EXT */
+
 	return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id);
 }
-#endif /* CONFIG_NET_TC_SKB_EXT */
+
+static void mlx5e_restore_skb_sample(struct mlx5e_priv *priv, struct sk_buff *skb,
+				     struct mlx5_mapped_obj *mapped_obj,
+				     struct mlx5e_tc_update_priv *tc_priv)
+{
+	if (!mlx5e_restore_tunnel(priv, skb, tc_priv, mapped_obj->sample.tunnel_id)) {
+		netdev_dbg(priv->netdev,
+			   "Failed to restore tunnel info for sampled packet\n");
+		return;
+	}
+#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE)
+	mlx5e_tc_sample_skb(skb, mapped_obj);
+#endif /* CONFIG_MLX5_TC_SAMPLE */
+	mlx5_rep_tc_post_napi_receive(tc_priv);
+}
 
 bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 			     struct sk_buff *skb,
@@ -647,7 +663,7 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 	struct mlx5_mapped_obj mapped_obj;
 	struct mlx5_eswitch *esw;
 	struct mlx5e_priv *priv;
-	u32 reg_c0, reg_c1;
+	u32 reg_c0;
 	int err;
 
 	reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK);
@@ -659,8 +675,6 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 	 */
 	skb->mark = 0;
 
-	reg_c1 = be32_to_cpu(cqe->ft_metadata);
-
 	priv = netdev_priv(skb->dev);
 	esw = priv->mdev->priv.eswitch;
 	err = mapping_find(esw->offloads.reg_c0_obj_pool, reg_c0, &mapped_obj);
@@ -671,18 +685,14 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 		return false;
 	}
 
-#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
-	if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN)
-		return mlx5e_restore_skb(skb, mapped_obj.chain, reg_c1, tc_priv);
-#endif /* CONFIG_NET_TC_SKB_EXT */
-#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE)
-	if (mapped_obj.type == MLX5_MAPPED_OBJ_SAMPLE) {
-		mlx5_esw_sample_skb(skb, &mapped_obj);
+	if (mapped_obj.type == MLX5_MAPPED_OBJ_CHAIN) {
+		u32 reg_c1 = be32_to_cpu(cqe->ft_metadata);
+
+		return mlx5e_restore_skb_chain(skb, mapped_obj.chain, reg_c1, tc_priv);
+	} else if (mapped_obj.type == MLX5_MAPPED_OBJ_SAMPLE) {
+		mlx5e_restore_skb_sample(priv, skb, &mapped_obj, tc_priv);
 		return false;
-	}
-#endif /* CONFIG_MLX5_TC_SAMPLE */
-	if (mapped_obj.type != MLX5_MAPPED_OBJ_SAMPLE &&
-	    mapped_obj.type != MLX5_MAPPED_OBJ_CHAIN) {
+	} else {
 		netdev_dbg(priv->netdev, "Invalid mapped object type: %d\n", mapped_obj.type);
 		return false;
 	}
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 9d361efd5ff7..bb682fd751c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -372,7 +372,7 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
 	for (i = 0; i < priv->channels.num; i++) {
 		struct mlx5e_channel *c = priv->channels.c[i];
 
-		for (tc = 0; tc < priv->channels.params.num_tc; tc++) {
+		for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) {
 			struct mlx5e_txqsq *sq = &c->sq[tc];
 
 			err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq, tc);
@@ -384,7 +384,7 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
 	if (!ptp_ch || !test_bit(MLX5E_PTP_STATE_TX, ptp_ch->state))
 		goto close_sqs_nest;
 
-	for (tc = 0; tc < priv->channels.params.num_tc; tc++) {
+	for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) {
 		err = mlx5e_tx_reporter_build_diagnose_output_ptpsq(fmsg,
 								    &ptp_ch->ptpsq[tc],
 								    tc);
@@ -494,7 +494,7 @@ static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv,
 	for (i = 0; i < priv->channels.num; i++) {
 		struct mlx5e_channel *c = priv->channels.c[i];
 
-		for (tc = 0; tc < priv->channels.params.num_tc; tc++) {
+		for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) {
 			struct mlx5e_txqsq *sq = &c->sq[tc];
 
 			err = mlx5e_health_queue_dump(priv, fmsg, sq->sqn, "SQ");
@@ -504,7 +504,7 @@ static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv,
 	}
 
 	if (ptp_ch && test_bit(MLX5E_PTP_STATE_TX, ptp_ch->state)) {
-		for (tc = 0; tc < priv->channels.params.num_tc; tc++) {
+		for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) {
 			struct mlx5e_txqsq *sq = &ptp_ch->ptpsq[tc].txqsq;
 
 			err = mlx5e_health_queue_dump(priv, fmsg, sq->sqn, "PTP SQ");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c
new file mode 100644
index 000000000000..b915fb29dd2c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */
+
+#include "rqt.h"
+#include <linux/mlx5/transobj.h>
+
+void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir,
+					 unsigned int num_channels)
+{
+	unsigned int i;
+
+	for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++)
+		indir->table[i] = i % num_channels;
+}
+
+static int mlx5e_rqt_init(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev,
+			  u16 max_size, u32 *init_rqns, u16 init_size)
+{
+	void *rqtc;
+	int inlen;
+	int err;
+	u32 *in;
+	int i;
+
+	rqt->mdev = mdev;
+	rqt->size = max_size;
+
+	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * init_size;
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context);
+
+	MLX5_SET(rqtc, rqtc, rqt_max_size, rqt->size);
+
+	MLX5_SET(rqtc, rqtc, rqt_actual_size, init_size);
+	for (i = 0; i < init_size; i++)
+		MLX5_SET(rqtc, rqtc, rq_num[i], init_rqns[i]);
+
+	err = mlx5_core_create_rqt(rqt->mdev, in, inlen, &rqt->rqtn);
+
+	kvfree(in);
+	return err;
+}
+
+int mlx5e_rqt_init_direct(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev,
+			  bool indir_enabled, u32 init_rqn)
+{
+	u16 max_size = indir_enabled ? MLX5E_INDIR_RQT_SIZE : 1;
+
+	return mlx5e_rqt_init(rqt, mdev, max_size, &init_rqn, 1);
+}
+
+static int mlx5e_bits_invert(unsigned long a, int size)
+{
+	int inv = 0;
+	int i;
+
+	for (i = 0; i < size; i++)
+		inv |= (test_bit(size - i - 1, &a) ? 1 : 0) << i;
+
+	return inv;
+}
+
+static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, unsigned int num_rqns,
+				 u8 hfunc, struct mlx5e_rss_params_indir *indir)
+{
+	unsigned int i;
+
+	for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++) {
+		unsigned int ix = i;
+
+		if (hfunc == ETH_RSS_HASH_XOR)
+			ix = mlx5e_bits_invert(ix, ilog2(MLX5E_INDIR_RQT_SIZE));
+
+		ix = indir->table[ix];
+
+		if (WARN_ON(ix >= num_rqns))
+			/* Could be a bug in the driver or in the kernel part of
+			 * ethtool: indir table refers to non-existent RQs.
+			 */
+			return -EINVAL;
+		rss_rqns[i] = rqns[ix];
+	}
+
+	return 0;
+}
+
+int mlx5e_rqt_init_indir(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev,
+			 u32 *rqns, unsigned int num_rqns,
+			 u8 hfunc, struct mlx5e_rss_params_indir *indir)
+{
+	u32 *rss_rqns;
+	int err;
+
+	rss_rqns = kvmalloc_array(MLX5E_INDIR_RQT_SIZE, sizeof(*rss_rqns), GFP_KERNEL);
+	if (!rss_rqns)
+		return -ENOMEM;
+
+	err = mlx5e_calc_indir_rqns(rss_rqns, rqns, num_rqns, hfunc, indir);
+	if (err)
+		goto out;
+
+	err = mlx5e_rqt_init(rqt, mdev, MLX5E_INDIR_RQT_SIZE, rss_rqns, MLX5E_INDIR_RQT_SIZE);
+
+out:
+	kvfree(rss_rqns);
+	return err;
+}
+
+void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt)
+{
+	mlx5_core_destroy_rqt(rqt->mdev, rqt->rqtn);
+}
+
+static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int size)
+{
+	unsigned int i;
+	void *rqtc;
+	int inlen;
+	u32 *in;
+	int err;
+
+	inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + sizeof(u32) * size;
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	rqtc = MLX5_ADDR_OF(modify_rqt_in, in, ctx);
+
+	MLX5_SET(modify_rqt_in, in, bitmask.rqn_list, 1);
+	MLX5_SET(rqtc, rqtc, rqt_actual_size, size);
+	for (i = 0; i < size; i++)
+		MLX5_SET(rqtc, rqtc, rq_num[i], rqns[i]);
+
+	err = mlx5_core_modify_rqt(rqt->mdev, rqt->rqtn, in, inlen);
+
+	kvfree(in);
+	return err;
+}
+
+int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn)
+{
+	return mlx5e_rqt_redirect(rqt, &rqn, 1);
+}
+
+int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_rqns,
+			     u8 hfunc, struct mlx5e_rss_params_indir *indir)
+{
+	u32 *rss_rqns;
+	int err;
+
+	if (WARN_ON(rqt->size != MLX5E_INDIR_RQT_SIZE))
+		return -EINVAL;
+
+	rss_rqns = kvmalloc_array(MLX5E_INDIR_RQT_SIZE, sizeof(*rss_rqns), GFP_KERNEL);
+	if (!rss_rqns)
+		return -ENOMEM;
+
+	err = mlx5e_calc_indir_rqns(rss_rqns, rqns, num_rqns, hfunc, indir);
+	if (err)
+		goto out;
+
+	err = mlx5e_rqt_redirect(rqt, rss_rqns, MLX5E_INDIR_RQT_SIZE);
+
+out:
+	kvfree(rss_rqns);
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h
new file mode 100644
index 000000000000..60c985a12f24
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */
+
+#ifndef __MLX5_EN_RQT_H__
+#define __MLX5_EN_RQT_H__
+
+#include <linux/kernel.h>
+
+#define MLX5E_INDIR_RQT_SIZE (1 << 8)
+
+struct mlx5_core_dev;
+
+struct mlx5e_rss_params_indir {
+	u32 table[MLX5E_INDIR_RQT_SIZE];
+};
+
+void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir,
+					 unsigned int num_channels);
+
+struct mlx5e_rqt {
+	struct mlx5_core_dev *mdev;
+	u32 rqtn;
+	u16 size;
+};
+
+int mlx5e_rqt_init_direct(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev,
+			  bool indir_enabled, u32 init_rqn);
+int mlx5e_rqt_init_indir(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev,
+			 u32 *rqns, unsigned int num_rqns,
+			 u8 hfunc, struct mlx5e_rss_params_indir *indir);
+void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt);
+
+static inline u32 mlx5e_rqt_get_rqtn(struct mlx5e_rqt *rqt)
+{
+	return rqt->rqtn;
+}
+
+int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn);
+int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_rqns,
+			     u8 hfunc, struct mlx5e_rss_params_indir *indir);
+
+#endif /* __MLX5_EN_RQT_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
new file mode 100644
index 000000000000..625cd49ef96c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
@@ -0,0 +1,588 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.
+
+#include "rss.h"
+
+#define mlx5e_rss_warn(__dev, format, ...)			\
+	dev_warn((__dev)->device, "%s:%d:(pid %d): " format,	\
+		 __func__, __LINE__, current->pid,		\
+		 ##__VA_ARGS__)
+
+static const struct mlx5e_rss_params_traffic_type rss_default_config[MLX5E_NUM_INDIR_TIRS] = {
+	[MLX5_TT_IPV4_TCP] = {
+		.l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+		.l4_prot_type = MLX5_L4_PROT_TYPE_TCP,
+		.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5_TT_IPV6_TCP] = {
+		.l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+		.l4_prot_type = MLX5_L4_PROT_TYPE_TCP,
+		.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5_TT_IPV4_UDP] = {
+		.l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+		.l4_prot_type = MLX5_L4_PROT_TYPE_UDP,
+		.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5_TT_IPV6_UDP] = {
+		.l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+		.l4_prot_type = MLX5_L4_PROT_TYPE_UDP,
+		.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5_TT_IPV4_IPSEC_AH] = {
+		.l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+		.l4_prot_type = 0,
+		.rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5_TT_IPV6_IPSEC_AH] = {
+		.l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+		.l4_prot_type = 0,
+		.rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5_TT_IPV4_IPSEC_ESP] = {
+		.l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+		.l4_prot_type = 0,
+		.rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5_TT_IPV6_IPSEC_ESP] = {
+		.l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+		.l4_prot_type = 0,
+		.rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5_TT_IPV4] = {
+		.l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+		.l4_prot_type = 0,
+		.rx_hash_fields = MLX5_HASH_IP,
+	},
+	[MLX5_TT_IPV6] = {
+		.l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+		.l4_prot_type = 0,
+		.rx_hash_fields = MLX5_HASH_IP,
+	},
+};
+
+struct mlx5e_rss_params_traffic_type
+mlx5e_rss_get_default_tt_config(enum mlx5_traffic_types tt)
+{
+	return rss_default_config[tt];
+}
+
+struct mlx5e_rss {
+	struct mlx5e_rss_params_hash hash;
+	struct mlx5e_rss_params_indir indir;
+	u32 rx_hash_fields[MLX5E_NUM_INDIR_TIRS];
+	struct mlx5e_tir *tir[MLX5E_NUM_INDIR_TIRS];
+	struct mlx5e_tir *inner_tir[MLX5E_NUM_INDIR_TIRS];
+	struct mlx5e_rqt rqt;
+	struct mlx5_core_dev *mdev;
+	u32 drop_rqn;
+	bool inner_ft_support;
+	bool enabled;
+	refcount_t refcnt;
+};
+
+struct mlx5e_rss *mlx5e_rss_alloc(void)
+{
+	return kvzalloc(sizeof(struct mlx5e_rss), GFP_KERNEL);
+}
+
+void mlx5e_rss_free(struct mlx5e_rss *rss)
+{
+	kvfree(rss);
+}
+
+static void mlx5e_rss_params_init(struct mlx5e_rss *rss)
+{
+	enum mlx5_traffic_types tt;
+
+	rss->hash.hfunc = ETH_RSS_HASH_TOP;
+	netdev_rss_key_fill(rss->hash.toeplitz_hash_key,
+			    sizeof(rss->hash.toeplitz_hash_key));
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
+		rss->rx_hash_fields[tt] =
+			mlx5e_rss_get_default_tt_config(tt).rx_hash_fields;
+}
+
+static struct mlx5e_tir **rss_get_tirp(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
+				       bool inner)
+{
+	return inner ? &rss->inner_tir[tt] : &rss->tir[tt];
+}
+
+static struct mlx5e_tir *rss_get_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
+				     bool inner)
+{
+	return *rss_get_tirp(rss, tt, inner);
+}
+
+static struct mlx5e_rss_params_traffic_type
+mlx5e_rss_get_tt_config(struct mlx5e_rss *rss, enum mlx5_traffic_types tt)
+{
+	struct mlx5e_rss_params_traffic_type rss_tt;
+
+	rss_tt = mlx5e_rss_get_default_tt_config(tt);
+	rss_tt.rx_hash_fields = rss->rx_hash_fields[tt];
+	return rss_tt;
+}
+
+static int mlx5e_rss_create_tir(struct mlx5e_rss *rss,
+				enum mlx5_traffic_types tt,
+				const struct mlx5e_lro_param *init_lro_param,
+				bool inner)
+{
+	struct mlx5e_rss_params_traffic_type rss_tt;
+	struct mlx5e_tir_builder *builder;
+	struct mlx5e_tir **tir_p;
+	struct mlx5e_tir *tir;
+	u32 rqtn;
+	int err;
+
+	if (inner && !rss->inner_ft_support) {
+		mlx5e_rss_warn(rss->mdev,
+			       "Cannot create inner indirect TIR[%d], RSS inner FT is not supported.\n",
+			       tt);
+		return -EINVAL;
+	}
+
+	tir_p = rss_get_tirp(rss, tt, inner);
+	if (*tir_p)
+		return -EINVAL;
+
+	tir = kvzalloc(sizeof(*tir), GFP_KERNEL);
+	if (!tir)
+		return -ENOMEM;
+
+	builder = mlx5e_tir_builder_alloc(false);
+	if (!builder) {
+		err = -ENOMEM;
+		goto free_tir;
+	}
+
+	rqtn = mlx5e_rqt_get_rqtn(&rss->rqt);
+	mlx5e_tir_builder_build_rqt(builder, rss->mdev->mlx5e_res.hw_objs.td.tdn,
+				    rqtn, rss->inner_ft_support);
+	mlx5e_tir_builder_build_lro(builder, init_lro_param);
+	rss_tt = mlx5e_rss_get_tt_config(rss, tt);
+	mlx5e_tir_builder_build_rss(builder, &rss->hash, &rss_tt, inner);
+
+	err = mlx5e_tir_init(tir, builder, rss->mdev, true);
+	mlx5e_tir_builder_free(builder);
+	if (err) {
+		mlx5e_rss_warn(rss->mdev, "Failed to create %sindirect TIR: err = %d, tt = %d\n",
+			       inner ? "inner " : "", err, tt);
+		goto free_tir;
+	}
+
+	*tir_p = tir;
+	return 0;
+
+free_tir:
+	kvfree(tir);
+	return err;
+}
+
+static void mlx5e_rss_destroy_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
+				  bool inner)
+{
+	struct mlx5e_tir **tir_p;
+	struct mlx5e_tir *tir;
+
+	tir_p = rss_get_tirp(rss, tt, inner);
+	if (!*tir_p)
+		return;
+
+	tir = *tir_p;
+	mlx5e_tir_destroy(tir);
+	kvfree(tir);
+	*tir_p = NULL;
+}
+
+static int mlx5e_rss_create_tirs(struct mlx5e_rss *rss,
+				 const struct mlx5e_lro_param *init_lro_param,
+				 bool inner)
+{
+	enum mlx5_traffic_types tt, max_tt;
+	int err;
+
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		err = mlx5e_rss_create_tir(rss, tt, init_lro_param, inner);
+		if (err)
+			goto err_destroy_tirs;
+	}
+
+	return 0;
+
+err_destroy_tirs:
+	max_tt = tt;
+	for (tt = 0; tt < max_tt; tt++)
+		mlx5e_rss_destroy_tir(rss, tt, inner);
+	return err;
+}
+
+static void mlx5e_rss_destroy_tirs(struct mlx5e_rss *rss, bool inner)
+{
+	enum mlx5_traffic_types tt;
+
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
+		mlx5e_rss_destroy_tir(rss, tt, inner);
+}
+
+static int mlx5e_rss_update_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
+				bool inner)
+{
+	struct mlx5e_rss_params_traffic_type rss_tt;
+	struct mlx5e_tir_builder *builder;
+	struct mlx5e_tir *tir;
+	int err;
+
+	tir = rss_get_tir(rss, tt, inner);
+	if (!tir)
+		return 0;
+
+	builder = mlx5e_tir_builder_alloc(true);
+	if (!builder)
+		return -ENOMEM;
+
+	rss_tt = mlx5e_rss_get_tt_config(rss, tt);
+
+	mlx5e_tir_builder_build_rss(builder, &rss->hash, &rss_tt, inner);
+	err = mlx5e_tir_modify(tir, builder);
+
+	mlx5e_tir_builder_free(builder);
+	return err;
+}
+
+static int mlx5e_rss_update_tirs(struct mlx5e_rss *rss)
+{
+	enum mlx5_traffic_types tt;
+	int err, retval;
+
+	retval = 0;
+
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		err = mlx5e_rss_update_tir(rss, tt, false);
+		if (err) {
+			retval = retval ? : err;
+			mlx5e_rss_warn(rss->mdev,
+				       "Failed to update RSS hash of indirect TIR for traffic type %d: err = %d\n",
+				       tt, err);
+		}
+
+		if (!rss->inner_ft_support)
+			continue;
+
+		err = mlx5e_rss_update_tir(rss, tt, true);
+		if (err) {
+			retval = retval ? : err;
+			mlx5e_rss_warn(rss->mdev,
+				       "Failed to update RSS hash of inner indirect TIR for traffic type %d: err = %d\n",
+				       tt, err);
+		}
+	}
+	return retval;
+}
+
+int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
+			   bool inner_ft_support, u32 drop_rqn)
+{
+	rss->mdev = mdev;
+	rss->inner_ft_support = inner_ft_support;
+	rss->drop_rqn = drop_rqn;
+
+	mlx5e_rss_params_init(rss);
+	refcount_set(&rss->refcnt, 1);
+
+	return mlx5e_rqt_init_direct(&rss->rqt, mdev, true, drop_rqn);
+}
+
+int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
+		   bool inner_ft_support, u32 drop_rqn,
+		   const struct mlx5e_lro_param *init_lro_param)
+{
+	int err;
+
+	err = mlx5e_rss_init_no_tirs(rss, mdev, inner_ft_support, drop_rqn);
+	if (err)
+		goto err_out;
+
+	err = mlx5e_rss_create_tirs(rss, init_lro_param, false);
+	if (err)
+		goto err_destroy_rqt;
+
+	if (inner_ft_support) {
+		err = mlx5e_rss_create_tirs(rss, init_lro_param, true);
+		if (err)
+			goto err_destroy_tirs;
+	}
+
+	return 0;
+
+err_destroy_tirs:
+	mlx5e_rss_destroy_tirs(rss, false);
+err_destroy_rqt:
+	mlx5e_rqt_destroy(&rss->rqt);
+err_out:
+	return err;
+}
+
+int mlx5e_rss_cleanup(struct mlx5e_rss *rss)
+{
+	if (!refcount_dec_if_one(&rss->refcnt))
+		return -EBUSY;
+
+	mlx5e_rss_destroy_tirs(rss, false);
+
+	if (rss->inner_ft_support)
+		mlx5e_rss_destroy_tirs(rss, true);
+
+	mlx5e_rqt_destroy(&rss->rqt);
+
+	return 0;
+}
+
+void mlx5e_rss_refcnt_inc(struct mlx5e_rss *rss)
+{
+	refcount_inc(&rss->refcnt);
+}
+
+void mlx5e_rss_refcnt_dec(struct mlx5e_rss *rss)
+{
+	refcount_dec(&rss->refcnt);
+}
+
+unsigned int mlx5e_rss_refcnt_read(struct mlx5e_rss *rss)
+{
+	return refcount_read(&rss->refcnt);
+}
+
+u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
+		       bool inner)
+{
+	struct mlx5e_tir *tir;
+
+	WARN_ON(inner && !rss->inner_ft_support);
+	tir = rss_get_tir(rss, tt, inner);
+	WARN_ON(!tir);
+
+	return mlx5e_tir_get_tirn(tir);
+}
+
+/* Fill the "tirn" output parameter.
+ * Create the requested TIR if it's its first usage.
+ */
+int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
+			  enum mlx5_traffic_types tt,
+			  const struct mlx5e_lro_param *init_lro_param,
+			  bool inner, u32 *tirn)
+{
+	struct mlx5e_tir *tir;
+
+	tir = rss_get_tir(rss, tt, inner);
+	if (!tir) { /* TIR doesn't exist, create one */
+		int err;
+
+		err = mlx5e_rss_create_tir(rss, tt, init_lro_param, inner);
+		if (err)
+			return err;
+		tir = rss_get_tir(rss, tt, inner);
+	}
+
+	*tirn = mlx5e_tir_get_tirn(tir);
+	return 0;
+}
+
+static void mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns)
+{
+	int err;
+
+	err = mlx5e_rqt_redirect_indir(&rss->rqt, rqns, num_rqns, rss->hash.hfunc, &rss->indir);
+	if (err)
+		mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to channels: err = %d\n",
+			       mlx5e_rqt_get_rqtn(&rss->rqt), err);
+}
+
+void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns)
+{
+	rss->enabled = true;
+	mlx5e_rss_apply(rss, rqns, num_rqns);
+}
+
+void mlx5e_rss_disable(struct mlx5e_rss *rss)
+{
+	int err;
+
+	rss->enabled = false;
+	err = mlx5e_rqt_redirect_direct(&rss->rqt, rss->drop_rqn);
+	if (err)
+		mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to drop RQ %#x: err = %d\n",
+			       mlx5e_rqt_get_rqtn(&rss->rqt), rss->drop_rqn, err);
+}
+
+int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_param)
+{
+	struct mlx5e_tir_builder *builder;
+	enum mlx5_traffic_types tt;
+	int err, final_err;
+
+	builder = mlx5e_tir_builder_alloc(true);
+	if (!builder)
+		return -ENOMEM;
+
+	mlx5e_tir_builder_build_lro(builder, lro_param);
+
+	final_err = 0;
+
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		struct mlx5e_tir *tir;
+
+		tir = rss_get_tir(rss, tt, false);
+		if (!tir)
+			goto inner_tir;
+		err = mlx5e_tir_modify(tir, builder);
+		if (err) {
+			mlx5e_rss_warn(rss->mdev, "Failed to update LRO state of indirect TIR %#x for traffic type %d: err = %d\n",
+				       mlx5e_tir_get_tirn(tir), tt, err);
+			if (!final_err)
+				final_err = err;
+		}
+
+inner_tir:
+		if (!rss->inner_ft_support)
+			continue;
+
+		tir = rss_get_tir(rss, tt, true);
+		if (!tir)
+			continue;
+		err = mlx5e_tir_modify(tir, builder);
+		if (err) {
+			mlx5e_rss_warn(rss->mdev, "Failed to update LRO state of inner indirect TIR %#x for traffic type %d: err = %d\n",
+				       mlx5e_tir_get_tirn(tir), tt, err);
+			if (!final_err)
+				final_err = err;
+		}
+	}
+
+	mlx5e_tir_builder_free(builder);
+	return final_err;
+}
+
+int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc)
+{
+	unsigned int i;
+
+	if (indir)
+		for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++)
+			indir[i] = rss->indir.table[i];
+
+	if (key)
+		memcpy(key, rss->hash.toeplitz_hash_key,
+		       sizeof(rss->hash.toeplitz_hash_key));
+
+	if (hfunc)
+		*hfunc = rss->hash.hfunc;
+
+	return 0;
+}
+
+int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
+		       const u8 *key, const u8 *hfunc,
+		       u32 *rqns, unsigned int num_rqns)
+{
+	bool changed_indir = false;
+	bool changed_hash = false;
+
+	if (hfunc && *hfunc != rss->hash.hfunc) {
+		switch (*hfunc) {
+		case ETH_RSS_HASH_XOR:
+		case ETH_RSS_HASH_TOP:
+			break;
+		default:
+			return -EINVAL;
+		}
+		changed_hash = true;
+		changed_indir = true;
+		rss->hash.hfunc = *hfunc;
+	}
+
+	if (key) {
+		if (rss->hash.hfunc == ETH_RSS_HASH_TOP)
+			changed_hash = true;
+		memcpy(rss->hash.toeplitz_hash_key, key,
+		       sizeof(rss->hash.toeplitz_hash_key));
+	}
+
+	if (indir) {
+		unsigned int i;
+
+		changed_indir = true;
+
+		for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++)
+			rss->indir.table[i] = indir[i];
+	}
+
+	if (changed_indir && rss->enabled)
+		mlx5e_rss_apply(rss, rqns, num_rqns);
+
+	if (changed_hash)
+		mlx5e_rss_update_tirs(rss);
+
+	return 0;
+}
+
+struct mlx5e_rss_params_hash mlx5e_rss_get_hash(struct mlx5e_rss *rss)
+{
+	return rss->hash;
+}
+
+u8 mlx5e_rss_get_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt)
+{
+	return rss->rx_hash_fields[tt];
+}
+
+int mlx5e_rss_set_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
+			      u8 rx_hash_fields)
+{
+	u8 old_rx_hash_fields;
+	int err;
+
+	old_rx_hash_fields = rss->rx_hash_fields[tt];
+
+	if (old_rx_hash_fields == rx_hash_fields)
+		return 0;
+
+	rss->rx_hash_fields[tt] = rx_hash_fields;
+
+	err = mlx5e_rss_update_tir(rss, tt, false);
+	if (err) {
+		rss->rx_hash_fields[tt] = old_rx_hash_fields;
+		mlx5e_rss_warn(rss->mdev,
+			       "Failed to update RSS hash fields of indirect TIR for traffic type %d: err = %d\n",
+			       tt, err);
+		return err;
+	}
+
+	if (!(rss->inner_ft_support))
+		return 0;
+
+	err = mlx5e_rss_update_tir(rss, tt, true);
+	if (err) {
+		/* Partial update happened. Try to revert - it may fail too, but
+		 * there is nothing more we can do.
+		 */
+		rss->rx_hash_fields[tt] = old_rx_hash_fields;
+		mlx5e_rss_warn(rss->mdev,
+			       "Failed to update RSS hash fields of inner indirect TIR for traffic type %d: err = %d\n",
+			       tt, err);
+		if (mlx5e_rss_update_tir(rss, tt, false))
+			mlx5e_rss_warn(rss->mdev,
+				       "Partial update of RSS hash fields happened: failed to revert indirect TIR for traffic type %d to the old values\n",
+				       tt);
+	}
+
+	return err;
+}
+
+void mlx5e_rss_set_indir_uniform(struct mlx5e_rss *rss, unsigned int nch)
+{
+	mlx5e_rss_params_indir_init_uniform(&rss->indir, nch);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
new file mode 100644
index 000000000000..d522a10dadf3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. */
+
+#ifndef __MLX5_EN_RSS_H__
+#define __MLX5_EN_RSS_H__
+
+#include "rqt.h"
+#include "tir.h"
+#include "fs.h"
+
+struct mlx5e_rss_params_traffic_type
+mlx5e_rss_get_default_tt_config(enum mlx5_traffic_types tt);
+
+struct mlx5e_rss;
+
+struct mlx5e_rss *mlx5e_rss_alloc(void);
+void mlx5e_rss_free(struct mlx5e_rss *rss);
+int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
+		   bool inner_ft_support, u32 drop_rqn,
+		   const struct mlx5e_lro_param *init_lro_param);
+int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
+			   bool inner_ft_support, u32 drop_rqn);
+int mlx5e_rss_cleanup(struct mlx5e_rss *rss);
+
+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);
+
+u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
+		       bool inner);
+int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
+			  enum mlx5_traffic_types tt,
+			  const struct mlx5e_lro_param *init_lro_param,
+			  bool inner, u32 *tirn);
+
+void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns);
+void mlx5e_rss_disable(struct mlx5e_rss *rss);
+
+int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_param);
+int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc);
+int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
+		       const u8 *key, const u8 *hfunc,
+		       u32 *rqns, 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);
+int mlx5e_rss_set_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
+			      u8 rx_hash_fields);
+void mlx5e_rss_set_indir_uniform(struct mlx5e_rss *rss, unsigned int nch);
+#endif /* __MLX5_EN_RSS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
new file mode 100644
index 000000000000..bf0313e2682b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -0,0 +1,690 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */
+
+#include "rx_res.h"
+#include "channels.h"
+#include "params.h"
+
+#define MLX5E_MAX_NUM_RSS 16
+
+struct mlx5e_rx_res {
+	struct mlx5_core_dev *mdev;
+	enum mlx5e_rx_res_features features;
+	unsigned int max_nch;
+	u32 drop_rqn;
+
+	struct mlx5e_rss *rss[MLX5E_MAX_NUM_RSS];
+	bool rss_active;
+	u32 rss_rqns[MLX5E_INDIR_RQT_SIZE];
+	unsigned int rss_nch;
+
+	struct {
+		struct mlx5e_rqt direct_rqt;
+		struct mlx5e_tir direct_tir;
+		struct mlx5e_rqt xsk_rqt;
+		struct mlx5e_tir xsk_tir;
+	} *channels;
+
+	struct {
+		struct mlx5e_rqt rqt;
+		struct mlx5e_tir tir;
+	} ptp;
+};
+
+/* API for rx_res_rss_* */
+
+static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res,
+				     const struct mlx5e_lro_param *init_lro_param,
+				     unsigned int init_nch)
+{
+	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
+	struct mlx5e_rss *rss;
+	int err;
+
+	if (WARN_ON(res->rss[0]))
+		return -EINVAL;
+
+	rss = mlx5e_rss_alloc();
+	if (!rss)
+		return -ENOMEM;
+
+	err = mlx5e_rss_init(rss, res->mdev, inner_ft_support, res->drop_rqn,
+			     init_lro_param);
+	if (err)
+		goto err_rss_free;
+
+	mlx5e_rss_set_indir_uniform(rss, init_nch);
+
+	res->rss[0] = rss;
+
+	return 0;
+
+err_rss_free:
+	mlx5e_rss_free(rss);
+	return err;
+}
+
+int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int init_nch)
+{
+	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
+	struct mlx5e_rss *rss;
+	int err, i;
+
+	for (i = 1; i < MLX5E_MAX_NUM_RSS; i++)
+		if (!res->rss[i])
+			break;
+
+	if (i == MLX5E_MAX_NUM_RSS)
+		return -ENOSPC;
+
+	rss = mlx5e_rss_alloc();
+	if (!rss)
+		return -ENOMEM;
+
+	err = mlx5e_rss_init_no_tirs(rss, res->mdev, inner_ft_support, res->drop_rqn);
+	if (err)
+		goto err_rss_free;
+
+	mlx5e_rss_set_indir_uniform(rss, init_nch);
+	if (res->rss_active)
+		mlx5e_rss_enable(rss, res->rss_rqns, res->rss_nch);
+
+	res->rss[i] = rss;
+	*rss_idx = i;
+
+	return 0;
+
+err_rss_free:
+	mlx5e_rss_free(rss);
+	return err;
+}
+
+static int __mlx5e_rx_res_rss_destroy(struct mlx5e_rx_res *res, u32 rss_idx)
+{
+	struct mlx5e_rss *rss = res->rss[rss_idx];
+	int err;
+
+	err = mlx5e_rss_cleanup(rss);
+	if (err)
+		return err;
+
+	mlx5e_rss_free(rss);
+	res->rss[rss_idx] = NULL;
+
+	return 0;
+}
+
+int mlx5e_rx_res_rss_destroy(struct mlx5e_rx_res *res, u32 rss_idx)
+{
+	struct mlx5e_rss *rss;
+
+	if (rss_idx >= MLX5E_MAX_NUM_RSS)
+		return -EINVAL;
+
+	rss = res->rss[rss_idx];
+	if (!rss)
+		return -EINVAL;
+
+	return __mlx5e_rx_res_rss_destroy(res, rss_idx);
+}
+
+static void mlx5e_rx_res_rss_destroy_all(struct mlx5e_rx_res *res)
+{
+	int i;
+
+	for (i = 0; i < MLX5E_MAX_NUM_RSS; i++) {
+		struct mlx5e_rss *rss = res->rss[i];
+		int err;
+
+		if (!rss)
+			continue;
+
+		err = __mlx5e_rx_res_rss_destroy(res, i);
+		if (err) {
+			unsigned int refcount;
+
+			refcount = mlx5e_rss_refcnt_read(rss);
+			mlx5_core_warn(res->mdev,
+				       "Failed to destroy RSS context %d, refcount = %u, err = %d\n",
+				       i, refcount, err);
+		}
+	}
+}
+
+static void mlx5e_rx_res_rss_enable(struct mlx5e_rx_res *res)
+{
+	int i;
+
+	res->rss_active = true;
+
+	for (i = 0; i < MLX5E_MAX_NUM_RSS; i++) {
+		struct mlx5e_rss *rss = res->rss[i];
+
+		if (!rss)
+			continue;
+		mlx5e_rss_enable(rss, res->rss_rqns, res->rss_nch);
+	}
+}
+
+static void mlx5e_rx_res_rss_disable(struct mlx5e_rx_res *res)
+{
+	int i;
+
+	res->rss_active = false;
+
+	for (i = 0; i < MLX5E_MAX_NUM_RSS; i++) {
+		struct mlx5e_rss *rss = res->rss[i];
+
+		if (!rss)
+			continue;
+		mlx5e_rss_disable(rss);
+	}
+}
+
+/* Updates the indirection table SW shadow, does not update the HW resources yet */
+void mlx5e_rx_res_rss_set_indir_uniform(struct mlx5e_rx_res *res, unsigned int nch)
+{
+	WARN_ON_ONCE(res->rss_active);
+	mlx5e_rss_set_indir_uniform(res->rss[0], nch);
+}
+
+int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
+			      u32 *indir, u8 *key, u8 *hfunc)
+{
+	struct mlx5e_rss *rss;
+
+	if (rss_idx >= MLX5E_MAX_NUM_RSS)
+		return -EINVAL;
+
+	rss = res->rss[rss_idx];
+	if (!rss)
+		return -ENOENT;
+
+	return mlx5e_rss_get_rxfh(rss, indir, key, hfunc);
+}
+
+int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
+			      const u32 *indir, const u8 *key, const u8 *hfunc)
+{
+	struct mlx5e_rss *rss;
+
+	if (rss_idx >= MLX5E_MAX_NUM_RSS)
+		return -EINVAL;
+
+	rss = res->rss[rss_idx];
+	if (!rss)
+		return -ENOENT;
+
+	return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, res->rss_nch);
+}
+
+u8 mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt)
+{
+	struct mlx5e_rss *rss = res->rss[0];
+
+	return mlx5e_rss_get_hash_fields(rss, tt);
+}
+
+int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt,
+				     u8 rx_hash_fields)
+{
+	struct mlx5e_rss *rss = res->rss[0];
+
+	return mlx5e_rss_set_hash_fields(rss, tt, rx_hash_fields);
+}
+
+int mlx5e_rx_res_rss_cnt(struct mlx5e_rx_res *res)
+{
+	int i, cnt;
+
+	cnt = 0;
+	for (i = 0; i < MLX5E_MAX_NUM_RSS; i++)
+		if (res->rss[i])
+			cnt++;
+
+	return cnt;
+}
+
+int mlx5e_rx_res_rss_index(struct mlx5e_rx_res *res, struct mlx5e_rss *rss)
+{
+	int i;
+
+	if (!rss)
+		return -EINVAL;
+
+	for (i = 0; i < MLX5E_MAX_NUM_RSS; i++)
+		if (rss == res->rss[i])
+			return i;
+
+	return -ENOENT;
+}
+
+struct mlx5e_rss *mlx5e_rx_res_rss_get(struct mlx5e_rx_res *res, u32 rss_idx)
+{
+	if (rss_idx >= MLX5E_MAX_NUM_RSS)
+		return NULL;
+
+	return res->rss[rss_idx];
+}
+
+/* End of API rx_res_rss_* */
+
+struct mlx5e_rx_res *mlx5e_rx_res_alloc(void)
+{
+	return kvzalloc(sizeof(struct mlx5e_rx_res), GFP_KERNEL);
+}
+
+static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res,
+				      const struct mlx5e_lro_param *init_lro_param)
+{
+	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
+	struct mlx5e_tir_builder *builder;
+	int err = 0;
+	int ix;
+
+	builder = mlx5e_tir_builder_alloc(false);
+	if (!builder)
+		return -ENOMEM;
+
+	res->channels = kvcalloc(res->max_nch, sizeof(*res->channels), GFP_KERNEL);
+	if (!res->channels) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	for (ix = 0; ix < res->max_nch; ix++) {
+		err = mlx5e_rqt_init_direct(&res->channels[ix].direct_rqt,
+					    res->mdev, false, res->drop_rqn);
+		if (err) {
+			mlx5_core_warn(res->mdev, "Failed to create a direct RQT: err = %d, ix = %u\n",
+				       err, ix);
+			goto err_destroy_direct_rqts;
+		}
+	}
+
+	for (ix = 0; ix < res->max_nch; ix++) {
+		mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn,
+					    mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
+					    inner_ft_support);
+		mlx5e_tir_builder_build_lro(builder, init_lro_param);
+		mlx5e_tir_builder_build_direct(builder);
+
+		err = mlx5e_tir_init(&res->channels[ix].direct_tir, builder, res->mdev, true);
+		if (err) {
+			mlx5_core_warn(res->mdev, "Failed to create a direct TIR: err = %d, ix = %u\n",
+				       err, ix);
+			goto err_destroy_direct_tirs;
+		}
+
+		mlx5e_tir_builder_clear(builder);
+	}
+
+	if (!(res->features & MLX5E_RX_RES_FEATURE_XSK))
+		goto out;
+
+	for (ix = 0; ix < res->max_nch; ix++) {
+		err = mlx5e_rqt_init_direct(&res->channels[ix].xsk_rqt,
+					    res->mdev, false, res->drop_rqn);
+		if (err) {
+			mlx5_core_warn(res->mdev, "Failed to create an XSK RQT: err = %d, ix = %u\n",
+				       err, ix);
+			goto err_destroy_xsk_rqts;
+		}
+	}
+
+	for (ix = 0; ix < res->max_nch; ix++) {
+		mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn,
+					    mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
+					    inner_ft_support);
+		mlx5e_tir_builder_build_lro(builder, init_lro_param);
+		mlx5e_tir_builder_build_direct(builder);
+
+		err = mlx5e_tir_init(&res->channels[ix].xsk_tir, builder, res->mdev, true);
+		if (err) {
+			mlx5_core_warn(res->mdev, "Failed to create an XSK TIR: err = %d, ix = %u\n",
+				       err, ix);
+			goto err_destroy_xsk_tirs;
+		}
+
+		mlx5e_tir_builder_clear(builder);
+	}
+
+	goto out;
+
+err_destroy_xsk_tirs:
+	while (--ix >= 0)
+		mlx5e_tir_destroy(&res->channels[ix].xsk_tir);
+
+	ix = res->max_nch;
+err_destroy_xsk_rqts:
+	while (--ix >= 0)
+		mlx5e_rqt_destroy(&res->channels[ix].xsk_rqt);
+
+	ix = res->max_nch;
+err_destroy_direct_tirs:
+	while (--ix >= 0)
+		mlx5e_tir_destroy(&res->channels[ix].direct_tir);
+
+	ix = res->max_nch;
+err_destroy_direct_rqts:
+	while (--ix >= 0)
+		mlx5e_rqt_destroy(&res->channels[ix].direct_rqt);
+
+	kvfree(res->channels);
+
+out:
+	mlx5e_tir_builder_free(builder);
+
+	return err;
+}
+
+static int mlx5e_rx_res_ptp_init(struct mlx5e_rx_res *res)
+{
+	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
+	struct mlx5e_tir_builder *builder;
+	int err;
+
+	builder = mlx5e_tir_builder_alloc(false);
+	if (!builder)
+		return -ENOMEM;
+
+	err = mlx5e_rqt_init_direct(&res->ptp.rqt, res->mdev, false, res->drop_rqn);
+	if (err)
+		goto out;
+
+	mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn,
+				    mlx5e_rqt_get_rqtn(&res->ptp.rqt),
+				    inner_ft_support);
+	mlx5e_tir_builder_build_direct(builder);
+
+	err = mlx5e_tir_init(&res->ptp.tir, builder, res->mdev, true);
+	if (err)
+		goto err_destroy_ptp_rqt;
+
+	goto out;
+
+err_destroy_ptp_rqt:
+	mlx5e_rqt_destroy(&res->ptp.rqt);
+
+out:
+	mlx5e_tir_builder_free(builder);
+	return err;
+}
+
+static void mlx5e_rx_res_channels_destroy(struct mlx5e_rx_res *res)
+{
+	unsigned int ix;
+
+	for (ix = 0; ix < res->max_nch; ix++) {
+		mlx5e_tir_destroy(&res->channels[ix].direct_tir);
+		mlx5e_rqt_destroy(&res->channels[ix].direct_rqt);
+
+		if (!(res->features & MLX5E_RX_RES_FEATURE_XSK))
+			continue;
+
+		mlx5e_tir_destroy(&res->channels[ix].xsk_tir);
+		mlx5e_rqt_destroy(&res->channels[ix].xsk_rqt);
+	}
+
+	kvfree(res->channels);
+}
+
+static void mlx5e_rx_res_ptp_destroy(struct mlx5e_rx_res *res)
+{
+	mlx5e_tir_destroy(&res->ptp.tir);
+	mlx5e_rqt_destroy(&res->ptp.rqt);
+}
+
+int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev,
+		      enum mlx5e_rx_res_features features, unsigned int max_nch,
+		      u32 drop_rqn, const struct mlx5e_lro_param *init_lro_param,
+		      unsigned int init_nch)
+{
+	int err;
+
+	res->mdev = mdev;
+	res->features = features;
+	res->max_nch = max_nch;
+	res->drop_rqn = drop_rqn;
+
+	err = mlx5e_rx_res_rss_init_def(res, init_lro_param, init_nch);
+	if (err)
+		goto err_out;
+
+	err = mlx5e_rx_res_channels_init(res, init_lro_param);
+	if (err)
+		goto err_rss_destroy;
+
+	err = mlx5e_rx_res_ptp_init(res);
+	if (err)
+		goto err_channels_destroy;
+
+	return 0;
+
+err_channels_destroy:
+	mlx5e_rx_res_channels_destroy(res);
+err_rss_destroy:
+	__mlx5e_rx_res_rss_destroy(res, 0);
+err_out:
+	return err;
+}
+
+void mlx5e_rx_res_destroy(struct mlx5e_rx_res *res)
+{
+	mlx5e_rx_res_ptp_destroy(res);
+	mlx5e_rx_res_channels_destroy(res);
+	mlx5e_rx_res_rss_destroy_all(res);
+}
+
+void mlx5e_rx_res_free(struct mlx5e_rx_res *res)
+{
+	kvfree(res);
+}
+
+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);
+}
+
+u32 mlx5e_rx_res_get_tirn_xsk(struct mlx5e_rx_res *res, unsigned int ix)
+{
+	WARN_ON(!(res->features & MLX5E_RX_RES_FEATURE_XSK));
+
+	return mlx5e_tir_get_tirn(&res->channels[ix].xsk_tir);
+}
+
+u32 mlx5e_rx_res_get_tirn_rss(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt)
+{
+	struct mlx5e_rss *rss = res->rss[0];
+
+	return mlx5e_rss_get_tirn(rss, tt, false);
+}
+
+u32 mlx5e_rx_res_get_tirn_rss_inner(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt)
+{
+	struct mlx5e_rss *rss = res->rss[0];
+
+	return mlx5e_rss_get_tirn(rss, tt, true);
+}
+
+u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res)
+{
+	WARN_ON(!(res->features & MLX5E_RX_RES_FEATURE_PTP));
+	return mlx5e_tir_get_tirn(&res->ptp.tir);
+}
+
+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);
+}
+
+void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs)
+{
+	unsigned int nch, ix;
+	int err;
+
+	nch = mlx5e_channels_get_num(chs);
+
+	for (ix = 0; ix < chs->num; ix++)
+		mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]);
+	res->rss_nch = chs->num;
+
+	mlx5e_rx_res_rss_enable(res);
+
+	for (ix = 0; ix < nch; ix++) {
+		u32 rqn;
+
+		mlx5e_channels_get_regular_rqn(chs, ix, &rqn);
+		err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, rqn);
+		if (err)
+			mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (channel %u): err = %d\n",
+				       mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
+				       rqn, ix, err);
+
+		if (!(res->features & MLX5E_RX_RES_FEATURE_XSK))
+			continue;
+
+		if (!mlx5e_channels_get_xsk_rqn(chs, ix, &rqn))
+			rqn = res->drop_rqn;
+		err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, rqn);
+		if (err)
+			mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to RQ %#x (channel %u): err = %d\n",
+				       mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
+				       rqn, ix, err);
+	}
+	for (ix = nch; ix < res->max_nch; ix++) {
+		err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, res->drop_rqn);
+		if (err)
+			mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (channel %u): err = %d\n",
+				       mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
+				       res->drop_rqn, ix, err);
+
+		if (!(res->features & MLX5E_RX_RES_FEATURE_XSK))
+			continue;
+
+		err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, res->drop_rqn);
+		if (err)
+			mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to drop RQ %#x (channel %u): err = %d\n",
+				       mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
+				       res->drop_rqn, ix, err);
+	}
+
+	if (res->features & MLX5E_RX_RES_FEATURE_PTP) {
+		u32 rqn;
+
+		if (mlx5e_channels_get_ptp_rqn(chs, &rqn))
+			rqn = res->drop_rqn;
+
+		err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, rqn);
+		if (err)
+			mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (PTP): err = %d\n",
+				       mlx5e_rqt_get_rqtn(&res->ptp.rqt),
+				       rqn, err);
+	}
+}
+
+void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res)
+{
+	unsigned int ix;
+	int err;
+
+	mlx5e_rx_res_rss_disable(res);
+
+	for (ix = 0; ix < res->max_nch; ix++) {
+		err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, res->drop_rqn);
+		if (err)
+			mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (channel %u): err = %d\n",
+				       mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
+				       res->drop_rqn, ix, err);
+
+		if (!(res->features & MLX5E_RX_RES_FEATURE_XSK))
+			continue;
+
+		err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, res->drop_rqn);
+		if (err)
+			mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to drop RQ %#x (channel %u): err = %d\n",
+				       mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
+				       res->drop_rqn, ix, err);
+	}
+
+	if (res->features & MLX5E_RX_RES_FEATURE_PTP) {
+		err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, res->drop_rqn);
+		if (err)
+			mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (PTP): err = %d\n",
+				       mlx5e_rqt_get_rqtn(&res->ptp.rqt),
+				       res->drop_rqn, err);
+	}
+}
+
+int mlx5e_rx_res_xsk_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs,
+			      unsigned int ix)
+{
+	u32 rqn;
+	int err;
+
+	if (!mlx5e_channels_get_xsk_rqn(chs, ix, &rqn))
+		return -EINVAL;
+
+	err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, rqn);
+	if (err)
+		mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to XSK RQ %#x (channel %u): err = %d\n",
+			       mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
+			       rqn, ix, err);
+	return err;
+}
+
+int mlx5e_rx_res_xsk_deactivate(struct mlx5e_rx_res *res, unsigned int ix)
+{
+	int err;
+
+	err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, res->drop_rqn);
+	if (err)
+		mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to drop RQ %#x (channel %u): err = %d\n",
+			       mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
+			       res->drop_rqn, ix, err);
+	return err;
+}
+
+int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param *lro_param)
+{
+	struct mlx5e_tir_builder *builder;
+	int err, final_err;
+	unsigned int ix;
+
+	builder = mlx5e_tir_builder_alloc(true);
+	if (!builder)
+		return -ENOMEM;
+
+	mlx5e_tir_builder_build_lro(builder, lro_param);
+
+	final_err = 0;
+
+	for (ix = 0; ix < MLX5E_MAX_NUM_RSS; ix++) {
+		struct mlx5e_rss *rss = res->rss[ix];
+
+		if (!rss)
+			continue;
+
+		err = mlx5e_rss_lro_set_param(rss, lro_param);
+		if (err)
+			final_err = final_err ? : err;
+	}
+
+	for (ix = 0; ix < res->max_nch; ix++) {
+		err = mlx5e_tir_modify(&res->channels[ix].direct_tir, builder);
+		if (err) {
+			mlx5_core_warn(res->mdev, "Failed to update LRO state of direct TIR %#x for channel %u: err = %d\n",
+				       mlx5e_tir_get_tirn(&res->channels[ix].direct_tir), ix, err);
+			if (!final_err)
+				final_err = err;
+		}
+	}
+
+	mlx5e_tir_builder_free(builder);
+	return final_err;
+}
+
+struct mlx5e_rss_params_hash mlx5e_rx_res_get_current_hash(struct mlx5e_rx_res *res)
+{
+	return mlx5e_rss_get_hash(res->rss[0]);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
new file mode 100644
index 000000000000..4a15942d79f7
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */
+
+#ifndef __MLX5_EN_RX_RES_H__
+#define __MLX5_EN_RX_RES_H__
+
+#include <linux/kernel.h>
+#include "rqt.h"
+#include "tir.h"
+#include "fs.h"
+#include "rss.h"
+
+struct mlx5e_rx_res;
+
+struct mlx5e_channels;
+struct mlx5e_rss_params_hash;
+
+enum mlx5e_rx_res_features {
+	MLX5E_RX_RES_FEATURE_INNER_FT = BIT(0),
+	MLX5E_RX_RES_FEATURE_XSK = BIT(1),
+	MLX5E_RX_RES_FEATURE_PTP = BIT(2),
+};
+
+/* Setup */
+struct mlx5e_rx_res *mlx5e_rx_res_alloc(void);
+int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev,
+		      enum mlx5e_rx_res_features features, unsigned int max_nch,
+		      u32 drop_rqn, const struct mlx5e_lro_param *init_lro_param,
+		      unsigned int init_nch);
+void mlx5e_rx_res_destroy(struct mlx5e_rx_res *res);
+void mlx5e_rx_res_free(struct mlx5e_rx_res *res);
+
+/* TIRN getters for flow steering */
+u32 mlx5e_rx_res_get_tirn_direct(struct mlx5e_rx_res *res, unsigned int ix);
+u32 mlx5e_rx_res_get_tirn_xsk(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);
+
+/* RQTN getters for modules that create their own TIRs */
+u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix);
+
+/* Activate/deactivate API */
+void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs);
+void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res);
+int mlx5e_rx_res_xsk_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs,
+			      unsigned int ix);
+int mlx5e_rx_res_xsk_deactivate(struct mlx5e_rx_res *res, unsigned int ix);
+
+/* 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);
+int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
+			      const u32 *indir, const u8 *key, const u8 *hfunc);
+
+u8 mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
+int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt,
+				     u8 rx_hash_fields);
+int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param *lro_param);
+
+int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int init_nch);
+int mlx5e_rx_res_rss_destroy(struct mlx5e_rx_res *res, u32 rss_idx);
+int mlx5e_rx_res_rss_cnt(struct mlx5e_rx_res *res);
+int mlx5e_rx_res_rss_index(struct mlx5e_rx_res *res, struct mlx5e_rss *rss);
+struct mlx5e_rss *mlx5e_rx_res_rss_get(struct mlx5e_rx_res *res, u32 rss_idx);
+
+/* Workaround for hairpin */
+struct mlx5e_rss_params_hash mlx5e_rx_res_get_current_hash(struct mlx5e_rx_res *res);
+
+#endif /* __MLX5_EN_RX_RES_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
new file mode 100644
index 000000000000..a3e43e898a56
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+#include "en_tc.h"
+#include "post_act.h"
+#include "mlx5_core.h"
+
+struct mlx5e_post_act {
+	enum mlx5_flow_namespace_type ns_type;
+	struct mlx5_fs_chains *chains;
+	struct mlx5_flow_table *ft;
+	struct mlx5e_priv *priv;
+	struct xarray ids;
+};
+
+struct mlx5e_post_act_handle {
+	enum mlx5_flow_namespace_type ns_type;
+	struct mlx5_flow_attr *attr;
+	struct mlx5_flow_handle *rule;
+	u32 id;
+};
+
+#define MLX5_POST_ACTION_BITS (mlx5e_tc_attr_to_reg_mappings[FTEID_TO_REG].mlen)
+#define MLX5_POST_ACTION_MAX GENMASK(MLX5_POST_ACTION_BITS - 1, 0)
+#define MLX5_POST_ACTION_MASK MLX5_POST_ACTION_MAX
+
+struct mlx5e_post_act *
+mlx5e_tc_post_act_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
+		       enum mlx5_flow_namespace_type ns_type)
+{
+	struct mlx5e_post_act *post_act;
+	int err;
+
+	if (ns_type == MLX5_FLOW_NAMESPACE_FDB &&
+	    !MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, ignore_flow_level)) {
+		mlx5_core_warn(priv->mdev, "firmware level support is missing\n");
+		err = -EOPNOTSUPP;
+		goto err_check;
+	} else if (!MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ignore_flow_level)) {
+		mlx5_core_warn(priv->mdev, "firmware level support is missing\n");
+		err = -EOPNOTSUPP;
+		goto err_check;
+	}
+
+	post_act = kzalloc(sizeof(*post_act), GFP_KERNEL);
+	if (!post_act) {
+		err = -ENOMEM;
+		goto err_check;
+	}
+	post_act->ft = mlx5_chains_create_global_table(chains);
+	if (IS_ERR(post_act->ft)) {
+		err = PTR_ERR(post_act->ft);
+		mlx5_core_warn(priv->mdev, "failed to create post action table, err: %d\n", err);
+		goto err_ft;
+	}
+	post_act->chains = chains;
+	post_act->ns_type = ns_type;
+	post_act->priv = priv;
+	xa_init_flags(&post_act->ids, XA_FLAGS_ALLOC1);
+	return post_act;
+
+err_ft:
+	kfree(post_act);
+err_check:
+	return ERR_PTR(err);
+}
+
+void
+mlx5e_tc_post_act_destroy(struct mlx5e_post_act *post_act)
+{
+	if (IS_ERR_OR_NULL(post_act))
+		return;
+
+	xa_destroy(&post_act->ids);
+	mlx5_chains_destroy_global_table(post_act->chains, post_act->ft);
+	kfree(post_act);
+}
+
+struct mlx5e_post_act_handle *
+mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *attr)
+{
+	u32 attr_sz = ns_to_attr_sz(post_act->ns_type);
+	struct mlx5e_post_act_handle *handle = NULL;
+	struct mlx5_flow_attr *post_attr = NULL;
+	struct mlx5_flow_spec *spec = NULL;
+	int err;
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	post_attr = mlx5_alloc_flow_attr(post_act->ns_type);
+	if (!handle || !spec || !post_attr) {
+		kfree(post_attr);
+		kvfree(spec);
+		kfree(handle);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	memcpy(post_attr, attr, attr_sz);
+	post_attr->chain = 0;
+	post_attr->prio = 0;
+	post_attr->ft = post_act->ft;
+	post_attr->inner_match_level = MLX5_MATCH_NONE;
+	post_attr->outer_match_level = MLX5_MATCH_NONE;
+	post_attr->action &= ~(MLX5_FLOW_CONTEXT_ACTION_DECAP);
+
+	handle->ns_type = post_act->ns_type;
+	/* Splits were handled before post action */
+	if (handle->ns_type == MLX5_FLOW_NAMESPACE_FDB)
+		post_attr->esw_attr->split_count = 0;
+
+	err = xa_alloc(&post_act->ids, &handle->id, post_attr,
+		       XA_LIMIT(1, MLX5_POST_ACTION_MAX), GFP_KERNEL);
+	if (err)
+		goto err_xarray;
+
+	/* Post action rule matches on fte_id and executes original rule's
+	 * tc rule action
+	 */
+	mlx5e_tc_match_to_reg_match(spec, FTEID_TO_REG,
+				    handle->id, MLX5_POST_ACTION_MASK);
+
+	handle->rule = mlx5_tc_rule_insert(post_act->priv, spec, post_attr);
+	if (IS_ERR(handle->rule)) {
+		err = PTR_ERR(handle->rule);
+		netdev_warn(post_act->priv->netdev, "Failed to add post action rule");
+		goto err_rule;
+	}
+	handle->attr = post_attr;
+
+	kvfree(spec);
+	return handle;
+
+err_rule:
+	xa_erase(&post_act->ids, handle->id);
+err_xarray:
+	kfree(post_attr);
+	kvfree(spec);
+	kfree(handle);
+	return ERR_PTR(err);
+}
+
+void
+mlx5e_tc_post_act_del(struct mlx5e_post_act *post_act, struct mlx5e_post_act_handle *handle)
+{
+	mlx5_tc_rule_delete(post_act->priv, handle->rule, handle->attr);
+	xa_erase(&post_act->ids, handle->id);
+	kfree(handle->attr);
+	kfree(handle);
+}
+
+struct mlx5_flow_table *
+mlx5e_tc_post_act_get_ft(struct mlx5e_post_act *post_act)
+{
+	return post_act->ft;
+}
+
+/* Allocate a header modify action to write the post action handle fte id to a register. */
+int
+mlx5e_tc_post_act_set_handle(struct mlx5_core_dev *dev,
+			     struct mlx5e_post_act_handle *handle,
+			     struct mlx5e_tc_mod_hdr_acts *acts)
+{
+	return mlx5e_tc_match_to_reg_set(dev, acts, handle->ns_type, FTEID_TO_REG, handle->id);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.h
new file mode 100644
index 000000000000..b530ec1981a5
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef __MLX5_POST_ACTION_H__
+#define __MLX5_POST_ACTION_H__
+
+#include "en.h"
+#include "lib/fs_chains.h"
+
+struct mlx5_flow_attr;
+struct mlx5e_priv;
+struct mlx5e_tc_mod_hdr_acts;
+
+struct mlx5e_post_act *
+mlx5e_tc_post_act_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
+		       enum mlx5_flow_namespace_type ns_type);
+
+void
+mlx5e_tc_post_act_destroy(struct mlx5e_post_act *post_act);
+
+struct mlx5e_post_act_handle *
+mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *attr);
+
+void
+mlx5e_tc_post_act_del(struct mlx5e_post_act *post_act, struct mlx5e_post_act_handle *handle);
+
+struct mlx5_flow_table *
+mlx5e_tc_post_act_get_ft(struct mlx5e_post_act *post_act);
+
+int
+mlx5e_tc_post_act_set_handle(struct mlx5_core_dev *dev,
+			     struct mlx5e_post_act_handle *handle,
+			     struct mlx5e_tc_mod_hdr_acts *acts);
+
+#endif /* __MLX5_POST_ACTION_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
index d3ad78aa9d45..6552ecee3f9b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
@@ -4,7 +4,8 @@
 #include <linux/skbuff.h>
 #include <net/psample.h>
 #include "en/mapping.h"
-#include "esw/sample.h"
+#include "en/tc/post_act.h"
+#include "sample.h"
 #include "eswitch.h"
 #include "en_tc.h"
 #include "fs_core.h"
@@ -17,17 +18,18 @@ static const struct esw_vport_tbl_namespace mlx5_esw_vport_tbl_sample_ns = {
 	.flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT | MLX5_FLOW_TABLE_TUNNEL_EN_DECAP,
 };
 
-struct mlx5_esw_psample {
-	struct mlx5e_priv *priv;
+struct mlx5e_tc_psample {
+	struct mlx5_eswitch *esw;
 	struct mlx5_flow_table *termtbl;
 	struct mlx5_flow_handle *termtbl_rule;
 	DECLARE_HASHTABLE(hashtbl, 8);
 	struct mutex ht_lock; /* protect hashtbl */
 	DECLARE_HASHTABLE(restore_hashtbl, 8);
 	struct mutex restore_lock; /* protect restore_hashtbl */
+	struct mlx5e_post_act *post_act;
 };
 
-struct mlx5_sampler {
+struct mlx5e_sampler {
 	struct hlist_node hlist;
 	u32 sampler_id;
 	u32 sample_ratio;
@@ -36,29 +38,32 @@ struct mlx5_sampler {
 	int count;
 };
 
-struct mlx5_sample_flow {
-	struct mlx5_sampler *sampler;
-	struct mlx5_sample_restore *restore;
+struct mlx5e_sample_flow {
+	struct mlx5e_sampler *sampler;
+	struct mlx5e_sample_restore *restore;
 	struct mlx5_flow_attr *pre_attr;
 	struct mlx5_flow_handle *pre_rule;
-	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_attr *post_attr;
+	struct mlx5_flow_handle *post_rule;
+	struct mlx5e_post_act_handle *post_act_handle;
 };
 
-struct mlx5_sample_restore {
+struct mlx5e_sample_restore {
 	struct hlist_node hlist;
 	struct mlx5_modify_hdr *modify_hdr;
 	struct mlx5_flow_handle *rule;
+	struct mlx5e_post_act_handle *post_act_handle;
 	u32 obj_id;
 	int count;
 };
 
 static int
-sampler_termtbl_create(struct mlx5_esw_psample *esw_psample)
+sampler_termtbl_create(struct mlx5e_tc_psample *tc_psample)
 {
-	struct mlx5_core_dev *dev = esw_psample->priv->mdev;
-	struct mlx5_eswitch *esw = dev->priv.eswitch;
+	struct mlx5_eswitch *esw = tc_psample->esw;
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_destination dest = {};
+	struct mlx5_core_dev *dev = esw->dev;
 	struct mlx5_flow_namespace *root_ns;
 	struct mlx5_flow_act act = {};
 	int err;
@@ -79,20 +84,20 @@ sampler_termtbl_create(struct mlx5_esw_psample *esw_psample)
 	ft_attr.prio = FDB_SLOW_PATH;
 	ft_attr.max_fte = 1;
 	ft_attr.level = 1;
-	esw_psample->termtbl = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr);
-	if (IS_ERR(esw_psample->termtbl)) {
-		err = PTR_ERR(esw_psample->termtbl);
+	tc_psample->termtbl = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr);
+	if (IS_ERR(tc_psample->termtbl)) {
+		err = PTR_ERR(tc_psample->termtbl);
 		mlx5_core_warn(dev, "failed to create termtbl, err: %d\n", err);
 		return err;
 	}
 
 	act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	dest.vport.num = esw->manager_vport;
-	esw_psample->termtbl_rule = mlx5_add_flow_rules(esw_psample->termtbl, NULL, &act, &dest, 1);
-	if (IS_ERR(esw_psample->termtbl_rule)) {
-		err = PTR_ERR(esw_psample->termtbl_rule);
+	tc_psample->termtbl_rule = mlx5_add_flow_rules(tc_psample->termtbl, NULL, &act, &dest, 1);
+	if (IS_ERR(tc_psample->termtbl_rule)) {
+		err = PTR_ERR(tc_psample->termtbl_rule);
 		mlx5_core_warn(dev, "failed to create termtbl rule, err: %d\n", err);
-		mlx5_destroy_flow_table(esw_psample->termtbl);
+		mlx5_destroy_flow_table(tc_psample->termtbl);
 		return err;
 	}
 
@@ -100,14 +105,14 @@ sampler_termtbl_create(struct mlx5_esw_psample *esw_psample)
 }
 
 static void
-sampler_termtbl_destroy(struct mlx5_esw_psample *esw_psample)
+sampler_termtbl_destroy(struct mlx5e_tc_psample *tc_psample)
 {
-	mlx5_del_flow_rules(esw_psample->termtbl_rule);
-	mlx5_destroy_flow_table(esw_psample->termtbl);
+	mlx5_del_flow_rules(tc_psample->termtbl_rule);
+	mlx5_destroy_flow_table(tc_psample->termtbl);
 }
 
 static int
-sampler_obj_create(struct mlx5_core_dev *mdev, struct mlx5_sampler *sampler)
+sampler_obj_create(struct mlx5_core_dev *mdev, struct mlx5e_sampler *sampler)
 {
 	u32 in[MLX5_ST_SZ_DW(create_sampler_obj_in)] = {};
 	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)];
@@ -163,16 +168,16 @@ sampler_cmp(u32 sample_ratio1, u32 default_table_id1, u32 sample_ratio2, u32 def
 	return sample_ratio1 != sample_ratio2 || default_table_id1 != default_table_id2;
 }
 
-static struct mlx5_sampler *
-sampler_get(struct mlx5_esw_psample *esw_psample, u32 sample_ratio, u32 default_table_id)
+static struct mlx5e_sampler *
+sampler_get(struct mlx5e_tc_psample *tc_psample, u32 sample_ratio, u32 default_table_id)
 {
-	struct mlx5_sampler *sampler;
+	struct mlx5e_sampler *sampler;
 	u32 hash_key;
 	int err;
 
-	mutex_lock(&esw_psample->ht_lock);
+	mutex_lock(&tc_psample->ht_lock);
 	hash_key = sampler_hash(sample_ratio, default_table_id);
-	hash_for_each_possible(esw_psample->hashtbl, sampler, hlist, hash_key)
+	hash_for_each_possible(tc_psample->hashtbl, sampler, hlist, hash_key)
 		if (!sampler_cmp(sampler->sample_ratio, sampler->default_table_id,
 				 sample_ratio, default_table_id))
 			goto add_ref;
@@ -183,42 +188,49 @@ sampler_get(struct mlx5_esw_psample *esw_psample, u32 sample_ratio, u32 default_
 		goto err_alloc;
 	}
 
-	sampler->sample_table_id = esw_psample->termtbl->id;
+	sampler->sample_table_id = tc_psample->termtbl->id;
 	sampler->default_table_id = default_table_id;
 	sampler->sample_ratio = sample_ratio;
 
-	err = sampler_obj_create(esw_psample->priv->mdev, sampler);
+	err = sampler_obj_create(tc_psample->esw->dev, sampler);
 	if (err)
 		goto err_create;
 
-	hash_add(esw_psample->hashtbl, &sampler->hlist, hash_key);
+	hash_add(tc_psample->hashtbl, &sampler->hlist, hash_key);
 
 add_ref:
 	sampler->count++;
-	mutex_unlock(&esw_psample->ht_lock);
+	mutex_unlock(&tc_psample->ht_lock);
 	return sampler;
 
 err_create:
 	kfree(sampler);
 err_alloc:
-	mutex_unlock(&esw_psample->ht_lock);
+	mutex_unlock(&tc_psample->ht_lock);
 	return ERR_PTR(err);
 }
 
 static void
-sampler_put(struct mlx5_esw_psample *esw_psample, struct mlx5_sampler *sampler)
+sampler_put(struct mlx5e_tc_psample *tc_psample, struct mlx5e_sampler *sampler)
 {
-	mutex_lock(&esw_psample->ht_lock);
+	mutex_lock(&tc_psample->ht_lock);
 	if (--sampler->count == 0) {
 		hash_del(&sampler->hlist);
-		sampler_obj_destroy(esw_psample->priv->mdev, sampler->sampler_id);
+		sampler_obj_destroy(tc_psample->esw->dev, sampler->sampler_id);
 		kfree(sampler);
 	}
-	mutex_unlock(&esw_psample->ht_lock);
+	mutex_unlock(&tc_psample->ht_lock);
 }
 
+/* obj_id is used to restore the sample parameters.
+ * Set fte_id in original flow table, then match it in the default table.
+ * Only set it for NICs can preserve reg_c or decap action. For other cases,
+ * use the same match in the default table.
+ * Use one header rewrite for both obj_id and fte_id.
+ */
 static struct mlx5_modify_hdr *
-sample_metadata_rule_get(struct mlx5_core_dev *mdev, u32 obj_id)
+sample_modify_hdr_get(struct mlx5_core_dev *mdev, u32 obj_id,
+		      struct mlx5e_post_act_handle *handle)
 {
 	struct mlx5e_tc_mod_hdr_acts mod_acts = {};
 	struct mlx5_modify_hdr *modify_hdr;
@@ -229,6 +241,12 @@ sample_metadata_rule_get(struct mlx5_core_dev *mdev, u32 obj_id)
 	if (err)
 		goto err_set_regc0;
 
+	if (handle) {
+		err = mlx5e_tc_post_act_set_handle(mdev, handle, &mod_acts);
+		if (err)
+			goto err_post_act;
+	}
+
 	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_FDB,
 					      mod_acts.num_actions,
 					      mod_acts.actions);
@@ -241,23 +259,40 @@ sample_metadata_rule_get(struct mlx5_core_dev *mdev, u32 obj_id)
 	return modify_hdr;
 
 err_modify_hdr:
+err_post_act:
 	dealloc_mod_hdr_actions(&mod_acts);
 err_set_regc0:
 	return ERR_PTR(err);
 }
 
-static struct mlx5_sample_restore *
-sample_restore_get(struct mlx5_esw_psample *esw_psample, u32 obj_id)
+static u32
+restore_hash(u32 obj_id, struct mlx5e_post_act_handle *post_act_handle)
 {
-	struct mlx5_core_dev *mdev = esw_psample->priv->mdev;
-	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	struct mlx5_sample_restore *restore;
+	return jhash_2words(obj_id, hash32_ptr(post_act_handle), 0);
+}
+
+static bool
+restore_equal(struct mlx5e_sample_restore *restore, u32 obj_id,
+	      struct mlx5e_post_act_handle *post_act_handle)
+{
+	return restore->obj_id == obj_id && restore->post_act_handle == post_act_handle;
+}
+
+static struct mlx5e_sample_restore *
+sample_restore_get(struct mlx5e_tc_psample *tc_psample, u32 obj_id,
+		   struct mlx5e_post_act_handle *post_act_handle)
+{
+	struct mlx5_eswitch *esw = tc_psample->esw;
+	struct mlx5_core_dev *mdev = esw->dev;
+	struct mlx5e_sample_restore *restore;
 	struct mlx5_modify_hdr *modify_hdr;
+	u32 hash_key;
 	int err;
 
-	mutex_lock(&esw_psample->restore_lock);
-	hash_for_each_possible(esw_psample->restore_hashtbl, restore, hlist, obj_id)
-		if (restore->obj_id == obj_id)
+	mutex_lock(&tc_psample->restore_lock);
+	hash_key = restore_hash(obj_id, post_act_handle);
+	hash_for_each_possible(tc_psample->restore_hashtbl, restore, hlist, hash_key)
+		if (restore_equal(restore, obj_id, post_act_handle))
 			goto add_ref;
 
 	restore = kzalloc(sizeof(*restore), GFP_KERNEL);
@@ -266,8 +301,9 @@ sample_restore_get(struct mlx5_esw_psample *esw_psample, u32 obj_id)
 		goto err_alloc;
 	}
 	restore->obj_id = obj_id;
+	restore->post_act_handle = post_act_handle;
 
-	modify_hdr = sample_metadata_rule_get(mdev, obj_id);
+	modify_hdr = sample_modify_hdr_get(mdev, obj_id, post_act_handle);
 	if (IS_ERR(modify_hdr)) {
 		err = PTR_ERR(modify_hdr);
 		goto err_modify_hdr;
@@ -280,10 +316,10 @@ sample_restore_get(struct mlx5_esw_psample *esw_psample, u32 obj_id)
 		goto err_restore;
 	}
 
-	hash_add(esw_psample->restore_hashtbl, &restore->hlist, obj_id);
+	hash_add(tc_psample->restore_hashtbl, &restore->hlist, hash_key);
 add_ref:
 	restore->count++;
-	mutex_unlock(&esw_psample->restore_lock);
+	mutex_unlock(&tc_psample->restore_lock);
 	return restore;
 
 err_restore:
@@ -291,26 +327,26 @@ err_restore:
 err_modify_hdr:
 	kfree(restore);
 err_alloc:
-	mutex_unlock(&esw_psample->restore_lock);
+	mutex_unlock(&tc_psample->restore_lock);
 	return ERR_PTR(err);
 }
 
 static void
-sample_restore_put(struct mlx5_esw_psample *esw_psample, struct mlx5_sample_restore *restore)
+sample_restore_put(struct mlx5e_tc_psample *tc_psample, struct mlx5e_sample_restore *restore)
 {
-	mutex_lock(&esw_psample->restore_lock);
+	mutex_lock(&tc_psample->restore_lock);
 	if (--restore->count == 0)
 		hash_del(&restore->hlist);
-	mutex_unlock(&esw_psample->restore_lock);
+	mutex_unlock(&tc_psample->restore_lock);
 
 	if (!restore->count) {
 		mlx5_del_flow_rules(restore->rule);
-		mlx5_modify_header_dealloc(esw_psample->priv->mdev, restore->modify_hdr);
+		mlx5_modify_header_dealloc(tc_psample->esw->dev, restore->modify_hdr);
 		kfree(restore);
 	}
 }
 
-void mlx5_esw_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj)
+void mlx5e_tc_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj)
 {
 	u32 trunc_size = mapped_obj->sample.trunc_size;
 	struct psample_group psample_group = {};
@@ -325,6 +361,87 @@ void mlx5_esw_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj
 	psample_sample_packet(&psample_group, skb, mapped_obj->sample.rate, &md);
 }
 
+static int
+add_post_rule(struct mlx5_eswitch *esw, struct mlx5e_sample_flow *sample_flow,
+	      struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr,
+	      u32 *default_tbl_id)
+{
+	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
+	u32 attr_sz = ns_to_attr_sz(MLX5_FLOW_NAMESPACE_FDB);
+	struct mlx5_vport_tbl_attr per_vport_tbl_attr;
+	struct mlx5_flow_table *default_tbl;
+	struct mlx5_flow_attr *post_attr;
+	int err;
+
+	/* Allocate default table per vport, chain and prio. Otherwise, there is
+	 * only one default table for the same sampler object. Rules with different
+	 * prio and chain may overlap. For CT sample action, per vport default
+	 * table is needed to resotre the metadata.
+	 */
+	per_vport_tbl_attr.chain = attr->chain;
+	per_vport_tbl_attr.prio = attr->prio;
+	per_vport_tbl_attr.vport = esw_attr->in_rep->vport;
+	per_vport_tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns;
+	default_tbl = mlx5_esw_vporttbl_get(esw, &per_vport_tbl_attr);
+	if (IS_ERR(default_tbl)) {
+		err = PTR_ERR(default_tbl);
+		goto err_default_tbl;
+	}
+	*default_tbl_id = default_tbl->id;
+
+	post_attr = mlx5_alloc_flow_attr(MLX5_FLOW_NAMESPACE_FDB);
+	if (!post_attr) {
+		err = -ENOMEM;
+		goto err_attr;
+	}
+	sample_flow->post_attr = post_attr;
+	memcpy(post_attr, attr, attr_sz);
+	/* Perform the original matches on the default table.
+	 * Offload all actions except the sample action.
+	 */
+	post_attr->chain = 0;
+	post_attr->prio = 0;
+	post_attr->ft = default_tbl;
+	post_attr->flags = MLX5_ESW_ATTR_FLAG_NO_IN_PORT;
+
+	/* When offloading sample and encap action, if there is no valid
+	 * neigh data struct, a slow path rule is offloaded first. Source
+	 * port metadata match is set at that time. A per vport table is
+	 * already allocated. No need to match it again. So clear the source
+	 * port metadata match.
+	 */
+	mlx5_eswitch_clear_rule_source_port(esw, spec);
+	sample_flow->post_rule = mlx5_eswitch_add_offloaded_rule(esw, spec, post_attr);
+	if (IS_ERR(sample_flow->post_rule)) {
+		err = PTR_ERR(sample_flow->post_rule);
+		goto err_rule;
+	}
+	return 0;
+
+err_rule:
+	kfree(post_attr);
+err_attr:
+	mlx5_esw_vporttbl_put(esw, &per_vport_tbl_attr);
+err_default_tbl:
+	return err;
+}
+
+static void
+del_post_rule(struct mlx5_eswitch *esw, struct mlx5e_sample_flow *sample_flow,
+	      struct mlx5_flow_attr *attr)
+{
+	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
+	struct mlx5_vport_tbl_attr tbl_attr;
+
+	mlx5_eswitch_del_offloaded_rule(esw, sample_flow->post_rule, sample_flow->post_attr);
+	kfree(sample_flow->post_attr);
+	tbl_attr.chain = attr->chain;
+	tbl_attr.prio = attr->prio;
+	tbl_attr.vport = esw_attr->in_rep->vport;
+	tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns;
+	mlx5_esw_vporttbl_put(esw, &tbl_attr);
+}
+
 /* For the following typical flow table:
  *
  * +-------------------------------+
@@ -342,8 +459,9 @@ void mlx5_esw_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj
  *         +---------------------+
  *         +   original match    +
  *         +---------------------+
- *                    |
- *                    v
+ *               | set fte_id (if reg_c preserve cap)
+ *               | do decap (if required)
+ *               v
  * +------------------------------------------------+
  * +                Flow Sampler Object             +
  * +------------------------------------------------+
@@ -353,80 +471,82 @@ void mlx5_esw_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj
  * +------------------------------------------------+
  *            |                            |
  *            v                            v
- * +-----------------------------+  +----------------------------------------+
- * +        sample table         +  + default table per <vport, chain, prio> +
- * +-----------------------------+  +----------------------------------------+
- * + forward to management vport +  +            original match              +
- * +-----------------------------+  +----------------------------------------+
- *                                  +            other actions               +
- *                                  +----------------------------------------+
+ * +-----------------------------+  +-------------------+
+ * +        sample table         +  +   default table   +
+ * +-----------------------------+  +-------------------+
+ * + forward to management vport +             |
+ * +-----------------------------+             |
+ *                                     +-------+------+
+ *                                     |              |reg_c preserve cap
+ *                                     |              |or decap action
+ *                                     v              v
+ *                        +-----------------+   +-------------+
+ *                        + per vport table +   + post action +
+ *                        +-----------------+   +-------------+
+ *                        + original match  +
+ *                        +-----------------+
+ *                        + other actions   +
+ *                        +-----------------+
  */
 struct mlx5_flow_handle *
-mlx5_esw_sample_offload(struct mlx5_esw_psample *esw_psample,
+mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
 			struct mlx5_flow_spec *spec,
-			struct mlx5_flow_attr *attr)
+			struct mlx5_flow_attr *attr,
+			u32 tunnel_id)
 {
+	struct mlx5e_post_act_handle *post_act_handle = NULL;
 	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
-	struct mlx5_vport_tbl_attr per_vport_tbl_attr;
 	struct mlx5_esw_flow_attr *pre_esw_attr;
 	struct mlx5_mapped_obj restore_obj = {};
-	struct mlx5_sample_flow *sample_flow;
-	struct mlx5_sample_attr *sample_attr;
-	struct mlx5_flow_table *default_tbl;
+	struct mlx5e_sample_flow *sample_flow;
+	struct mlx5e_sample_attr *sample_attr;
 	struct mlx5_flow_attr *pre_attr;
 	struct mlx5_eswitch *esw;
+	u32 default_tbl_id;
 	u32 obj_id;
 	int err;
 
-	if (IS_ERR_OR_NULL(esw_psample))
+	if (IS_ERR_OR_NULL(tc_psample))
 		return ERR_PTR(-EOPNOTSUPP);
 
 	/* If slow path flag is set, eg. when the neigh is invalid for encap,
 	 * don't offload sample action.
 	 */
-	esw = esw_psample->priv->mdev->priv.eswitch;
+	esw = tc_psample->esw;
 	if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)
 		return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
 
 	sample_flow = kzalloc(sizeof(*sample_flow), GFP_KERNEL);
 	if (!sample_flow)
 		return ERR_PTR(-ENOMEM);
-	esw_attr->sample->sample_flow = sample_flow;
-
-	/* Allocate default table per vport, chain and prio. Otherwise, there is
-	 * only one default table for the same sampler object. Rules with different
-	 * prio and chain may overlap. For CT sample action, per vport default
-	 * table is needed to resotre the metadata.
-	 */
-	per_vport_tbl_attr.chain = attr->chain;
-	per_vport_tbl_attr.prio = attr->prio;
-	per_vport_tbl_attr.vport = esw_attr->in_rep->vport;
-	per_vport_tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns;
-	default_tbl = mlx5_esw_vporttbl_get(esw, &per_vport_tbl_attr);
-	if (IS_ERR(default_tbl)) {
-		err = PTR_ERR(default_tbl);
-		goto err_default_tbl;
-	}
+	sample_attr = attr->sample_attr;
+	sample_attr->sample_flow = sample_flow;
 
-	/* Perform the original matches on the default table.
-	 * Offload all actions except the sample action.
-	 */
-	esw_attr->sample->sample_default_tbl = default_tbl;
-	/* When offloading sample and encap action, if there is no valid
-	 * neigh data struct, a slow path rule is offloaded first. Source
-	 * port metadata match is set at that time. A per vport table is
-	 * already allocated. No need to match it again. So clear the source
-	 * port metadata match.
+	/* For NICs with reg_c_preserve support or decap action, use
+	 * post action instead of the per vport, chain and prio table.
+	 * Only match the fte id instead of the same match in the
+	 * original flow table.
 	 */
-	mlx5_eswitch_clear_rule_source_port(esw, spec);
-	sample_flow->rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
-	if (IS_ERR(sample_flow->rule)) {
-		err = PTR_ERR(sample_flow->rule);
-		goto err_offload_rule;
+	if (MLX5_CAP_GEN(esw->dev, reg_c_preserve) ||
+	    attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
+		struct mlx5_flow_table *ft;
+
+		ft = mlx5e_tc_post_act_get_ft(tc_psample->post_act);
+		default_tbl_id = ft->id;
+		post_act_handle = mlx5e_tc_post_act_add(tc_psample->post_act, attr);
+		if (IS_ERR(post_act_handle)) {
+			err = PTR_ERR(post_act_handle);
+			goto err_post_act;
+		}
+		sample_flow->post_act_handle = post_act_handle;
+	} else {
+		err = add_post_rule(esw, sample_flow, spec, attr, &default_tbl_id);
+		if (err)
+			goto err_post_rule;
 	}
 
 	/* Create sampler object. */
-	sample_flow->sampler = sampler_get(esw_psample, esw_attr->sample->rate, default_tbl->id);
+	sample_flow->sampler = sampler_get(tc_psample, sample_attr->rate, default_tbl_id);
 	if (IS_ERR(sample_flow->sampler)) {
 		err = PTR_ERR(sample_flow->sampler);
 		goto err_sampler;
@@ -434,16 +554,17 @@ mlx5_esw_sample_offload(struct mlx5_esw_psample *esw_psample,
 
 	/* Create an id mapping reg_c0 value to sample object. */
 	restore_obj.type = MLX5_MAPPED_OBJ_SAMPLE;
-	restore_obj.sample.group_id = esw_attr->sample->group_num;
-	restore_obj.sample.rate = esw_attr->sample->rate;
-	restore_obj.sample.trunc_size = esw_attr->sample->trunc_size;
+	restore_obj.sample.group_id = sample_attr->group_num;
+	restore_obj.sample.rate = sample_attr->rate;
+	restore_obj.sample.trunc_size = sample_attr->trunc_size;
+	restore_obj.sample.tunnel_id = tunnel_id;
 	err = mapping_add(esw->offloads.reg_c0_obj_pool, &restore_obj, &obj_id);
 	if (err)
 		goto err_obj_id;
-	esw_attr->sample->restore_obj_id = obj_id;
+	sample_attr->restore_obj_id = obj_id;
 
 	/* Create sample restore context. */
-	sample_flow->restore = sample_restore_get(esw_psample, obj_id);
+	sample_flow->restore = sample_restore_get(tc_psample, obj_id, post_act_handle);
 	if (IS_ERR(sample_flow->restore)) {
 		err = PTR_ERR(sample_flow->restore);
 		goto err_sample_restore;
@@ -455,21 +576,23 @@ mlx5_esw_sample_offload(struct mlx5_esw_psample *esw_psample,
 	pre_attr = mlx5_alloc_flow_attr(MLX5_FLOW_NAMESPACE_FDB);
 	if (!pre_attr) {
 		err = -ENOMEM;
-		goto err_alloc_flow_attr;
-	}
-	sample_attr = kzalloc(sizeof(*sample_attr), GFP_KERNEL);
-	if (!sample_attr) {
-		err = -ENOMEM;
-		goto err_alloc_sample_attr;
+		goto err_alloc_pre_flow_attr;
 	}
-	pre_esw_attr = pre_attr->esw_attr;
 	pre_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+	/* For decap action, do decap in the original flow table instead of the
+	 * default flow table.
+	 */
+	if (tunnel_id)
+		pre_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
 	pre_attr->modify_hdr = sample_flow->restore->modify_hdr;
 	pre_attr->flags = MLX5_ESW_ATTR_FLAG_SAMPLE;
+	pre_attr->inner_match_level = attr->inner_match_level;
+	pre_attr->outer_match_level = attr->outer_match_level;
 	pre_attr->chain = attr->chain;
 	pre_attr->prio = attr->prio;
-	pre_esw_attr->sample = sample_attr;
-	pre_esw_attr->sample->sampler_id = sample_flow->sampler->sampler_id;
+	pre_attr->sample_attr = attr->sample_attr;
+	sample_attr->sampler_id = sample_flow->sampler->sampler_id;
+	pre_esw_attr = pre_attr->esw_attr;
 	pre_esw_attr->in_mdev = esw_attr->in_mdev;
 	pre_esw_attr->in_rep = esw_attr->in_rep;
 	sample_flow->pre_rule = mlx5_eswitch_add_offloaded_rule(esw, spec, pre_attr);
@@ -479,108 +602,113 @@ mlx5_esw_sample_offload(struct mlx5_esw_psample *esw_psample,
 	}
 	sample_flow->pre_attr = pre_attr;
 
-	return sample_flow->rule;
+	return sample_flow->post_rule;
 
 err_pre_offload_rule:
-	kfree(sample_attr);
-err_alloc_sample_attr:
 	kfree(pre_attr);
-err_alloc_flow_attr:
-	sample_restore_put(esw_psample, sample_flow->restore);
+err_alloc_pre_flow_attr:
+	sample_restore_put(tc_psample, sample_flow->restore);
 err_sample_restore:
 	mapping_remove(esw->offloads.reg_c0_obj_pool, obj_id);
 err_obj_id:
-	sampler_put(esw_psample, sample_flow->sampler);
+	sampler_put(tc_psample, sample_flow->sampler);
 err_sampler:
-	/* For sample offload, rule is added in default_tbl. No need to call
-	 * mlx5_esw_chains_put_table()
-	 */
-	attr->prio = 0;
-	attr->chain = 0;
-	mlx5_eswitch_del_offloaded_rule(esw, sample_flow->rule, attr);
-err_offload_rule:
-	mlx5_esw_vporttbl_put(esw, &per_vport_tbl_attr);
-err_default_tbl:
+	if (!post_act_handle)
+		del_post_rule(esw, sample_flow, attr);
+err_post_rule:
+	if (post_act_handle)
+		mlx5e_tc_post_act_del(tc_psample->post_act, post_act_handle);
+err_post_act:
 	kfree(sample_flow);
 	return ERR_PTR(err);
 }
 
 void
-mlx5_esw_sample_unoffload(struct mlx5_esw_psample *esw_psample,
+mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *tc_psample,
 			  struct mlx5_flow_handle *rule,
 			  struct mlx5_flow_attr *attr)
 {
 	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
-	struct mlx5_sample_flow *sample_flow;
+	struct mlx5e_sample_flow *sample_flow;
 	struct mlx5_vport_tbl_attr tbl_attr;
-	struct mlx5_flow_attr *pre_attr;
 	struct mlx5_eswitch *esw;
 
-	if (IS_ERR_OR_NULL(esw_psample))
+	if (IS_ERR_OR_NULL(tc_psample))
 		return;
 
 	/* If slow path flag is set, sample action is not offloaded.
 	 * No need to delete sample rule.
 	 */
-	esw = esw_psample->priv->mdev->priv.eswitch;
+	esw = tc_psample->esw;
 	if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) {
 		mlx5_eswitch_del_offloaded_rule(esw, rule, attr);
 		return;
 	}
 
-	sample_flow = esw_attr->sample->sample_flow;
-	pre_attr = sample_flow->pre_attr;
-	memset(pre_attr, 0, sizeof(*pre_attr));
-	esw = esw_psample->priv->mdev->priv.eswitch;
-	mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, pre_attr);
-	mlx5_eswitch_del_offloaded_rule(esw, sample_flow->rule, attr);
-
-	sample_restore_put(esw_psample, sample_flow->restore);
-	mapping_remove(esw->offloads.reg_c0_obj_pool, esw_attr->sample->restore_obj_id);
-	sampler_put(esw_psample, sample_flow->sampler);
-	tbl_attr.chain = attr->chain;
-	tbl_attr.prio = attr->prio;
-	tbl_attr.vport = esw_attr->in_rep->vport;
-	tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns;
-	mlx5_esw_vporttbl_put(esw, &tbl_attr);
+	/* The following delete order can't be changed, otherwise,
+	 * will hit fw syndromes.
+	 */
+	sample_flow = attr->sample_attr->sample_flow;
+	mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, sample_flow->pre_attr);
+	if (!sample_flow->post_act_handle)
+		mlx5_eswitch_del_offloaded_rule(esw, sample_flow->post_rule,
+						sample_flow->post_attr);
+
+	sample_restore_put(tc_psample, sample_flow->restore);
+	mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr->restore_obj_id);
+	sampler_put(tc_psample, sample_flow->sampler);
+	if (sample_flow->post_act_handle) {
+		mlx5e_tc_post_act_del(tc_psample->post_act, sample_flow->post_act_handle);
+	} else {
+		tbl_attr.chain = attr->chain;
+		tbl_attr.prio = attr->prio;
+		tbl_attr.vport = esw_attr->in_rep->vport;
+		tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns;
+		mlx5_esw_vporttbl_put(esw, &tbl_attr);
+		kfree(sample_flow->post_attr);
+	}
 
-	kfree(pre_attr->esw_attr->sample);
-	kfree(pre_attr);
+	kfree(sample_flow->pre_attr);
 	kfree(sample_flow);
 }
 
-struct mlx5_esw_psample *
-mlx5_esw_sample_init(struct mlx5e_priv *priv)
+struct mlx5e_tc_psample *
+mlx5e_tc_sample_init(struct mlx5_eswitch *esw, struct mlx5e_post_act *post_act)
 {
-	struct mlx5_esw_psample *esw_psample;
+	struct mlx5e_tc_psample *tc_psample;
 	int err;
 
-	esw_psample = kzalloc(sizeof(*esw_psample), GFP_KERNEL);
-	if (!esw_psample)
+	tc_psample = kzalloc(sizeof(*tc_psample), GFP_KERNEL);
+	if (!tc_psample)
 		return ERR_PTR(-ENOMEM);
-	esw_psample->priv = priv;
-	err = sampler_termtbl_create(esw_psample);
+	if (IS_ERR_OR_NULL(post_act)) {
+		err = PTR_ERR(post_act);
+		goto err_post_act;
+	}
+	tc_psample->post_act = post_act;
+	tc_psample->esw = esw;
+	err = sampler_termtbl_create(tc_psample);
 	if (err)
-		goto err_termtbl;
+		goto err_post_act;
 
-	mutex_init(&esw_psample->ht_lock);
-	mutex_init(&esw_psample->restore_lock);
+	mutex_init(&tc_psample->ht_lock);
+	mutex_init(&tc_psample->restore_lock);
 
-	return esw_psample;
+	return tc_psample;
 
-err_termtbl:
-	kfree(esw_psample);
+err_post_act:
+	kfree(tc_psample);
 	return ERR_PTR(err);
 }
 
 void
-mlx5_esw_sample_cleanup(struct mlx5_esw_psample *esw_psample)
+mlx5e_tc_sample_cleanup(struct mlx5e_tc_psample *tc_psample)
 {
-	if (IS_ERR_OR_NULL(esw_psample))
+	if (IS_ERR_OR_NULL(tc_psample))
 		return;
 
-	mutex_destroy(&esw_psample->restore_lock);
-	mutex_destroy(&esw_psample->ht_lock);
-	sampler_termtbl_destroy(esw_psample);
-	kfree(esw_psample);
+	mutex_destroy(&tc_psample->restore_lock);
+	mutex_destroy(&tc_psample->ht_lock);
+	sampler_termtbl_destroy(tc_psample);
+	kfree(tc_psample);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h
new file mode 100644
index 000000000000..db0146df9b30
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_TC_SAMPLE_H__
+#define __MLX5_EN_TC_SAMPLE_H__
+
+#include "eswitch.h"
+
+struct mlx5_flow_attr;
+struct mlx5e_tc_psample;
+struct mlx5e_post_act;
+
+struct mlx5e_sample_attr {
+	u32 group_num;
+	u32 rate;
+	u32 trunc_size;
+	u32 restore_obj_id;
+	u32 sampler_id;
+	struct mlx5e_sample_flow *sample_flow;
+};
+
+void mlx5e_tc_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj);
+
+struct mlx5_flow_handle *
+mlx5e_tc_sample_offload(struct mlx5e_tc_psample *sample_priv,
+			struct mlx5_flow_spec *spec,
+			struct mlx5_flow_attr *attr,
+			u32 tunnel_id);
+
+void
+mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *sample_priv,
+			  struct mlx5_flow_handle *rule,
+			  struct mlx5_flow_attr *attr);
+
+struct mlx5e_tc_psample *
+mlx5e_tc_sample_init(struct mlx5_eswitch *esw, struct mlx5e_post_act *post_act);
+
+void
+mlx5e_tc_sample_cleanup(struct mlx5e_tc_psample *tc_psample);
+
+#endif /* __MLX5_EN_TC_SAMPLE_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 91e7a01e32be..6c949abcd2e1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -19,6 +19,7 @@
 #include "en/tc_ct.h"
 #include "en/mod_hdr.h"
 #include "en/mapping.h"
+#include "en/tc/post_act.h"
 #include "en.h"
 #include "en_tc.h"
 #include "en_rep.h"
@@ -32,10 +33,6 @@
 #define MLX5_CT_STATE_RELATED_BIT BIT(5)
 #define MLX5_CT_STATE_INVALID_BIT BIT(6)
 
-#define MLX5_FTE_ID_BITS (mlx5e_tc_attr_to_reg_mappings[FTEID_TO_REG].mlen)
-#define MLX5_FTE_ID_MAX GENMASK(MLX5_FTE_ID_BITS - 1, 0)
-#define MLX5_FTE_ID_MASK MLX5_FTE_ID_MAX
-
 #define MLX5_CT_LABELS_BITS (mlx5e_tc_attr_to_reg_mappings[LABELS_TO_REG].mlen)
 #define MLX5_CT_LABELS_MASK GENMASK(MLX5_CT_LABELS_BITS - 1, 0)
 
@@ -46,14 +43,13 @@ struct mlx5_tc_ct_priv {
 	struct mlx5_core_dev *dev;
 	const struct net_device *netdev;
 	struct mod_hdr_tbl *mod_hdr_tbl;
-	struct idr fte_ids;
 	struct xarray tuple_ids;
 	struct rhashtable zone_ht;
 	struct rhashtable ct_tuples_ht;
 	struct rhashtable ct_tuples_nat_ht;
 	struct mlx5_flow_table *ct;
 	struct mlx5_flow_table *ct_nat;
-	struct mlx5_flow_table *post_ct;
+	struct mlx5e_post_act *post_act;
 	struct mutex control_lock; /* guards parallel adds/dels */
 	struct mapping_ctx *zone_mapping;
 	struct mapping_ctx *labels_mapping;
@@ -64,11 +60,9 @@ struct mlx5_tc_ct_priv {
 
 struct mlx5_ct_flow {
 	struct mlx5_flow_attr *pre_ct_attr;
-	struct mlx5_flow_attr *post_ct_attr;
 	struct mlx5_flow_handle *pre_ct_rule;
-	struct mlx5_flow_handle *post_ct_rule;
+	struct mlx5e_post_act_handle *post_act_handle;
 	struct mlx5_ct_ft *ft;
-	u32 fte_id;
 	u32 chain_mapping;
 };
 
@@ -768,7 +762,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 		       MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 		       MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	attr->dest_chain = 0;
-	attr->dest_ft = ct_priv->post_ct;
+	attr->dest_ft = mlx5e_tc_post_act_get_ft(ct_priv->post_act);
 	attr->ft = nat ? ct_priv->ct_nat : ct_priv->ct;
 	attr->outer_match_level = MLX5_MATCH_L4;
 	attr->counter = entry->counter->counter;
@@ -1432,7 +1426,7 @@ static int tc_ct_pre_ct_add_rules(struct mlx5_ct_ft *ct_ft,
 		ctstate |= MLX5_CT_STATE_NAT_BIT;
 	mlx5e_tc_match_to_reg_match(spec, CTSTATE_TO_REG, ctstate, ctstate);
 
-	dest.ft = ct_priv->post_ct;
+	dest.ft = mlx5e_tc_post_act_get_ft(ct_priv->post_act);
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -1716,9 +1710,9 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft)
  *      | do decap
  *      v
  * +---------------------+
- * + pre_ct/pre_ct_nat   +  if matches     +---------------------+
- * + zone+nat match      +---------------->+ post_ct (see below) +
- * +---------------------+  set zone       +---------------------+
+ * + pre_ct/pre_ct_nat   +  if matches     +-------------------------+
+ * + zone+nat match      +---------------->+ post_act (see below) +
+ * +---------------------+  set zone       +-------------------------+
  *      | set zone
  *      v
  * +--------------------+
@@ -1732,7 +1726,7 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft)
  *      | do nat (if needed)
  *      v
  * +--------------+
- * + post_ct      + original filter actions
+ * + post_act  + original filter actions
  * + fte_id match +------------------------>
  * +--------------+
  */
@@ -1746,19 +1740,15 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,
 	struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev);
 	struct mlx5e_tc_mod_hdr_acts pre_mod_acts = {};
 	u32 attr_sz = ns_to_attr_sz(ct_priv->ns_type);
-	struct mlx5_flow_spec *post_ct_spec = NULL;
+	struct mlx5e_post_act_handle *handle;
 	struct mlx5_flow_attr *pre_ct_attr;
 	struct mlx5_modify_hdr *mod_hdr;
-	struct mlx5_flow_handle *rule;
 	struct mlx5_ct_flow *ct_flow;
 	int chain_mapping = 0, err;
 	struct mlx5_ct_ft *ft;
-	u32 fte_id = 1;
 
-	post_ct_spec = kvzalloc(sizeof(*post_ct_spec), GFP_KERNEL);
 	ct_flow = kzalloc(sizeof(*ct_flow), GFP_KERNEL);
-	if (!post_ct_spec || !ct_flow) {
-		kvfree(post_ct_spec);
+	if (!ct_flow) {
 		kfree(ct_flow);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -1773,14 +1763,13 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,
 	}
 	ct_flow->ft = ft;
 
-	err = idr_alloc_u32(&ct_priv->fte_ids, ct_flow, &fte_id,
-			    MLX5_FTE_ID_MAX, GFP_KERNEL);
-	if (err) {
-		netdev_warn(priv->netdev,
-			    "Failed to allocate fte id, err: %d\n", err);
-		goto err_idr;
+	handle = mlx5e_tc_post_act_add(ct_priv->post_act, attr);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		ct_dbg("Failed to allocate post action handle");
+		goto err_post_act_handle;
 	}
-	ct_flow->fte_id = fte_id;
+	ct_flow->post_act_handle = handle;
 
 	/* Base flow attributes of both rules on original rule attribute */
 	ct_flow->pre_ct_attr = mlx5_alloc_flow_attr(ct_priv->ns_type);
@@ -1789,15 +1778,8 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,
 		goto err_alloc_pre;
 	}
 
-	ct_flow->post_ct_attr = mlx5_alloc_flow_attr(ct_priv->ns_type);
-	if (!ct_flow->post_ct_attr) {
-		err = -ENOMEM;
-		goto err_alloc_post;
-	}
-
 	pre_ct_attr = ct_flow->pre_ct_attr;
 	memcpy(pre_ct_attr, attr, attr_sz);
-	memcpy(ct_flow->post_ct_attr, attr, attr_sz);
 
 	/* Modify the original rule's action to fwd and modify, leave decap */
 	pre_ct_attr->action = attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP;
@@ -1823,10 +1805,9 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,
 		goto err_mapping;
 	}
 
-	err = mlx5e_tc_match_to_reg_set(priv->mdev, &pre_mod_acts, ct_priv->ns_type,
-					FTEID_TO_REG, fte_id);
+	err = mlx5e_tc_post_act_set_handle(priv->mdev, handle, &pre_mod_acts);
 	if (err) {
-		ct_dbg("Failed to set fte_id register mapping");
+		ct_dbg("Failed to set post action handle");
 		goto err_mapping;
 	}
 
@@ -1857,33 +1838,6 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,
 	}
 	pre_ct_attr->modify_hdr = mod_hdr;
 
-	/* Post ct rule matches on fte_id and executes original rule's
-	 * tc rule action
-	 */
-	mlx5e_tc_match_to_reg_match(post_ct_spec, FTEID_TO_REG,
-				    fte_id, MLX5_FTE_ID_MASK);
-
-	/* Put post_ct rule on post_ct flow table */
-	ct_flow->post_ct_attr->chain = 0;
-	ct_flow->post_ct_attr->prio = 0;
-	ct_flow->post_ct_attr->ft = ct_priv->post_ct;
-
-	/* Splits were handled before CT */
-	if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB)
-		ct_flow->post_ct_attr->esw_attr->split_count = 0;
-
-	ct_flow->post_ct_attr->inner_match_level = MLX5_MATCH_NONE;
-	ct_flow->post_ct_attr->outer_match_level = MLX5_MATCH_NONE;
-	ct_flow->post_ct_attr->action &= ~(MLX5_FLOW_CONTEXT_ACTION_DECAP);
-	rule = mlx5_tc_rule_insert(priv, post_ct_spec,
-				   ct_flow->post_ct_attr);
-	ct_flow->post_ct_rule = rule;
-	if (IS_ERR(ct_flow->post_ct_rule)) {
-		err = PTR_ERR(ct_flow->post_ct_rule);
-		ct_dbg("Failed to add post ct rule");
-		goto err_insert_post_ct;
-	}
-
 	/* Change original rule point to ct table */
 	pre_ct_attr->dest_chain = 0;
 	pre_ct_attr->dest_ft = nat ? ft->pre_ct_nat.ft : ft->pre_ct.ft;
@@ -1897,28 +1851,21 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,
 
 	attr->ct_attr.ct_flow = ct_flow;
 	dealloc_mod_hdr_actions(&pre_mod_acts);
-	kvfree(post_ct_spec);
 
-	return rule;
+	return ct_flow->pre_ct_rule;
 
 err_insert_orig:
-	mlx5_tc_rule_delete(priv, ct_flow->post_ct_rule,
-			    ct_flow->post_ct_attr);
-err_insert_post_ct:
 	mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr);
 err_mapping:
 	dealloc_mod_hdr_actions(&pre_mod_acts);
 	mlx5_chains_put_chain_mapping(ct_priv->chains, ct_flow->chain_mapping);
 err_get_chain:
-	kfree(ct_flow->post_ct_attr);
-err_alloc_post:
 	kfree(ct_flow->pre_ct_attr);
 err_alloc_pre:
-	idr_remove(&ct_priv->fte_ids, fte_id);
-err_idr:
+	mlx5e_tc_post_act_del(ct_priv->post_act, handle);
+err_post_act_handle:
 	mlx5_tc_ct_del_ft_cb(ct_priv, ft);
 err_ft:
-	kvfree(post_ct_spec);
 	kfree(ct_flow);
 	netdev_warn(priv->netdev, "Failed to offload ct flow, err %d\n", err);
 	return ERR_PTR(err);
@@ -2029,16 +1976,13 @@ __mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *ct_priv,
 			    pre_ct_attr);
 	mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr);
 
-	if (ct_flow->post_ct_rule) {
-		mlx5_tc_rule_delete(priv, ct_flow->post_ct_rule,
-				    ct_flow->post_ct_attr);
+	if (ct_flow->post_act_handle) {
 		mlx5_chains_put_chain_mapping(ct_priv->chains, ct_flow->chain_mapping);
-		idr_remove(&ct_priv->fte_ids, ct_flow->fte_id);
+		mlx5e_tc_post_act_del(ct_priv->post_act, ct_flow->post_act_handle);
 		mlx5_tc_ct_del_ft_cb(ct_priv, ct_flow->ft);
 	}
 
 	kfree(ct_flow->pre_ct_attr);
-	kfree(ct_flow->post_ct_attr);
 	kfree(ct_flow);
 }
 
@@ -2064,11 +2008,6 @@ static int
 mlx5_tc_ct_init_check_esw_support(struct mlx5_eswitch *esw,
 				  const char **err_msg)
 {
-	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level)) {
-		*err_msg = "firmware level support is missing";
-		return -EOPNOTSUPP;
-	}
-
 	if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) {
 		/* vlan workaround should be avoided for multi chain rules.
 		 * This is just a sanity check as pop vlan action should
@@ -2098,20 +2037,9 @@ mlx5_tc_ct_init_check_esw_support(struct mlx5_eswitch *esw,
 }
 
 static int
-mlx5_tc_ct_init_check_nic_support(struct mlx5e_priv *priv,
-				  const char **err_msg)
-{
-	if (!MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ignore_flow_level)) {
-		*err_msg = "firmware level support is missing";
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
-static int
 mlx5_tc_ct_init_check_support(struct mlx5e_priv *priv,
 			      enum mlx5_flow_namespace_type ns_type,
+			      struct mlx5e_post_act *post_act,
 			      const char **err_msg)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -2122,10 +2050,14 @@ mlx5_tc_ct_init_check_support(struct mlx5e_priv *priv,
 	*err_msg = "tc skb extension missing";
 	return -EOPNOTSUPP;
 #endif
+	if (IS_ERR_OR_NULL(post_act)) {
+		*err_msg = "tc ct offload not supported, post action is missing";
+		return -EOPNOTSUPP;
+	}
+
 	if (ns_type == MLX5_FLOW_NAMESPACE_FDB)
 		return mlx5_tc_ct_init_check_esw_support(esw, err_msg);
-	else
-		return mlx5_tc_ct_init_check_nic_support(priv, err_msg);
+	return 0;
 }
 
 #define INIT_ERR_PREFIX "tc ct offload init failed"
@@ -2133,19 +2065,19 @@ mlx5_tc_ct_init_check_support(struct mlx5e_priv *priv,
 struct mlx5_tc_ct_priv *
 mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
 		struct mod_hdr_tbl *mod_hdr,
-		enum mlx5_flow_namespace_type ns_type)
+		enum mlx5_flow_namespace_type ns_type,
+		struct mlx5e_post_act *post_act)
 {
 	struct mlx5_tc_ct_priv *ct_priv;
 	struct mlx5_core_dev *dev;
 	const char *msg;
+	u64 mapping_id;
 	int err;
 
 	dev = priv->mdev;
-	err = mlx5_tc_ct_init_check_support(priv, ns_type, &msg);
+	err = mlx5_tc_ct_init_check_support(priv, ns_type, post_act, &msg);
 	if (err) {
-		mlx5_core_warn(dev,
-			       "tc ct offload not supported, %s\n",
-			       msg);
+		mlx5_core_warn(dev, "tc ct offload not supported, %s\n", msg);
 		goto err_support;
 	}
 
@@ -2153,13 +2085,17 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
 	if (!ct_priv)
 		goto err_alloc;
 
-	ct_priv->zone_mapping = mapping_create(sizeof(u16), 0, true);
+	mapping_id = mlx5_query_nic_system_image_guid(dev);
+
+	ct_priv->zone_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_ZONE,
+						      sizeof(u16), 0, true);
 	if (IS_ERR(ct_priv->zone_mapping)) {
 		err = PTR_ERR(ct_priv->zone_mapping);
 		goto err_mapping_zone;
 	}
 
-	ct_priv->labels_mapping = mapping_create(sizeof(u32) * 4, 0, true);
+	ct_priv->labels_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_LABELS,
+							sizeof(u32) * 4, 0, true);
 	if (IS_ERR(ct_priv->labels_mapping)) {
 		err = PTR_ERR(ct_priv->labels_mapping);
 		goto err_mapping_labels;
@@ -2189,16 +2125,7 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
 		goto err_ct_nat_tbl;
 	}
 
-	ct_priv->post_ct = mlx5_chains_create_global_table(chains);
-	if (IS_ERR(ct_priv->post_ct)) {
-		err = PTR_ERR(ct_priv->post_ct);
-		mlx5_core_warn(dev,
-			       "%s, failed to create post ct table err: %d\n",
-			       INIT_ERR_PREFIX, err);
-		goto err_post_ct_tbl;
-	}
-
-	idr_init(&ct_priv->fte_ids);
+	ct_priv->post_act = post_act;
 	mutex_init(&ct_priv->control_lock);
 	rhashtable_init(&ct_priv->zone_ht, &zone_params);
 	rhashtable_init(&ct_priv->ct_tuples_ht, &tuples_ht_params);
@@ -2206,8 +2133,6 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
 
 	return ct_priv;
 
-err_post_ct_tbl:
-	mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat);
 err_ct_nat_tbl:
 	mlx5_chains_destroy_global_table(chains, ct_priv->ct);
 err_ct_tbl:
@@ -2232,7 +2157,6 @@ mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv)
 
 	chains = ct_priv->chains;
 
-	mlx5_chains_destroy_global_table(chains, ct_priv->post_ct);
 	mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat);
 	mlx5_chains_destroy_global_table(chains, ct_priv->ct);
 	mapping_destroy(ct_priv->zone_mapping);
@@ -2242,7 +2166,6 @@ mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv)
 	rhashtable_destroy(&ct_priv->ct_tuples_nat_ht);
 	rhashtable_destroy(&ct_priv->zone_ht);
 	mutex_destroy(&ct_priv->control_lock);
-	idr_destroy(&ct_priv->fte_ids);
 	kfree(ct_priv);
 }
 
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 644cf1641cde..363329f4aac6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
@@ -92,7 +92,8 @@ struct mlx5_ct_attr {
 struct mlx5_tc_ct_priv *
 mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
 		struct mod_hdr_tbl *mod_hdr,
-		enum mlx5_flow_namespace_type ns_type);
+		enum mlx5_flow_namespace_type ns_type,
+		struct mlx5e_post_act *post_act);
 void
 mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv);
 
@@ -132,7 +133,8 @@ mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv,
 static inline struct mlx5_tc_ct_priv *
 mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
 		struct mod_hdr_tbl *mod_hdr,
-		enum mlx5_flow_namespace_type ns_type)
+		enum mlx5_flow_namespace_type ns_type,
+		struct mlx5e_post_act *post_act)
 {
 	return NULL;
 }
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 1e2d117082d4..b4e986818794 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -525,7 +525,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	e->out_dev = attr.out_dev;
 	e->route_dev_ifindex = attr.route_dev->ifindex;
 
-	/* It's importent to add the neigh to the hash table before checking
+	/* It's important to add the neigh to the hash table before checking
 	 * the neigh validity state. So if we'll get a notification, in case the
 	 * neigh changes it's validity state, we would find the relevant neigh
 	 * in the hash.
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 2e846b741280..1c44c6c345f5 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
@@ -147,7 +147,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 	mlx5e_rep_queue_neigh_stats_work(priv);
 
 	list_for_each_entry(flow, flow_list, tmp_list) {
-		if (!mlx5e_is_offloaded_flow(flow))
+		if (!mlx5e_is_offloaded_flow(flow) || !flow_flag_test(flow, SLOW))
 			continue;
 		attr = flow->attr;
 		esw_attr = attr->esw_attr;
@@ -188,7 +188,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 	int err;
 
 	list_for_each_entry(flow, flow_list, tmp_list) {
-		if (!mlx5e_is_offloaded_flow(flow))
+		if (!mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, SLOW))
 			continue;
 		attr = flow->attr;
 		esw_attr = attr->esw_attr;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
new file mode 100644
index 000000000000..de936dc4bc48
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */
+
+#include "tir.h"
+#include "params.h"
+#include <linux/mlx5/transobj.h>
+
+#define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ (64 * 1024)
+
+/* max() doesn't work inside square brackets. */
+#define MLX5E_TIR_CMD_IN_SZ_DW ( \
+	MLX5_ST_SZ_DW(create_tir_in) > MLX5_ST_SZ_DW(modify_tir_in) ? \
+	MLX5_ST_SZ_DW(create_tir_in) : MLX5_ST_SZ_DW(modify_tir_in) \
+)
+
+struct mlx5e_tir_builder {
+	u32 in[MLX5E_TIR_CMD_IN_SZ_DW];
+	bool modify;
+};
+
+struct mlx5e_tir_builder *mlx5e_tir_builder_alloc(bool modify)
+{
+	struct mlx5e_tir_builder *builder;
+
+	builder = kvzalloc(sizeof(*builder), GFP_KERNEL);
+	builder->modify = modify;
+
+	return builder;
+}
+
+void mlx5e_tir_builder_free(struct mlx5e_tir_builder *builder)
+{
+	kvfree(builder);
+}
+
+void mlx5e_tir_builder_clear(struct mlx5e_tir_builder *builder)
+{
+	memset(builder->in, 0, sizeof(builder->in));
+}
+
+static void *mlx5e_tir_builder_get_tirc(struct mlx5e_tir_builder *builder)
+{
+	if (builder->modify)
+		return MLX5_ADDR_OF(modify_tir_in, builder->in, ctx);
+	return MLX5_ADDR_OF(create_tir_in, builder->in, ctx);
+}
+
+void mlx5e_tir_builder_build_inline(struct mlx5e_tir_builder *builder, u32 tdn, u32 rqn)
+{
+	void *tirc = mlx5e_tir_builder_get_tirc(builder);
+
+	WARN_ON(builder->modify);
+
+	MLX5_SET(tirc, tirc, transport_domain, tdn);
+	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT);
+	MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_NONE);
+	MLX5_SET(tirc, tirc, inline_rqn, rqn);
+}
+
+void mlx5e_tir_builder_build_rqt(struct mlx5e_tir_builder *builder, u32 tdn,
+				 u32 rqtn, bool inner_ft_support)
+{
+	void *tirc = mlx5e_tir_builder_get_tirc(builder);
+
+	WARN_ON(builder->modify);
+
+	MLX5_SET(tirc, tirc, transport_domain, tdn);
+	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
+	MLX5_SET(tirc, tirc, indirect_table, rqtn);
+	MLX5_SET(tirc, tirc, tunneled_offload_en, inner_ft_support);
+}
+
+void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder,
+				 const struct mlx5e_lro_param *lro_param)
+{
+	void *tirc = mlx5e_tir_builder_get_tirc(builder);
+	const unsigned int rough_max_l2_l3_hdr_sz = 256;
+
+	if (builder->modify)
+		MLX5_SET(modify_tir_in, builder->in, bitmask.lro, 1);
+
+	if (!lro_param->enabled)
+		return;
+
+	MLX5_SET(tirc, tirc, lro_enable_mask,
+		 MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO |
+		 MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO);
+	MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
+		 (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - rough_max_l2_l3_hdr_sz) >> 8);
+	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, lro_param->timeout);
+}
+
+static int mlx5e_hfunc_to_hw(u8 hfunc)
+{
+	switch (hfunc) {
+	case ETH_RSS_HASH_TOP:
+		return MLX5_RX_HASH_FN_TOEPLITZ;
+	case ETH_RSS_HASH_XOR:
+		return MLX5_RX_HASH_FN_INVERTED_XOR8;
+	default:
+		return MLX5_RX_HASH_FN_NONE;
+	}
+}
+
+void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder,
+				 const struct mlx5e_rss_params_hash *rss_hash,
+				 const struct mlx5e_rss_params_traffic_type *rss_tt,
+				 bool inner)
+{
+	void *tirc = mlx5e_tir_builder_get_tirc(builder);
+	void *hfso;
+
+	if (builder->modify)
+		MLX5_SET(modify_tir_in, builder->in, bitmask.hash, 1);
+
+	MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_hfunc_to_hw(rss_hash->hfunc));
+	if (rss_hash->hfunc == ETH_RSS_HASH_TOP) {
+		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);
+		memcpy(rss_key, rss_hash->toeplitz_hash_key, len);
+	}
+
+	if (inner)
+		hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner);
+	else
+		hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
+	MLX5_SET(rx_hash_field_select, hfso, l3_prot_type, rss_tt->l3_prot_type);
+	MLX5_SET(rx_hash_field_select, hfso, l4_prot_type, rss_tt->l4_prot_type);
+	MLX5_SET(rx_hash_field_select, hfso, selected_fields, rss_tt->rx_hash_fields);
+}
+
+void mlx5e_tir_builder_build_direct(struct mlx5e_tir_builder *builder)
+{
+	void *tirc = mlx5e_tir_builder_get_tirc(builder);
+
+	WARN_ON(builder->modify);
+
+	MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8);
+}
+
+void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder)
+{
+	void *tirc = mlx5e_tir_builder_get_tirc(builder);
+
+	WARN_ON(builder->modify);
+
+	MLX5_SET(tirc, tirc, tls_en, 1);
+	MLX5_SET(tirc, tirc, self_lb_block,
+		 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST |
+		 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST);
+}
+
+int mlx5e_tir_init(struct mlx5e_tir *tir, struct mlx5e_tir_builder *builder,
+		   struct mlx5_core_dev *mdev, bool reg)
+{
+	int err;
+
+	tir->mdev = mdev;
+
+	err = mlx5_core_create_tir(tir->mdev, builder->in, &tir->tirn);
+	if (err)
+		return err;
+
+	if (reg) {
+		struct mlx5e_hw_objs *res = &tir->mdev->mlx5e_res.hw_objs;
+
+		mutex_lock(&res->td.list_lock);
+		list_add(&tir->list, &res->td.tirs_list);
+		mutex_unlock(&res->td.list_lock);
+	} else {
+		INIT_LIST_HEAD(&tir->list);
+	}
+
+	return 0;
+}
+
+void mlx5e_tir_destroy(struct mlx5e_tir *tir)
+{
+	struct mlx5e_hw_objs *res = &tir->mdev->mlx5e_res.hw_objs;
+
+	/* Skip mutex if list_del is no-op (the TIR wasn't registered in the
+	 * list). list_empty will never return true for an item of tirs_list,
+	 * and READ_ONCE/WRITE_ONCE in list_empty/list_del guarantee consistency
+	 * of the list->next value.
+	 */
+	if (!list_empty(&tir->list)) {
+		mutex_lock(&res->td.list_lock);
+		list_del(&tir->list);
+		mutex_unlock(&res->td.list_lock);
+	}
+
+	mlx5_core_destroy_tir(tir->mdev, tir->tirn);
+}
+
+int mlx5e_tir_modify(struct mlx5e_tir *tir, struct mlx5e_tir_builder *builder)
+{
+	return mlx5_core_modify_tir(tir->mdev, tir->tirn, builder->in);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
new file mode 100644
index 000000000000..e45149a78ed9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, Mellanox Technologies inc. All rights reserved. */
+
+#ifndef __MLX5_EN_TIR_H__
+#define __MLX5_EN_TIR_H__
+
+#include <linux/kernel.h>
+
+struct mlx5e_rss_params_hash {
+	u8 hfunc;
+	u8 toeplitz_hash_key[40];
+};
+
+struct mlx5e_rss_params_traffic_type {
+	u8 l3_prot_type;
+	u8 l4_prot_type;
+	u32 rx_hash_fields;
+};
+
+struct mlx5e_tir_builder;
+struct mlx5e_lro_param;
+
+struct mlx5e_tir_builder *mlx5e_tir_builder_alloc(bool modify);
+void mlx5e_tir_builder_free(struct mlx5e_tir_builder *builder);
+void mlx5e_tir_builder_clear(struct mlx5e_tir_builder *builder);
+
+void mlx5e_tir_builder_build_inline(struct mlx5e_tir_builder *builder, u32 tdn, u32 rqn);
+void mlx5e_tir_builder_build_rqt(struct mlx5e_tir_builder *builder, u32 tdn,
+				 u32 rqtn, bool inner_ft_support);
+void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder,
+				 const struct mlx5e_lro_param *lro_param);
+void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder,
+				 const struct mlx5e_rss_params_hash *rss_hash,
+				 const struct mlx5e_rss_params_traffic_type *rss_tt,
+				 bool inner);
+void mlx5e_tir_builder_build_direct(struct mlx5e_tir_builder *builder);
+void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder);
+
+struct mlx5_core_dev;
+
+struct mlx5e_tir {
+	struct mlx5_core_dev *mdev;
+	u32 tirn;
+	struct list_head list;
+};
+
+int mlx5e_tir_init(struct mlx5e_tir *tir, struct mlx5e_tir_builder *builder,
+		   struct mlx5_core_dev *mdev, bool reg);
+void mlx5e_tir_destroy(struct mlx5e_tir *tir);
+
+static inline u32 mlx5e_tir_get_tirn(struct mlx5e_tir *tir)
+{
+	return tir->tirn;
+}
+
+int mlx5e_tir_modify(struct mlx5e_tir *tir, struct mlx5e_tir_builder *builder);
+
+#endif /* __MLX5_EN_TIR_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
index 7f94508594fb..d54607a42740 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
@@ -92,30 +92,19 @@ static void mlx5e_close_trap_rq(struct mlx5e_rq *rq)
 static int mlx5e_create_trap_direct_rq_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir,
 					   u32 rqn)
 {
-	void *tirc;
-	int inlen;
-	u32 *in;
+	struct mlx5e_tir_builder *builder;
 	int err;
 
-	inlen = MLX5_ST_SZ_BYTES(create_tir_in);
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
+	builder = mlx5e_tir_builder_alloc(false);
+	if (!builder)
 		return -ENOMEM;
 
-	tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
-	MLX5_SET(tirc, tirc, transport_domain, mdev->mlx5e_res.hw_objs.td.tdn);
-	MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_NONE);
-	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT);
-	MLX5_SET(tirc, tirc, inline_rqn, rqn);
-	err = mlx5e_create_tir(mdev, tir, in);
-	kvfree(in);
+	mlx5e_tir_builder_build_inline(builder, mdev->mlx5e_res.hw_objs.td.tdn, rqn);
+	err = mlx5e_tir_init(tir, builder, mdev, true);
 
-	return err;
-}
+	mlx5e_tir_builder_free(builder);
 
-static void mlx5e_destroy_trap_direct_rq_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir)
-{
-	mlx5e_destroy_tir(mdev, tir);
+	return err;
 }
 
 static void mlx5e_build_trap_params(struct mlx5_core_dev *mdev,
@@ -173,7 +162,7 @@ err_napi_del:
 
 void mlx5e_close_trap(struct mlx5e_trap *trap)
 {
-	mlx5e_destroy_trap_direct_rq_tir(trap->mdev, &trap->tir);
+	mlx5e_tir_destroy(&trap->tir);
 	mlx5e_close_trap_rq(&trap->rq);
 	netif_napi_del(&trap->napi);
 	kvfree(trap);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
index 71e8d66fa150..7b562d2c8a19 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
@@ -122,7 +122,7 @@ static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
 	 * any Fill Ring entries at the setup stage.
 	 */
 
-	err = mlx5e_xsk_redirect_rqt_to_channel(priv, priv->channels.c[ix]);
+	err = mlx5e_rx_res_xsk_activate(priv->rx_res, &priv->channels, ix);
 	if (unlikely(err))
 		goto err_deactivate;
 
@@ -169,7 +169,7 @@ static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix)
 		goto remove_pool;
 
 	c = priv->channels.c[ix];
-	mlx5e_xsk_redirect_rqt_to_drop(priv, ix);
+	mlx5e_rx_res_xsk_deactivate(priv->rx_res, ix);
 	mlx5e_deactivate_xsk(c);
 	mlx5e_close_xsk(c);
 
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 a8315f166696..538bc2419bd8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -126,7 +126,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	/* Create a separate SQ, so that when the buff pool is disabled, we could
 	 * close this SQ safely and stop receiving CQEs. In other case, e.g., if
 	 * the XDPSQ was used instead, we might run into trouble when the buff pool
-	 * is disabled and then reenabled, but the SQ continues receiving CQEs
+	 * is disabled and then re-enabled, but the SQ continues receiving CQEs
 	 * from the old buff pool.
 	 */
 	err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, pool, &c->xsksq, true);
@@ -183,73 +183,3 @@ void mlx5e_deactivate_xsk(struct mlx5e_channel *c)
 	mlx5e_deactivate_rq(&c->xskrq);
 	/* TX queue is disabled on close. */
 }
-
-static int mlx5e_redirect_xsk_rqt(struct mlx5e_priv *priv, u16 ix, u32 rqn)
-{
-	struct mlx5e_redirect_rqt_param direct_rrp = {
-		.is_rss = false,
-		{
-			.rqn = rqn,
-		},
-	};
-
-	u32 rqtn = priv->xsk_tir[ix].rqt.rqtn;
-
-	return mlx5e_redirect_rqt(priv, rqtn, 1, direct_rrp);
-}
-
-int mlx5e_xsk_redirect_rqt_to_channel(struct mlx5e_priv *priv, struct mlx5e_channel *c)
-{
-	return mlx5e_redirect_xsk_rqt(priv, c->ix, c->xskrq.rqn);
-}
-
-int mlx5e_xsk_redirect_rqt_to_drop(struct mlx5e_priv *priv, u16 ix)
-{
-	return mlx5e_redirect_xsk_rqt(priv, ix, priv->drop_rq.rqn);
-}
-
-int mlx5e_xsk_redirect_rqts_to_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs)
-{
-	int err, i;
-
-	if (!priv->xsk.refcnt)
-		return 0;
-
-	for (i = 0; i < chs->num; i++) {
-		struct mlx5e_channel *c = chs->c[i];
-
-		if (!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
-			continue;
-
-		err = mlx5e_xsk_redirect_rqt_to_channel(priv, c);
-		if (unlikely(err))
-			goto err_stop;
-	}
-
-	return 0;
-
-err_stop:
-	for (i--; i >= 0; i--) {
-		if (!test_bit(MLX5E_CHANNEL_STATE_XSK, chs->c[i]->state))
-			continue;
-
-		mlx5e_xsk_redirect_rqt_to_drop(priv, i);
-	}
-
-	return err;
-}
-
-void mlx5e_xsk_redirect_rqts_to_drop(struct mlx5e_priv *priv, struct mlx5e_channels *chs)
-{
-	int i;
-
-	if (!priv->xsk.refcnt)
-		return;
-
-	for (i = 0; i < chs->num; i++) {
-		if (!test_bit(MLX5E_CHANNEL_STATE_XSK, chs->c[i]->state))
-			continue;
-
-		mlx5e_xsk_redirect_rqt_to_drop(priv, i);
-	}
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h
index ca20f1ff5e39..50e111b85efd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h
@@ -17,9 +17,5 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
 void mlx5e_close_xsk(struct mlx5e_channel *c);
 void mlx5e_activate_xsk(struct mlx5e_channel *c);
 void mlx5e_deactivate_xsk(struct mlx5e_channel *c);
-int mlx5e_xsk_redirect_rqt_to_channel(struct mlx5e_priv *priv, struct mlx5e_channel *c);
-int mlx5e_xsk_redirect_rqt_to_drop(struct mlx5e_priv *priv, u16 ix);
-int mlx5e_xsk_redirect_rqts_to_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs);
-void mlx5e_xsk_redirect_rqts_to_drop(struct mlx5e_priv *priv, struct mlx5e_channels *chs);
 
 #endif /* __MLX5_EN_XSK_SETUP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
index e51f60b55daa..4c4ee524176c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
@@ -16,13 +16,13 @@ struct mlx5e_accel_fs_tcp {
 	struct mlx5_flow_handle *default_rules[ACCEL_FS_TCP_NUM_TYPES];
 };
 
-static enum mlx5e_traffic_types fs_accel2tt(enum accel_fs_tcp_type i)
+static enum mlx5_traffic_types fs_accel2tt(enum accel_fs_tcp_type i)
 {
 	switch (i) {
 	case ACCEL_FS_IPV4_TCP:
-		return MLX5E_TT_IPV4_TCP;
+		return MLX5_TT_IPV4_TCP;
 	default: /* ACCEL_FS_IPV6_TCP */
-		return MLX5E_TT_IPV6_TCP;
+		return MLX5_TT_IPV6_TCP;
 	}
 }
 
@@ -161,7 +161,7 @@ static int accel_fs_tcp_add_default_rule(struct mlx5e_priv *priv,
 	fs_tcp = priv->fs.accel_tcp;
 	accel_fs_t = &fs_tcp->tables[type];
 
-	dest = mlx5e_ttc_get_default_dest(priv, fs_accel2tt(type));
+	dest = mlx5_ttc_get_default_dest(priv->fs.ttc, fs_accel2tt(type));
 	rule = mlx5_add_flow_rules(accel_fs_t->t, NULL, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -307,7 +307,7 @@ static int accel_fs_tcp_disable(struct mlx5e_priv *priv)
 
 	for (i = 0; i < ACCEL_FS_TCP_NUM_TYPES; i++) {
 		/* Modify ttc rules destination to point back to the indir TIRs */
-		err = mlx5e_ttc_fwd_default_dest(priv, fs_accel2tt(i));
+		err = mlx5_ttc_fwd_default_dest(priv->fs.ttc, fs_accel2tt(i));
 		if (err) {
 			netdev_err(priv->netdev,
 				   "%s: modify ttc[%d] default destination failed, err(%d)\n",
@@ -329,7 +329,7 @@ static int accel_fs_tcp_enable(struct mlx5e_priv *priv)
 		dest.ft = priv->fs.accel_tcp->tables[i].t;
 
 		/* Modify ttc rules destination to point on the accel_fs FTs */
-		err = mlx5e_ttc_fwd_dest(priv, fs_accel2tt(i), &dest);
+		err = mlx5_ttc_fwd_dest(priv->fs.ttc, fs_accel2tt(i), &dest);
 		if (err) {
 			netdev_err(priv->netdev,
 				   "%s: modify ttc[%d] destination to accel failed, err(%d)\n",
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 34119ce92031..17da23dff0ed 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
@@ -41,11 +41,11 @@ struct mlx5e_ipsec_tx {
 };
 
 /* IPsec RX flow steering */
-static enum mlx5e_traffic_types fs_esp2tt(enum accel_fs_esp_type i)
+static enum mlx5_traffic_types fs_esp2tt(enum accel_fs_esp_type i)
 {
 	if (i == ACCEL_FS_ESP4)
-		return MLX5E_TT_IPV4_IPSEC_ESP;
-	return MLX5E_TT_IPV6_IPSEC_ESP;
+		return MLX5_TT_IPV4_IPSEC_ESP;
+	return MLX5_TT_IPV6_IPSEC_ESP;
 }
 
 static int rx_err_add_rule(struct mlx5e_priv *priv,
@@ -265,7 +265,8 @@ static int rx_create(struct mlx5e_priv *priv, enum accel_fs_esp_type type)
 	accel_esp = priv->ipsec->rx_fs;
 	fs_prot = &accel_esp->fs_prot[type];
 
-	fs_prot->default_dest = mlx5e_ttc_get_default_dest(priv, fs_esp2tt(type));
+	fs_prot->default_dest =
+		mlx5_ttc_get_default_dest(priv->fs.ttc, fs_esp2tt(type));
 
 	err = rx_err_create_ft(priv, fs_prot, &fs_prot->rx_err);
 	if (err)
@@ -301,7 +302,7 @@ static int rx_ft_get(struct mlx5e_priv *priv, enum accel_fs_esp_type type)
 	/* connect */
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest.ft = fs_prot->ft;
-	mlx5e_ttc_fwd_dest(priv, fs_esp2tt(type), &dest);
+	mlx5_ttc_fwd_dest(priv->fs.ttc, fs_esp2tt(type), &dest);
 
 out:
 	mutex_unlock(&fs_prot->prot_mutex);
@@ -320,7 +321,7 @@ static void rx_ft_put(struct mlx5e_priv *priv, enum accel_fs_esp_type type)
 		goto out;
 
 	/* disconnect */
-	mlx5e_ttc_fwd_default_dest(priv, fs_esp2tt(type));
+	mlx5_ttc_fwd_default_dest(priv->fs.ttc, fs_esp2tt(type));
 
 	/* remove FT */
 	rx_destroy(priv, type);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index 4e58fade7a60..62abce008c7b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -49,7 +49,7 @@ struct mlx5e_ktls_offload_context_rx {
 	struct mlx5e_rq_stats *rq_stats;
 	struct mlx5e_tls_sw_stats *sw_stats;
 	struct completion add_ctx;
-	u32 tirn;
+	struct mlx5e_tir tir;
 	u32 key_id;
 	u32 rxq;
 	DECLARE_BITMAP(flags, MLX5E_NUM_PRIV_RX_FLAGS);
@@ -99,31 +99,22 @@ mlx5e_ktls_rx_resync_create_resp_list(void)
 	return resp_list;
 }
 
-static int mlx5e_ktls_create_tir(struct mlx5_core_dev *mdev, u32 *tirn, u32 rqtn)
+static int mlx5e_ktls_create_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir, u32 rqtn)
 {
-	int err, inlen;
-	void *tirc;
-	u32 *in;
+	struct mlx5e_tir_builder *builder;
+	int err;
 
-	inlen = MLX5_ST_SZ_BYTES(create_tir_in);
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
+	builder = mlx5e_tir_builder_alloc(false);
+	if (!builder)
 		return -ENOMEM;
 
-	tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
-
-	MLX5_SET(tirc, tirc, transport_domain, mdev->mlx5e_res.hw_objs.td.tdn);
-	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
-	MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8);
-	MLX5_SET(tirc, tirc, indirect_table, rqtn);
-	MLX5_SET(tirc, tirc, tls_en, 1);
-	MLX5_SET(tirc, tirc, self_lb_block,
-		 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST |
-		 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST);
+	mlx5e_tir_builder_build_rqt(builder, mdev->mlx5e_res.hw_objs.td.tdn, rqtn, false);
+	mlx5e_tir_builder_build_direct(builder);
+	mlx5e_tir_builder_build_tls(builder);
+	err = mlx5e_tir_init(tir, builder, mdev, false);
 
-	err = mlx5_core_create_tir(mdev, in, tirn);
+	mlx5e_tir_builder_free(builder);
 
-	kvfree(in);
 	return err;
 }
 
@@ -139,7 +130,8 @@ static void accel_rule_handle_work(struct work_struct *work)
 		goto out;
 
 	rule = mlx5e_accel_fs_add_sk(accel_rule->priv, priv_rx->sk,
-				     priv_rx->tirn, MLX5_FS_DEFAULT_FLOW_TAG);
+				     mlx5e_tir_get_tirn(&priv_rx->tir),
+				     MLX5_FS_DEFAULT_FLOW_TAG);
 	if (!IS_ERR_OR_NULL(rule))
 		accel_rule->rule = rule;
 out:
@@ -173,8 +165,8 @@ post_static_params(struct mlx5e_icosq *sq,
 	pi = mlx5e_icosq_get_next_pi(sq, num_wqebbs);
 	wqe = MLX5E_TLS_FETCH_SET_STATIC_PARAMS_WQE(sq, pi);
 	mlx5e_ktls_build_static_params(wqe, sq->pc, sq->sqn, &priv_rx->crypto_info,
-				       priv_rx->tirn, priv_rx->key_id,
-				       priv_rx->resync.seq, false,
+				       mlx5e_tir_get_tirn(&priv_rx->tir),
+				       priv_rx->key_id, priv_rx->resync.seq, false,
 				       TLS_OFFLOAD_CTX_DIR_RX);
 	wi = (struct mlx5e_icosq_wqe_info) {
 		.wqe_type = MLX5E_ICOSQ_WQE_UMR_TLS,
@@ -202,8 +194,9 @@ post_progress_params(struct mlx5e_icosq *sq,
 
 	pi = mlx5e_icosq_get_next_pi(sq, num_wqebbs);
 	wqe = MLX5E_TLS_FETCH_SET_PROGRESS_PARAMS_WQE(sq, pi);
-	mlx5e_ktls_build_progress_params(wqe, sq->pc, sq->sqn, priv_rx->tirn, false,
-					 next_record_tcp_sn,
+	mlx5e_ktls_build_progress_params(wqe, sq->pc, sq->sqn,
+					 mlx5e_tir_get_tirn(&priv_rx->tir),
+					 false, next_record_tcp_sn,
 					 TLS_OFFLOAD_CTX_DIR_RX);
 	wi = (struct mlx5e_icosq_wqe_info) {
 		.wqe_type = MLX5E_ICOSQ_WQE_SET_PSV_TLS,
@@ -325,7 +318,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 	psv = &wqe->psv;
 	psv->num_psv      = 1 << 4;
 	psv->l_key        = sq->channel->mkey_be;
-	psv->psv_index[0] = cpu_to_be32(priv_rx->tirn);
+	psv->psv_index[0] = cpu_to_be32(mlx5e_tir_get_tirn(&priv_rx->tir));
 	psv->va           = cpu_to_be64(buf->dma_addr);
 
 	wi = (struct mlx5e_icosq_wqe_info) {
@@ -635,9 +628,9 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk,
 	priv_rx->sw_stats = &priv->tls->sw_stats;
 	mlx5e_set_ktls_rx_priv_ctx(tls_ctx, priv_rx);
 
-	rqtn = priv->direct_tir[rxq].rqt.rqtn;
+	rqtn = mlx5e_rx_res_get_rqtn_direct(priv->rx_res, rxq);
 
-	err = mlx5e_ktls_create_tir(mdev, &priv_rx->tirn, rqtn);
+	err = mlx5e_ktls_create_tir(mdev, &priv_rx->tir, rqtn);
 	if (err)
 		goto err_create_tir;
 
@@ -658,7 +651,7 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk,
 	return 0;
 
 err_post_wqes:
-	mlx5_core_destroy_tir(mdev, priv_rx->tirn);
+	mlx5e_tir_destroy(&priv_rx->tir);
 err_create_tir:
 	mlx5_ktls_destroy_key(mdev, priv_rx->key_id);
 err_create_key:
@@ -693,7 +686,7 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx)
 	if (priv_rx->rule.rule)
 		mlx5e_accel_fs_del_sk(priv_rx->rule.rule);
 
-	mlx5_core_destroy_tir(mdev, priv_rx->tirn);
+	mlx5e_tir_destroy(&priv_rx->tir);
 	mlx5_ktls_destroy_key(mdev, priv_rx->key_id);
 	/* priv_rx should normally be freed here, but if there is an outstanding
 	 * GET_PSV, deallocation will be delayed until the CQE for GET_PSV is
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 25403af32859..fe5d82fa6e92 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -98,17 +98,17 @@ struct arfs_rule {
 	for (j = 0; j < ARFS_HASH_SIZE; j++) \
 		hlist_for_each_entry_safe(hn, tmp, &hash[j], hlist)
 
-static enum mlx5e_traffic_types arfs_get_tt(enum arfs_type type)
+static enum mlx5_traffic_types arfs_get_tt(enum arfs_type type)
 {
 	switch (type) {
 	case ARFS_IPV4_TCP:
-		return MLX5E_TT_IPV4_TCP;
+		return MLX5_TT_IPV4_TCP;
 	case ARFS_IPV4_UDP:
-		return MLX5E_TT_IPV4_UDP;
+		return MLX5_TT_IPV4_UDP;
 	case ARFS_IPV6_TCP:
-		return MLX5E_TT_IPV6_TCP;
+		return MLX5_TT_IPV6_TCP;
 	case ARFS_IPV6_UDP:
-		return MLX5E_TT_IPV6_UDP;
+		return MLX5_TT_IPV6_UDP;
 	default:
 		return -EINVAL;
 	}
@@ -120,7 +120,7 @@ static int arfs_disable(struct mlx5e_priv *priv)
 
 	for (i = 0; i < ARFS_NUM_TYPES; i++) {
 		/* Modify ttc rules destination back to their default */
-		err = mlx5e_ttc_fwd_default_dest(priv, arfs_get_tt(i));
+		err = mlx5_ttc_fwd_default_dest(priv->fs.ttc, arfs_get_tt(i));
 		if (err) {
 			netdev_err(priv->netdev,
 				   "%s: modify ttc[%d] default destination failed, err(%d)\n",
@@ -149,7 +149,7 @@ int mlx5e_arfs_enable(struct mlx5e_priv *priv)
 	for (i = 0; i < ARFS_NUM_TYPES; i++) {
 		dest.ft = priv->fs.arfs->arfs_tables[i].ft.t;
 		/* Modify ttc rules destination to point on the aRFS FTs */
-		err = mlx5e_ttc_fwd_dest(priv, arfs_get_tt(i), &dest);
+		err = mlx5_ttc_fwd_dest(priv->fs.ttc, arfs_get_tt(i), &dest);
 		if (err) {
 			netdev_err(priv->netdev,
 				   "%s: modify ttc[%d] dest to arfs, failed err(%d)\n",
@@ -192,10 +192,9 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
 				 enum arfs_type type)
 {
 	struct arfs_table *arfs_t = &priv->fs.arfs->arfs_tables[type];
-	struct mlx5e_tir *tir = priv->indir_tir;
 	struct mlx5_flow_destination dest = {};
 	MLX5_DECLARE_FLOW_ACT(flow_act);
-	enum mlx5e_traffic_types tt;
+	enum mlx5_traffic_types tt;
 	int err = 0;
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
@@ -206,10 +205,10 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
 		return -EINVAL;
 	}
 
-	/* FIXME: Must use mlx5e_ttc_get_default_dest(),
+	/* FIXME: Must use mlx5_ttc_get_default_dest(),
 	 * but can't since TTC default is not setup yet !
 	 */
-	dest.tir_num = tir[tt].tirn;
+	dest.tir_num = mlx5e_rx_res_get_tirn_rss(priv->rx_res, tt);
 	arfs_t->default_rule = mlx5_add_flow_rules(arfs_t->ft.t, NULL,
 						   &flow_act,
 						   &dest, 1);
@@ -553,7 +552,7 @@ static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv,
 		       16);
 	}
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
-	dest.tir_num = priv->direct_tir[arfs_rule->rxq].tirn;
+	dest.tir_num = mlx5e_rx_res_get_tirn_direct(priv->rx_res, arfs_rule->rxq);
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -576,7 +575,7 @@ static void arfs_modify_rule_rq(struct mlx5e_priv *priv,
 	int err = 0;
 
 	dst.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
-	dst.tir_num = priv->direct_tir[rxq].tirn;
+	dst.tir_num = mlx5e_rx_res_get_tirn_direct(priv->rx_res, rxq);
 	err =  mlx5_modify_rule_destination(rule, &dst, NULL);
 	if (err)
 		netdev_warn(priv->netdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 8c166ee56d8b..84eb7201c142 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -33,36 +33,9 @@
 #include "en.h"
 
 /* mlx5e global resources should be placed in this file.
- * Global resources are common to all the netdevices crated on the same nic.
+ * Global resources are common to all the netdevices created on the same nic.
  */
 
-int mlx5e_create_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir, u32 *in)
-{
-	struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs;
-	int err;
-
-	err = mlx5_core_create_tir(mdev, in, &tir->tirn);
-	if (err)
-		return err;
-
-	mutex_lock(&res->td.list_lock);
-	list_add(&tir->list, &res->td.tirs_list);
-	mutex_unlock(&res->td.list_lock);
-
-	return 0;
-}
-
-void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
-		       struct mlx5e_tir *tir)
-{
-	struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs;
-
-	mutex_lock(&res->td.list_lock);
-	mlx5_core_destroy_tir(mdev, tir->tirn);
-	list_del(&tir->list);
-	mutex_unlock(&res->td.list_lock);
-}
-
 void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc)
 {
 	bool ro_pci_enable = pcie_relaxed_ordering_enabled(mdev->pdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index bd72572e03d1..2cfd12953909 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -420,6 +420,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 	unsigned int count = ch->combined_count;
 	struct mlx5e_params new_params;
 	bool arfs_enabled;
+	int rss_cnt;
 	bool opened;
 	int err = 0;
 
@@ -455,6 +456,27 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 		goto out;
 	}
 
+	/* Don't allow changing the number of channels if non-default RSS contexts exist,
+	 * the kernel doesn't protect against set_channels operations that break them.
+	 */
+	rss_cnt = mlx5e_rx_res_rss_cnt(priv->rx_res) - 1;
+	if (rss_cnt) {
+		err = -EINVAL;
+		netdev_err(priv->netdev, "%s: Non-default RSS contexts exist (%d), cannot change the number of channels\n",
+			   __func__, rss_cnt);
+		goto out;
+	}
+
+	/* Don't allow changing the number of channels if MQPRIO mode channel offload is active,
+	 * because it defines a partition over the channels queues.
+	 */
+	if (cur_params->mqprio.mode == TC_MQPRIO_MODE_CHANNEL) {
+		err = -EINVAL;
+		netdev_err(priv->netdev, "%s: MQPRIO mode channel offload is active, cannot change the number of channels\n",
+			   __func__);
+		goto out;
+	}
+
 	new_params = *cur_params;
 	new_params.num_channels = count;
 
@@ -512,7 +534,9 @@ int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv,
 }
 
 static int mlx5e_get_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *coal)
+			      struct ethtool_coalesce *coal,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
@@ -630,7 +654,9 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 }
 
 static int mlx5e_set_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *coal)
+			      struct ethtool_coalesce *coal,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv    = netdev_priv(netdev);
 
@@ -1172,7 +1198,7 @@ static int mlx5e_set_link_ksettings(struct net_device *netdev,
 
 u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv)
 {
-	return sizeof(priv->rss_params.toeplitz_hash_key);
+	return sizeof_field(struct mlx5e_rss_params_hash, toeplitz_hash_key);
 }
 
 static u32 mlx5e_get_rxfh_key_size(struct net_device *netdev)
@@ -1194,88 +1220,64 @@ static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev)
 	return mlx5e_ethtool_get_rxfh_indir_size(priv);
 }
 
-int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-		   u8 *hfunc)
+static int mlx5e_get_rxfh_context(struct net_device *dev, u32 *indir,
+				  u8 *key, u8 *hfunc, u32 rss_context)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5e_rss_params *rss = &priv->rss_params;
-
-	if (indir)
-		memcpy(indir, rss->indirection_rqt,
-		       sizeof(rss->indirection_rqt));
-
-	if (key)
-		memcpy(key, rss->toeplitz_hash_key,
-		       sizeof(rss->toeplitz_hash_key));
-
-	if (hfunc)
-		*hfunc = rss->hfunc;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	int err;
 
-	return 0;
+	mutex_lock(&priv->state_lock);
+	err = mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rss_context, indir, key, hfunc);
+	mutex_unlock(&priv->state_lock);
+	return err;
 }
 
-int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
-		   const u8 *key, const u8 hfunc)
+static int mlx5e_set_rxfh_context(struct net_device *dev, const u32 *indir,
+				  const u8 *key, const u8 hfunc,
+				  u32 *rss_context, bool delete)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_rss_params *rss = &priv->rss_params;
-	int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
-	bool refresh_tirs = false;
-	bool refresh_rqt = false;
-	void *in;
-
-	if ((hfunc != ETH_RSS_HASH_NO_CHANGE) &&
-	    (hfunc != ETH_RSS_HASH_XOR) &&
-	    (hfunc != ETH_RSS_HASH_TOP))
-		return -EINVAL;
-
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
+	int err;
 
 	mutex_lock(&priv->state_lock);
-
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != rss->hfunc) {
-		rss->hfunc = hfunc;
-		refresh_rqt = true;
-		refresh_tirs = true;
-	}
-
-	if (indir) {
-		memcpy(rss->indirection_rqt, indir,
-		       sizeof(rss->indirection_rqt));
-		refresh_rqt = true;
+	if (delete) {
+		err = mlx5e_rx_res_rss_destroy(priv->rx_res, *rss_context);
+		goto unlock;
 	}
 
-	if (key) {
-		memcpy(rss->toeplitz_hash_key, key,
-		       sizeof(rss->toeplitz_hash_key));
-		refresh_tirs = refresh_tirs || rss->hfunc == ETH_RSS_HASH_TOP;
-	}
+	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
+		unsigned int count = priv->channels.params.num_channels;
 
-	if (refresh_rqt && test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		struct mlx5e_redirect_rqt_param rrp = {
-			.is_rss = true,
-			{
-				.rss = {
-					.hfunc = rss->hfunc,
-					.channels  = &priv->channels,
-				},
-			},
-		};
-		u32 rqtn = priv->indir_rqt.rqtn;
-
-		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp);
+		err = mlx5e_rx_res_rss_init(priv->rx_res, rss_context, count);
+		if (err)
+			goto unlock;
 	}
 
-	if (refresh_tirs)
-		mlx5e_modify_tirs_hash(priv, in);
+	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, *rss_context, indir, key,
+					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc);
 
+unlock:
 	mutex_unlock(&priv->state_lock);
+	return err;
+}
 
-	kvfree(in);
+int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
+		   u8 *hfunc)
+{
+	return mlx5e_get_rxfh_context(netdev, indir, key, hfunc, 0);
+}
 
-	return 0;
+int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
+		   const u8 *key, const u8 hfunc)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	int err;
+
+	mutex_lock(&priv->state_lock);
+	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, 0, indir, key,
+					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc);
+	mutex_unlock(&priv->state_lock);
+	return err;
 }
 
 #define MLX5E_PFC_PREVEN_AUTO_TOUT_MSEC		100
@@ -2358,6 +2360,8 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_rxfh_indir_size = mlx5e_get_rxfh_indir_size,
 	.get_rxfh          = mlx5e_get_rxfh,
 	.set_rxfh          = mlx5e_set_rxfh,
+	.get_rxfh_context  = mlx5e_get_rxfh_context,
+	.set_rxfh_context  = mlx5e_set_rxfh_context,
 	.get_rxnfc         = mlx5e_get_rxnfc,
 	.set_rxnfc         = mlx5e_set_rxnfc,
 	.get_tunable       = mlx5e_get_tunable,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 0b75fab41ae8..c06b4b938ae7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -718,7 +718,7 @@ static int mlx5e_add_promisc_rule(struct mlx5e_priv *priv)
 	if (!spec)
 		return -ENOMEM;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest.ft = priv->fs.ttc.ft.t;
+	dest.ft = mlx5_get_ttc_flow_table(priv->fs.ttc);
 
 	rule_p = &priv->fs.promisc.rule;
 	*rule_p = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
@@ -854,593 +854,59 @@ void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft)
 	ft->t = NULL;
 }
 
-static void mlx5e_cleanup_ttc_rules(struct mlx5e_ttc_table *ttc)
-{
-	int i;
-
-	for (i = 0; i < MLX5E_NUM_TT; i++) {
-		if (!IS_ERR_OR_NULL(ttc->rules[i].rule)) {
-			mlx5_del_flow_rules(ttc->rules[i].rule);
-			ttc->rules[i].rule = NULL;
-		}
-	}
-
-	for (i = 0; i < MLX5E_NUM_TUNNEL_TT; i++) {
-		if (!IS_ERR_OR_NULL(ttc->tunnel_rules[i])) {
-			mlx5_del_flow_rules(ttc->tunnel_rules[i]);
-			ttc->tunnel_rules[i] = NULL;
-		}
-	}
-}
-
-struct mlx5e_etype_proto {
-	u16 etype;
-	u8 proto;
-};
-
-static struct mlx5e_etype_proto ttc_rules[] = {
-	[MLX5E_TT_IPV4_TCP] = {
-		.etype = ETH_P_IP,
-		.proto = IPPROTO_TCP,
-	},
-	[MLX5E_TT_IPV6_TCP] = {
-		.etype = ETH_P_IPV6,
-		.proto = IPPROTO_TCP,
-	},
-	[MLX5E_TT_IPV4_UDP] = {
-		.etype = ETH_P_IP,
-		.proto = IPPROTO_UDP,
-	},
-	[MLX5E_TT_IPV6_UDP] = {
-		.etype = ETH_P_IPV6,
-		.proto = IPPROTO_UDP,
-	},
-	[MLX5E_TT_IPV4_IPSEC_AH] = {
-		.etype = ETH_P_IP,
-		.proto = IPPROTO_AH,
-	},
-	[MLX5E_TT_IPV6_IPSEC_AH] = {
-		.etype = ETH_P_IPV6,
-		.proto = IPPROTO_AH,
-	},
-	[MLX5E_TT_IPV4_IPSEC_ESP] = {
-		.etype = ETH_P_IP,
-		.proto = IPPROTO_ESP,
-	},
-	[MLX5E_TT_IPV6_IPSEC_ESP] = {
-		.etype = ETH_P_IPV6,
-		.proto = IPPROTO_ESP,
-	},
-	[MLX5E_TT_IPV4] = {
-		.etype = ETH_P_IP,
-		.proto = 0,
-	},
-	[MLX5E_TT_IPV6] = {
-		.etype = ETH_P_IPV6,
-		.proto = 0,
-	},
-	[MLX5E_TT_ANY] = {
-		.etype = 0,
-		.proto = 0,
-	},
-};
-
-static struct mlx5e_etype_proto ttc_tunnel_rules[] = {
-	[MLX5E_TT_IPV4_GRE] = {
-		.etype = ETH_P_IP,
-		.proto = IPPROTO_GRE,
-	},
-	[MLX5E_TT_IPV6_GRE] = {
-		.etype = ETH_P_IPV6,
-		.proto = IPPROTO_GRE,
-	},
-	[MLX5E_TT_IPV4_IPIP] = {
-		.etype = ETH_P_IP,
-		.proto = IPPROTO_IPIP,
-	},
-	[MLX5E_TT_IPV6_IPIP] = {
-		.etype = ETH_P_IPV6,
-		.proto = IPPROTO_IPIP,
-	},
-	[MLX5E_TT_IPV4_IPV6] = {
-		.etype = ETH_P_IP,
-		.proto = IPPROTO_IPV6,
-	},
-	[MLX5E_TT_IPV6_IPV6] = {
-		.etype = ETH_P_IPV6,
-		.proto = IPPROTO_IPV6,
-	},
-
-};
-
-u8 mlx5e_get_proto_by_tunnel_type(enum mlx5e_tunnel_types tt)
-{
-	return ttc_tunnel_rules[tt].proto;
-}
-
-static bool mlx5e_tunnel_proto_supported_rx(struct mlx5_core_dev *mdev, u8 proto_type)
-{
-	switch (proto_type) {
-	case IPPROTO_GRE:
-		return MLX5_CAP_ETH(mdev, tunnel_stateless_gre);
-	case IPPROTO_IPIP:
-	case IPPROTO_IPV6:
-		return (MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip) ||
-			MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip_rx));
-	default:
-		return false;
-	}
-}
-
-static bool mlx5e_tunnel_any_rx_proto_supported(struct mlx5_core_dev *mdev)
-{
-	int tt;
-
-	for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) {
-		if (mlx5e_tunnel_proto_supported_rx(mdev, ttc_tunnel_rules[tt].proto))
-			return true;
-	}
-	return false;
-}
-
-bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev)
-{
-	return (mlx5e_tunnel_any_rx_proto_supported(mdev) &&
-		MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version));
-}
-
-static u8 mlx5e_etype_to_ipv(u16 ethertype)
-{
-	if (ethertype == ETH_P_IP)
-		return 4;
-
-	if (ethertype == ETH_P_IPV6)
-		return 6;
-
-	return 0;
-}
-
-static struct mlx5_flow_handle *
-mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
-			struct mlx5_flow_table *ft,
-			struct mlx5_flow_destination *dest,
-			u16 etype,
-			u8 proto)
-{
-	int match_ipv_outer = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ft_field_support.outer_ip_version);
-	MLX5_DECLARE_FLOW_ACT(flow_act);
-	struct mlx5_flow_handle *rule;
-	struct mlx5_flow_spec *spec;
-	int err = 0;
-	u8 ipv;
-
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec)
-		return ERR_PTR(-ENOMEM);
-
-	if (proto) {
-		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol);
-		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, proto);
-	}
-
-	ipv = mlx5e_etype_to_ipv(etype);
-	if (match_ipv_outer && ipv) {
-		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_version);
-		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_version, ipv);
-	} else if (etype) {
-		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ethertype);
-		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype);
-	}
-
-	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1);
-	if (IS_ERR(rule)) {
-		err = PTR_ERR(rule);
-		netdev_err(priv->netdev, "%s: add rule failed\n", __func__);
-	}
-
-	kvfree(spec);
-	return err ? ERR_PTR(err) : rule;
-}
-
-static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv,
-					  struct ttc_params *params,
-					  struct mlx5e_ttc_table *ttc)
-{
-	struct mlx5_flow_destination dest = {};
-	struct mlx5_flow_handle **trules;
-	struct mlx5e_ttc_rule *rules;
-	struct mlx5_flow_table *ft;
-	int tt;
-	int err;
-
-	ft = ttc->ft.t;
-	rules = ttc->rules;
-
-	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
-	for (tt = 0; tt < MLX5E_NUM_TT; tt++) {
-		struct mlx5e_ttc_rule *rule = &rules[tt];
-
-		if (tt == MLX5E_TT_ANY)
-			dest.tir_num = params->any_tt_tirn;
-		else
-			dest.tir_num = params->indir_tirn[tt];
-
-		rule->rule = mlx5e_generate_ttc_rule(priv, ft, &dest,
-						     ttc_rules[tt].etype,
-						     ttc_rules[tt].proto);
-		if (IS_ERR(rule->rule)) {
-			err = PTR_ERR(rule->rule);
-			rule->rule = NULL;
-			goto del_rules;
-		}
-		rule->default_dest = dest;
-	}
-
-	if (!params->inner_ttc || !mlx5e_tunnel_inner_ft_supported(priv->mdev))
-		return 0;
-
-	trules    = ttc->tunnel_rules;
-	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest.ft   = params->inner_ttc->ft.t;
-	for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) {
-		if (!mlx5e_tunnel_proto_supported_rx(priv->mdev,
-						     ttc_tunnel_rules[tt].proto))
-			continue;
-		trules[tt] = mlx5e_generate_ttc_rule(priv, ft, &dest,
-						     ttc_tunnel_rules[tt].etype,
-						     ttc_tunnel_rules[tt].proto);
-		if (IS_ERR(trules[tt])) {
-			err = PTR_ERR(trules[tt]);
-			trules[tt] = NULL;
-			goto del_rules;
-		}
-	}
-
-	return 0;
-
-del_rules:
-	mlx5e_cleanup_ttc_rules(ttc);
-	return err;
-}
-
-static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc,
-					 bool use_ipv)
-{
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct mlx5e_flow_table *ft = &ttc->ft;
-	int ix = 0;
-	u32 *in;
-	int err;
-	u8 *mc;
-
-	ft->g = kcalloc(MLX5E_TTC_NUM_GROUPS,
-			sizeof(*ft->g), GFP_KERNEL);
-	if (!ft->g)
-		return -ENOMEM;
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in) {
-		kfree(ft->g);
-		ft->g = NULL;
-		return -ENOMEM;
-	}
-
-	/* L4 Group */
-	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
-	MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol);
-	if (use_ipv)
-		MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_version);
-	else
-		MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype);
-	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
-	MLX5_SET_CFG(in, start_flow_index, ix);
-	ix += MLX5E_TTC_GROUP1_SIZE;
-	MLX5_SET_CFG(in, end_flow_index, ix - 1);
-	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
-	if (IS_ERR(ft->g[ft->num_groups]))
-		goto err;
-	ft->num_groups++;
-
-	/* L3 Group */
-	MLX5_SET(fte_match_param, mc, outer_headers.ip_protocol, 0);
-	MLX5_SET_CFG(in, start_flow_index, ix);
-	ix += MLX5E_TTC_GROUP2_SIZE;
-	MLX5_SET_CFG(in, end_flow_index, ix - 1);
-	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
-	if (IS_ERR(ft->g[ft->num_groups]))
-		goto err;
-	ft->num_groups++;
-
-	/* Any Group */
-	memset(in, 0, inlen);
-	MLX5_SET_CFG(in, start_flow_index, ix);
-	ix += MLX5E_TTC_GROUP3_SIZE;
-	MLX5_SET_CFG(in, end_flow_index, ix - 1);
-	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
-	if (IS_ERR(ft->g[ft->num_groups]))
-		goto err;
-	ft->num_groups++;
-
-	kvfree(in);
-	return 0;
-
-err:
-	err = PTR_ERR(ft->g[ft->num_groups]);
-	ft->g[ft->num_groups] = NULL;
-	kvfree(in);
-
-	return err;
-}
-
-static struct mlx5_flow_handle *
-mlx5e_generate_inner_ttc_rule(struct mlx5e_priv *priv,
-			      struct mlx5_flow_table *ft,
-			      struct mlx5_flow_destination *dest,
-			      u16 etype, u8 proto)
-{
-	MLX5_DECLARE_FLOW_ACT(flow_act);
-	struct mlx5_flow_handle *rule;
-	struct mlx5_flow_spec *spec;
-	int err = 0;
-	u8 ipv;
-
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec)
-		return ERR_PTR(-ENOMEM);
-
-	ipv = mlx5e_etype_to_ipv(etype);
-	if (etype && ipv) {
-		spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS;
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_version);
-		MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_version, ipv);
-	}
-
-	if (proto) {
-		spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS;
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_protocol);
-		MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_protocol, proto);
-	}
-
-	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1);
-	if (IS_ERR(rule)) {
-		err = PTR_ERR(rule);
-		netdev_err(priv->netdev, "%s: add rule failed\n", __func__);
-	}
-
-	kvfree(spec);
-	return err ? ERR_PTR(err) : rule;
-}
-
-static int mlx5e_generate_inner_ttc_table_rules(struct mlx5e_priv *priv,
-						struct ttc_params *params,
-						struct mlx5e_ttc_table *ttc)
-{
-	struct mlx5_flow_destination dest = {};
-	struct mlx5e_ttc_rule *rules;
-	struct mlx5_flow_table *ft;
-	int err;
-	int tt;
-
-	ft = ttc->ft.t;
-	rules = ttc->rules;
-	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
-
-	for (tt = 0; tt < MLX5E_NUM_TT; tt++) {
-		struct mlx5e_ttc_rule *rule = &rules[tt];
-
-		if (tt == MLX5E_TT_ANY)
-			dest.tir_num = params->any_tt_tirn;
-		else
-			dest.tir_num = params->indir_tirn[tt];
-
-		rule->rule = mlx5e_generate_inner_ttc_rule(priv, ft, &dest,
-							   ttc_rules[tt].etype,
-							   ttc_rules[tt].proto);
-		if (IS_ERR(rule->rule)) {
-			err = PTR_ERR(rule->rule);
-			rule->rule = NULL;
-			goto del_rules;
-		}
-		rule->default_dest = dest;
-	}
-
-	return 0;
-
-del_rules:
-
-	mlx5e_cleanup_ttc_rules(ttc);
-	return err;
-}
-
-static int mlx5e_create_inner_ttc_table_groups(struct mlx5e_ttc_table *ttc)
-{
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct mlx5e_flow_table *ft = &ttc->ft;
-	int ix = 0;
-	u32 *in;
-	int err;
-	u8 *mc;
-
-	ft->g = kcalloc(MLX5E_INNER_TTC_NUM_GROUPS, sizeof(*ft->g), GFP_KERNEL);
-	if (!ft->g)
-		return -ENOMEM;
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in) {
-		kfree(ft->g);
-		ft->g = NULL;
-		return -ENOMEM;
-	}
-
-	/* L4 Group */
-	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
-	MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_protocol);
-	MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_version);
-	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_INNER_HEADERS);
-	MLX5_SET_CFG(in, start_flow_index, ix);
-	ix += MLX5E_INNER_TTC_GROUP1_SIZE;
-	MLX5_SET_CFG(in, end_flow_index, ix - 1);
-	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
-	if (IS_ERR(ft->g[ft->num_groups]))
-		goto err;
-	ft->num_groups++;
-
-	/* L3 Group */
-	MLX5_SET(fte_match_param, mc, inner_headers.ip_protocol, 0);
-	MLX5_SET_CFG(in, start_flow_index, ix);
-	ix += MLX5E_INNER_TTC_GROUP2_SIZE;
-	MLX5_SET_CFG(in, end_flow_index, ix - 1);
-	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
-	if (IS_ERR(ft->g[ft->num_groups]))
-		goto err;
-	ft->num_groups++;
-
-	/* Any Group */
-	memset(in, 0, inlen);
-	MLX5_SET_CFG(in, start_flow_index, ix);
-	ix += MLX5E_INNER_TTC_GROUP3_SIZE;
-	MLX5_SET_CFG(in, end_flow_index, ix - 1);
-	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
-	if (IS_ERR(ft->g[ft->num_groups]))
-		goto err;
-	ft->num_groups++;
-
-	kvfree(in);
-	return 0;
-
-err:
-	err = PTR_ERR(ft->g[ft->num_groups]);
-	ft->g[ft->num_groups] = NULL;
-	kvfree(in);
-
-	return err;
-}
-
-void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv,
-				struct ttc_params *ttc_params)
-{
-	ttc_params->any_tt_tirn = priv->direct_tir[0].tirn;
-	ttc_params->inner_ttc = &priv->fs.inner_ttc;
-}
-
-void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params)
+static void mlx5e_set_inner_ttc_params(struct mlx5e_priv *priv,
+				       struct ttc_params *ttc_params)
 {
 	struct mlx5_flow_table_attr *ft_attr = &ttc_params->ft_attr;
+	int tt;
 
-	ft_attr->max_fte = MLX5E_INNER_TTC_TABLE_SIZE;
+	memset(ttc_params, 0, sizeof(*ttc_params));
+	ttc_params->ns = mlx5_get_flow_namespace(priv->mdev,
+						 MLX5_FLOW_NAMESPACE_KERNEL);
 	ft_attr->level = MLX5E_INNER_TTC_FT_LEVEL;
 	ft_attr->prio = MLX5E_NIC_PRIO;
+
+	for (tt = 0; tt < MLX5_NUM_TT; tt++) {
+		ttc_params->dests[tt].type = MLX5_FLOW_DESTINATION_TYPE_TIR;
+		ttc_params->dests[tt].tir_num =
+			tt == MLX5_TT_ANY ?
+				mlx5e_rx_res_get_tirn_direct(priv->rx_res, 0) :
+				mlx5e_rx_res_get_tirn_rss_inner(priv->rx_res,
+								tt);
+	}
 }
 
-void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params)
+void mlx5e_set_ttc_params(struct mlx5e_priv *priv,
+			  struct ttc_params *ttc_params, bool tunnel)
 
 {
 	struct mlx5_flow_table_attr *ft_attr = &ttc_params->ft_attr;
+	int tt;
 
-	ft_attr->max_fte = MLX5E_TTC_TABLE_SIZE;
+	memset(ttc_params, 0, sizeof(*ttc_params));
+	ttc_params->ns = mlx5_get_flow_namespace(priv->mdev,
+						 MLX5_FLOW_NAMESPACE_KERNEL);
 	ft_attr->level = MLX5E_TTC_FT_LEVEL;
 	ft_attr->prio = MLX5E_NIC_PRIO;
-}
-
-int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
-				 struct mlx5e_ttc_table *ttc)
-{
-	struct mlx5e_flow_table *ft = &ttc->ft;
-	int err;
 
-	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
-		return 0;
-
-	ft->t = mlx5_create_flow_table(priv->fs.ns, &params->ft_attr);
-	if (IS_ERR(ft->t)) {
-		err = PTR_ERR(ft->t);
-		ft->t = NULL;
-		return err;
+	for (tt = 0; tt < MLX5_NUM_TT; tt++) {
+		ttc_params->dests[tt].type = MLX5_FLOW_DESTINATION_TYPE_TIR;
+		ttc_params->dests[tt].tir_num =
+			tt == MLX5_TT_ANY ?
+				mlx5e_rx_res_get_tirn_direct(priv->rx_res, 0) :
+				mlx5e_rx_res_get_tirn_rss(priv->rx_res, tt);
 	}
 
-	err = mlx5e_create_inner_ttc_table_groups(ttc);
-	if (err)
-		goto err;
-
-	err = mlx5e_generate_inner_ttc_table_rules(priv, params, ttc);
-	if (err)
-		goto err;
-
-	return 0;
-
-err:
-	mlx5e_destroy_flow_table(ft);
-	return err;
-}
-
-void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv,
-				   struct mlx5e_ttc_table *ttc)
-{
-	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+	ttc_params->inner_ttc = tunnel;
+	if (!tunnel || !mlx5_tunnel_inner_ft_supported(priv->mdev))
 		return;
 
-	mlx5e_cleanup_ttc_rules(ttc);
-	mlx5e_destroy_flow_table(&ttc->ft);
-}
-
-void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv,
-			     struct mlx5e_ttc_table *ttc)
-{
-	mlx5e_cleanup_ttc_rules(ttc);
-	mlx5e_destroy_flow_table(&ttc->ft);
-}
-
-int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
-			   struct mlx5e_ttc_table *ttc)
-{
-	bool match_ipv_outer = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ft_field_support.outer_ip_version);
-	struct mlx5e_flow_table *ft = &ttc->ft;
-	int err;
-
-	ft->t = mlx5_create_flow_table(priv->fs.ns, &params->ft_attr);
-	if (IS_ERR(ft->t)) {
-		err = PTR_ERR(ft->t);
-		ft->t = NULL;
-		return err;
+	for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) {
+		ttc_params->tunnel_dests[tt].type =
+			MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+		ttc_params->tunnel_dests[tt].ft =
+			mlx5_get_ttc_flow_table(priv->fs.inner_ttc);
 	}
-
-	err = mlx5e_create_ttc_table_groups(ttc, match_ipv_outer);
-	if (err)
-		goto err;
-
-	err = mlx5e_generate_ttc_table_rules(priv, params, ttc);
-	if (err)
-		goto err;
-
-	return 0;
-err:
-	mlx5e_destroy_flow_table(ft);
-	return err;
-}
-
-int mlx5e_ttc_fwd_dest(struct mlx5e_priv *priv, enum mlx5e_traffic_types type,
-		       struct mlx5_flow_destination *new_dest)
-{
-	return mlx5_modify_rule_destination(priv->fs.ttc.rules[type].rule, new_dest, NULL);
-}
-
-struct mlx5_flow_destination
-mlx5e_ttc_get_default_dest(struct mlx5e_priv *priv, enum mlx5e_traffic_types type)
-{
-	struct mlx5_flow_destination *dest = &priv->fs.ttc.rules[type].default_dest;
-
-	WARN_ONCE(dest->type != MLX5_FLOW_DESTINATION_TYPE_TIR,
-		  "TTC[%d] default dest is not setup yet", type);
-
-	return *dest;
-}
-
-int mlx5e_ttc_fwd_default_dest(struct mlx5e_priv *priv, enum mlx5e_traffic_types type)
-{
-	struct mlx5_flow_destination dest = mlx5e_ttc_get_default_dest(priv, type);
-
-	return mlx5e_ttc_fwd_dest(priv, type, &dest);
 }
 
 static void mlx5e_del_l2_flow_rule(struct mlx5e_priv *priv,
@@ -1473,7 +939,7 @@ static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv,
 			       outer_headers.dmac_47_16);
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest.ft = priv->fs.ttc.ft.t;
+	dest.ft = mlx5_get_ttc_flow_table(priv->fs.ttc);
 
 	switch (type) {
 	case MLX5E_FULLMATCH:
@@ -1769,10 +1235,47 @@ static void mlx5e_destroy_vlan_table(struct mlx5e_priv *priv)
 	kvfree(priv->fs.vlan);
 }
 
-int mlx5e_create_flow_steering(struct mlx5e_priv *priv)
+static void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv)
+{
+	if (!mlx5_tunnel_inner_ft_supported(priv->mdev))
+		return;
+	mlx5_destroy_ttc_table(priv->fs.inner_ttc);
+}
+
+void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv)
+{
+	mlx5_destroy_ttc_table(priv->fs.ttc);
+}
+
+static int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv)
 {
 	struct ttc_params ttc_params = {};
-	int tt, err;
+
+	if (!mlx5_tunnel_inner_ft_supported(priv->mdev))
+		return 0;
+
+	mlx5e_set_inner_ttc_params(priv, &ttc_params);
+	priv->fs.inner_ttc = mlx5_create_inner_ttc_table(priv->mdev,
+							 &ttc_params);
+	if (IS_ERR(priv->fs.inner_ttc))
+		return PTR_ERR(priv->fs.inner_ttc);
+	return 0;
+}
+
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv)
+{
+	struct ttc_params ttc_params = {};
+
+	mlx5e_set_ttc_params(priv, &ttc_params, true);
+	priv->fs.ttc = mlx5_create_ttc_table(priv->mdev, &ttc_params);
+	if (IS_ERR(priv->fs.ttc))
+		return PTR_ERR(priv->fs.ttc);
+	return 0;
+}
+
+int mlx5e_create_flow_steering(struct mlx5e_priv *priv)
+{
+	int err;
 
 	priv->fs.ns = mlx5_get_flow_namespace(priv->mdev,
 					       MLX5_FLOW_NAMESPACE_KERNEL);
@@ -1787,23 +1290,15 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv)
 		priv->netdev->hw_features &= ~NETIF_F_NTUPLE;
 	}
 
-	mlx5e_set_ttc_basic_params(priv, &ttc_params);
-	mlx5e_set_inner_ttc_ft_params(&ttc_params);
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
-		ttc_params.indir_tirn[tt] = priv->inner_indir_tir[tt].tirn;
-
-	err = mlx5e_create_inner_ttc_table(priv, &ttc_params, &priv->fs.inner_ttc);
+	err = mlx5e_create_inner_ttc_table(priv);
 	if (err) {
-		netdev_err(priv->netdev, "Failed to create inner ttc table, err=%d\n",
+		netdev_err(priv->netdev,
+			   "Failed to create inner ttc table, err=%d\n",
 			   err);
 		goto err_destroy_arfs_tables;
 	}
 
-	mlx5e_set_ttc_ft_params(&ttc_params);
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
-		ttc_params.indir_tirn[tt] = priv->indir_tir[tt].tirn;
-
-	err = mlx5e_create_ttc_table(priv, &ttc_params, &priv->fs.ttc);
+	err = mlx5e_create_ttc_table(priv);
 	if (err) {
 		netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n",
 			   err);
@@ -1837,9 +1332,9 @@ err_destory_vlan_table:
 err_destroy_l2_table:
 	mlx5e_destroy_l2_table(priv);
 err_destroy_ttc_table:
-	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
+	mlx5e_destroy_ttc_table(priv);
 err_destroy_inner_ttc_table:
-	mlx5e_destroy_inner_ttc_table(priv, &priv->fs.inner_ttc);
+	mlx5e_destroy_inner_ttc_table(priv);
 err_destroy_arfs_tables:
 	mlx5e_arfs_destroy_tables(priv);
 
@@ -1851,8 +1346,8 @@ void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv)
 	mlx5e_ptp_free_rx_fs(priv);
 	mlx5e_destroy_vlan_table(priv);
 	mlx5e_destroy_l2_table(priv);
-	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
-	mlx5e_destroy_inner_ttc_table(priv, &priv->fs.inner_ttc);
+	mlx5e_destroy_ttc_table(priv);
+	mlx5e_destroy_inner_ttc_table(priv);
 	mlx5e_arfs_destroy_tables(priv);
 	mlx5e_ethtool_cleanup_steering(priv);
 }
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 b416a8ee2eed..03693fa74a70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -35,11 +35,19 @@
 #include "en/params.h"
 #include "en/xsk/pool.h"
 
+static int flow_type_to_traffic_type(u32 flow_type);
+
+static u32 flow_type_mask(u32 flow_type)
+{
+	return flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS);
+}
+
 struct mlx5e_ethtool_rule {
 	struct list_head             list;
 	struct ethtool_rx_flow_spec  flow_spec;
 	struct mlx5_flow_handle	     *rule;
 	struct mlx5e_ethtool_table   *eth_ft;
+	struct mlx5e_rss             *rss;
 };
 
 static void put_flow_table(struct mlx5e_ethtool_table *eth_ft)
@@ -66,7 +74,7 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv,
 	int table_size;
 	int prio;
 
-	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+	switch (flow_type_mask(fs->flow_type)) {
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
 	case TCP_V6_FLOW:
@@ -329,7 +337,7 @@ static int set_flow_attrs(u32 *match_c, u32 *match_v,
 					     outer_headers);
 	void *outer_headers_v = MLX5_ADDR_OF(fte_match_param, match_v,
 					     outer_headers);
-	u32 flow_type = fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT);
+	u32 flow_type = flow_type_mask(fs->flow_type);
 
 	switch (flow_type) {
 	case TCP_V4_FLOW:
@@ -397,10 +405,53 @@ static bool outer_header_zero(u32 *match_criteria)
 						  size - 1);
 }
 
+static int flow_get_tirn(struct mlx5e_priv *priv,
+			 struct mlx5e_ethtool_rule *eth_rule,
+			 struct ethtool_rx_flow_spec *fs,
+			 u32 rss_context, u32 *tirn)
+{
+	if (fs->flow_type & FLOW_RSS) {
+		struct mlx5e_lro_param lro_param;
+		struct mlx5e_rss *rss;
+		u32 flow_type;
+		int err;
+		int tt;
+
+		rss = mlx5e_rx_res_rss_get(priv->rx_res, rss_context);
+		if (!rss)
+			return -ENOENT;
+
+		flow_type = flow_type_mask(fs->flow_type);
+		tt = flow_type_to_traffic_type(flow_type);
+		if (tt < 0)
+			return -EINVAL;
+
+		lro_param = mlx5e_get_lro_param(&priv->channels.params);
+		err = mlx5e_rss_obtain_tirn(rss, tt, &lro_param, false, tirn);
+		if (err)
+			return err;
+		eth_rule->rss = rss;
+		mlx5e_rss_refcnt_inc(eth_rule->rss);
+	} else {
+		struct mlx5e_params *params = &priv->channels.params;
+		enum mlx5e_rq_group group;
+		u16 ix;
+
+		mlx5e_qid_get_ch_and_group(params, fs->ring_cookie, &ix, &group);
+
+		*tirn = group == MLX5E_RQ_GROUP_XSK ?
+			mlx5e_rx_res_get_tirn_xsk(priv->rx_res, ix) :
+			mlx5e_rx_res_get_tirn_direct(priv->rx_res, ix);
+	}
+
+	return 0;
+}
+
 static struct mlx5_flow_handle *
 add_ethtool_flow_rule(struct mlx5e_priv *priv,
+		      struct mlx5e_ethtool_rule *eth_rule,
 		      struct mlx5_flow_table *ft,
-		      struct ethtool_rx_flow_spec *fs)
+		      struct ethtool_rx_flow_spec *fs, u32 rss_context)
 {
 	struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND };
 	struct mlx5_flow_destination *dst = NULL;
@@ -419,22 +470,17 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv,
 	if (fs->ring_cookie == RX_CLS_FLOW_DISC) {
 		flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
 	} else {
-		struct mlx5e_params *params = &priv->channels.params;
-		enum mlx5e_rq_group group;
-		struct mlx5e_tir *tir;
-		u16 ix;
-
-		mlx5e_qid_get_ch_and_group(params, fs->ring_cookie, &ix, &group);
-		tir = group == MLX5E_RQ_GROUP_XSK ? priv->xsk_tir : priv->direct_tir;
-
 		dst = kzalloc(sizeof(*dst), GFP_KERNEL);
 		if (!dst) {
 			err = -ENOMEM;
 			goto free;
 		}
 
+		err = flow_get_tirn(priv, eth_rule, fs, rss_context, &dst->tir_num);
+		if (err)
+			goto free;
+
 		dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR;
-		dst->tir_num = tir[ix].tirn;
 		flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	}
 
@@ -458,6 +504,8 @@ static void del_ethtool_rule(struct mlx5e_priv *priv,
 {
 	if (eth_rule->rule)
 		mlx5_del_flow_rules(eth_rule->rule);
+	if (eth_rule->rss)
+		mlx5e_rss_refcnt_dec(eth_rule->rss);
 	list_del(&eth_rule->list);
 	priv->fs.ethtool.tot_num_rules--;
 	put_flow_table(eth_rule->eth_ft);
@@ -618,7 +666,7 @@ static int validate_flow(struct mlx5e_priv *priv,
 					fs->ring_cookie))
 			return -EINVAL;
 
-	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+	switch (flow_type_mask(fs->flow_type)) {
 	case ETHER_FLOW:
 		num_tuples += validate_ethter(fs);
 		break;
@@ -667,7 +715,7 @@ static int validate_flow(struct mlx5e_priv *priv,
 
 static int
 mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
-			   struct ethtool_rx_flow_spec *fs)
+			   struct ethtool_rx_flow_spec *fs, u32 rss_context)
 {
 	struct mlx5e_ethtool_table *eth_ft;
 	struct mlx5e_ethtool_rule *eth_rule;
@@ -698,7 +746,7 @@ mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
 		err = -EINVAL;
 		goto del_ethtool_rule;
 	}
-	rule = add_ethtool_flow_rule(priv, eth_ft->ft, fs);
+	rule = add_ethtool_flow_rule(priv, eth_rule, eth_ft->ft, fs, rss_context);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
 		goto del_ethtool_rule;
@@ -744,10 +792,20 @@ mlx5e_ethtool_get_flow(struct mlx5e_priv *priv,
 		return -EINVAL;
 
 	list_for_each_entry(eth_rule, &priv->fs.ethtool.rules, list) {
-		if (eth_rule->flow_spec.location == location) {
-			info->fs = eth_rule->flow_spec;
+		int index;
+
+		if (eth_rule->flow_spec.location != location)
+			continue;
+		if (!info)
 			return 0;
-		}
+		info->fs = eth_rule->flow_spec;
+		if (!eth_rule->rss)
+			return 0;
+		index = mlx5e_rx_res_rss_index(priv->rx_res, eth_rule->rss);
+		if (index < 0)
+			return index;
+		info->rss_context = index;
+		return 0;
 	}
 
 	return -ENOENT;
@@ -763,7 +821,7 @@ mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv,
 
 	info->data = MAX_NUM_OF_ETHTOOL_RULES;
 	while ((!err || err == -ENOENT) && idx < info->rule_cnt) {
-		err = mlx5e_ethtool_get_flow(priv, info, location);
+		err = mlx5e_ethtool_get_flow(priv, NULL, location);
 		if (!err)
 			rule_locs[idx++] = location;
 		location++;
@@ -785,45 +843,44 @@ void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv)
 	INIT_LIST_HEAD(&priv->fs.ethtool.rules);
 }
 
-static enum mlx5e_traffic_types flow_type_to_traffic_type(u32 flow_type)
+static int flow_type_to_traffic_type(u32 flow_type)
 {
 	switch (flow_type) {
 	case TCP_V4_FLOW:
-		return  MLX5E_TT_IPV4_TCP;
+		return MLX5_TT_IPV4_TCP;
 	case TCP_V6_FLOW:
-		return MLX5E_TT_IPV6_TCP;
+		return MLX5_TT_IPV6_TCP;
 	case UDP_V4_FLOW:
-		return MLX5E_TT_IPV4_UDP;
+		return MLX5_TT_IPV4_UDP;
 	case UDP_V6_FLOW:
-		return MLX5E_TT_IPV6_UDP;
+		return MLX5_TT_IPV6_UDP;
 	case AH_V4_FLOW:
-		return MLX5E_TT_IPV4_IPSEC_AH;
+		return MLX5_TT_IPV4_IPSEC_AH;
 	case AH_V6_FLOW:
-		return MLX5E_TT_IPV6_IPSEC_AH;
+		return MLX5_TT_IPV6_IPSEC_AH;
 	case ESP_V4_FLOW:
-		return MLX5E_TT_IPV4_IPSEC_ESP;
+		return MLX5_TT_IPV4_IPSEC_ESP;
 	case ESP_V6_FLOW:
-		return MLX5E_TT_IPV6_IPSEC_ESP;
+		return MLX5_TT_IPV6_IPSEC_ESP;
 	case IPV4_FLOW:
-		return MLX5E_TT_IPV4;
+		return MLX5_TT_IPV4;
 	case IPV6_FLOW:
-		return MLX5E_TT_IPV6;
+		return MLX5_TT_IPV6;
 	default:
-		return MLX5E_NUM_INDIR_TIRS;
+		return -EINVAL;
 	}
 }
 
 static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv,
 				  struct ethtool_rxnfc *nfc)
 {
-	int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
-	enum mlx5e_traffic_types tt;
 	u8 rx_hash_field = 0;
-	void *in;
+	int err;
+	int tt;
 
 	tt = flow_type_to_traffic_type(nfc->flow_type);
-	if (tt == MLX5E_NUM_INDIR_TIRS)
-		return -EINVAL;
+	if (tt < 0)
+		return tt;
 
 	/*  RSS does not support anything other than hashing to queues
 	 *  on src IP, dest IP, TCP/UDP src port and TCP/UDP dest
@@ -848,35 +905,24 @@ static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv,
 	if (nfc->data & RXH_L4_B_2_3)
 		rx_hash_field |= MLX5_HASH_FIELD_SEL_L4_DPORT;
 
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
 	mutex_lock(&priv->state_lock);
-
-	if (rx_hash_field == priv->rss_params.rx_hash_fields[tt])
-		goto out;
-
-	priv->rss_params.rx_hash_fields[tt] = rx_hash_field;
-	mlx5e_modify_tirs_hash(priv, in);
-
-out:
+	err = mlx5e_rx_res_rss_set_hash_fields(priv->rx_res, tt, rx_hash_field);
 	mutex_unlock(&priv->state_lock);
-	kvfree(in);
-	return 0;
+
+	return err;
 }
 
 static int mlx5e_get_rss_hash_opt(struct mlx5e_priv *priv,
 				  struct ethtool_rxnfc *nfc)
 {
-	enum mlx5e_traffic_types tt;
 	u32 hash_field = 0;
+	int tt;
 
 	tt = flow_type_to_traffic_type(nfc->flow_type);
-	if (tt == MLX5E_NUM_INDIR_TIRS)
-		return -EINVAL;
+	if (tt < 0)
+		return tt;
 
-	hash_field = priv->rss_params.rx_hash_fields[tt];
+	hash_field = mlx5e_rx_res_rss_get_hash_fields(priv->rx_res, tt);
 	nfc->data = 0;
 
 	if (hash_field & MLX5_HASH_FIELD_SEL_SRC_IP)
@@ -898,7 +944,7 @@ int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 
 	switch (cmd->cmd) {
 	case ETHTOOL_SRXCLSRLINS:
-		err = mlx5e_ethtool_flow_replace(priv, &cmd->fs);
+		err = mlx5e_ethtool_flow_replace(priv, &cmd->fs, cmd->rss_context);
 		break;
 	case ETHTOOL_SRXCLSRLDEL:
 		err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 24f919ef9b8e..47efd858964d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1619,7 +1619,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 				  (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
 
 	MLX5_SET(cqc,   cqc, cq_period_mode, param->cq_period_mode);
-	MLX5_SET(cqc,   cqc, c_eqn,         eqn);
+	MLX5_SET(cqc,   cqc, c_eqn_or_apu_element, eqn);
 	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);
 	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
 					    MLX5_ADAPTER_PAGE_SHIFT);
@@ -1711,7 +1711,7 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c,
 {
 	int err, tc;
 
-	for (tc = 0; tc < params->num_tc; tc++) {
+	for (tc = 0; tc < mlx5e_get_dcb_num_tc(params); tc++) {
 		int txq_ix = c->ix + tc * params->num_channels;
 
 		err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix,
@@ -1992,7 +1992,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->pdev     = mlx5_core_dma_dev(priv->mdev);
 	c->netdev   = priv->netdev;
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key);
-	c->num_tc   = params->num_tc;
+	c->num_tc   = mlx5e_get_dcb_num_tc(params);
 	c->xdp      = !!params->xdp_prog;
 	c->stats    = &priv->channel_stats[ix].ch;
 	c->aff_mask = irq_get_effective_affinity_mask(irq);
@@ -2185,400 +2185,14 @@ void mlx5e_close_channels(struct mlx5e_channels *chs)
 	chs->num = 0;
 }
 
-static int
-mlx5e_create_rqt(struct mlx5e_priv *priv, int sz, struct mlx5e_rqt *rqt)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	void *rqtc;
-	int inlen;
-	int err;
-	u32 *in;
-	int i;
-
-	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * sz;
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
-	rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context);
-
-	MLX5_SET(rqtc, rqtc, rqt_actual_size, sz);
-	MLX5_SET(rqtc, rqtc, rqt_max_size, sz);
-
-	for (i = 0; i < sz; i++)
-		MLX5_SET(rqtc, rqtc, rq_num[i], priv->drop_rq.rqn);
-
-	err = mlx5_core_create_rqt(mdev, in, inlen, &rqt->rqtn);
-	if (!err)
-		rqt->enabled = true;
-
-	kvfree(in);
-	return err;
-}
-
-void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt)
-{
-	rqt->enabled = false;
-	mlx5_core_destroy_rqt(priv->mdev, rqt->rqtn);
-}
-
-int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv)
-{
-	struct mlx5e_rqt *rqt = &priv->indir_rqt;
-	int err;
-
-	err = mlx5e_create_rqt(priv, MLX5E_INDIR_RQT_SIZE, rqt);
-	if (err)
-		mlx5_core_warn(priv->mdev, "create indirect rqts failed, %d\n", err);
-	return err;
-}
-
-int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n)
-{
-	int err;
-	int ix;
-
-	for (ix = 0; ix < n; ix++) {
-		err = mlx5e_create_rqt(priv, 1 /*size */, &tirs[ix].rqt);
-		if (unlikely(err))
-			goto err_destroy_rqts;
-	}
-
-	return 0;
-
-err_destroy_rqts:
-	mlx5_core_warn(priv->mdev, "create rqts failed, %d\n", err);
-	for (ix--; ix >= 0; ix--)
-		mlx5e_destroy_rqt(priv, &tirs[ix].rqt);
-
-	return err;
-}
-
-void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n)
-{
-	int i;
-
-	for (i = 0; i < n; i++)
-		mlx5e_destroy_rqt(priv, &tirs[i].rqt);
-}
-
-static int mlx5e_rx_hash_fn(int hfunc)
-{
-	return (hfunc == ETH_RSS_HASH_TOP) ?
-	       MLX5_RX_HASH_FN_TOEPLITZ :
-	       MLX5_RX_HASH_FN_INVERTED_XOR8;
-}
-
-int mlx5e_bits_invert(unsigned long a, int size)
-{
-	int inv = 0;
-	int i;
-
-	for (i = 0; i < size; i++)
-		inv |= (test_bit(size - i - 1, &a) ? 1 : 0) << i;
-
-	return inv;
-}
-
-static void mlx5e_fill_rqt_rqns(struct mlx5e_priv *priv, int sz,
-				struct mlx5e_redirect_rqt_param rrp, void *rqtc)
-{
-	int i;
-
-	for (i = 0; i < sz; i++) {
-		u32 rqn;
-
-		if (rrp.is_rss) {
-			int ix = i;
-
-			if (rrp.rss.hfunc == ETH_RSS_HASH_XOR)
-				ix = mlx5e_bits_invert(i, ilog2(sz));
-
-			ix = priv->rss_params.indirection_rqt[ix];
-			rqn = rrp.rss.channels->c[ix]->rq.rqn;
-		} else {
-			rqn = rrp.rqn;
-		}
-		MLX5_SET(rqtc, rqtc, rq_num[i], rqn);
-	}
-}
-
-int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
-		       struct mlx5e_redirect_rqt_param rrp)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	void *rqtc;
-	int inlen;
-	u32 *in;
-	int err;
-
-	inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + sizeof(u32) * sz;
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
-	rqtc = MLX5_ADDR_OF(modify_rqt_in, in, ctx);
-
-	MLX5_SET(rqtc, rqtc, rqt_actual_size, sz);
-	MLX5_SET(modify_rqt_in, in, bitmask.rqn_list, 1);
-	mlx5e_fill_rqt_rqns(priv, sz, rrp, rqtc);
-	err = mlx5_core_modify_rqt(mdev, rqtn, in, inlen);
-
-	kvfree(in);
-	return err;
-}
-
-static u32 mlx5e_get_direct_rqn(struct mlx5e_priv *priv, int ix,
-				struct mlx5e_redirect_rqt_param rrp)
-{
-	if (!rrp.is_rss)
-		return rrp.rqn;
-
-	if (ix >= rrp.rss.channels->num)
-		return priv->drop_rq.rqn;
-
-	return rrp.rss.channels->c[ix]->rq.rqn;
-}
-
-static void mlx5e_redirect_rqts(struct mlx5e_priv *priv,
-				struct mlx5e_redirect_rqt_param rrp,
-				struct mlx5e_redirect_rqt_param *ptp_rrp)
-{
-	u32 rqtn;
-	int ix;
-
-	if (priv->indir_rqt.enabled) {
-		/* RSS RQ table */
-		rqtn = priv->indir_rqt.rqtn;
-		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp);
-	}
-
-	for (ix = 0; ix < priv->max_nch; ix++) {
-		struct mlx5e_redirect_rqt_param direct_rrp = {
-			.is_rss = false,
-			{
-				.rqn    = mlx5e_get_direct_rqn(priv, ix, rrp)
-			},
-		};
-
-		/* Direct RQ Tables */
-		if (!priv->direct_tir[ix].rqt.enabled)
-			continue;
-
-		rqtn = priv->direct_tir[ix].rqt.rqtn;
-		mlx5e_redirect_rqt(priv, rqtn, 1, direct_rrp);
-	}
-	if (ptp_rrp) {
-		rqtn = priv->ptp_tir.rqt.rqtn;
-		mlx5e_redirect_rqt(priv, rqtn, 1, *ptp_rrp);
-	}
-}
-
-static void mlx5e_redirect_rqts_to_channels(struct mlx5e_priv *priv,
-					    struct mlx5e_channels *chs)
-{
-	bool rx_ptp_support = priv->profile->rx_ptp_support;
-	struct mlx5e_redirect_rqt_param *ptp_rrp_p = NULL;
-	struct mlx5e_redirect_rqt_param rrp = {
-		.is_rss        = true,
-		{
-			.rss = {
-				.channels  = chs,
-				.hfunc     = priv->rss_params.hfunc,
-			}
-		},
-	};
-	struct mlx5e_redirect_rqt_param ptp_rrp;
-
-	if (rx_ptp_support) {
-		u32 ptp_rqn;
-
-		ptp_rrp.is_rss = false;
-		ptp_rrp.rqn = mlx5e_ptp_get_rqn(priv->channels.ptp, &ptp_rqn) ?
-			      priv->drop_rq.rqn : ptp_rqn;
-		ptp_rrp_p = &ptp_rrp;
-	}
-	mlx5e_redirect_rqts(priv, rrp, ptp_rrp_p);
-}
-
-static void mlx5e_redirect_rqts_to_drop(struct mlx5e_priv *priv)
-{
-	bool rx_ptp_support = priv->profile->rx_ptp_support;
-	struct mlx5e_redirect_rqt_param drop_rrp = {
-		.is_rss = false,
-		{
-			.rqn = priv->drop_rq.rqn,
-		},
-	};
-
-	mlx5e_redirect_rqts(priv, drop_rrp, rx_ptp_support ? &drop_rrp : NULL);
-}
-
-static const struct mlx5e_tirc_config tirc_default_config[MLX5E_NUM_INDIR_TIRS] = {
-	[MLX5E_TT_IPV4_TCP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
-				.l4_prot_type = MLX5_L4_PROT_TYPE_TCP,
-				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
-	},
-	[MLX5E_TT_IPV6_TCP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
-				.l4_prot_type = MLX5_L4_PROT_TYPE_TCP,
-				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
-	},
-	[MLX5E_TT_IPV4_UDP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
-				.l4_prot_type = MLX5_L4_PROT_TYPE_UDP,
-				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
-	},
-	[MLX5E_TT_IPV6_UDP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
-				.l4_prot_type = MLX5_L4_PROT_TYPE_UDP,
-				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
-	},
-	[MLX5E_TT_IPV4_IPSEC_AH] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
-				     .l4_prot_type = 0,
-				     .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
-	},
-	[MLX5E_TT_IPV6_IPSEC_AH] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
-				     .l4_prot_type = 0,
-				     .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
-	},
-	[MLX5E_TT_IPV4_IPSEC_ESP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
-				      .l4_prot_type = 0,
-				      .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
-	},
-	[MLX5E_TT_IPV6_IPSEC_ESP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
-				      .l4_prot_type = 0,
-				      .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
-	},
-	[MLX5E_TT_IPV4] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
-			    .l4_prot_type = 0,
-			    .rx_hash_fields = MLX5_HASH_IP,
-	},
-	[MLX5E_TT_IPV6] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
-			    .l4_prot_type = 0,
-			    .rx_hash_fields = MLX5_HASH_IP,
-	},
-};
-
-struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt)
-{
-	return tirc_default_config[tt];
-}
-
-static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
-{
-	if (!params->lro_en)
-		return;
-
-#define ROUGH_MAX_L2_L3_HDR_SZ 256
-
-	MLX5_SET(tirc, tirc, lro_enable_mask,
-		 MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO |
-		 MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO);
-	MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
-		 (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
-	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, params->lro_timeout);
-}
-
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params,
-				    const struct mlx5e_tirc_config *ttconfig,
-				    void *tirc, bool inner)
-{
-	void *hfso = inner ? MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner) :
-			     MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
-
-	MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(rss_params->hfunc));
-	if (rss_params->hfunc == ETH_RSS_HASH_TOP) {
-		void *rss_key = MLX5_ADDR_OF(tirc, tirc,
-					     rx_hash_toeplitz_key);
-		size_t len = MLX5_FLD_SZ_BYTES(tirc,
-					       rx_hash_toeplitz_key);
-
-		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
-		memcpy(rss_key, rss_params->toeplitz_hash_key, len);
-	}
-	MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-		 ttconfig->l3_prot_type);
-	MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-		 ttconfig->l4_prot_type);
-	MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-		 ttconfig->rx_hash_fields);
-}
-
-static void mlx5e_update_rx_hash_fields(struct mlx5e_tirc_config *ttconfig,
-					enum mlx5e_traffic_types tt,
-					u32 rx_hash_fields)
-{
-	*ttconfig                = tirc_default_config[tt];
-	ttconfig->rx_hash_fields = rx_hash_fields;
-}
-
-void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in)
-{
-	void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
-	struct mlx5e_rss_params *rss = &priv->rss_params;
-	struct mlx5_core_dev *mdev = priv->mdev;
-	int ctxlen = MLX5_ST_SZ_BYTES(tirc);
-	struct mlx5e_tirc_config ttconfig;
-	int tt;
-
-	MLX5_SET(modify_tir_in, in, bitmask.hash, 1);
-
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		memset(tirc, 0, ctxlen);
-		mlx5e_update_rx_hash_fields(&ttconfig, tt,
-					    rss->rx_hash_fields[tt]);
-		mlx5e_build_indir_tir_ctx_hash(rss, &ttconfig, tirc, false);
-		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in);
-	}
-
-	/* Verify inner tirs resources allocated */
-	if (!priv->inner_indir_tir[0].tirn)
-		return;
-
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		memset(tirc, 0, ctxlen);
-		mlx5e_update_rx_hash_fields(&ttconfig, tt,
-					    rss->rx_hash_fields[tt]);
-		mlx5e_build_indir_tir_ctx_hash(rss, &ttconfig, tirc, true);
-		mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in);
-	}
-}
-
 static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
-
-	void *in;
-	void *tirc;
-	int inlen;
-	int err;
-	int tt;
-	int ix;
-
-	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
-	MLX5_SET(modify_tir_in, in, bitmask.lro, 1);
-	tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
+	struct mlx5e_rx_res *res = priv->rx_res;
+	struct mlx5e_lro_param lro_param;
 
-	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
+	lro_param = mlx5e_get_lro_param(&priv->channels.params);
 
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		err = mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in);
-		if (err)
-			goto free_in;
-	}
-
-	for (ix = 0; ix < priv->max_nch; ix++) {
-		err = mlx5_core_modify_tir(mdev, priv->direct_tir[ix].tirn, in);
-		if (err)
-			goto free_in;
-	}
-
-free_in:
-	kvfree(in);
-
-	return err;
+	return mlx5e_rx_res_lro_set_param(res, &lro_param);
 }
 
 static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_lro);
@@ -2649,22 +2263,34 @@ void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv)
 				ETH_MAX_MTU);
 }
 
-static void mlx5e_netdev_set_tcs(struct net_device *netdev, u16 nch, u8 ntc)
+static int mlx5e_netdev_set_tcs(struct net_device *netdev, u16 nch, u8 ntc,
+				struct tc_mqprio_qopt_offload *mqprio)
 {
-	int tc;
+	int tc, err;
 
 	netdev_reset_tc(netdev);
 
 	if (ntc == 1)
-		return;
+		return 0;
 
-	netdev_set_num_tc(netdev, ntc);
+	err = netdev_set_num_tc(netdev, ntc);
+	if (err) {
+		netdev_WARN(netdev, "netdev_set_num_tc failed (%d), ntc = %d\n", err, ntc);
+		return err;
+	}
 
-	/* Map netdev TCs to offset 0
-	 * We have our own UP to TXQ mapping for QoS
-	 */
-	for (tc = 0; tc < ntc; tc++)
-		netdev_set_tc_queue(netdev, tc, nch, 0);
+	for (tc = 0; tc < ntc; tc++) {
+		u16 count, offset;
+
+		/* For DCB mode, map netdev TCs to offset 0
+		 * We have our own UP to TXQ mapping for QoS
+		 */
+		count = mqprio ? mqprio->qopt.count[tc] : nch;
+		offset = mqprio ? mqprio->qopt.offset[tc] : 0;
+		netdev_set_tc_queue(netdev, tc, count, offset);
+	}
+
+	return 0;
 }
 
 int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv)
@@ -2674,7 +2300,7 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv)
 	qos_queues = mlx5e_qos_cur_leaf_nodes(priv);
 
 	nch = priv->channels.params.num_channels;
-	ntc = priv->channels.params.num_tc;
+	ntc = mlx5e_get_dcb_num_tc(&priv->channels.params);
 	num_txqs = nch * ntc + qos_queues;
 	if (MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_TX_PORT_TS))
 		num_txqs += ntc;
@@ -2698,11 +2324,12 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
 	old_ntc = netdev->num_tc ? : 1;
 
 	nch = priv->channels.params.num_channels;
-	ntc = priv->channels.params.num_tc;
+	ntc = mlx5e_get_dcb_num_tc(&priv->channels.params);
 	num_rxqs = nch * priv->profile->rq_groups;
 
-	mlx5e_netdev_set_tcs(netdev, nch, ntc);
-
+	err = mlx5e_netdev_set_tcs(netdev, nch, ntc, NULL);
+	if (err)
+		goto err_out;
 	err = mlx5e_update_tx_netdev_queues(priv);
 	if (err)
 		goto err_tcs;
@@ -2723,7 +2350,8 @@ err_txqs:
 	WARN_ON_ONCE(netif_set_real_num_tx_queues(netdev, old_num_txqs));
 
 err_tcs:
-	mlx5e_netdev_set_tcs(netdev, old_num_txqs / old_ntc, old_ntc);
+	mlx5e_netdev_set_tcs(netdev, old_num_txqs / old_ntc, old_ntc, NULL);
+err_out:
 	return err;
 }
 
@@ -2759,9 +2387,9 @@ int mlx5e_num_channels_changed(struct mlx5e_priv *priv)
 
 	mlx5e_set_default_xps_cpumasks(priv, &priv->channels.params);
 
-	if (!netif_is_rxfh_configured(priv->netdev))
-		mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
-					      MLX5E_INDIR_RQT_SIZE, count);
+	/* This function may be called on attach, before priv->rx_res is created. */
+	if (!netif_is_rxfh_configured(priv->netdev) && priv->rx_res)
+		mlx5e_rx_res_rss_set_indir_uniform(priv->rx_res, count);
 
 	return 0;
 }
@@ -2773,7 +2401,7 @@ static void mlx5e_build_txq_maps(struct mlx5e_priv *priv)
 	int i, ch, tc, num_tc;
 
 	ch = priv->channels.num;
-	num_tc = priv->channels.params.num_tc;
+	num_tc = mlx5e_get_dcb_num_tc(&priv->channels.params);
 
 	for (i = 0; i < ch; i++) {
 		for (tc = 0; tc < num_tc; tc++) {
@@ -2804,7 +2432,7 @@ static void mlx5e_update_num_tc_x_num_ch(struct mlx5e_priv *priv)
 {
 	/* Sync with mlx5e_select_queue. */
 	WRITE_ONCE(priv->num_tc_x_num_ch,
-		   priv->channels.params.num_tc * priv->channels.num);
+		   mlx5e_get_dcb_num_tc(&priv->channels.params) * priv->channels.num);
 }
 
 void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
@@ -2820,16 +2448,15 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 		mlx5e_add_sqs_fwd_rules(priv);
 
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
-	mlx5e_redirect_rqts_to_channels(priv, &priv->channels);
 
-	mlx5e_xsk_redirect_rqts_to_channels(priv, &priv->channels);
+	if (priv->rx_res)
+		mlx5e_rx_res_channels_activate(priv->rx_res, &priv->channels);
 }
 
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
-	mlx5e_xsk_redirect_rqts_to_drop(priv, &priv->channels);
-
-	mlx5e_redirect_rqts_to_drop(priv);
+	if (priv->rx_res)
+		mlx5e_rx_res_channels_deactivate(priv->rx_res);
 
 	if (mlx5e_is_vport_rep(priv))
 		mlx5e_remove_sqs_fwd_rules(priv);
@@ -3204,224 +2831,152 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 	mlx5e_destroy_tises(priv);
 }
 
-static void mlx5e_build_indir_tir_ctx_common(struct mlx5e_priv *priv,
-					     u32 rqtn, u32 *tirc)
-{
-	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.hw_objs.td.tdn);
-	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
-	MLX5_SET(tirc, tirc, indirect_table, rqtn);
-	MLX5_SET(tirc, tirc, tunneled_offload_en,
-		 priv->channels.params.tunneled_offload_en);
-
-	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
-}
-
-static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv,
-				      enum mlx5e_traffic_types tt,
-				      u32 *tirc)
+static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable)
 {
-	mlx5e_build_indir_tir_ctx_common(priv, priv->indir_rqt.rqtn, tirc);
-	mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
-				       &tirc_default_config[tt], tirc, false);
-}
+	int err = 0;
+	int i;
 
-static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *tirc)
-{
-	mlx5e_build_indir_tir_ctx_common(priv, rqtn, tirc);
-	MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8);
-}
+	for (i = 0; i < chs->num; i++) {
+		err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable);
+		if (err)
+			return err;
+	}
 
-static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv,
-					    enum mlx5e_traffic_types tt,
-					    u32 *tirc)
-{
-	mlx5e_build_indir_tir_ctx_common(priv, priv->indir_rqt.rqtn, tirc);
-	mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
-				       &tirc_default_config[tt], tirc, true);
+	return 0;
 }
 
-int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc)
+static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
 {
-	struct mlx5e_tir *tir;
-	void *tirc;
-	int inlen;
-	int i = 0;
 	int err;
-	u32 *in;
-	int tt;
-
-	inlen = MLX5_ST_SZ_BYTES(create_tir_in);
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		memset(in, 0, inlen);
-		tir = &priv->indir_tir[tt];
-		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
-		mlx5e_build_indir_tir_ctx(priv, tt, tirc);
-		err = mlx5e_create_tir(priv->mdev, tir, in);
-		if (err) {
-			mlx5_core_warn(priv->mdev, "create indirect tirs failed, %d\n", err);
-			goto err_destroy_inner_tirs;
-		}
-	}
-
-	if (!inner_ttc || !mlx5e_tunnel_inner_ft_supported(priv->mdev))
-		goto out;
+	int i;
 
-	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) {
-		memset(in, 0, inlen);
-		tir = &priv->inner_indir_tir[i];
-		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
-		mlx5e_build_inner_indir_tir_ctx(priv, i, tirc);
-		err = mlx5e_create_tir(priv->mdev, tir, in);
-		if (err) {
-			mlx5_core_warn(priv->mdev, "create inner indirect tirs failed, %d\n", err);
-			goto err_destroy_inner_tirs;
-		}
+	for (i = 0; i < chs->num; i++) {
+		err = mlx5e_modify_rq_vsd(&chs->c[i]->rq, vsd);
+		if (err)
+			return err;
 	}
-
-out:
-	kvfree(in);
+	if (chs->ptp && test_bit(MLX5E_PTP_STATE_RX, chs->ptp->state))
+		return mlx5e_modify_rq_vsd(&chs->ptp->rq, vsd);
 
 	return 0;
-
-err_destroy_inner_tirs:
-	for (i--; i >= 0; i--)
-		mlx5e_destroy_tir(priv->mdev, &priv->inner_indir_tir[i]);
-
-	for (tt--; tt >= 0; tt--)
-		mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[tt]);
-
-	kvfree(in);
-
-	return err;
 }
 
-int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n)
+static int mlx5e_setup_tc_mqprio_dcb(struct mlx5e_priv *priv,
+				     struct tc_mqprio_qopt *mqprio)
 {
-	struct mlx5e_tir *tir;
-	void *tirc;
-	int inlen;
-	int err = 0;
-	u32 *in;
-	int ix;
-
-	inlen = MLX5_ST_SZ_BYTES(create_tir_in);
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
+	struct mlx5e_params new_params;
+	u8 tc = mqprio->num_tc;
+	int err;
 
-	for (ix = 0; ix < n; ix++) {
-		memset(in, 0, inlen);
-		tir = &tirs[ix];
-		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
-		mlx5e_build_direct_tir_ctx(priv, tir->rqt.rqtn, tirc);
-		err = mlx5e_create_tir(priv->mdev, tir, in);
-		if (unlikely(err))
-			goto err_destroy_ch_tirs;
-	}
+	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
 
-	goto out;
+	if (tc && tc != MLX5E_MAX_NUM_TC)
+		return -EINVAL;
 
-err_destroy_ch_tirs:
-	mlx5_core_warn(priv->mdev, "create tirs failed, %d\n", err);
-	for (ix--; ix >= 0; ix--)
-		mlx5e_destroy_tir(priv->mdev, &tirs[ix]);
+	new_params = priv->channels.params;
+	new_params.mqprio.mode = TC_MQPRIO_MODE_DCB;
+	new_params.mqprio.num_tc = tc ? tc : 1;
 
-out:
-	kvfree(in);
+	err = mlx5e_safe_switch_params(priv, &new_params,
+				       mlx5e_num_channels_changed_ctx, NULL, true);
 
+	priv->max_opened_tc = max_t(u8, priv->max_opened_tc,
+				    mlx5e_get_dcb_num_tc(&priv->channels.params));
 	return err;
 }
 
-void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv)
+static int mlx5e_mqprio_channel_validate(struct mlx5e_priv *priv,
+					 struct tc_mqprio_qopt_offload *mqprio)
 {
+	struct net_device *netdev = priv->netdev;
+	int agg_count = 0;
 	int i;
 
-	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
-		mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[i]);
-
-	/* Verify inner tirs resources allocated */
-	if (!priv->inner_indir_tir[0].tirn)
-		return;
-
-	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
-		mlx5e_destroy_tir(priv->mdev, &priv->inner_indir_tir[i]);
-}
-
-void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs, int n)
-{
-	int i;
+	if (mqprio->qopt.offset[0] != 0 || mqprio->qopt.num_tc < 1 ||
+	    mqprio->qopt.num_tc > MLX5E_MAX_NUM_MQPRIO_CH_TC)
+		return -EINVAL;
 
-	for (i = 0; i < n; i++)
-		mlx5e_destroy_tir(priv->mdev, &tirs[i]);
-}
+	for (i = 0; i < mqprio->qopt.num_tc; i++) {
+		if (!mqprio->qopt.count[i]) {
+			netdev_err(netdev, "Zero size for queue-group (%d) is not supported\n", i);
+			return -EINVAL;
+		}
+		if (mqprio->min_rate[i]) {
+			netdev_err(netdev, "Min tx rate is not supported\n");
+			return -EINVAL;
+		}
+		if (mqprio->max_rate[i]) {
+			netdev_err(netdev, "Max tx rate is not supported\n");
+			return -EINVAL;
+		}
 
-static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable)
-{
-	int err = 0;
-	int i;
+		if (mqprio->qopt.offset[i] != agg_count) {
+			netdev_err(netdev, "Discontinuous queues config is not supported\n");
+			return -EINVAL;
+		}
+		agg_count += mqprio->qopt.count[i];
+	}
 
-	for (i = 0; i < chs->num; i++) {
-		err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable);
-		if (err)
-			return err;
+	if (priv->channels.params.num_channels < agg_count) {
+		netdev_err(netdev, "Num of queues (%d) exceeds available (%d)\n",
+			   agg_count, priv->channels.params.num_channels);
+		return -EINVAL;
 	}
 
 	return 0;
 }
 
-static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
+static int mlx5e_mqprio_channel_set_tcs_ctx(struct mlx5e_priv *priv, void *ctx)
 {
-	int err;
-	int i;
+	struct tc_mqprio_qopt_offload *mqprio = (struct tc_mqprio_qopt_offload *)ctx;
+	struct net_device *netdev = priv->netdev;
+	u8 num_tc;
 
-	for (i = 0; i < chs->num; i++) {
-		err = mlx5e_modify_rq_vsd(&chs->c[i]->rq, vsd);
-		if (err)
-			return err;
-	}
-	if (chs->ptp && test_bit(MLX5E_PTP_STATE_RX, chs->ptp->state))
-		return mlx5e_modify_rq_vsd(&chs->ptp->rq, vsd);
+	if (priv->channels.params.mqprio.mode != TC_MQPRIO_MODE_CHANNEL)
+		return -EINVAL;
+
+	num_tc = priv->channels.params.mqprio.num_tc;
+	mlx5e_netdev_set_tcs(netdev, 0, num_tc, mqprio);
 
 	return 0;
 }
 
-static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
-				 struct tc_mqprio_qopt *mqprio)
+static int mlx5e_setup_tc_mqprio_channel(struct mlx5e_priv *priv,
+					 struct tc_mqprio_qopt_offload *mqprio)
 {
 	struct mlx5e_params new_params;
-	u8 tc = mqprio->num_tc;
-	int err = 0;
+	int err;
 
-	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	err = mlx5e_mqprio_channel_validate(priv, mqprio);
+	if (err)
+		return err;
 
-	if (tc && tc != MLX5E_MAX_NUM_TC)
-		return -EINVAL;
+	new_params = priv->channels.params;
+	new_params.mqprio.mode = TC_MQPRIO_MODE_CHANNEL;
+	new_params.mqprio.num_tc = mqprio->qopt.num_tc;
+	err = mlx5e_safe_switch_params(priv, &new_params,
+				       mlx5e_mqprio_channel_set_tcs_ctx, mqprio, true);
 
-	mutex_lock(&priv->state_lock);
+	return err;
+}
 
+static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
+				 struct tc_mqprio_qopt_offload *mqprio)
+{
 	/* MQPRIO is another toplevel qdisc that can't be attached
 	 * simultaneously with the offloaded HTB.
 	 */
-	if (WARN_ON(priv->htb.maj_id)) {
-		err = -EINVAL;
-		goto out;
-	}
-
-	new_params = priv->channels.params;
-	new_params.num_tc = tc ? tc : 1;
-
-	err = mlx5e_safe_switch_params(priv, &new_params,
-				       mlx5e_num_channels_changed_ctx, NULL, true);
+	if (WARN_ON(priv->htb.maj_id))
+		return -EINVAL;
 
-out:
-	priv->max_opened_tc = max_t(u8, priv->max_opened_tc,
-				    priv->channels.params.num_tc);
-	mutex_unlock(&priv->state_lock);
-	return err;
+	switch (mqprio->mode) {
+	case TC_MQPRIO_MODE_DCB:
+		return mlx5e_setup_tc_mqprio_dcb(priv, &mqprio->qopt);
+	case TC_MQPRIO_MODE_CHANNEL:
+		return mlx5e_setup_tc_mqprio_channel(priv, mqprio);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static int mlx5e_setup_tc_htb(struct mlx5e_priv *priv, struct tc_htb_qopt_offload *htb)
@@ -3445,8 +3000,7 @@ static int mlx5e_setup_tc_htb(struct mlx5e_priv *priv, struct tc_htb_qopt_offloa
 		return mlx5e_htb_leaf_to_inner(priv, htb->parent_classid, htb->classid,
 					       htb->rate, htb->ceil, htb->extack);
 	case TC_HTB_LEAF_DEL:
-		return mlx5e_htb_leaf_del(priv, htb->classid, &htb->moved_qid, &htb->qid,
-					  htb->extack);
+		return mlx5e_htb_leaf_del(priv, &htb->classid, htb->extack);
 	case TC_HTB_LEAF_DEL_LAST:
 	case TC_HTB_LEAF_DEL_LAST_FORCE:
 		return mlx5e_htb_leaf_del_last(priv, htb->classid,
@@ -3493,7 +3047,10 @@ static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
 						  priv, priv, true);
 	}
 	case TC_SETUP_QDISC_MQPRIO:
-		return mlx5e_setup_tc_mqprio(priv, type_data);
+		mutex_lock(&priv->state_lock);
+		err = mlx5e_setup_tc_mqprio(priv, type_data);
+		mutex_unlock(&priv->state_lock);
+		return err;
 	case TC_SETUP_QDISC_HTB:
 		mutex_lock(&priv->state_lock);
 		err = mlx5e_setup_tc_htb(priv, type_data);
@@ -4582,7 +4139,7 @@ const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_set_features        = mlx5e_set_features,
 	.ndo_fix_features        = mlx5e_fix_features,
 	.ndo_change_mtu          = mlx5e_change_nic_mtu,
-	.ndo_do_ioctl            = mlx5e_ioctl,
+	.ndo_eth_ioctl            = mlx5e_ioctl,
 	.ndo_set_tx_maxrate      = mlx5e_set_tx_maxrate,
 	.ndo_features_check      = mlx5e_features_check,
 	.ndo_tx_timeout          = mlx5e_tx_timeout,
@@ -4611,15 +4168,6 @@ const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_get_devlink_port    = mlx5e_get_devlink_port,
 };
 
-void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len,
-				   int num_channels)
-{
-	int i;
-
-	for (i = 0; i < len; i++)
-		indirection_rqt[i] = i % num_channels;
-}
-
 static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
 {
 	int i;
@@ -4632,24 +4180,8 @@ static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeo
 	return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]);
 }
 
-void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
-			    u16 num_channels)
-{
-	enum mlx5e_traffic_types tt;
-
-	rss_params->hfunc = ETH_RSS_HASH_TOP;
-	netdev_rss_key_fill(rss_params->toeplitz_hash_key,
-			    sizeof(rss_params->toeplitz_hash_key));
-	mlx5e_build_default_indir_rqt(rss_params->indirection_rqt,
-				      MLX5E_INDIR_RQT_SIZE, num_channels);
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
-		rss_params->rx_hash_fields[tt] =
-			tirc_default_config[tt].rx_hash_fields;
-}
-
 void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu)
 {
-	struct mlx5e_rss_params *rss_params = &priv->rss_params;
 	struct mlx5e_params *params = &priv->channels.params;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 rx_cq_period_mode;
@@ -4660,12 +4192,12 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	params->hard_mtu = MLX5E_ETH_HARD_MTU;
 	params->num_channels = min_t(unsigned int, MLX5E_MAX_NUM_CHANNELS / 2,
 				     priv->max_nch);
-	params->num_tc       = 1;
+	params->mqprio.num_tc = 1;
 
 	/* Set an initial non-zero value, so that mlx5e_select_queue won't
 	 * divide by zero if called before first activating channels.
 	 */
-	priv->num_tc_x_num_ch = params->num_channels * params->num_tc;
+	priv->num_tc_x_num_ch = params->num_channels * params->mqprio.num_tc;
 
 	/* SQ */
 	params->log_sq_size = is_kdump_kernel() ?
@@ -4709,10 +4241,7 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	/* TX inline */
 	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
 
-	/* RSS */
-	mlx5e_build_rss_params(rss_params, params->num_channels);
-	params->tunneled_offload_en =
-		mlx5e_tunnel_inner_ft_supported(mdev);
+	params->tunneled_offload_en = mlx5_tunnel_inner_ft_supported(mdev);
 
 	/* AF_XDP */
 	params->xsk = xsk;
@@ -4772,8 +4301,8 @@ static bool mlx5e_tunnel_any_tx_proto_supported(struct mlx5_core_dev *mdev)
 {
 	int tt;
 
-	for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) {
-		if (mlx5e_tunnel_proto_supported_tx(mdev, mlx5e_get_proto_by_tunnel_type(tt)))
+	for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) {
+		if (mlx5e_tunnel_proto_supported_tx(mdev, mlx5_get_proto_by_tunnel_type(tt)))
 			return true;
 	}
 	return (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev));
@@ -4812,7 +4341,14 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->hw_enc_features  |= NETIF_F_HW_VLAN_CTAG_TX;
 	netdev->hw_enc_features  |= NETIF_F_HW_VLAN_CTAG_RX;
 
+	/* Tunneled LRO is not supported in the driver, and the same RQs are
+	 * shared between inner and outer TIRs, so the driver can't disable LRO
+	 * for inner TIRs while having it enabled for outer TIRs. Due to this,
+	 * block LRO altogether if the firmware declares tunneled LRO support.
+	 */
 	if (!!MLX5_CAP_ETH(mdev, lro_cap) &&
+	    !MLX5_CAP_ETH(mdev, tunnel_lro_vxlan) &&
+	    !MLX5_CAP_ETH(mdev, tunnel_lro_gre) &&
 	    mlx5e_check_fragmented_striding_rq_cap(mdev))
 		netdev->vlan_features    |= NETIF_F_LRO;
 
@@ -4939,7 +4475,6 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 			  struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct devlink_port *dl_port;
 	int err;
 
 	mlx5e_build_nic_params(priv, &priv->xsk, netdev->mtu);
@@ -4955,19 +4490,13 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 	if (err)
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
 
-	dl_port = mlx5e_devlink_get_dl_port(priv);
-	if (dl_port->registered)
-		mlx5e_health_create_reporters(priv);
-
+	mlx5e_health_create_reporters(priv);
 	return 0;
 }
 
 static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
-	struct devlink_port *dl_port = mlx5e_devlink_get_dl_port(priv);
-
-	if (dl_port->registered)
-		mlx5e_health_destroy_reporters(priv);
+	mlx5e_health_destroy_reporters(priv);
 	mlx5e_tls_cleanup(priv);
 	mlx5e_ipsec_cleanup(priv);
 }
@@ -4975,9 +4504,14 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 max_nch = priv->max_nch;
+	enum mlx5e_rx_res_features features;
+	struct mlx5e_lro_param lro_param;
 	int err;
 
+	priv->rx_res = mlx5e_rx_res_alloc();
+	if (!priv->rx_res)
+		return -ENOMEM;
+
 	mlx5e_create_q_counters(priv);
 
 	err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
@@ -4986,42 +4520,20 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 		goto err_destroy_q_counters;
 	}
 
-	err = mlx5e_create_indirect_rqt(priv);
+	features = MLX5E_RX_RES_FEATURE_XSK | MLX5E_RX_RES_FEATURE_PTP;
+	if (priv->channels.params.tunneled_offload_en)
+		features |= MLX5E_RX_RES_FEATURE_INNER_FT;
+	lro_param = mlx5e_get_lro_param(&priv->channels.params);
+	err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, features,
+				priv->max_nch, priv->drop_rq.rqn, &lro_param,
+				priv->channels.params.num_channels);
 	if (err)
 		goto err_close_drop_rq;
 
-	err = mlx5e_create_direct_rqts(priv, priv->direct_tir, max_nch);
-	if (err)
-		goto err_destroy_indirect_rqts;
-
-	err = mlx5e_create_indirect_tirs(priv, true);
-	if (err)
-		goto err_destroy_direct_rqts;
-
-	err = mlx5e_create_direct_tirs(priv, priv->direct_tir, max_nch);
-	if (err)
-		goto err_destroy_indirect_tirs;
-
-	err = mlx5e_create_direct_rqts(priv, priv->xsk_tir, max_nch);
-	if (unlikely(err))
-		goto err_destroy_direct_tirs;
-
-	err = mlx5e_create_direct_tirs(priv, priv->xsk_tir, max_nch);
-	if (unlikely(err))
-		goto err_destroy_xsk_rqts;
-
-	err = mlx5e_create_direct_rqts(priv, &priv->ptp_tir, 1);
-	if (err)
-		goto err_destroy_xsk_tirs;
-
-	err = mlx5e_create_direct_tirs(priv, &priv->ptp_tir, 1);
-	if (err)
-		goto err_destroy_ptp_rqt;
-
 	err = mlx5e_create_flow_steering(priv);
 	if (err) {
 		mlx5_core_warn(mdev, "create flow steering failed, %d\n", err);
-		goto err_destroy_ptp_direct_tir;
+		goto err_destroy_rx_res;
 	}
 
 	err = mlx5e_tc_nic_init(priv);
@@ -5042,46 +4554,27 @@ err_tc_nic_cleanup:
 	mlx5e_tc_nic_cleanup(priv);
 err_destroy_flow_steering:
 	mlx5e_destroy_flow_steering(priv);
-err_destroy_ptp_direct_tir:
-	mlx5e_destroy_direct_tirs(priv, &priv->ptp_tir, 1);
-err_destroy_ptp_rqt:
-	mlx5e_destroy_direct_rqts(priv, &priv->ptp_tir, 1);
-err_destroy_xsk_tirs:
-	mlx5e_destroy_direct_tirs(priv, priv->xsk_tir, max_nch);
-err_destroy_xsk_rqts:
-	mlx5e_destroy_direct_rqts(priv, priv->xsk_tir, max_nch);
-err_destroy_direct_tirs:
-	mlx5e_destroy_direct_tirs(priv, priv->direct_tir, max_nch);
-err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv);
-err_destroy_direct_rqts:
-	mlx5e_destroy_direct_rqts(priv, priv->direct_tir, max_nch);
-err_destroy_indirect_rqts:
-	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+err_destroy_rx_res:
+	mlx5e_rx_res_destroy(priv->rx_res);
 err_close_drop_rq:
 	mlx5e_close_drop_rq(&priv->drop_rq);
 err_destroy_q_counters:
 	mlx5e_destroy_q_counters(priv);
+	mlx5e_rx_res_free(priv->rx_res);
+	priv->rx_res = NULL;
 	return err;
 }
 
 static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
 {
-	u16 max_nch = priv->max_nch;
-
 	mlx5e_accel_cleanup_rx(priv);
 	mlx5e_tc_nic_cleanup(priv);
 	mlx5e_destroy_flow_steering(priv);
-	mlx5e_destroy_direct_tirs(priv, &priv->ptp_tir, 1);
-	mlx5e_destroy_direct_rqts(priv, &priv->ptp_tir, 1);
-	mlx5e_destroy_direct_tirs(priv, priv->xsk_tir, max_nch);
-	mlx5e_destroy_direct_rqts(priv, priv->xsk_tir, max_nch);
-	mlx5e_destroy_direct_tirs(priv, priv->direct_tir, max_nch);
-	mlx5e_destroy_indirect_tirs(priv);
-	mlx5e_destroy_direct_rqts(priv, priv->direct_tir, max_nch);
-	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+	mlx5e_rx_res_destroy(priv->rx_res);
 	mlx5e_close_drop_rq(&priv->drop_rq);
 	mlx5e_destroy_q_counters(priv);
+	mlx5e_rx_res_free(priv->rx_res);
+	priv->rx_res = NULL;
 }
 
 static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index bf94bcb6fa5d..ae71a17fdb27 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -49,6 +49,7 @@
 #include "en/devlink.h"
 #include "fs_core.h"
 #include "lib/mlx5.h"
+#include "lib/devcom.h"
 #define CREATE_TRACE_POINTS
 #include "diag/en_rep_tracepoint.h"
 #include "en_accel/ipsec.h"
@@ -250,7 +251,9 @@ static int mlx5e_rep_set_channels(struct net_device *dev,
 }
 
 static int mlx5e_rep_get_coalesce(struct net_device *netdev,
-				  struct ethtool_coalesce *coal)
+				  struct ethtool_coalesce *coal,
+				  struct kernel_ethtool_coalesce *kernel_coal,
+				  struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
@@ -258,7 +261,9 @@ static int mlx5e_rep_get_coalesce(struct net_device *netdev,
 }
 
 static int mlx5e_rep_set_coalesce(struct net_device *netdev,
-				  struct ethtool_coalesce *coal)
+				  struct ethtool_coalesce *coal,
+				  struct kernel_ethtool_coalesce *kernel_coal,
+				  struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
@@ -310,6 +315,8 @@ static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw,
 	rpriv = mlx5e_rep_to_rep_priv(rep);
 	list_for_each_entry_safe(rep_sq, tmp, &rpriv->vport_sqs_list, list) {
 		mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule);
+		if (rep_sq->send_to_vport_rule_peer)
+			mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule_peer);
 		list_del(&rep_sq->list);
 		kfree(rep_sq);
 	}
@@ -319,6 +326,7 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw,
 				 struct mlx5_eswitch_rep *rep,
 				 u32 *sqns_array, int sqns_num)
 {
+	struct mlx5_eswitch *peer_esw = NULL;
 	struct mlx5_flow_handle *flow_rule;
 	struct mlx5e_rep_priv *rpriv;
 	struct mlx5e_rep_sq *rep_sq;
@@ -329,6 +337,10 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw,
 		return 0;
 
 	rpriv = mlx5e_rep_to_rep_priv(rep);
+	if (mlx5_devcom_is_paired(esw->dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS))
+		peer_esw = mlx5_devcom_get_peer_data(esw->dev->priv.devcom,
+						     MLX5_DEVCOM_ESW_OFFLOADS);
+
 	for (i = 0; i < sqns_num; i++) {
 		rep_sq = kzalloc(sizeof(*rep_sq), GFP_KERNEL);
 		if (!rep_sq) {
@@ -337,7 +349,7 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw,
 		}
 
 		/* Add re-inject rule to the PF/representor sqs */
-		flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw, rep,
+		flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw, esw, rep,
 								sqns_array[i]);
 		if (IS_ERR(flow_rule)) {
 			err = PTR_ERR(flow_rule);
@@ -345,12 +357,34 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw,
 			goto out_err;
 		}
 		rep_sq->send_to_vport_rule = flow_rule;
+		rep_sq->sqn = sqns_array[i];
+
+		if (peer_esw) {
+			flow_rule = mlx5_eswitch_add_send_to_vport_rule(peer_esw, esw,
+									rep, sqns_array[i]);
+			if (IS_ERR(flow_rule)) {
+				err = PTR_ERR(flow_rule);
+				mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule);
+				kfree(rep_sq);
+				goto out_err;
+			}
+			rep_sq->send_to_vport_rule_peer = flow_rule;
+		}
+
 		list_add(&rep_sq->list, &rpriv->vport_sqs_list);
 	}
+
+	if (peer_esw)
+		mlx5_devcom_release_peer_data(esw->dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+
 	return 0;
 
 out_err:
 	mlx5e_sqs2vport_stop(esw, rep);
+
+	if (peer_esw)
+		mlx5_devcom_release_peer_data(esw->dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+
 	return err;
 }
 
@@ -364,7 +398,8 @@ int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv)
 	int err = -ENOMEM;
 	u32 *sqs;
 
-	sqs = kcalloc(priv->channels.num * priv->channels.params.num_tc, sizeof(*sqs), GFP_KERNEL);
+	sqs = kcalloc(priv->channels.num * mlx5e_get_dcb_num_tc(&priv->channels.params),
+		      sizeof(*sqs), GFP_KERNEL);
 	if (!sqs)
 		goto out;
 
@@ -581,13 +616,10 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
 	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
 
-	params->num_tc                = 1;
+	params->mqprio.num_tc       = 1;
 	params->tunneled_offload_en = false;
 
 	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
-
-	/* RSS */
-	mlx5e_build_rss_params(&priv->rss_params, params->num_channels);
 }
 
 static void mlx5e_build_rep_netdev(struct net_device *netdev,
@@ -651,25 +683,23 @@ static int mlx5e_create_rep_ttc_table(struct mlx5e_priv *priv)
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct ttc_params ttc_params = {};
-	int tt, err;
+	int err;
 
 	priv->fs.ns = mlx5_get_flow_namespace(priv->mdev,
 					      MLX5_FLOW_NAMESPACE_KERNEL);
 
 	/* The inner_ttc in the ttc params is intentionally not set */
-	ttc_params.any_tt_tirn = priv->direct_tir[0].tirn;
-	mlx5e_set_ttc_ft_params(&ttc_params);
+	mlx5e_set_ttc_params(priv, &ttc_params, false);
 
 	if (rep->vport != MLX5_VPORT_UPLINK)
 		/* To give uplik rep TTC a lower level for chaining from root ft */
 		ttc_params.ft_attr.level = MLX5E_TTC_FT_LEVEL + 1;
 
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
-		ttc_params.indir_tirn[tt] = priv->indir_tir[tt].tirn;
-
-	err = mlx5e_create_ttc_table(priv, &ttc_params, &priv->fs.ttc);
-	if (err) {
-		netdev_err(priv->netdev, "Failed to create rep ttc table, err=%d\n", err);
+	priv->fs.ttc = mlx5_create_ttc_table(priv->mdev, &ttc_params);
+	if (IS_ERR(priv->fs.ttc)) {
+		err = PTR_ERR(priv->fs.ttc);
+		netdev_err(priv->netdev, "Failed to create rep ttc table, err=%d\n",
+			   err);
 		return err;
 	}
 	return 0;
@@ -687,7 +717,7 @@ static int mlx5e_create_rep_root_ft(struct mlx5e_priv *priv)
 		/* non uplik reps will skip any bypass tables and go directly to
 		 * their own ttc
 		 */
-		rpriv->root_ft = priv->fs.ttc.ft.t;
+		rpriv->root_ft = mlx5_get_ttc_flow_table(priv->fs.ttc);
 		return 0;
 	}
 
@@ -760,9 +790,13 @@ int mlx5e_rep_bond_update(struct mlx5e_priv *priv, bool cleanup)
 static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 max_nch = priv->max_nch;
+	struct mlx5e_lro_param lro_param;
 	int err;
 
+	priv->rx_res = mlx5e_rx_res_alloc();
+	if (!priv->rx_res)
+		return -ENOMEM;
+
 	mlx5e_init_l2_addr(priv);
 
 	err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
@@ -771,25 +805,16 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 		return err;
 	}
 
-	err = mlx5e_create_indirect_rqt(priv);
+	lro_param = mlx5e_get_lro_param(&priv->channels.params);
+	err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0,
+				priv->max_nch, priv->drop_rq.rqn, &lro_param,
+				priv->channels.params.num_channels);
 	if (err)
 		goto err_close_drop_rq;
 
-	err = mlx5e_create_direct_rqts(priv, priv->direct_tir, max_nch);
-	if (err)
-		goto err_destroy_indirect_rqts;
-
-	err = mlx5e_create_indirect_tirs(priv, false);
-	if (err)
-		goto err_destroy_direct_rqts;
-
-	err = mlx5e_create_direct_tirs(priv, priv->direct_tir, max_nch);
-	if (err)
-		goto err_destroy_indirect_tirs;
-
 	err = mlx5e_create_rep_ttc_table(priv);
 	if (err)
-		goto err_destroy_direct_tirs;
+		goto err_destroy_rx_res;
 
 	err = mlx5e_create_rep_root_ft(priv);
 	if (err)
@@ -806,33 +831,26 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 err_destroy_root_ft:
 	mlx5e_destroy_rep_root_ft(priv);
 err_destroy_ttc_table:
-	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
-err_destroy_direct_tirs:
-	mlx5e_destroy_direct_tirs(priv, priv->direct_tir, max_nch);
-err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv);
-err_destroy_direct_rqts:
-	mlx5e_destroy_direct_rqts(priv, priv->direct_tir, max_nch);
-err_destroy_indirect_rqts:
-	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+	mlx5_destroy_ttc_table(priv->fs.ttc);
+err_destroy_rx_res:
+	mlx5e_rx_res_destroy(priv->rx_res);
 err_close_drop_rq:
 	mlx5e_close_drop_rq(&priv->drop_rq);
+	mlx5e_rx_res_free(priv->rx_res);
+	priv->rx_res = NULL;
 	return err;
 }
 
 static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 {
-	u16 max_nch = priv->max_nch;
-
 	mlx5e_ethtool_cleanup_steering(priv);
 	rep_vport_rx_rule_destroy(priv);
 	mlx5e_destroy_rep_root_ft(priv);
-	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
-	mlx5e_destroy_direct_tirs(priv, priv->direct_tir, max_nch);
-	mlx5e_destroy_indirect_tirs(priv);
-	mlx5e_destroy_direct_rqts(priv, priv->direct_tir, max_nch);
-	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+	mlx5_destroy_ttc_table(priv->fs.ttc);
+	mlx5e_rx_res_destroy(priv->rx_res);
 	mlx5e_close_drop_rq(&priv->drop_rq);
+	mlx5e_rx_res_free(priv->rx_res);
+	priv->rx_res = NULL;
 }
 
 static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv)
@@ -1264,10 +1282,64 @@ static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep)
 	return rpriv->netdev;
 }
 
+static void mlx5e_vport_rep_event_unpair(struct mlx5_eswitch_rep *rep)
+{
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5e_rep_sq *rep_sq;
+
+	rpriv = mlx5e_rep_to_rep_priv(rep);
+	list_for_each_entry(rep_sq, &rpriv->vport_sqs_list, list) {
+		if (!rep_sq->send_to_vport_rule_peer)
+			continue;
+		mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule_peer);
+		rep_sq->send_to_vport_rule_peer = NULL;
+	}
+}
+
+static int mlx5e_vport_rep_event_pair(struct mlx5_eswitch *esw,
+				      struct mlx5_eswitch_rep *rep,
+				      struct mlx5_eswitch *peer_esw)
+{
+	struct mlx5_flow_handle *flow_rule;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5e_rep_sq *rep_sq;
+
+	rpriv = mlx5e_rep_to_rep_priv(rep);
+	list_for_each_entry(rep_sq, &rpriv->vport_sqs_list, list) {
+		if (rep_sq->send_to_vport_rule_peer)
+			continue;
+		flow_rule = mlx5_eswitch_add_send_to_vport_rule(peer_esw, esw, rep, rep_sq->sqn);
+		if (IS_ERR(flow_rule))
+			goto err_out;
+		rep_sq->send_to_vport_rule_peer = flow_rule;
+	}
+
+	return 0;
+err_out:
+	mlx5e_vport_rep_event_unpair(rep);
+	return PTR_ERR(flow_rule);
+}
+
+static int mlx5e_vport_rep_event(struct mlx5_eswitch *esw,
+				 struct mlx5_eswitch_rep *rep,
+				 enum mlx5_switchdev_event event,
+				 void *data)
+{
+	int err = 0;
+
+	if (event == MLX5_SWITCHDEV_EVENT_PAIR)
+		err = mlx5e_vport_rep_event_pair(esw, rep, data);
+	else if (event == MLX5_SWITCHDEV_EVENT_UNPAIR)
+		mlx5e_vport_rep_event_unpair(rep);
+
+	return err;
+}
+
 static const struct mlx5_eswitch_rep_ops rep_ops = {
 	.load = mlx5e_vport_rep_load,
 	.unload = mlx5e_vport_rep_unload,
-	.get_proto_dev = mlx5e_vport_rep_get_proto_dev
+	.get_proto_dev = mlx5e_vport_rep_get_proto_dev,
+	.event = mlx5e_vport_rep_event,
 };
 
 static int mlx5e_rep_probe(struct auxiliary_device *adev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 47a2dfb7792a..48a203a9e7d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -60,6 +60,7 @@ struct mlx5e_neigh_update_table {
 struct mlx5_tc_ct_priv;
 struct mlx5e_rep_bond;
 struct mlx5e_tc_tun_encap;
+struct mlx5e_post_act;
 
 struct mlx5_rep_uplink_priv {
 	/* Filters DB - instantiated by the uplink representor and shared by
@@ -88,8 +89,9 @@ struct mlx5_rep_uplink_priv {
 	/* maps tun_enc_opts to a unique id*/
 	struct mapping_ctx *tunnel_enc_opts_mapping;
 
+	struct mlx5e_post_act *post_act;
 	struct mlx5_tc_ct_priv *ct_priv;
-	struct mlx5_esw_psample *esw_psample;
+	struct mlx5e_tc_psample *tc_psample;
 
 	/* support eswitch vports bonding */
 	struct mlx5e_rep_bond *bond;
@@ -146,7 +148,7 @@ struct mlx5e_neigh_hash_entry {
 	 */
 	refcount_t refcnt;
 
-	/* Save the last reported time offloaded trafic pass over one of the
+	/* Save the last reported time offloaded traffic pass over one of the
 	 * neigh hash entry flows. Use it to periodically update the neigh
 	 * 'used' value and avoid neigh deleting by the kernel.
 	 */
@@ -207,6 +209,8 @@ struct mlx5e_encap_entry {
 
 struct mlx5e_rep_sq {
 	struct mlx5_flow_handle	*send_to_vport_rule;
+	struct mlx5_flow_handle *send_to_vport_rule_peer;
+	u32 sqn;
 	struct list_head	 list;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index d273758255c3..ba8164792016 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -34,25 +34,20 @@
 #include <net/flow_offload.h>
 #include <net/sch_generic.h>
 #include <net/pkt_cls.h>
-#include <net/tc_act/tc_gact.h>
-#include <net/tc_act/tc_skbedit.h>
 #include <linux/mlx5/fs.h>
 #include <linux/mlx5/device.h>
 #include <linux/rhashtable.h>
 #include <linux/refcount.h>
 #include <linux/completion.h>
-#include <net/tc_act/tc_mirred.h>
-#include <net/tc_act/tc_vlan.h>
-#include <net/tc_act/tc_tunnel_key.h>
 #include <net/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_csum.h>
-#include <net/tc_act/tc_mpls.h>
 #include <net/psample.h>
 #include <net/arp.h>
 #include <net/ipv6_stubs.h>
 #include <net/bareudp.h>
 #include <net/bonding.h>
 #include "en.h"
+#include "en/tc/post_act.h"
 #include "en_rep.h"
 #include "en/rep/tc.h"
 #include "en/rep/neigh.h"
@@ -66,7 +61,7 @@
 #include "en/mod_hdr.h"
 #include "en/tc_priv.h"
 #include "en/tc_tun_encap.h"
-#include "esw/sample.h"
+#include "en/tc/sample.h"
 #include "lib/devcom.h"
 #include "lib/geneve.h"
 #include "lib/fs_chains.h"
@@ -103,7 +98,7 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = {
 	[MARK_TO_REG] = mark_to_reg_ct,
 	[LABELS_TO_REG] = labels_to_reg_ct,
 	[FTEID_TO_REG] = fteid_to_reg_ct,
-	/* For NIC rules we store the retore metadata directly
+	/* For NIC rules we store the restore metadata directly
 	 * into reg_b that is passed to SW since we don't
 	 * jump between steering domains.
 	 */
@@ -252,7 +247,7 @@ get_ct_priv(struct mlx5e_priv *priv)
 }
 
 #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE)
-static struct mlx5_esw_psample *
+static struct mlx5e_tc_psample *
 get_sample_priv(struct mlx5e_priv *priv)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -263,7 +258,7 @@ get_sample_priv(struct mlx5e_priv *priv)
 		uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
 		uplink_priv = &uplink_rpriv->uplink_priv;
 
-		return uplink_priv->esw_psample;
+		return uplink_priv->tc_psample;
 	}
 
 	return NULL;
@@ -340,12 +335,12 @@ struct mlx5e_hairpin {
 	struct mlx5_core_dev *func_mdev;
 	struct mlx5e_priv *func_priv;
 	u32 tdn;
-	u32 tirn;
+	struct mlx5e_tir direct_tir;
 
 	int num_channels;
 	struct mlx5e_rqt indir_rqt;
-	u32 indir_tirn[MLX5E_NUM_INDIR_TIRS];
-	struct mlx5e_ttc_table ttc;
+	struct mlx5e_tir indir_tir[MLX5E_NUM_INDIR_TIRS];
+	struct mlx5_ttc_table *ttc;
 };
 
 struct mlx5e_hairpin_entry {
@@ -482,126 +477,101 @@ struct mlx5_core_dev *mlx5e_hairpin_get_mdev(struct net *net, int ifindex)
 
 static int mlx5e_hairpin_create_transport(struct mlx5e_hairpin *hp)
 {
-	u32 in[MLX5_ST_SZ_DW(create_tir_in)] = {};
-	void *tirc;
+	struct mlx5e_tir_builder *builder;
 	int err;
 
+	builder = mlx5e_tir_builder_alloc(false);
+	if (!builder)
+		return -ENOMEM;
+
 	err = mlx5_core_alloc_transport_domain(hp->func_mdev, &hp->tdn);
 	if (err)
-		goto alloc_tdn_err;
-
-	tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
-
-	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT);
-	MLX5_SET(tirc, tirc, inline_rqn, hp->pair->rqn[0]);
-	MLX5_SET(tirc, tirc, transport_domain, hp->tdn);
+		goto out;
 
-	err = mlx5_core_create_tir(hp->func_mdev, in, &hp->tirn);
+	mlx5e_tir_builder_build_inline(builder, hp->tdn, hp->pair->rqn[0]);
+	err = mlx5e_tir_init(&hp->direct_tir, builder, hp->func_mdev, false);
 	if (err)
 		goto create_tir_err;
 
-	return 0;
+out:
+	mlx5e_tir_builder_free(builder);
+	return err;
 
 create_tir_err:
 	mlx5_core_dealloc_transport_domain(hp->func_mdev, hp->tdn);
-alloc_tdn_err:
-	return err;
+
+	goto out;
 }
 
 static void mlx5e_hairpin_destroy_transport(struct mlx5e_hairpin *hp)
 {
-	mlx5_core_destroy_tir(hp->func_mdev, hp->tirn);
+	mlx5e_tir_destroy(&hp->direct_tir);
 	mlx5_core_dealloc_transport_domain(hp->func_mdev, hp->tdn);
 }
 
-static int mlx5e_hairpin_fill_rqt_rqns(struct mlx5e_hairpin *hp, void *rqtc)
-{
-	struct mlx5e_priv *priv = hp->func_priv;
-	int i, ix, sz = MLX5E_INDIR_RQT_SIZE;
-	u32 *indirection_rqt, rqn;
-
-	indirection_rqt = kcalloc(sz, sizeof(*indirection_rqt), GFP_KERNEL);
-	if (!indirection_rqt)
-		return -ENOMEM;
-
-	mlx5e_build_default_indir_rqt(indirection_rqt, sz,
-				      hp->num_channels);
-
-	for (i = 0; i < sz; i++) {
-		ix = i;
-		if (priv->rss_params.hfunc == ETH_RSS_HASH_XOR)
-			ix = mlx5e_bits_invert(i, ilog2(sz));
-		ix = indirection_rqt[ix];
-		rqn = hp->pair->rqn[ix];
-		MLX5_SET(rqtc, rqtc, rq_num[i], rqn);
-	}
-
-	kfree(indirection_rqt);
-	return 0;
-}
-
 static int mlx5e_hairpin_create_indirect_rqt(struct mlx5e_hairpin *hp)
 {
-	int inlen, err, sz = MLX5E_INDIR_RQT_SIZE;
 	struct mlx5e_priv *priv = hp->func_priv;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	void *rqtc;
-	u32 *in;
+	struct mlx5e_rss_params_indir *indir;
+	int err;
 
-	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * sz;
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
+	indir = kvmalloc(sizeof(*indir), GFP_KERNEL);
+	if (!indir)
 		return -ENOMEM;
 
-	rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context);
-
-	MLX5_SET(rqtc, rqtc, rqt_actual_size, sz);
-	MLX5_SET(rqtc, rqtc, rqt_max_size, sz);
-
-	err = mlx5e_hairpin_fill_rqt_rqns(hp, rqtc);
-	if (err)
-		goto out;
-
-	err = mlx5_core_create_rqt(mdev, in, inlen, &hp->indir_rqt.rqtn);
-	if (!err)
-		hp->indir_rqt.enabled = true;
+	mlx5e_rss_params_indir_init_uniform(indir, hp->num_channels);
+	err = mlx5e_rqt_init_indir(&hp->indir_rqt, mdev, hp->pair->rqn, hp->num_channels,
+				   mlx5e_rx_res_get_current_hash(priv->rx_res).hfunc,
+				   indir);
 
-out:
-	kvfree(in);
+	kvfree(indir);
 	return err;
 }
 
 static int mlx5e_hairpin_create_indirect_tirs(struct mlx5e_hairpin *hp)
 {
 	struct mlx5e_priv *priv = hp->func_priv;
-	u32 in[MLX5_ST_SZ_DW(create_tir_in)];
-	int tt, i, err;
-	void *tirc;
+	struct mlx5e_rss_params_hash rss_hash;
+	enum mlx5_traffic_types tt, max_tt;
+	struct mlx5e_tir_builder *builder;
+	int err = 0;
+
+	builder = mlx5e_tir_builder_alloc(false);
+	if (!builder)
+		return -ENOMEM;
+
+	rss_hash = mlx5e_rx_res_get_current_hash(priv->rx_res);
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		struct mlx5e_tirc_config ttconfig = mlx5e_tirc_get_default_config(tt);
+		struct mlx5e_rss_params_traffic_type rss_tt;
 
-		memset(in, 0, MLX5_ST_SZ_BYTES(create_tir_in));
-		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
+		rss_tt = mlx5e_rss_get_default_tt_config(tt);
 
-		MLX5_SET(tirc, tirc, transport_domain, hp->tdn);
-		MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
-		MLX5_SET(tirc, tirc, indirect_table, hp->indir_rqt.rqtn);
-		mlx5e_build_indir_tir_ctx_hash(&priv->rss_params, &ttconfig, tirc, false);
+		mlx5e_tir_builder_build_rqt(builder, hp->tdn,
+					    mlx5e_rqt_get_rqtn(&hp->indir_rqt),
+					    false);
+		mlx5e_tir_builder_build_rss(builder, &rss_hash, &rss_tt, false);
 
-		err = mlx5_core_create_tir(hp->func_mdev, in,
-					   &hp->indir_tirn[tt]);
+		err = mlx5e_tir_init(&hp->indir_tir[tt], builder, hp->func_mdev, false);
 		if (err) {
 			mlx5_core_warn(hp->func_mdev, "create indirect tirs failed, %d\n", err);
 			goto err_destroy_tirs;
 		}
+
+		mlx5e_tir_builder_clear(builder);
 	}
-	return 0;
 
-err_destroy_tirs:
-	for (i = 0; i < tt; i++)
-		mlx5_core_destroy_tir(hp->func_mdev, hp->indir_tirn[i]);
+out:
+	mlx5e_tir_builder_free(builder);
 	return err;
+
+err_destroy_tirs:
+	max_tt = tt;
+	for (tt = 0; tt < max_tt; tt++)
+		mlx5e_tir_destroy(&hp->indir_tir[tt]);
+
+	goto out;
 }
 
 static void mlx5e_hairpin_destroy_indirect_tirs(struct mlx5e_hairpin *hp)
@@ -609,7 +579,7 @@ static void mlx5e_hairpin_destroy_indirect_tirs(struct mlx5e_hairpin *hp)
 	int tt;
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
-		mlx5_core_destroy_tir(hp->func_mdev, hp->indir_tirn[tt]);
+		mlx5e_tir_destroy(&hp->indir_tir[tt]);
 }
 
 static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp,
@@ -620,12 +590,16 @@ static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp,
 
 	memset(ttc_params, 0, sizeof(*ttc_params));
 
-	ttc_params->any_tt_tirn = hp->tirn;
-
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
-		ttc_params->indir_tirn[tt] = hp->indir_tirn[tt];
+	ttc_params->ns = mlx5_get_flow_namespace(hp->func_mdev,
+						 MLX5_FLOW_NAMESPACE_KERNEL);
+	for (tt = 0; tt < MLX5_NUM_TT; tt++) {
+		ttc_params->dests[tt].type = MLX5_FLOW_DESTINATION_TYPE_TIR;
+		ttc_params->dests[tt].tir_num =
+			tt == MLX5_TT_ANY ?
+				mlx5e_tir_get_tirn(&hp->direct_tir) :
+				mlx5e_tir_get_tirn(&hp->indir_tir[tt]);
+	}
 
-	ft_attr->max_fte = MLX5E_TTC_TABLE_SIZE;
 	ft_attr->level = MLX5E_TC_TTC_FT_LEVEL;
 	ft_attr->prio = MLX5E_TC_PRIO;
 }
@@ -645,30 +619,31 @@ static int mlx5e_hairpin_rss_init(struct mlx5e_hairpin *hp)
 		goto err_create_indirect_tirs;
 
 	mlx5e_hairpin_set_ttc_params(hp, &ttc_params);
-	err = mlx5e_create_ttc_table(priv, &ttc_params, &hp->ttc);
-	if (err)
+	hp->ttc = mlx5_create_ttc_table(priv->mdev, &ttc_params);
+	if (IS_ERR(hp->ttc)) {
+		err = PTR_ERR(hp->ttc);
 		goto err_create_ttc_table;
+	}
 
 	netdev_dbg(priv->netdev, "add hairpin: using %d channels rss ttc table id %x\n",
-		   hp->num_channels, hp->ttc.ft.t->id);
+		   hp->num_channels,
+		   mlx5_get_ttc_flow_table(priv->fs.ttc)->id);
 
 	return 0;
 
 err_create_ttc_table:
 	mlx5e_hairpin_destroy_indirect_tirs(hp);
 err_create_indirect_tirs:
-	mlx5e_destroy_rqt(priv, &hp->indir_rqt);
+	mlx5e_rqt_destroy(&hp->indir_rqt);
 
 	return err;
 }
 
 static void mlx5e_hairpin_rss_cleanup(struct mlx5e_hairpin *hp)
 {
-	struct mlx5e_priv *priv = hp->func_priv;
-
-	mlx5e_destroy_ttc_table(priv, &hp->ttc);
+	mlx5_destroy_ttc_table(hp->ttc);
 	mlx5e_hairpin_destroy_indirect_tirs(hp);
-	mlx5e_destroy_rqt(priv, &hp->indir_rqt);
+	mlx5e_rqt_destroy(&hp->indir_rqt);
 }
 
 static struct mlx5e_hairpin *
@@ -903,16 +878,17 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 	}
 
 	netdev_dbg(priv->netdev, "add hairpin: tirn %x rqn %x peer %s sqn %x prio %d (log) data %d packets %d\n",
-		   hp->tirn, hp->pair->rqn[0],
+		   mlx5e_tir_get_tirn(&hp->direct_tir), hp->pair->rqn[0],
 		   dev_name(hp->pair->peer_mdev->device),
 		   hp->pair->sqn[0], match_prio, params.log_data_size, params.log_num_packets);
 
 attach_flow:
 	if (hpe->hp->num_channels > 1) {
 		flow_flag_set(flow, HAIRPIN_RSS);
-		flow->attr->nic_attr->hairpin_ft = hpe->hp->ttc.ft.t;
+		flow->attr->nic_attr->hairpin_ft =
+			mlx5_get_ttc_flow_table(hpe->hp->ttc);
 	} else {
-		flow->attr->nic_attr->hairpin_tirn = hpe->hp->tirn;
+		flow->attr->nic_attr->hairpin_tirn = mlx5e_tir_get_tirn(&hpe->hp->direct_tir);
 	}
 
 	flow->hpe = hpe;
@@ -1056,15 +1032,17 @@ err_ft_get:
 
 static int
 mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
-		      struct mlx5e_tc_flow_parse_attr *parse_attr,
 		      struct mlx5e_tc_flow *flow,
 		      struct netlink_ext_ack *extack)
 {
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5_flow_attr *attr = flow->attr;
 	struct mlx5_core_dev *dev = priv->mdev;
-	struct mlx5_fc *counter = NULL;
+	struct mlx5_fc *counter;
 	int err;
 
+	parse_attr = attr->parse_attr;
+
 	if (flow_flag_test(flow, HAIRPIN)) {
 		err = mlx5e_hairpin_flow_add(priv, flow, parse_attr, extack);
 		if (err)
@@ -1170,7 +1148,8 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
 					       mod_hdr_acts);
 #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE)
 	} else if (flow_flag_test(flow, SAMPLE)) {
-		rule = mlx5_esw_sample_offload(get_sample_priv(flow->priv), spec, attr);
+		rule = mlx5e_tc_sample_offload(get_sample_priv(flow->priv), spec, attr,
+					       mlx5e_tc_get_flow_tun_id(flow));
 #endif
 	} else {
 		rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
@@ -1209,7 +1188,7 @@ void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw,
 
 #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE)
 	if (flow_flag_test(flow, SAMPLE)) {
-		mlx5_esw_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr);
+		mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr);
 		return;
 	}
 #endif
@@ -1338,6 +1317,7 @@ bool mlx5e_tc_is_vf_tunnel(struct net_device *out_dev, struct net_device *route_
 int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *route_dev, u16 *vport)
 {
 	struct mlx5e_priv *out_priv, *route_priv;
+	struct mlx5_devcom *devcom = NULL;
 	struct mlx5_core_dev *route_mdev;
 	struct mlx5_eswitch *esw;
 	u16 vhca_id;
@@ -1349,7 +1329,24 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro
 	route_mdev = route_priv->mdev;
 
 	vhca_id = MLX5_CAP_GEN(route_mdev, vhca_id);
+	if (mlx5_lag_is_active(out_priv->mdev)) {
+		/* In lag case we may get devices from different eswitch instances.
+		 * If we failed to get vport num, it means, mostly, that we on the wrong
+		 * eswitch.
+		 */
+		err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport);
+		if (err != -ENOENT)
+			return err;
+
+		devcom = out_priv->mdev->priv.devcom;
+		esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+		if (!esw)
+			return -ENODEV;
+	}
+
 	err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport);
+	if (devcom)
+		mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
 	return err;
 }
 
@@ -1384,9 +1381,9 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	bool vf_tun = false, encap_valid = true;
 	struct net_device *encap_dev = NULL;
 	struct mlx5_esw_flow_attr *esw_attr;
-	struct mlx5_fc *counter = NULL;
 	struct mlx5e_rep_priv *rpriv;
 	struct mlx5e_priv *out_priv;
+	struct mlx5_fc *counter;
 	u32 max_prio, max_chain;
 	int err = 0;
 	int out_index;
@@ -1573,6 +1570,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 		else
 			mlx5e_detach_mod_hdr(priv, flow);
 	}
+	kfree(attr->sample_attr);
 	kvfree(attr->parse_attr);
 	kvfree(attr->esw_attr->rx_tun_attr);
 
@@ -1582,7 +1580,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	if (flow_flag_test(flow, L3_TO_L2_DECAP))
 		mlx5e_detach_decap(priv, flow);
 
-	kfree(flow->attr->esw_attr->sample);
 	kfree(flow->attr);
 }
 
@@ -1647,17 +1644,22 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 	}
 }
 
-static int flow_has_tc_fwd_action(struct flow_cls_offload *f)
+static bool flow_requires_tunnel_mapping(u32 chain, struct flow_cls_offload *f)
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_action *flow_action = &rule->action;
 	const struct flow_action_entry *act;
 	int i;
 
+	if (chain)
+		return false;
+
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {
 		case FLOW_ACTION_GOTO:
 			return true;
+		case FLOW_ACTION_SAMPLE:
+			return true;
 		default:
 			continue;
 		}
@@ -1898,7 +1900,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 
 	needs_mapping = !!flow->attr->chain;
-	sets_mapping = !flow->attr->chain && flow_has_tc_fwd_action(f);
+	sets_mapping = flow_requires_tunnel_mapping(flow->attr->chain, f);
 	*match_inner = !needs_mapping;
 
 	if ((needs_mapping || sets_mapping) &&
@@ -2471,7 +2473,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_3;
 		}
 	}
-	/* Currenlty supported only for MPLS over UDP */
+	/* Currently supported only for MPLS over UDP */
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS) &&
 	    !netif_is_bareudp(filter_dev)) {
 		NL_SET_ERR_MSG_MOD(extack,
@@ -2725,7 +2727,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		if (s_mask && a_mask) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "can't set and add to the same HW field");
-			printk(KERN_WARNING "mlx5: can't set and add to the same HW field (%x)\n", f->field);
+			netdev_warn(priv->netdev,
+				    "mlx5: can't set and add to the same HW field (%x)\n",
+				    f->field);
 			return -EOPNOTSUPP;
 		}
 
@@ -2764,8 +2768,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		if (first < next_z && next_z < last) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "rewrite of few sub-fields isn't supported");
-			printk(KERN_WARNING "mlx5: rewrite of few sub-fields (mask %lx) isn't offloaded\n",
-			       mask);
+			netdev_warn(priv->netdev,
+				    "mlx5: rewrite of few sub-fields (mask %lx) isn't offloaded\n",
+				    mask);
 			return -EOPNOTSUPP;
 		}
 
@@ -3352,10 +3357,10 @@ static int validate_goto_chain(struct mlx5e_priv *priv,
 
 static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 				struct flow_action *flow_action,
-				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow,
 				struct netlink_ext_ack *extack)
 {
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5_flow_attr *attr = flow->attr;
 	struct pedit_headers_action hdrs[2] = {};
 	const struct flow_action_entry *act;
@@ -3371,8 +3376,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 
 	nic_attr = attr->nic_attr;
-
 	nic_attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
+	parse_attr = attr->parse_attr;
 
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {
@@ -3381,10 +3386,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 				  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 			break;
 		case FLOW_ACTION_DROP:
-			action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
-			if (MLX5_CAP_FLOWTABLE(priv->mdev,
-					       flow_table_properties_nic_receive.flow_counter))
-				action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+			action |= MLX5_FLOW_CONTEXT_ACTION_DROP |
+				  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 			break;
 		case FLOW_ACTION_MANGLE:
 		case FLOW_ACTION_ADD:
@@ -3425,7 +3428,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 						   "device is not on same HW, can't offload");
 				netdev_warn(priv->netdev, "device %s not on same HW, can't offload\n",
 					    peer_dev->name);
-				return -EINVAL;
+				return -EOPNOTSUPP;
 			}
 			}
 			break;
@@ -3435,7 +3438,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 			if (mark & ~MLX5E_TC_FLOW_ID_MASK) {
 				NL_SET_ERR_MSG_MOD(extack,
 						   "Bad flow mark - only 16 bit is supported");
-				return -EINVAL;
+				return -EOPNOTSUPP;
 			}
 
 			nic_attr->flow_tag = mark;
@@ -3732,20 +3735,19 @@ static int verify_uplink_forwarding(struct mlx5e_priv *priv,
 static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 				struct flow_action *flow_action,
 				struct mlx5e_tc_flow *flow,
-				struct netlink_ext_ack *extack,
-				struct net_device *filter_dev)
+				struct netlink_ext_ack *extack)
 {
 	struct pedit_headers_action hdrs[2] = {};
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5e_sample_attr sample_attr = {};
 	const struct ip_tunnel_info *info = NULL;
 	struct mlx5_flow_attr *attr = flow->attr;
 	int ifindexes[MLX5_MAX_FLOW_FWD_VPORTS];
 	bool ft_flow = mlx5e_is_ft_flow(flow);
 	const struct flow_action_entry *act;
 	struct mlx5_esw_flow_attr *esw_attr;
-	struct mlx5_sample_attr sample = {};
 	bool encap = false, decap = false;
 	u32 action = attr->action;
 	int err, i, if_count = 0;
@@ -3798,7 +3800,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 						   "mpls pop supported only as first action");
 				return -EOPNOTSUPP;
 			}
-			if (!netif_is_bareudp(filter_dev)) {
+			if (!netif_is_bareudp(parse_attr->filter_dev)) {
 				NL_SET_ERR_MSG_MOD(extack,
 						   "mpls pop supported only on bareudp devices");
 				return -EOPNOTSUPP;
@@ -3947,7 +3949,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 					    "devices %s %s not on same switch HW, can't offload forwarding\n",
 					    priv->netdev->name,
 					    out_dev->name);
-				return -EINVAL;
+				return -EOPNOTSUPP;
 			}
 			}
 			break;
@@ -4016,10 +4018,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 				NL_SET_ERR_MSG_MOD(extack, "Sample action with connection tracking is not supported");
 				return -EOPNOTSUPP;
 			}
-			sample.rate = act->sample.rate;
-			sample.group_num = act->sample.psample_group->group_num;
+			sample_attr.rate = act->sample.rate;
+			sample_attr.group_num = act->sample.psample_group->group_num;
 			if (act->sample.truncate)
-				sample.trunc_size = act->sample.trunc_size;
+				sample_attr.trunc_size = act->sample.trunc_size;
 			flow_flag_set(flow, SAMPLE);
 			break;
 		default:
@@ -4104,10 +4106,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 	 * no errors after parsing.
 	 */
 	if (flow_flag_test(flow, SAMPLE)) {
-		esw_attr->sample = kzalloc(sizeof(*esw_attr->sample), GFP_KERNEL);
-		if (!esw_attr->sample)
+		attr->sample_attr = kzalloc(sizeof(*attr->sample_attr), GFP_KERNEL);
+		if (!attr->sample_attr)
 			return -ENOMEM;
-		*esw_attr->sample = sample;
+		*attr->sample_attr = sample_attr;
 	}
 
 	return 0;
@@ -4300,7 +4302,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto err_free;
 
-	err = parse_tc_fdb_actions(priv, &rule->action, flow, extack, filter_dev);
+	err = parse_tc_fdb_actions(priv, &rule->action, flow, extack);
 	if (err)
 		goto err_free;
 
@@ -4446,11 +4448,11 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto err_free;
 
-	err = parse_tc_nic_actions(priv, &rule->action, parse_attr, flow, extack);
+	err = parse_tc_nic_actions(priv, &rule->action, flow, extack);
 	if (err)
 		goto err_free;
 
-	err = mlx5e_tc_add_nic_flow(priv, parse_attr, flow, extack);
+	err = mlx5e_tc_add_nic_flow(priv, flow, extack);
 	if (err)
 		goto err_free;
 
@@ -4705,7 +4707,7 @@ static int apply_police_params(struct mlx5e_priv *priv, u64 rate,
 		rate_mbps = max_t(u32, rate, 1);
 	}
 
-	err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps);
+	err = mlx5_esw_qos_modify_vport_rate(esw, vport_num, rate_mbps);
 	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware");
 
@@ -4877,6 +4879,7 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *dev = priv->mdev;
 	struct mapping_ctx *chains_mapping;
 	struct mlx5_chains_attr attr = {};
+	u64 mapping_id;
 	int err;
 
 	mlx5e_mod_hdr_tbl_init(&tc->mod_hdr);
@@ -4890,8 +4893,12 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 
 	lockdep_set_class(&tc->ht.mutex, &tc_ht_lock_key);
 
-	chains_mapping = mapping_create(sizeof(struct mlx5_mapped_obj),
-					MLX5E_TC_TABLE_CHAIN_TAG_MASK, true);
+	mapping_id = mlx5_query_nic_system_image_guid(dev);
+
+	chains_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_CHAIN,
+					       sizeof(struct mlx5_mapped_obj),
+					       MLX5E_TC_TABLE_CHAIN_TAG_MASK, true);
+
 	if (IS_ERR(chains_mapping)) {
 		err = PTR_ERR(chains_mapping);
 		goto err_mapping;
@@ -4913,8 +4920,9 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 		goto err_chains;
 	}
 
+	tc->post_act = mlx5e_tc_post_act_init(priv, tc->chains, MLX5_FLOW_NAMESPACE_KERNEL);
 	tc->ct = mlx5_tc_ct_init(priv, tc->chains, &priv->fs.tc.mod_hdr,
-				 MLX5_FLOW_NAMESPACE_KERNEL);
+				 MLX5_FLOW_NAMESPACE_KERNEL, tc->post_act);
 
 	tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event;
 	err = register_netdevice_notifier_dev_net(priv->netdev,
@@ -4930,6 +4938,7 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 
 err_reg:
 	mlx5_tc_ct_clean(tc->ct);
+	mlx5e_tc_post_act_destroy(tc->post_act);
 	mlx5_chains_destroy(tc->chains);
 err_chains:
 	mapping_destroy(chains_mapping);
@@ -4968,6 +4977,7 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv)
 	mutex_destroy(&tc->t_lock);
 
 	mlx5_tc_ct_clean(tc->ct);
+	mlx5e_tc_post_act_destroy(tc->post_act);
 	mapping_destroy(tc->mapping);
 	mlx5_chains_destroy(tc->chains);
 }
@@ -4980,6 +4990,7 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht)
 	struct mapping_ctx *mapping;
 	struct mlx5_eswitch *esw;
 	struct mlx5e_priv *priv;
+	u64 mapping_id;
 	int err = 0;
 
 	uplink_priv = container_of(tc_ht, struct mlx5_rep_uplink_priv, tc_ht);
@@ -4987,17 +4998,24 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht)
 	priv = netdev_priv(rpriv->netdev);
 	esw = priv->mdev->priv.eswitch;
 
+	uplink_priv->post_act = mlx5e_tc_post_act_init(priv, esw_chains(esw),
+						       MLX5_FLOW_NAMESPACE_FDB);
 	uplink_priv->ct_priv = mlx5_tc_ct_init(netdev_priv(priv->netdev),
 					       esw_chains(esw),
 					       &esw->offloads.mod_hdr,
-					       MLX5_FLOW_NAMESPACE_FDB);
+					       MLX5_FLOW_NAMESPACE_FDB,
+					       uplink_priv->post_act);
 
 #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE)
-	uplink_priv->esw_psample = mlx5_esw_sample_init(netdev_priv(priv->netdev));
+	uplink_priv->tc_psample = mlx5e_tc_sample_init(esw, uplink_priv->post_act);
 #endif
 
-	mapping = mapping_create(sizeof(struct tunnel_match_key),
-				 TUNNEL_INFO_BITS_MASK, true);
+	mapping_id = mlx5_query_nic_system_image_guid(esw->dev);
+
+	mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_TUNNEL,
+					sizeof(struct tunnel_match_key),
+					TUNNEL_INFO_BITS_MASK, true);
+
 	if (IS_ERR(mapping)) {
 		err = PTR_ERR(mapping);
 		goto err_tun_mapping;
@@ -5005,7 +5023,8 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht)
 	uplink_priv->tunnel_mapping = mapping;
 
 	/* 0xFFF is reserved for stack devices slow path table mark */
-	mapping = mapping_create(sz_enc_opts, ENC_OPTS_BITS_MASK - 1, true);
+	mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_TUNNEL_ENC_OPTS,
+					sz_enc_opts, ENC_OPTS_BITS_MASK - 1, true);
 	if (IS_ERR(mapping)) {
 		err = PTR_ERR(mapping);
 		goto err_enc_opts_mapping;
@@ -5034,11 +5053,12 @@ err_enc_opts_mapping:
 	mapping_destroy(uplink_priv->tunnel_mapping);
 err_tun_mapping:
 #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE)
-	mlx5_esw_sample_cleanup(uplink_priv->esw_psample);
+	mlx5e_tc_sample_cleanup(uplink_priv->tc_psample);
 #endif
 	mlx5_tc_ct_clean(uplink_priv->ct_priv);
 	netdev_warn(priv->netdev,
 		    "Failed to initialize tc (eswitch), err: %d", err);
+	mlx5e_tc_post_act_destroy(uplink_priv->post_act);
 	return err;
 }
 
@@ -5055,9 +5075,10 @@ void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht)
 	mapping_destroy(uplink_priv->tunnel_mapping);
 
 #if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE)
-	mlx5_esw_sample_cleanup(uplink_priv->esw_psample);
+	mlx5e_tc_sample_cleanup(uplink_priv->tc_psample);
 #endif
 	mlx5_tc_ct_clean(uplink_priv->ct_priv);
+	mlx5e_tc_post_act_destroy(uplink_priv->post_act);
 }
 
 int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index f7cbeb0b66d2..1a4cd882f0fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -70,6 +70,7 @@ struct mlx5_flow_attr {
 	struct mlx5_fc *counter;
 	struct mlx5_modify_hdr *modify_hdr;
 	struct mlx5_ct_attr ct_attr;
+	struct mlx5e_sample_attr *sample_attr;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	u32 chain;
 	u16 prio;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
index 505bf811984a..2e504c7461c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
@@ -15,6 +15,15 @@ static void esw_acl_egress_ofld_fwd2vport_destroy(struct mlx5_vport *vport)
 	vport->egress.offloads.fwd_rule = NULL;
 }
 
+static void esw_acl_egress_ofld_bounce_rule_destroy(struct mlx5_vport *vport)
+{
+	if (!vport->egress.offloads.bounce_rule)
+		return;
+
+	mlx5_del_flow_rules(vport->egress.offloads.bounce_rule);
+	vport->egress.offloads.bounce_rule = NULL;
+}
+
 static int esw_acl_egress_ofld_fwd2vport_create(struct mlx5_eswitch *esw,
 						struct mlx5_vport *vport,
 						struct mlx5_flow_destination *fwd_dest)
@@ -87,6 +96,7 @@ static void esw_acl_egress_ofld_rules_destroy(struct mlx5_vport *vport)
 {
 	esw_acl_egress_vlan_destroy(vport);
 	esw_acl_egress_ofld_fwd2vport_destroy(vport);
+	esw_acl_egress_ofld_bounce_rule_destroy(vport);
 }
 
 static int esw_acl_egress_ofld_groups_create(struct mlx5_eswitch *esw,
@@ -145,6 +155,12 @@ static void esw_acl_egress_ofld_groups_destroy(struct mlx5_vport *vport)
 		mlx5_destroy_flow_group(vport->egress.offloads.fwd_grp);
 		vport->egress.offloads.fwd_grp = NULL;
 	}
+
+	if (!IS_ERR_OR_NULL(vport->egress.offloads.bounce_grp)) {
+		mlx5_destroy_flow_group(vport->egress.offloads.bounce_grp);
+		vport->egress.offloads.bounce_grp = NULL;
+	}
+
 	esw_acl_egress_vlan_grp_destroy(vport);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index 69a3630818d7..7e221038df8d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -5,6 +5,7 @@
 #include <linux/notifier.h>
 #include <net/netevent.h>
 #include <net/switchdev.h>
+#include "lib/devcom.h"
 #include "bridge.h"
 #include "eswitch.h"
 #include "bridge_priv.h"
@@ -56,7 +57,6 @@ struct mlx5_esw_bridge {
 
 	struct list_head fdb_list;
 	struct rhashtable fdb_ht;
-	struct xarray vports;
 
 	struct mlx5_flow_table *egress_ft;
 	struct mlx5_flow_group *egress_vlan_fg;
@@ -77,6 +77,15 @@ mlx5_esw_bridge_fdb_offload_notify(struct net_device *dev, const unsigned char *
 	call_switchdev_notifiers(val, dev, &send_info.info, NULL);
 }
 
+static void
+mlx5_esw_bridge_fdb_del_notify(struct mlx5_esw_bridge_fdb_entry *entry)
+{
+	if (!(entry->flags & (MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER | MLX5_ESW_BRIDGE_FLAG_PEER)))
+		mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
+						   entry->key.vid,
+						   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+}
+
 static struct mlx5_flow_table *
 mlx5_esw_bridge_table_create(int max_fte, u32 level, struct mlx5_eswitch *esw)
 {
@@ -400,9 +409,10 @@ mlx5_esw_bridge_egress_table_cleanup(struct mlx5_esw_bridge *bridge)
 }
 
 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 *bridge)
+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 *bridge,
+					     struct mlx5_eswitch *esw)
 {
 	struct mlx5_esw_bridge_offloads *br_offloads = bridge->br_offloads;
 	struct mlx5_flow_act flow_act = {
@@ -430,7 +440,7 @@ mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr,
 	MLX5_SET(fte_match_param, rule_spec->match_criteria,
 		 misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask());
 	MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_0,
-		 mlx5_eswitch_get_vport_metadata_for_match(br_offloads->esw, vport_num));
+		 mlx5_eswitch_get_vport_metadata_for_match(esw, vport_num));
 
 	if (vlan && vlan->pkt_reformat_push) {
 		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
@@ -459,6 +469,35 @@ mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr,
 }
 
 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 *bridge)
+{
+	return mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id,
+							    bridge, bridge->br_offloads->esw);
+}
+
+static struct mlx5_flow_handle *
+mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, const unsigned char *addr,
+					 struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
+					 struct mlx5_esw_bridge *bridge)
+{
+	struct mlx5_devcom *devcom = bridge->br_offloads->esw->dev->priv.devcom;
+	static struct mlx5_flow_handle *handle;
+	struct mlx5_eswitch *peer_esw;
+
+	peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	if (!peer_esw)
+		return ERR_PTR(-ENODEV);
+
+	handle = mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id,
+							      bridge, peer_esw);
+
+	mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	return handle;
+}
+
+static struct mlx5_flow_handle *
 mlx5_esw_bridge_ingress_filter_flow_create(u16 vport_num, const unsigned char *addr,
 					   struct mlx5_esw_bridge *bridge)
 {
@@ -505,7 +544,7 @@ mlx5_esw_bridge_ingress_filter_flow_create(u16 vport_num, const unsigned char *a
 }
 
 static struct mlx5_flow_handle *
-mlx5_esw_bridge_egress_flow_create(u16 vport_num, const unsigned char *addr,
+mlx5_esw_bridge_egress_flow_create(u16 vport_num, u16 esw_owner_vhca_id, const unsigned char *addr,
 				   struct mlx5_esw_bridge_vlan *vlan,
 				   struct mlx5_esw_bridge *bridge)
 {
@@ -550,6 +589,10 @@ mlx5_esw_bridge_egress_flow_create(u16 vport_num, const unsigned char *addr,
 			 vlan->vid);
 	}
 
+	if (MLX5_CAP_ESW(bridge->br_offloads->esw->dev, merged_eswitch)) {
+		dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID;
+		dest.vport.vhca_id = esw_owner_vhca_id;
+	}
 	handle = mlx5_add_flow_rules(bridge->egress_ft, rule_spec, &flow_act, &dest, 1);
 
 	kvfree(rule_spec);
@@ -576,7 +619,6 @@ static struct mlx5_esw_bridge *mlx5_esw_bridge_create(int ifindex,
 		goto err_fdb_ht;
 
 	INIT_LIST_HEAD(&bridge->fdb_list);
-	xa_init(&bridge->vports);
 	bridge->ifindex = ifindex;
 	bridge->refcnt = 1;
 	bridge->ageing_time = clock_t_to_jiffies(BR_DEFAULT_AGEING_TIME);
@@ -603,7 +645,6 @@ static void mlx5_esw_bridge_put(struct mlx5_esw_bridge_offloads *br_offloads,
 		return;
 
 	mlx5_esw_bridge_egress_table_cleanup(bridge);
-	WARN_ON(!xa_empty(&bridge->vports));
 	list_del(&bridge->list);
 	rhashtable_destroy(&bridge->fdb_ht);
 	kvfree(bridge);
@@ -639,30 +680,40 @@ mlx5_esw_bridge_lookup(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads
 	return bridge;
 }
 
+static unsigned long mlx5_esw_bridge_port_key_from_data(u16 vport_num, u16 esw_owner_vhca_id)
+{
+	return vport_num | (unsigned long)esw_owner_vhca_id << sizeof(vport_num) * BITS_PER_BYTE;
+}
+
+static unsigned long mlx5_esw_bridge_port_key(struct mlx5_esw_bridge_port *port)
+{
+	return mlx5_esw_bridge_port_key_from_data(port->vport_num, port->esw_owner_vhca_id);
+}
+
 static int mlx5_esw_bridge_port_insert(struct mlx5_esw_bridge_port *port,
-				       struct mlx5_esw_bridge *bridge)
+				       struct mlx5_esw_bridge_offloads *br_offloads)
 {
-	return xa_insert(&bridge->vports, port->vport_num, port, GFP_KERNEL);
+	return xa_insert(&br_offloads->ports, mlx5_esw_bridge_port_key(port), port, GFP_KERNEL);
 }
 
 static struct mlx5_esw_bridge_port *
-mlx5_esw_bridge_port_lookup(u16 vport_num, struct mlx5_esw_bridge *bridge)
+mlx5_esw_bridge_port_lookup(u16 vport_num, u16 esw_owner_vhca_id,
+			    struct mlx5_esw_bridge_offloads *br_offloads)
 {
-	return xa_load(&bridge->vports, vport_num);
+	return xa_load(&br_offloads->ports, mlx5_esw_bridge_port_key_from_data(vport_num,
+									       esw_owner_vhca_id));
 }
 
 static void mlx5_esw_bridge_port_erase(struct mlx5_esw_bridge_port *port,
-				       struct mlx5_esw_bridge *bridge)
+				       struct mlx5_esw_bridge_offloads *br_offloads)
 {
-	xa_erase(&bridge->vports, port->vport_num);
+	xa_erase(&br_offloads->ports, mlx5_esw_bridge_port_key(port));
 }
 
-static void mlx5_esw_bridge_fdb_entry_refresh(unsigned long lastuse,
-					      struct mlx5_esw_bridge_fdb_entry *entry)
+static void mlx5_esw_bridge_fdb_entry_refresh(struct mlx5_esw_bridge_fdb_entry *entry)
 {
 	trace_mlx5_esw_bridge_fdb_entry_refresh(entry);
 
-	entry->lastuse = lastuse;
 	mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
 					   entry->key.vid,
 					   SWITCHDEV_FDB_ADD_TO_BRIDGE);
@@ -690,10 +741,7 @@ static void mlx5_esw_bridge_fdb_flush(struct mlx5_esw_bridge *bridge)
 	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
 
 	list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) {
-		if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER))
-			mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
-							   entry->key.vid,
-							   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+		mlx5_esw_bridge_fdb_del_notify(entry);
 		mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
 	}
 }
@@ -841,10 +889,7 @@ static void mlx5_esw_bridge_vlan_flush(struct mlx5_esw_bridge_vlan *vlan,
 	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
 
 	list_for_each_entry_safe(entry, tmp, &vlan->fdb_list, vlan_list) {
-		if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER))
-			mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
-							   entry->key.vid,
-							   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+		mlx5_esw_bridge_fdb_del_notify(entry);
 		mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
 	}
 
@@ -875,13 +920,13 @@ static void mlx5_esw_bridge_port_vlans_flush(struct mlx5_esw_bridge_port *port,
 }
 
 static struct mlx5_esw_bridge_vlan *
-mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, struct mlx5_esw_bridge *bridge,
-				 struct mlx5_eswitch *esw)
+mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, u16 esw_owner_vhca_id,
+				 struct mlx5_esw_bridge *bridge, struct mlx5_eswitch *esw)
 {
 	struct mlx5_esw_bridge_port *port;
 	struct mlx5_esw_bridge_vlan *vlan;
 
-	port = mlx5_esw_bridge_port_lookup(vport_num, bridge);
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, bridge->br_offloads);
 	if (!port) {
 		/* FDB is added asynchronously on wq while port might have been deleted
 		 * concurrently. Report on 'info' logging level and skip the FDB offload.
@@ -904,24 +949,23 @@ mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, struct mlx5_esw_bridge
 }
 
 static struct mlx5_esw_bridge_fdb_entry *
-mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, const unsigned char *addr,
-			       u16 vid, bool added_by_user, struct mlx5_eswitch *esw,
-			       struct mlx5_esw_bridge *bridge)
+mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+			       const unsigned char *addr, u16 vid, bool added_by_user, bool peer,
+			       struct mlx5_eswitch *esw, struct mlx5_esw_bridge *bridge)
 {
 	struct mlx5_esw_bridge_vlan *vlan = NULL;
 	struct mlx5_esw_bridge_fdb_entry *entry;
 	struct mlx5_flow_handle *handle;
 	struct mlx5_fc *counter;
-	struct mlx5e_priv *priv;
 	int err;
 
 	if (bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG && vid) {
-		vlan = mlx5_esw_bridge_port_vlan_lookup(vid, vport_num, bridge, esw);
+		vlan = mlx5_esw_bridge_port_vlan_lookup(vid, vport_num, esw_owner_vhca_id, bridge,
+							esw);
 		if (IS_ERR(vlan))
 			return ERR_CAST(vlan);
 	}
 
-	priv = netdev_priv(dev);
 	entry = kvzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
 		return ERR_PTR(-ENOMEM);
@@ -930,19 +974,25 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, const unsi
 	entry->key.vid = vid;
 	entry->dev = dev;
 	entry->vport_num = vport_num;
+	entry->esw_owner_vhca_id = esw_owner_vhca_id;
 	entry->lastuse = jiffies;
 	if (added_by_user)
 		entry->flags |= MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER;
+	if (peer)
+		entry->flags |= MLX5_ESW_BRIDGE_FLAG_PEER;
 
-	counter = mlx5_fc_create(priv->mdev, true);
+	counter = mlx5_fc_create(esw->dev, true);
 	if (IS_ERR(counter)) {
 		err = PTR_ERR(counter);
 		goto err_ingress_fc_create;
 	}
 	entry->ingress_counter = counter;
 
-	handle = mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan, mlx5_fc_id(counter),
-						     bridge);
+	handle = peer ?
+		mlx5_esw_bridge_ingress_flow_peer_create(vport_num, addr, vlan,
+							 mlx5_fc_id(counter), bridge) :
+		mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan,
+						    mlx5_fc_id(counter), bridge);
 	if (IS_ERR(handle)) {
 		err = PTR_ERR(handle);
 		esw_warn(esw->dev, "Failed to create ingress flow(vport=%u,err=%d)\n",
@@ -962,7 +1012,8 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, const unsi
 		entry->filter_handle = handle;
 	}
 
-	handle = mlx5_esw_bridge_egress_flow_create(vport_num, addr, vlan, bridge);
+	handle = mlx5_esw_bridge_egress_flow_create(vport_num, esw_owner_vhca_id, addr, vlan,
+						    bridge);
 	if (IS_ERR(handle)) {
 		err = PTR_ERR(handle);
 		esw_warn(esw->dev, "Failed to create egress flow(vport=%u,err=%d)\n",
@@ -994,32 +1045,37 @@ err_egress_flow_create:
 err_ingress_filter_flow_create:
 	mlx5_del_flow_rules(entry->ingress_handle);
 err_ingress_flow_create:
-	mlx5_fc_destroy(priv->mdev, entry->ingress_counter);
+	mlx5_fc_destroy(esw->dev, entry->ingress_counter);
 err_ingress_fc_create:
 	kvfree(entry);
 	return ERR_PTR(err);
 }
 
-int mlx5_esw_bridge_ageing_time_set(unsigned long ageing_time, struct mlx5_eswitch *esw,
-				    struct mlx5_vport *vport)
+int mlx5_esw_bridge_ageing_time_set(u16 vport_num, u16 esw_owner_vhca_id, unsigned long ageing_time,
+				    struct mlx5_esw_bridge_offloads *br_offloads)
 {
-	if (!vport->bridge)
+	struct mlx5_esw_bridge_port *port;
+
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port)
 		return -EINVAL;
 
-	vport->bridge->ageing_time = clock_t_to_jiffies(ageing_time);
+	port->bridge->ageing_time = clock_t_to_jiffies(ageing_time);
 	return 0;
 }
 
-int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw,
-				       struct mlx5_vport *vport)
+int mlx5_esw_bridge_vlan_filtering_set(u16 vport_num, u16 esw_owner_vhca_id, bool enable,
+				       struct mlx5_esw_bridge_offloads *br_offloads)
 {
+	struct mlx5_esw_bridge_port *port;
 	struct mlx5_esw_bridge *bridge;
 	bool filtering;
 
-	if (!vport->bridge)
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port)
 		return -EINVAL;
 
-	bridge = vport->bridge;
+	bridge = port->bridge;
 	filtering = bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG;
 	if (filtering == enable)
 		return 0;
@@ -1033,114 +1089,143 @@ int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw,
 	return 0;
 }
 
-static int mlx5_esw_bridge_vport_init(struct mlx5_esw_bridge_offloads *br_offloads,
-				      struct mlx5_esw_bridge *bridge,
-				      struct mlx5_vport *vport)
+static int mlx5_esw_bridge_vport_init(u16 vport_num, u16 esw_owner_vhca_id, u16 flags,
+				      struct mlx5_esw_bridge_offloads *br_offloads,
+				      struct mlx5_esw_bridge *bridge)
 {
 	struct mlx5_eswitch *esw = br_offloads->esw;
 	struct mlx5_esw_bridge_port *port;
 	int err;
 
 	port = kvzalloc(sizeof(*port), GFP_KERNEL);
-	if (!port) {
-		err = -ENOMEM;
-		goto err_port_alloc;
-	}
+	if (!port)
+		return -ENOMEM;
 
-	port->vport_num = vport->vport;
+	port->vport_num = vport_num;
+	port->esw_owner_vhca_id = esw_owner_vhca_id;
+	port->bridge = bridge;
+	port->flags |= flags;
 	xa_init(&port->vlans);
-	err = mlx5_esw_bridge_port_insert(port, bridge);
+	err = mlx5_esw_bridge_port_insert(port, br_offloads);
 	if (err) {
-		esw_warn(esw->dev, "Failed to insert port metadata (vport=%u,err=%d)\n",
-			 vport->vport, err);
+		esw_warn(esw->dev,
+			 "Failed to insert port metadata (vport=%u,esw_owner_vhca_id=%u,err=%d)\n",
+			 port->vport_num, port->esw_owner_vhca_id, err);
 		goto err_port_insert;
 	}
 	trace_mlx5_esw_bridge_vport_init(port);
 
-	vport->bridge = bridge;
 	return 0;
 
 err_port_insert:
 	kvfree(port);
-err_port_alloc:
-	mlx5_esw_bridge_put(br_offloads, bridge);
 	return err;
 }
 
 static int mlx5_esw_bridge_vport_cleanup(struct mlx5_esw_bridge_offloads *br_offloads,
-					 struct mlx5_vport *vport)
+					 struct mlx5_esw_bridge_port *port)
 {
-	struct mlx5_esw_bridge *bridge = vport->bridge;
+	u16 vport_num = port->vport_num, esw_owner_vhca_id = port->esw_owner_vhca_id;
+	struct mlx5_esw_bridge *bridge = port->bridge;
 	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
-	struct mlx5_esw_bridge_port *port;
 
 	list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list)
-		if (entry->vport_num == vport->vport)
+		if (entry->vport_num == vport_num && entry->esw_owner_vhca_id == esw_owner_vhca_id)
 			mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
 
-	port = mlx5_esw_bridge_port_lookup(vport->vport, bridge);
-	if (!port) {
-		WARN(1, "Vport %u metadata not found on bridge", vport->vport);
-		return -EINVAL;
-	}
-
 	trace_mlx5_esw_bridge_vport_cleanup(port);
 	mlx5_esw_bridge_port_vlans_flush(port, bridge);
-	mlx5_esw_bridge_port_erase(port, bridge);
+	mlx5_esw_bridge_port_erase(port, br_offloads);
 	kvfree(port);
 	mlx5_esw_bridge_put(br_offloads, bridge);
-	vport->bridge = NULL;
 	return 0;
 }
 
-int mlx5_esw_bridge_vport_link(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads,
-			       struct mlx5_vport *vport, struct netlink_ext_ack *extack)
+static int mlx5_esw_bridge_vport_link_with_flags(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+						 u16 flags,
+						 struct mlx5_esw_bridge_offloads *br_offloads,
+						 struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_bridge *bridge;
 	int err;
 
-	WARN_ON(vport->bridge);
-
 	bridge = mlx5_esw_bridge_lookup(ifindex, br_offloads);
 	if (IS_ERR(bridge)) {
 		NL_SET_ERR_MSG_MOD(extack, "Error checking for existing bridge with same ifindex");
 		return PTR_ERR(bridge);
 	}
 
-	err = mlx5_esw_bridge_vport_init(br_offloads, bridge, vport);
-	if (err)
+	err = mlx5_esw_bridge_vport_init(vport_num, esw_owner_vhca_id, flags, br_offloads, bridge);
+	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Error initializing port");
+		goto err_vport;
+	}
+	return 0;
+
+err_vport:
+	mlx5_esw_bridge_put(br_offloads, bridge);
 	return err;
 }
 
-int mlx5_esw_bridge_vport_unlink(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads,
-				 struct mlx5_vport *vport, struct netlink_ext_ack *extack)
+int mlx5_esw_bridge_vport_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+			       struct mlx5_esw_bridge_offloads *br_offloads,
+			       struct netlink_ext_ack *extack)
 {
-	struct mlx5_esw_bridge *bridge = vport->bridge;
+	return mlx5_esw_bridge_vport_link_with_flags(ifindex, vport_num, esw_owner_vhca_id, 0,
+						     br_offloads, extack);
+}
+
+int mlx5_esw_bridge_vport_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+				 struct mlx5_esw_bridge_offloads *br_offloads,
+				 struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_bridge_port *port;
 	int err;
 
-	if (!bridge) {
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port) {
 		NL_SET_ERR_MSG_MOD(extack, "Port is not attached to any bridge");
 		return -EINVAL;
 	}
-	if (bridge->ifindex != ifindex) {
+	if (port->bridge->ifindex != ifindex) {
 		NL_SET_ERR_MSG_MOD(extack, "Port is attached to another bridge");
 		return -EINVAL;
 	}
 
-	err = mlx5_esw_bridge_vport_cleanup(br_offloads, vport);
+	err = mlx5_esw_bridge_vport_cleanup(br_offloads, port);
 	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "Port cleanup failed");
 	return err;
 }
 
-int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw,
-				  struct mlx5_vport *vport, struct netlink_ext_ack *extack)
+int mlx5_esw_bridge_vport_peer_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+				    struct mlx5_esw_bridge_offloads *br_offloads,
+				    struct netlink_ext_ack *extack)
+{
+	if (!MLX5_CAP_ESW(br_offloads->esw->dev, merged_eswitch))
+		return 0;
+
+	return mlx5_esw_bridge_vport_link_with_flags(ifindex, vport_num, esw_owner_vhca_id,
+						     MLX5_ESW_BRIDGE_PORT_FLAG_PEER,
+						     br_offloads, extack);
+}
+
+int mlx5_esw_bridge_vport_peer_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+				      struct mlx5_esw_bridge_offloads *br_offloads,
+				      struct netlink_ext_ack *extack)
+{
+	return mlx5_esw_bridge_vport_unlink(ifindex, vport_num, esw_owner_vhca_id, br_offloads,
+					    extack);
+}
+
+int mlx5_esw_bridge_port_vlan_add(u16 vport_num, u16 esw_owner_vhca_id, u16 vid, u16 flags,
+				  struct mlx5_esw_bridge_offloads *br_offloads,
+				  struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_bridge_port *port;
 	struct mlx5_esw_bridge_vlan *vlan;
 
-	port = mlx5_esw_bridge_port_lookup(vport->vport, vport->bridge);
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
 	if (!port)
 		return -EINVAL;
 
@@ -1148,10 +1233,10 @@ int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw,
 	if (vlan) {
 		if (vlan->flags == flags)
 			return 0;
-		mlx5_esw_bridge_vlan_cleanup(port, vlan, vport->bridge);
+		mlx5_esw_bridge_vlan_cleanup(port, vlan, port->bridge);
 	}
 
-	vlan = mlx5_esw_bridge_vlan_create(vid, flags, port, esw);
+	vlan = mlx5_esw_bridge_vlan_create(vid, flags, port, br_offloads->esw);
 	if (IS_ERR(vlan)) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed to create VLAN entry");
 		return PTR_ERR(vlan);
@@ -1159,62 +1244,93 @@ int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw,
 	return 0;
 }
 
-void mlx5_esw_bridge_port_vlan_del(u16 vid, struct mlx5_eswitch *esw, struct mlx5_vport *vport)
+void mlx5_esw_bridge_port_vlan_del(u16 vport_num, u16 esw_owner_vhca_id, u16 vid,
+				   struct mlx5_esw_bridge_offloads *br_offloads)
 {
 	struct mlx5_esw_bridge_port *port;
 	struct mlx5_esw_bridge_vlan *vlan;
 
-	port = mlx5_esw_bridge_port_lookup(vport->vport, vport->bridge);
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
 	if (!port)
 		return;
 
 	vlan = mlx5_esw_bridge_vlan_lookup(vid, port);
 	if (!vlan)
 		return;
-	mlx5_esw_bridge_vlan_cleanup(port, vlan, vport->bridge);
+	mlx5_esw_bridge_vlan_cleanup(port, vlan, port->bridge);
 }
 
-void mlx5_esw_bridge_fdb_create(struct net_device *dev, struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport,
-				struct switchdev_notifier_fdb_info *fdb_info)
+void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				     struct mlx5_esw_bridge_offloads *br_offloads,
+				     struct switchdev_notifier_fdb_info *fdb_info)
 {
-	struct mlx5_esw_bridge *bridge = vport->bridge;
 	struct mlx5_esw_bridge_fdb_entry *entry;
-	u16 vport_num = vport->vport;
+	struct mlx5_esw_bridge_fdb_key key;
+	struct mlx5_esw_bridge_port *port;
+	struct mlx5_esw_bridge *bridge;
 
-	if (!bridge) {
-		esw_info(esw->dev, "Vport is not assigned to bridge (vport=%u)\n", vport_num);
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port || port->flags & MLX5_ESW_BRIDGE_PORT_FLAG_PEER)
+		return;
+
+	bridge = port->bridge;
+	ether_addr_copy(key.addr, fdb_info->addr);
+	key.vid = fdb_info->vid;
+	entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params);
+	if (!entry) {
+		esw_debug(br_offloads->esw->dev,
+			  "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n",
+			  key.addr, key.vid, vport_num);
 		return;
 	}
 
-	entry = mlx5_esw_bridge_fdb_entry_init(dev, vport_num, fdb_info->addr, fdb_info->vid,
-					       fdb_info->added_by_user, esw, bridge);
+	entry->lastuse = jiffies;
+}
+
+void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				struct mlx5_esw_bridge_offloads *br_offloads,
+				struct switchdev_notifier_fdb_info *fdb_info)
+{
+	struct mlx5_esw_bridge_fdb_entry *entry;
+	struct mlx5_esw_bridge_port *port;
+	struct mlx5_esw_bridge *bridge;
+
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port)
+		return;
+
+	bridge = port->bridge;
+	entry = mlx5_esw_bridge_fdb_entry_init(dev, vport_num, esw_owner_vhca_id, fdb_info->addr,
+					       fdb_info->vid, fdb_info->added_by_user,
+					       port->flags & MLX5_ESW_BRIDGE_PORT_FLAG_PEER,
+					       br_offloads->esw, bridge);
 	if (IS_ERR(entry))
 		return;
 
 	if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)
 		mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid,
 						   SWITCHDEV_FDB_OFFLOADED);
-	else
+	else if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_PEER))
 		/* Take over dynamic entries to prevent kernel bridge from aging them out. */
 		mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid,
 						   SWITCHDEV_FDB_ADD_TO_BRIDGE);
 }
 
-void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport,
+void mlx5_esw_bridge_fdb_remove(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				struct mlx5_esw_bridge_offloads *br_offloads,
 				struct switchdev_notifier_fdb_info *fdb_info)
 {
-	struct mlx5_esw_bridge *bridge = vport->bridge;
+	struct mlx5_eswitch *esw = br_offloads->esw;
 	struct mlx5_esw_bridge_fdb_entry *entry;
 	struct mlx5_esw_bridge_fdb_key key;
-	u16 vport_num = vport->vport;
+	struct mlx5_esw_bridge_port *port;
+	struct mlx5_esw_bridge *bridge;
 
-	if (!bridge) {
-		esw_warn(esw->dev, "Vport is not assigned to bridge (vport=%u)\n", vport_num);
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port)
 		return;
-	}
 
+	bridge = port->bridge;
 	ether_addr_copy(key.addr, fdb_info->addr);
 	key.vid = fdb_info->vid;
 	entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params);
@@ -1225,9 +1341,7 @@ void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw
 		return;
 	}
 
-	if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER))
-		mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid,
-						   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+	mlx5_esw_bridge_fdb_del_notify(entry);
 	mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
 }
 
@@ -1245,11 +1359,10 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads)
 				continue;
 
 			if (time_after(lastuse, entry->lastuse)) {
-				mlx5_esw_bridge_fdb_entry_refresh(lastuse, entry);
-			} else if (time_is_before_jiffies(entry->lastuse + bridge->ageing_time)) {
-				mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
-								   entry->key.vid,
-								   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+				mlx5_esw_bridge_fdb_entry_refresh(entry);
+			} else if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_PEER) &&
+				   time_is_before_jiffies(entry->lastuse + bridge->ageing_time)) {
+				mlx5_esw_bridge_fdb_del_notify(entry);
 				mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
 			}
 		}
@@ -1258,13 +1371,11 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads)
 
 static void mlx5_esw_bridge_flush(struct mlx5_esw_bridge_offloads *br_offloads)
 {
-	struct mlx5_eswitch *esw = br_offloads->esw;
-	struct mlx5_vport *vport;
+	struct mlx5_esw_bridge_port *port;
 	unsigned long i;
 
-	mlx5_esw_for_each_vport(esw, i, vport)
-		if (vport->bridge)
-			mlx5_esw_bridge_vport_cleanup(br_offloads, vport);
+	xa_for_each(&br_offloads->ports, i, port)
+		mlx5_esw_bridge_vport_cleanup(br_offloads, port);
 
 	WARN_ONCE(!list_empty(&br_offloads->bridges),
 		  "Cleaning up bridge offloads while still having bridges attached\n");
@@ -1279,6 +1390,7 @@ struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw)
 		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&br_offloads->bridges);
+	xa_init(&br_offloads->ports);
 	br_offloads->esw = esw;
 	esw->br_offloads = br_offloads;
 
@@ -1293,6 +1405,7 @@ void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw)
 		return;
 
 	mlx5_esw_bridge_flush(br_offloads);
+	WARN_ON(!xa_empty(&br_offloads->ports));
 
 	esw->br_offloads = NULL;
 	kvfree(br_offloads);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
index d826942b27fc..efc39975226e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
@@ -7,6 +7,7 @@
 #include <linux/notifier.h>
 #include <linux/list.h>
 #include <linux/workqueue.h>
+#include <linux/xarray.h>
 #include "eswitch.h"
 
 struct mlx5_flow_table;
@@ -15,6 +16,8 @@ struct mlx5_flow_group;
 struct mlx5_esw_bridge_offloads {
 	struct mlx5_eswitch *esw;
 	struct list_head bridges;
+	struct xarray ports;
+
 	struct notifier_block netdev_nb;
 	struct notifier_block nb_blk;
 	struct notifier_block nb;
@@ -31,23 +34,36 @@ struct mlx5_esw_bridge_offloads {
 
 struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw);
 void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw);
-int mlx5_esw_bridge_vport_link(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads,
-			       struct mlx5_vport *vport, struct netlink_ext_ack *extack);
-int mlx5_esw_bridge_vport_unlink(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads,
-				 struct mlx5_vport *vport, struct netlink_ext_ack *extack);
-void mlx5_esw_bridge_fdb_create(struct net_device *dev, struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport,
+int mlx5_esw_bridge_vport_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+			       struct mlx5_esw_bridge_offloads *br_offloads,
+			       struct netlink_ext_ack *extack);
+int mlx5_esw_bridge_vport_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+				 struct mlx5_esw_bridge_offloads *br_offloads,
+				 struct netlink_ext_ack *extack);
+int mlx5_esw_bridge_vport_peer_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+				    struct mlx5_esw_bridge_offloads *br_offloads,
+				    struct netlink_ext_ack *extack);
+int mlx5_esw_bridge_vport_peer_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+				      struct mlx5_esw_bridge_offloads *br_offloads,
+				      struct netlink_ext_ack *extack);
+void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				     struct mlx5_esw_bridge_offloads *br_offloads,
+				     struct switchdev_notifier_fdb_info *fdb_info);
+void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				struct mlx5_esw_bridge_offloads *br_offloads,
 				struct switchdev_notifier_fdb_info *fdb_info);
-void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport,
+void mlx5_esw_bridge_fdb_remove(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				struct mlx5_esw_bridge_offloads *br_offloads,
 				struct switchdev_notifier_fdb_info *fdb_info);
 void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads);
-int mlx5_esw_bridge_ageing_time_set(unsigned long ageing_time, struct mlx5_eswitch *esw,
-				    struct mlx5_vport *vport);
-int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw,
-				       struct mlx5_vport *vport);
-int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw,
-				  struct mlx5_vport *vport, struct netlink_ext_ack *extack);
-void mlx5_esw_bridge_port_vlan_del(u16 vid, struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+int mlx5_esw_bridge_ageing_time_set(u16 vport_num, u16 esw_owner_vhca_id, unsigned long ageing_time,
+				    struct mlx5_esw_bridge_offloads *br_offloads);
+int mlx5_esw_bridge_vlan_filtering_set(u16 vport_num, u16 esw_owner_vhca_id, bool enable,
+				       struct mlx5_esw_bridge_offloads *br_offloads);
+int mlx5_esw_bridge_port_vlan_add(u16 vport_num, u16 esw_owner_vhca_id, u16 vid, u16 flags,
+				  struct mlx5_esw_bridge_offloads *br_offloads,
+				  struct netlink_ext_ack *extack);
+void mlx5_esw_bridge_port_vlan_del(u16 vport_num, u16 esw_owner_vhca_id, u16 vid,
+				   struct mlx5_esw_bridge_offloads *br_offloads);
 
 #endif /* __MLX5_ESW_BRIDGE_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
index d9ab2e8bc2cb..52964a82d6a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
@@ -19,6 +19,11 @@ struct mlx5_esw_bridge_fdb_key {
 
 enum {
 	MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER = BIT(0),
+	MLX5_ESW_BRIDGE_FLAG_PEER = BIT(1),
+};
+
+enum {
+	MLX5_ESW_BRIDGE_PORT_FLAG_PEER = BIT(0),
 };
 
 struct mlx5_esw_bridge_fdb_entry {
@@ -28,6 +33,7 @@ struct mlx5_esw_bridge_fdb_entry {
 	struct list_head list;
 	struct list_head vlan_list;
 	u16 vport_num;
+	u16 esw_owner_vhca_id;
 	u16 flags;
 
 	struct mlx5_flow_handle *ingress_handle;
@@ -47,6 +53,9 @@ struct mlx5_esw_bridge_vlan {
 
 struct mlx5_esw_bridge_port {
 	u16 vport_num;
+	u16 esw_owner_vhca_id;
+	u16 flags;
+	struct mlx5_esw_bridge *bridge;
 	struct xarray vlans;
 };
 
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 1703384eca95..20af557ae30c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -91,9 +91,15 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 	if (err)
 		goto reg_err;
 
+	err = devlink_rate_leaf_create(dl_port, vport);
+	if (err)
+		goto rate_err;
+
 	vport->dl_port = dl_port;
 	return 0;
 
+rate_err:
+	devlink_port_unregister(dl_port);
 reg_err:
 	mlx5_esw_dl_port_free(dl_port);
 	return err;
@@ -109,6 +115,12 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vpo
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
 	if (IS_ERR(vport))
 		return;
+
+	if (vport->dl_port->devlink_rate) {
+		mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL);
+		devlink_rate_leaf_destroy(vport->dl_port);
+	}
+
 	devlink_port_unregister(vport->dl_port);
 	mlx5_esw_dl_port_free(vport->dl_port);
 	vport->dl_port = NULL;
@@ -148,8 +160,16 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p
 	if (err)
 		return err;
 
+	err = devlink_rate_leaf_create(dl_port, vport);
+	if (err)
+		goto rate_err;
+
 	vport->dl_port = dl_port;
 	return 0;
+
+rate_err:
+	devlink_port_unregister(dl_port);
+	return err;
 }
 
 void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num)
@@ -159,6 +179,12 @@ void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
 	if (IS_ERR(vport))
 		return;
+
+	if (vport->dl_port->devlink_rate) {
+		mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL);
+		devlink_rate_leaf_destroy(vport->dl_port);
+	}
+
 	devlink_port_unregister(vport->dl_port);
 	vport->dl_port = NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h
index 227964b7d3b9..3401188e0a60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h
@@ -85,11 +85,18 @@ DECLARE_EVENT_CLASS(mlx5_esw_bridge_port_template,
 		    TP_ARGS(port),
 		    TP_STRUCT__entry(
 			    __field(u16, vport_num)
+			    __field(u16, esw_owner_vhca_id)
+			    __field(u16, flags)
 			    ),
 		    TP_fast_assign(
 			    __entry->vport_num = port->vport_num;
+			    __entry->esw_owner_vhca_id = port->esw_owner_vhca_id;
+			    __entry->flags = port->flags;
 			    ),
-		    TP_printk("vport_num=%hu", __entry->vport_num)
+		    TP_printk("vport_num=%hu esw_owner_vhca_id=%hu flags=%hx",
+			      __entry->vport_num,
+			      __entry->esw_owner_vhca_id,
+			      __entry->flags)
 	);
 
 DEFINE_EVENT(mlx5_esw_bridge_port_template,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/qos_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/qos_tracepoint.h
new file mode 100644
index 000000000000..458baf0c6415
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/qos_tracepoint.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlx5
+
+#if !defined(_MLX5_ESW_TP_) || defined(TRACE_HEADER_MULTI_READ)
+#define _MLX5_ESW_TP_
+
+#include <linux/tracepoint.h>
+#include "eswitch.h"
+
+TRACE_EVENT(mlx5_esw_vport_qos_destroy,
+	    TP_PROTO(const struct mlx5_vport *vport),
+	    TP_ARGS(vport),
+	    TP_STRUCT__entry(__string(devname, dev_name(vport->dev->device))
+			     __field(unsigned short, vport_id)
+			     __field(unsigned int,   tsar_ix)
+			     ),
+	    TP_fast_assign(__assign_str(devname, dev_name(vport->dev->device));
+		    __entry->vport_id = vport->vport;
+		    __entry->tsar_ix = vport->qos.esw_tsar_ix;
+	    ),
+	    TP_printk("(%s) vport=%hu tsar_ix=%u\n",
+		      __get_str(devname), __entry->vport_id, __entry->tsar_ix
+		      )
+);
+
+DECLARE_EVENT_CLASS(mlx5_esw_vport_qos_template,
+		    TP_PROTO(const struct mlx5_vport *vport, u32 bw_share, u32 max_rate),
+		    TP_ARGS(vport, bw_share, max_rate),
+		    TP_STRUCT__entry(__string(devname, dev_name(vport->dev->device))
+				     __field(unsigned short, vport_id)
+				     __field(unsigned int, tsar_ix)
+				     __field(unsigned int, bw_share)
+				     __field(unsigned int, max_rate)
+				     __field(void *, group)
+				     ),
+		    TP_fast_assign(__assign_str(devname, dev_name(vport->dev->device));
+			    __entry->vport_id = vport->vport;
+			    __entry->tsar_ix = vport->qos.esw_tsar_ix;
+			    __entry->bw_share = bw_share;
+			    __entry->max_rate = max_rate;
+			    __entry->group = vport->qos.group;
+		    ),
+		    TP_printk("(%s) vport=%hu tsar_ix=%u bw_share=%u, max_rate=%u group=%p\n",
+			      __get_str(devname), __entry->vport_id, __entry->tsar_ix,
+			      __entry->bw_share, __entry->max_rate, __entry->group
+			      )
+);
+
+DEFINE_EVENT(mlx5_esw_vport_qos_template, mlx5_esw_vport_qos_create,
+	     TP_PROTO(const struct mlx5_vport *vport, u32 bw_share, u32 max_rate),
+	     TP_ARGS(vport, bw_share, max_rate)
+	     );
+
+DEFINE_EVENT(mlx5_esw_vport_qos_template, mlx5_esw_vport_qos_config,
+	     TP_PROTO(const struct mlx5_vport *vport, u32 bw_share, u32 max_rate),
+	     TP_ARGS(vport, bw_share, max_rate)
+	     );
+
+DECLARE_EVENT_CLASS(mlx5_esw_group_qos_template,
+		    TP_PROTO(const struct mlx5_core_dev *dev,
+			     const struct mlx5_esw_rate_group *group,
+			     unsigned int tsar_ix),
+		    TP_ARGS(dev, group, tsar_ix),
+		    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+				     __field(const void *, group)
+				     __field(unsigned int, tsar_ix)
+				     ),
+		    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+			    __entry->group = group;
+			    __entry->tsar_ix = tsar_ix;
+		    ),
+		    TP_printk("(%s) group=%p tsar_ix=%u\n",
+			      __get_str(devname), __entry->group, __entry->tsar_ix
+			      )
+);
+
+DEFINE_EVENT(mlx5_esw_group_qos_template, mlx5_esw_group_qos_create,
+	     TP_PROTO(const struct mlx5_core_dev *dev,
+		      const struct mlx5_esw_rate_group *group,
+		      unsigned int tsar_ix),
+	     TP_ARGS(dev, group, tsar_ix)
+	     );
+
+DEFINE_EVENT(mlx5_esw_group_qos_template, mlx5_esw_group_qos_destroy,
+	     TP_PROTO(const struct mlx5_core_dev *dev,
+		      const struct mlx5_esw_rate_group *group,
+		      unsigned int tsar_ix),
+	     TP_ARGS(dev, group, tsar_ix)
+	     );
+
+TRACE_EVENT(mlx5_esw_group_qos_config,
+	    TP_PROTO(const struct mlx5_core_dev *dev,
+		     const struct mlx5_esw_rate_group *group,
+		     unsigned int tsar_ix, u32 bw_share, u32 max_rate),
+	    TP_ARGS(dev, group, tsar_ix, bw_share, max_rate),
+	    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+			     __field(const void *, group)
+			     __field(unsigned int, tsar_ix)
+			     __field(unsigned int, bw_share)
+			     __field(unsigned int, max_rate)
+			     ),
+	    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+		    __entry->group = group;
+		    __entry->tsar_ix = tsar_ix;
+		    __entry->bw_share = bw_share;
+		    __entry->max_rate = max_rate;
+	    ),
+	    TP_printk("(%s) group=%p tsar_ix=%u bw_share=%u max_rate=%u\n",
+		      __get_str(devname), __entry->group, __entry->tsar_ix,
+		      __entry->bw_share, __entry->max_rate
+		      )
+);
+#endif /* _MLX5_ESW_TP_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH esw/diag
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE qos_tracepoint
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c
index 3da7becc1069..425c91814b34 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c
@@ -364,6 +364,7 @@ static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw,
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
 	dest.vport.num = e->vport;
 	dest.vport.vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id);
+	dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID;
 	e->fwd_rule = mlx5_add_flow_rules(e->ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(e->fwd_rule)) {
 		mlx5_destroy_flow_group(e->fwd_grp);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
index d9041b16611d..df277a6cddc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
@@ -11,6 +11,7 @@
 #include "mlx5_core.h"
 #include "eswitch.h"
 #include "fs_core.h"
+#include "esw/qos.h"
 
 enum {
 	LEGACY_VEPA_PRIO = 0,
@@ -508,3 +509,22 @@ unlock:
 	mutex_unlock(&esw->state_lock);
 	return err;
 }
+
+int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport,
+				u32 max_rate, u32 min_rate)
+{
+	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+	int err;
+
+	if (!mlx5_esw_allowed(esw))
+		return -EPERM;
+	if (IS_ERR(evport))
+		return PTR_ERR(evport);
+
+	mutex_lock(&esw->state_lock);
+	err = mlx5_esw_qos_set_vport_min_rate(esw, evport, min_rate, NULL);
+	if (!err)
+		err = mlx5_esw_qos_set_vport_max_rate(esw, evport, max_rate, NULL);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
new file mode 100644
index 000000000000..985e305179d1
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -0,0 +1,869 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include "eswitch.h"
+#include "esw/qos.h"
+#include "en/port.h"
+#define CREATE_TRACE_POINTS
+#include "diag/qos_tracepoint.h"
+
+/* Minimum supported BW share value by the HW is 1 Mbit/sec */
+#define MLX5_MIN_BW_SHARE 1
+
+#define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \
+	min_t(u32, max_t(u32, DIV_ROUND_UP(rate, divider), MLX5_MIN_BW_SHARE), limit)
+
+struct mlx5_esw_rate_group {
+	u32 tsar_ix;
+	u32 max_rate;
+	u32 min_rate;
+	u32 bw_share;
+	struct list_head list;
+};
+
+static int esw_qos_tsar_config(struct mlx5_core_dev *dev, u32 *sched_ctx,
+			       u32 parent_ix, u32 tsar_ix,
+			       u32 max_rate, u32 bw_share)
+{
+	u32 bitmask = 0;
+
+	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
+		return -EOPNOTSUPP;
+
+	MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_ix);
+	MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate);
+	MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share);
+	bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW;
+	bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE;
+
+	return mlx5_modify_scheduling_element_cmd(dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  sched_ctx,
+						  tsar_ix,
+						  bitmask);
+}
+
+static int esw_qos_group_config(struct mlx5_eswitch *esw, struct mlx5_esw_rate_group *group,
+				u32 max_rate, u32 bw_share, struct netlink_ext_ack *extack)
+{
+	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_core_dev *dev = esw->dev;
+	int err;
+
+	err = esw_qos_tsar_config(dev, sched_ctx,
+				  esw->qos.root_tsar_ix, group->tsar_ix,
+				  max_rate, bw_share);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch modify group TSAR element failed");
+
+	trace_mlx5_esw_group_qos_config(dev, group, group->tsar_ix, bw_share, max_rate);
+
+	return err;
+}
+
+static int esw_qos_vport_config(struct mlx5_eswitch *esw,
+				struct mlx5_vport *vport,
+				u32 max_rate, u32 bw_share,
+				struct netlink_ext_ack *extack)
+{
+	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_esw_rate_group *group = vport->qos.group;
+	struct mlx5_core_dev *dev = esw->dev;
+	u32 parent_tsar_ix;
+	void *vport_elem;
+	int err;
+
+	if (!vport->qos.enabled)
+		return -EIO;
+
+	parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix;
+	MLX5_SET(scheduling_context, sched_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
+	vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
+				  element_attributes);
+	MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
+
+	err = esw_qos_tsar_config(dev, sched_ctx, parent_tsar_ix, vport->qos.esw_tsar_ix,
+				  max_rate, bw_share);
+	if (err) {
+		esw_warn(esw->dev,
+			 "E-Switch modify TSAR vport element failed (vport=%d,err=%d)\n",
+			 vport->vport, err);
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch modify TSAR vport element failed");
+		return err;
+	}
+
+	trace_mlx5_esw_vport_qos_config(vport, bw_share, max_rate);
+
+	return 0;
+}
+
+static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw,
+					      struct mlx5_esw_rate_group *group,
+					      bool group_level)
+{
+	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	struct mlx5_vport *evport;
+	u32 max_guarantee = 0;
+	unsigned long i;
+
+	if (group_level) {
+		struct mlx5_esw_rate_group *group;
+
+		list_for_each_entry(group, &esw->qos.groups, list) {
+			if (group->min_rate < max_guarantee)
+				continue;
+			max_guarantee = group->min_rate;
+		}
+	} else {
+		mlx5_esw_for_each_vport(esw, i, evport) {
+			if (!evport->enabled || !evport->qos.enabled ||
+			    evport->qos.group != group || evport->qos.min_rate < max_guarantee)
+				continue;
+			max_guarantee = evport->qos.min_rate;
+		}
+	}
+
+	if (max_guarantee)
+		return max_t(u32, max_guarantee / fw_max_bw_share, 1);
+
+	/* If vports min rate divider is 0 but their group has bw_share configured, then
+	 * need to set bw_share for vports to minimal value.
+	 */
+	if (!group_level && !max_guarantee && group->bw_share)
+		return 1;
+	return 0;
+}
+
+static u32 esw_qos_calc_bw_share(u32 min_rate, u32 divider, u32 fw_max)
+{
+	if (divider)
+		return MLX5_RATE_TO_BW_SHARE(min_rate, divider, fw_max);
+
+	return 0;
+}
+
+static int esw_qos_normalize_vports_min_rate(struct mlx5_eswitch *esw,
+					     struct mlx5_esw_rate_group *group,
+					     struct netlink_ext_ack *extack)
+{
+	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	u32 divider = esw_qos_calculate_min_rate_divider(esw, group, false);
+	struct mlx5_vport *evport;
+	unsigned long i;
+	u32 bw_share;
+	int err;
+
+	mlx5_esw_for_each_vport(esw, i, evport) {
+		if (!evport->enabled || !evport->qos.enabled || evport->qos.group != group)
+			continue;
+		bw_share = esw_qos_calc_bw_share(evport->qos.min_rate, divider, fw_max_bw_share);
+
+		if (bw_share == evport->qos.bw_share)
+			continue;
+
+		err = esw_qos_vport_config(esw, evport, evport->qos.max_rate, bw_share, extack);
+		if (err)
+			return err;
+
+		evport->qos.bw_share = bw_share;
+	}
+
+	return 0;
+}
+
+static int esw_qos_normalize_groups_min_rate(struct mlx5_eswitch *esw, u32 divider,
+					     struct netlink_ext_ack *extack)
+{
+	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	struct mlx5_esw_rate_group *group;
+	u32 bw_share;
+	int err;
+
+	list_for_each_entry(group, &esw->qos.groups, list) {
+		bw_share = esw_qos_calc_bw_share(group->min_rate, divider, fw_max_bw_share);
+
+		if (bw_share == group->bw_share)
+			continue;
+
+		err = esw_qos_group_config(esw, group, group->max_rate, bw_share, extack);
+		if (err)
+			return err;
+
+		group->bw_share = bw_share;
+
+		/* All the group's vports need to be set with default bw_share
+		 * to enable them with QOS
+		 */
+		err = esw_qos_normalize_vports_min_rate(esw, group, extack);
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int mlx5_esw_qos_set_vport_min_rate(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *evport,
+				    u32 min_rate,
+				    struct netlink_ext_ack *extack)
+{
+	u32 fw_max_bw_share, previous_min_rate;
+	bool min_rate_supported;
+	int err;
+
+	lockdep_assert_held(&esw->state_lock);
+	fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	min_rate_supported = MLX5_CAP_QOS(esw->dev, esw_bw_share) &&
+				fw_max_bw_share >= MLX5_MIN_BW_SHARE;
+	if (min_rate && !min_rate_supported)
+		return -EOPNOTSUPP;
+	if (min_rate == evport->qos.min_rate)
+		return 0;
+
+	previous_min_rate = evport->qos.min_rate;
+	evport->qos.min_rate = min_rate;
+	err = esw_qos_normalize_vports_min_rate(esw, evport->qos.group, extack);
+	if (err)
+		evport->qos.min_rate = previous_min_rate;
+
+	return err;
+}
+
+int mlx5_esw_qos_set_vport_max_rate(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *evport,
+				    u32 max_rate,
+				    struct netlink_ext_ack *extack)
+{
+	u32 act_max_rate = max_rate;
+	bool max_rate_supported;
+	int err;
+
+	lockdep_assert_held(&esw->state_lock);
+	max_rate_supported = MLX5_CAP_QOS(esw->dev, esw_rate_limit);
+
+	if (max_rate && !max_rate_supported)
+		return -EOPNOTSUPP;
+	if (max_rate == evport->qos.max_rate)
+		return 0;
+
+	/* If parent group has rate limit need to set to group
+	 * value when new max rate is 0.
+	 */
+	if (evport->qos.group && !max_rate)
+		act_max_rate = evport->qos.group->max_rate;
+
+	err = esw_qos_vport_config(esw, evport, act_max_rate, evport->qos.bw_share, extack);
+
+	if (!err)
+		evport->qos.max_rate = max_rate;
+
+	return err;
+}
+
+static int esw_qos_set_group_min_rate(struct mlx5_eswitch *esw, struct mlx5_esw_rate_group *group,
+				      u32 min_rate, struct netlink_ext_ack *extack)
+{
+	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	struct mlx5_core_dev *dev = esw->dev;
+	u32 previous_min_rate, divider;
+	int err;
+
+	if (!(MLX5_CAP_QOS(dev, esw_bw_share) && fw_max_bw_share >= MLX5_MIN_BW_SHARE))
+		return -EOPNOTSUPP;
+
+	if (min_rate == group->min_rate)
+		return 0;
+
+	previous_min_rate = group->min_rate;
+	group->min_rate = min_rate;
+	divider = esw_qos_calculate_min_rate_divider(esw, group, true);
+	err = esw_qos_normalize_groups_min_rate(esw, divider, extack);
+	if (err) {
+		group->min_rate = previous_min_rate;
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch group min rate setting failed");
+
+		/* Attempt restoring previous configuration */
+		divider = esw_qos_calculate_min_rate_divider(esw, group, true);
+		if (esw_qos_normalize_groups_min_rate(esw, divider, extack))
+			NL_SET_ERR_MSG_MOD(extack, "E-Switch BW share restore failed");
+	}
+
+	return err;
+}
+
+static int esw_qos_set_group_max_rate(struct mlx5_eswitch *esw,
+				      struct mlx5_esw_rate_group *group,
+				      u32 max_rate, struct netlink_ext_ack *extack)
+{
+	struct mlx5_vport *vport;
+	unsigned long i;
+	int err;
+
+	if (group->max_rate == max_rate)
+		return 0;
+
+	err = esw_qos_group_config(esw, group, max_rate, group->bw_share, extack);
+	if (err)
+		return err;
+
+	group->max_rate = max_rate;
+
+	/* Any unlimited vports in the group should be set
+	 * with the value of the group.
+	 */
+	mlx5_esw_for_each_vport(esw, i, vport) {
+		if (!vport->enabled || !vport->qos.enabled ||
+		    vport->qos.group != group || vport->qos.max_rate)
+			continue;
+
+		err = esw_qos_vport_config(esw, vport, max_rate, vport->qos.bw_share, extack);
+		if (err)
+			NL_SET_ERR_MSG_MOD(extack,
+					   "E-Switch vport implicit rate limit setting failed");
+	}
+
+	return err;
+}
+
+static int esw_qos_vport_create_sched_element(struct mlx5_eswitch *esw,
+					      struct mlx5_vport *vport,
+					      u32 max_rate, u32 bw_share)
+{
+	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_esw_rate_group *group = vport->qos.group;
+	struct mlx5_core_dev *dev = esw->dev;
+	u32 parent_tsar_ix;
+	void *vport_elem;
+	int err;
+
+	parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix;
+	MLX5_SET(scheduling_context, sched_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
+	vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes);
+	MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
+	MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_tsar_ix);
+	MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate);
+	MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share);
+
+	err = mlx5_create_scheduling_element_cmd(dev,
+						 SCHEDULING_HIERARCHY_E_SWITCH,
+						 sched_ctx,
+						 &vport->qos.esw_tsar_ix);
+	if (err) {
+		esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n",
+			 vport->vport, err);
+		return err;
+	}
+
+	return 0;
+}
+
+static int esw_qos_update_group_scheduling_element(struct mlx5_eswitch *esw,
+						   struct mlx5_vport *vport,
+						   struct mlx5_esw_rate_group *curr_group,
+						   struct mlx5_esw_rate_group *new_group,
+						   struct netlink_ext_ack *extack)
+{
+	u32 max_rate;
+	int err;
+
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  vport->qos.esw_tsar_ix);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR vport element failed");
+		return err;
+	}
+
+	vport->qos.group = new_group;
+	max_rate = vport->qos.max_rate ? vport->qos.max_rate : new_group->max_rate;
+
+	/* If vport is unlimited, we set the group's value.
+	 * Therefore, if the group is limited it will apply to
+	 * the vport as well and if not, vport will remain unlimited.
+	 */
+	err = esw_qos_vport_create_sched_element(esw, vport, max_rate, vport->qos.bw_share);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch vport group set failed.");
+		goto err_sched;
+	}
+
+	return 0;
+
+err_sched:
+	vport->qos.group = curr_group;
+	max_rate = vport->qos.max_rate ? vport->qos.max_rate : curr_group->max_rate;
+	if (esw_qos_vport_create_sched_element(esw, vport, max_rate, vport->qos.bw_share))
+		esw_warn(esw->dev, "E-Switch vport group restore failed (vport=%d)\n",
+			 vport->vport);
+
+	return err;
+}
+
+static int esw_qos_vport_update_group(struct mlx5_eswitch *esw,
+				      struct mlx5_vport *vport,
+				      struct mlx5_esw_rate_group *group,
+				      struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_rate_group *new_group, *curr_group;
+	int err;
+
+	if (!vport->enabled)
+		return -EINVAL;
+
+	curr_group = vport->qos.group;
+	new_group = group ?: esw->qos.group0;
+	if (curr_group == new_group)
+		return 0;
+
+	err = esw_qos_update_group_scheduling_element(esw, vport, curr_group, new_group, extack);
+	if (err)
+		return err;
+
+	/* Recalculate bw share weights of old and new groups */
+	if (vport->qos.bw_share) {
+		esw_qos_normalize_vports_min_rate(esw, curr_group, extack);
+		esw_qos_normalize_vports_min_rate(esw, new_group, extack);
+	}
+
+	return 0;
+}
+
+static struct mlx5_esw_rate_group *
+esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack)
+{
+	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_esw_rate_group *group;
+	u32 divider;
+	int err;
+
+	if (!MLX5_CAP_QOS(esw->dev, log_esw_max_sched_depth))
+		return ERR_PTR(-EOPNOTSUPP);
+
+	group = kzalloc(sizeof(*group), GFP_KERNEL);
+	if (!group)
+		return ERR_PTR(-ENOMEM);
+
+	MLX5_SET(scheduling_context, tsar_ctx, parent_element_id,
+		 esw->qos.root_tsar_ix);
+	err = mlx5_create_scheduling_element_cmd(esw->dev,
+						 SCHEDULING_HIERARCHY_E_SWITCH,
+						 tsar_ctx,
+						 &group->tsar_ix);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch create TSAR for group failed");
+		goto err_sched_elem;
+	}
+
+	list_add_tail(&group->list, &esw->qos.groups);
+
+	divider = esw_qos_calculate_min_rate_divider(esw, group, true);
+	if (divider) {
+		err = esw_qos_normalize_groups_min_rate(esw, divider, extack);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack, "E-Switch groups normalization failed");
+			goto err_min_rate;
+		}
+	}
+	trace_mlx5_esw_group_qos_create(esw->dev, group, group->tsar_ix);
+
+	return group;
+
+err_min_rate:
+	list_del(&group->list);
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  group->tsar_ix);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR for group failed");
+err_sched_elem:
+	kfree(group);
+	return ERR_PTR(err);
+}
+
+static int esw_qos_destroy_rate_group(struct mlx5_eswitch *esw,
+				      struct mlx5_esw_rate_group *group,
+				      struct netlink_ext_ack *extack)
+{
+	u32 divider;
+	int err;
+
+	list_del(&group->list);
+
+	divider = esw_qos_calculate_min_rate_divider(esw, NULL, true);
+	err = esw_qos_normalize_groups_min_rate(esw, divider, extack);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch groups' normalization failed");
+
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  group->tsar_ix);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR_ID failed");
+
+	trace_mlx5_esw_group_qos_destroy(esw->dev, group, group->tsar_ix);
+	kfree(group);
+	return err;
+}
+
+static bool esw_qos_element_type_supported(struct mlx5_core_dev *dev, int type)
+{
+	switch (type) {
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_TASR;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_VPORT;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_VPORT_TC;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC;
+	}
+	return false;
+}
+
+void mlx5_esw_qos_create(struct mlx5_eswitch *esw)
+{
+	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_core_dev *dev = esw->dev;
+	__be32 *attr;
+	int err;
+
+	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
+		return;
+
+	if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR))
+		return;
+
+	mutex_lock(&esw->state_lock);
+	if (esw->qos.enabled)
+		goto unlock;
+
+	MLX5_SET(scheduling_context, tsar_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
+
+	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
+	*attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16);
+
+	err = mlx5_create_scheduling_element_cmd(dev,
+						 SCHEDULING_HIERARCHY_E_SWITCH,
+						 tsar_ctx,
+						 &esw->qos.root_tsar_ix);
+	if (err) {
+		esw_warn(dev, "E-Switch create root TSAR failed (%d)\n", err);
+		goto unlock;
+	}
+
+	INIT_LIST_HEAD(&esw->qos.groups);
+	if (MLX5_CAP_QOS(dev, log_esw_max_sched_depth)) {
+		esw->qos.group0 = esw_qos_create_rate_group(esw, NULL);
+		if (IS_ERR(esw->qos.group0)) {
+			esw_warn(dev, "E-Switch create rate group 0 failed (%ld)\n",
+				 PTR_ERR(esw->qos.group0));
+			goto err_group0;
+		}
+	}
+	esw->qos.enabled = true;
+unlock:
+	mutex_unlock(&esw->state_lock);
+	return;
+
+err_group0:
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  esw->qos.root_tsar_ix);
+	if (err)
+		esw_warn(esw->dev, "E-Switch destroy root TSAR failed (%d)\n", err);
+	mutex_unlock(&esw->state_lock);
+}
+
+void mlx5_esw_qos_destroy(struct mlx5_eswitch *esw)
+{
+	struct devlink *devlink = priv_to_devlink(esw->dev);
+	int err;
+
+	devlink_rate_nodes_destroy(devlink);
+	mutex_lock(&esw->state_lock);
+	if (!esw->qos.enabled)
+		goto unlock;
+
+	if (esw->qos.group0)
+		esw_qos_destroy_rate_group(esw, esw->qos.group0, NULL);
+
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  esw->qos.root_tsar_ix);
+	if (err)
+		esw_warn(esw->dev, "E-Switch destroy root TSAR failed (%d)\n", err);
+
+	esw->qos.enabled = false;
+unlock:
+	mutex_unlock(&esw->state_lock);
+}
+
+int mlx5_esw_qos_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+			      u32 max_rate, u32 bw_share)
+{
+	int err;
+
+	lockdep_assert_held(&esw->state_lock);
+	if (!esw->qos.enabled)
+		return 0;
+
+	if (vport->qos.enabled)
+		return -EEXIST;
+
+	vport->qos.group = esw->qos.group0;
+
+	err = esw_qos_vport_create_sched_element(esw, vport, max_rate, bw_share);
+	if (!err) {
+		vport->qos.enabled = true;
+		trace_mlx5_esw_vport_qos_create(vport, bw_share, max_rate);
+	}
+
+	return err;
+}
+
+void mlx5_esw_qos_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
+{
+	int err;
+
+	lockdep_assert_held(&esw->state_lock);
+	if (!esw->qos.enabled || !vport->qos.enabled)
+		return;
+	WARN(vport->qos.group && vport->qos.group != esw->qos.group0,
+	     "Disabling QoS on port before detaching it from group");
+
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  vport->qos.esw_tsar_ix);
+	if (err)
+		esw_warn(esw->dev, "E-Switch destroy TSAR vport element failed (vport=%d,err=%d)\n",
+			 vport->vport, err);
+
+	vport->qos.enabled = false;
+	trace_mlx5_esw_vport_qos_destroy(vport);
+}
+
+int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32 rate_mbps)
+{
+	u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_vport *vport;
+	u32 bitmask;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	if (!vport->qos.enabled)
+		return -EOPNOTSUPP;
+
+	MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps);
+	bitmask = MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW;
+
+	return mlx5_modify_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  ctx,
+						  vport->qos.esw_tsar_ix,
+						  bitmask);
+}
+
+#define MLX5_LINKSPEED_UNIT 125000 /* 1Mbps in Bps */
+
+/* Converts bytes per second value passed in a pointer into megabits per
+ * second, rewriting last. If converted rate exceed link speed or is not a
+ * fraction of Mbps - returns error.
+ */
+static int esw_qos_devlink_rate_to_mbps(struct mlx5_core_dev *mdev, const char *name,
+					u64 *rate, struct netlink_ext_ack *extack)
+{
+	u32 link_speed_max, reminder;
+	u64 value;
+	int err;
+
+	err = mlx5e_port_max_linkspeed(mdev, &link_speed_max);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to get link maximum speed");
+		return err;
+	}
+
+	value = div_u64_rem(*rate, MLX5_LINKSPEED_UNIT, &reminder);
+	if (reminder) {
+		pr_err("%s rate value %lluBps not in link speed units of 1Mbps.\n",
+		       name, *rate);
+		NL_SET_ERR_MSG_MOD(extack, "TX rate value not in link speed units of 1Mbps");
+		return -EINVAL;
+	}
+
+	if (value > link_speed_max) {
+		pr_err("%s rate value %lluMbps exceed link maximum speed %u.\n",
+		       name, value, link_speed_max);
+		NL_SET_ERR_MSG_MOD(extack, "TX rate value exceed link maximum speed");
+		return -EINVAL;
+	}
+
+	*rate = value;
+	return 0;
+}
+
+/* Eswitch devlink rate API */
+
+int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void *priv,
+					    u64 tx_share, struct netlink_ext_ack *extack)
+{
+	struct mlx5_vport *vport = priv;
+	struct mlx5_eswitch *esw;
+	int err;
+
+	esw = vport->dev->priv.eswitch;
+	if (!mlx5_esw_allowed(esw))
+		return -EPERM;
+
+	err = esw_qos_devlink_rate_to_mbps(vport->dev, "tx_share", &tx_share, extack);
+	if (err)
+		return err;
+
+	mutex_lock(&esw->state_lock);
+	err = mlx5_esw_qos_set_vport_min_rate(esw, vport, tx_share, extack);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *priv,
+					  u64 tx_max, struct netlink_ext_ack *extack)
+{
+	struct mlx5_vport *vport = priv;
+	struct mlx5_eswitch *esw;
+	int err;
+
+	esw = vport->dev->priv.eswitch;
+	if (!mlx5_esw_allowed(esw))
+		return -EPERM;
+
+	err = esw_qos_devlink_rate_to_mbps(vport->dev, "tx_max", &tx_max, extack);
+	if (err)
+		return err;
+
+	mutex_lock(&esw->state_lock);
+	err = mlx5_esw_qos_set_vport_max_rate(esw, vport, tx_max, extack);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_node_tx_share_set(struct devlink_rate *rate_node, void *priv,
+					    u64 tx_share, struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(rate_node->devlink);
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+	struct mlx5_esw_rate_group *group = priv;
+	int err;
+
+	err = esw_qos_devlink_rate_to_mbps(dev, "tx_share", &tx_share, extack);
+	if (err)
+		return err;
+
+	mutex_lock(&esw->state_lock);
+	err = esw_qos_set_group_min_rate(esw, group, tx_share, extack);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_node_tx_max_set(struct devlink_rate *rate_node, void *priv,
+					  u64 tx_max, struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(rate_node->devlink);
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+	struct mlx5_esw_rate_group *group = priv;
+	int err;
+
+	err = esw_qos_devlink_rate_to_mbps(dev, "tx_max", &tx_max, extack);
+	if (err)
+		return err;
+
+	mutex_lock(&esw->state_lock);
+	err = esw_qos_set_group_max_rate(esw, group, tx_max, extack);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv,
+				   struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_rate_group *group;
+	struct mlx5_eswitch *esw;
+	int err = 0;
+
+	esw = mlx5_devlink_eswitch_get(rate_node->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	mutex_lock(&esw->state_lock);
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Rate node creation supported only in switchdev mode");
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	group = esw_qos_create_rate_group(esw, extack);
+	if (IS_ERR(group)) {
+		err = PTR_ERR(group);
+		goto unlock;
+	}
+
+	*priv = group;
+unlock:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv,
+				   struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_rate_group *group = priv;
+	struct mlx5_eswitch *esw;
+	int err;
+
+	esw = mlx5_devlink_eswitch_get(rate_node->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	mutex_lock(&esw->state_lock);
+	err = esw_qos_destroy_rate_group(esw, group, extack);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_qos_vport_update_group(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *vport,
+				    struct mlx5_esw_rate_group *group,
+				    struct netlink_ext_ack *extack)
+{
+	int err;
+
+	mutex_lock(&esw->state_lock);
+	err = esw_qos_vport_update_group(esw, vport, group, extack);
+	mutex_unlock(&esw->state_lock);
+	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)
+{
+	struct mlx5_esw_rate_group *group;
+	struct mlx5_vport *vport = priv;
+
+	if (!parent)
+		return mlx5_esw_qos_vport_update_group(vport->dev->priv.eswitch,
+						       vport, NULL, extack);
+
+	group = parent_priv;
+	return mlx5_esw_qos_vport_update_group(vport->dev->priv.eswitch, vport, group, extack);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
new file mode 100644
index 000000000000..28451abe2d2f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef __MLX5_ESW_QOS_H__
+#define __MLX5_ESW_QOS_H__
+
+#ifdef CONFIG_MLX5_ESWITCH
+
+int mlx5_esw_qos_set_vport_min_rate(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *evport,
+				    u32 min_rate,
+				    struct netlink_ext_ack *extack);
+int mlx5_esw_qos_set_vport_max_rate(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *evport,
+				    u32 max_rate,
+				    struct netlink_ext_ack *extack);
+void mlx5_esw_qos_create(struct mlx5_eswitch *esw);
+void mlx5_esw_qos_destroy(struct mlx5_eswitch *esw);
+int mlx5_esw_qos_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+			      u32 max_rate, u32 bw_share);
+void mlx5_esw_qos_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+
+int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void *priv,
+					    u64 tx_share, struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *priv,
+					  u64 tx_max, struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_node_tx_share_set(struct devlink_rate *rate_node, void *priv,
+					    u64 tx_share, struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_node_tx_max_set(struct devlink_rate *rate_node, void *priv,
+					  u64 tx_max, struct netlink_ext_ack *extack);
+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);
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.h
deleted file mode 100644
index 2a3f4be10030..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.h
+++ /dev/null
@@ -1,42 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
-/* Copyright (c) 2021 Mellanox Technologies. */
-
-#ifndef __MLX5_EN_TC_SAMPLE_H__
-#define __MLX5_EN_TC_SAMPLE_H__
-
-#include "en.h"
-#include "eswitch.h"
-
-struct mlx5e_priv;
-struct mlx5_flow_attr;
-struct mlx5_esw_psample;
-
-struct mlx5_sample_attr {
-	u32 group_num;
-	u32 rate;
-	u32 trunc_size;
-	u32 restore_obj_id;
-	u32 sampler_id;
-	struct mlx5_flow_table *sample_default_tbl;
-	struct mlx5_sample_flow *sample_flow;
-};
-
-void mlx5_esw_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj);
-
-struct mlx5_flow_handle *
-mlx5_esw_sample_offload(struct mlx5_esw_psample *sample_priv,
-			struct mlx5_flow_spec *spec,
-			struct mlx5_flow_attr *attr);
-
-void
-mlx5_esw_sample_unoffload(struct mlx5_esw_psample *sample_priv,
-			  struct mlx5_flow_handle *rule,
-			  struct mlx5_flow_attr *attr);
-
-struct mlx5_esw_psample *
-mlx5_esw_sample_init(struct mlx5e_priv *priv);
-
-void
-mlx5_esw_sample_cleanup(struct mlx5_esw_psample *esw_psample);
-
-#endif /* __MLX5_EN_TC_SAMPLE_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 97e6cb6f13c1..ec136b499204 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -38,6 +38,7 @@
 #include <linux/mlx5/mpfs.h>
 #include "esw/acl/lgcy.h"
 #include "esw/legacy.h"
+#include "esw/qos.h"
 #include "mlx5_core.h"
 #include "lib/eq.h"
 #include "eswitch.h"
@@ -740,201 +741,6 @@ static void esw_vport_change_handler(struct work_struct *work)
 	mutex_unlock(&esw->state_lock);
 }
 
-static bool element_type_supported(struct mlx5_eswitch *esw, int type)
-{
-	const struct mlx5_core_dev *dev = esw->dev;
-
-	switch (type) {
-	case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR:
-		return MLX5_CAP_QOS(dev, esw_element_type) &
-		       ELEMENT_TYPE_CAP_MASK_TASR;
-	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT:
-		return MLX5_CAP_QOS(dev, esw_element_type) &
-		       ELEMENT_TYPE_CAP_MASK_VPORT;
-	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC:
-		return MLX5_CAP_QOS(dev, esw_element_type) &
-		       ELEMENT_TYPE_CAP_MASK_VPORT_TC;
-	case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC:
-		return MLX5_CAP_QOS(dev, esw_element_type) &
-		       ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC;
-	}
-	return false;
-}
-
-/* Vport QoS management */
-static void esw_create_tsar(struct mlx5_eswitch *esw)
-{
-	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
-	struct mlx5_core_dev *dev = esw->dev;
-	__be32 *attr;
-	int err;
-
-	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
-		return;
-
-	if (!element_type_supported(esw, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR))
-		return;
-
-	if (esw->qos.enabled)
-		return;
-
-	MLX5_SET(scheduling_context, tsar_ctx, element_type,
-		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
-
-	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
-	*attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16);
-
-	err = mlx5_create_scheduling_element_cmd(dev,
-						 SCHEDULING_HIERARCHY_E_SWITCH,
-						 tsar_ctx,
-						 &esw->qos.root_tsar_id);
-	if (err) {
-		esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err);
-		return;
-	}
-
-	esw->qos.enabled = true;
-}
-
-static void esw_destroy_tsar(struct mlx5_eswitch *esw)
-{
-	int err;
-
-	if (!esw->qos.enabled)
-		return;
-
-	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
-						  SCHEDULING_HIERARCHY_E_SWITCH,
-						  esw->qos.root_tsar_id);
-	if (err)
-		esw_warn(esw->dev, "E-Switch destroy TSAR failed (%d)\n", err);
-
-	esw->qos.enabled = false;
-}
-
-static int esw_vport_enable_qos(struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport,
-				u32 initial_max_rate, u32 initial_bw_share)
-{
-	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
-	struct mlx5_core_dev *dev = esw->dev;
-	void *vport_elem;
-	int err = 0;
-
-	if (!esw->qos.enabled)
-		return 0;
-
-	if (vport->qos.enabled)
-		return -EEXIST;
-
-	MLX5_SET(scheduling_context, sched_ctx, element_type,
-		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
-	vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
-				  element_attributes);
-	MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
-	MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
-		 esw->qos.root_tsar_id);
-	MLX5_SET(scheduling_context, sched_ctx, max_average_bw,
-		 initial_max_rate);
-	MLX5_SET(scheduling_context, sched_ctx, bw_share, initial_bw_share);
-
-	err = mlx5_create_scheduling_element_cmd(dev,
-						 SCHEDULING_HIERARCHY_E_SWITCH,
-						 sched_ctx,
-						 &vport->qos.esw_tsar_ix);
-	if (err) {
-		esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n",
-			 vport->vport, err);
-		return err;
-	}
-
-	vport->qos.enabled = true;
-	return 0;
-}
-
-static void esw_vport_disable_qos(struct mlx5_eswitch *esw,
-				  struct mlx5_vport *vport)
-{
-	int err;
-
-	if (!vport->qos.enabled)
-		return;
-
-	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
-						  SCHEDULING_HIERARCHY_E_SWITCH,
-						  vport->qos.esw_tsar_ix);
-	if (err)
-		esw_warn(esw->dev, "E-Switch destroy TSAR vport element failed (vport=%d,err=%d)\n",
-			 vport->vport, err);
-
-	vport->qos.enabled = false;
-}
-
-static int esw_vport_qos_config(struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport,
-				u32 max_rate, u32 bw_share)
-{
-	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
-	struct mlx5_core_dev *dev = esw->dev;
-	void *vport_elem;
-	u32 bitmask = 0;
-	int err = 0;
-
-	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
-		return -EOPNOTSUPP;
-
-	if (!vport->qos.enabled)
-		return -EIO;
-
-	MLX5_SET(scheduling_context, sched_ctx, element_type,
-		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
-	vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
-				  element_attributes);
-	MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
-	MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
-		 esw->qos.root_tsar_id);
-	MLX5_SET(scheduling_context, sched_ctx, max_average_bw,
-		 max_rate);
-	MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share);
-	bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW;
-	bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE;
-
-	err = mlx5_modify_scheduling_element_cmd(dev,
-						 SCHEDULING_HIERARCHY_E_SWITCH,
-						 sched_ctx,
-						 vport->qos.esw_tsar_ix,
-						 bitmask);
-	if (err) {
-		esw_warn(esw->dev, "E-Switch modify TSAR vport element failed (vport=%d,err=%d)\n",
-			 vport->vport, err);
-		return err;
-	}
-
-	return 0;
-}
-
-int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
-			       u32 rate_mbps)
-{
-	u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
-	struct mlx5_vport *vport;
-
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return PTR_ERR(vport);
-
-	if (!vport->qos.enabled)
-		return -EOPNOTSUPP;
-
-	MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps);
-
-	return mlx5_modify_scheduling_element_cmd(esw->dev,
-						  SCHEDULING_HIERARCHY_E_SWITCH,
-						  ctx,
-						  vport->qos.esw_tsar_ix,
-						  MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW);
-}
-
 static void node_guid_gen_from_mac(u64 *node_guid, const u8 *mac)
 {
 	((u8 *)node_guid)[7] = mac[0];
@@ -976,7 +782,7 @@ static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 		return err;
 
 	/* Attach vport to the eswitch rate limiter */
-	esw_vport_enable_qos(esw, vport, vport->qos.max_rate, vport->qos.bw_share);
+	mlx5_esw_qos_vport_enable(esw, vport, vport->qos.max_rate, vport->qos.bw_share);
 
 	if (mlx5_esw_is_manager_vport(esw, vport_num))
 		return 0;
@@ -1013,7 +819,7 @@ static void esw_vport_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport
 					      vport_num, 1,
 					      MLX5_VPORT_ADMIN_STATE_DOWN);
 
-	esw_vport_disable_qos(esw, vport);
+	mlx5_esw_qos_vport_disable(esw, vport);
 	esw_vport_cleanup_acl(esw, vport);
 }
 
@@ -1454,12 +1260,10 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int mode, int num_vfs)
 
 	mlx5_eswitch_update_num_of_vfs(esw, num_vfs);
 
-	esw_create_tsar(esw);
+	mlx5_esw_qos_create(esw);
 
 	esw->mode = mode;
 
-	mlx5_lag_update(esw->dev);
-
 	if (mode == MLX5_ESWITCH_LEGACY) {
 		err = esw_legacy_enable(esw);
 	} else {
@@ -1486,7 +1290,7 @@ abort:
 	if (mode == MLX5_ESWITCH_OFFLOADS)
 		mlx5_rescan_drivers(esw->dev);
 
-	esw_destroy_tsar(esw);
+	mlx5_esw_qos_destroy(esw);
 	mlx5_esw_acls_ns_cleanup(esw);
 	return err;
 }
@@ -1494,7 +1298,7 @@ abort:
 /**
  * mlx5_eswitch_enable - Enable eswitch
  * @esw:	Pointer to eswitch
- * @num_vfs:	Enable eswitch swich for given number of VFs.
+ * @num_vfs:	Enable eswitch switch for given number of VFs.
  *		Caller must pass num_vfs > 0 when enabling eswitch for
  *		vf vports.
  * mlx5_eswitch_enable() returns 0 on success or error code on failure.
@@ -1506,6 +1310,7 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 	if (!mlx5_esw_allowed(esw))
 		return 0;
 
+	mlx5_lag_disable_change(esw->dev);
 	down_write(&esw->mode_lock);
 	if (esw->mode == MLX5_ESWITCH_NONE) {
 		ret = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_LEGACY, num_vfs);
@@ -1519,6 +1324,7 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 			esw->esw_funcs.num_vfs = num_vfs;
 	}
 	up_write(&esw->mode_lock);
+	mlx5_lag_enable_change(esw->dev);
 	return ret;
 }
 
@@ -1550,12 +1356,10 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf)
 	old_mode = esw->mode;
 	esw->mode = MLX5_ESWITCH_NONE;
 
-	mlx5_lag_update(esw->dev);
-
 	if (old_mode == MLX5_ESWITCH_OFFLOADS)
 		mlx5_rescan_drivers(esw->dev);
 
-	esw_destroy_tsar(esw);
+	mlx5_esw_qos_destroy(esw);
 	mlx5_esw_acls_ns_cleanup(esw);
 
 	if (clear_vf)
@@ -1567,10 +1371,12 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf)
 	if (!mlx5_esw_allowed(esw))
 		return;
 
+	mlx5_lag_disable_change(esw->dev);
 	down_write(&esw->mode_lock);
 	mlx5_eswitch_disable_locked(esw, clear_vf);
 	esw->esw_funcs.num_vfs = 0;
 	up_write(&esw->mode_lock);
+	mlx5_lag_enable_change(esw->dev);
 }
 
 static int mlx5_query_hca_cap_host_pf(struct mlx5_core_dev *dev, void *out)
@@ -1759,7 +1565,9 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	ida_init(&esw->offloads.vport_metadata_ida);
 	xa_init_flags(&esw->offloads.vhca_map, XA_FLAGS_ALLOC);
 	mutex_init(&esw->state_lock);
+	lockdep_register_key(&esw->mode_lock_key);
 	init_rwsem(&esw->mode_lock);
+	lockdep_set_class(&esw->mode_lock, &esw->mode_lock_key);
 
 	esw->enabled_vports = 0;
 	esw->mode = MLX5_ESWITCH_NONE;
@@ -1793,6 +1601,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 
 	esw->dev->priv.eswitch = NULL;
 	destroy_workqueue(esw->work_queue);
+	lockdep_unregister_key(&esw->mode_lock_key);
 	mutex_destroy(&esw->state_lock);
 	WARN_ON(!xa_empty(&esw->offloads.vhca_map));
 	xa_destroy(&esw->offloads.vhca_map);
@@ -1889,8 +1698,7 @@ is_port_function_supported(struct mlx5_eswitch *esw, u16 vport_num)
 	       mlx5_esw_is_sf_vport(esw, vport_num);
 }
 
-int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink,
-					   struct devlink_port *port,
+int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port,
 					   u8 *hw_addr, int *hw_addr_len,
 					   struct netlink_ext_ack *extack)
 {
@@ -1899,7 +1707,7 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink,
 	int err = -EOPNOTSUPP;
 	u16 vport_num;
 
-	esw = mlx5_devlink_eswitch_get(devlink);
+	esw = mlx5_devlink_eswitch_get(port->devlink);
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
@@ -1923,8 +1731,7 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink,
 	return err;
 }
 
-int mlx5_devlink_port_function_hw_addr_set(struct devlink *devlink,
-					   struct devlink_port *port,
+int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port,
 					   const u8 *hw_addr, int hw_addr_len,
 					   struct netlink_ext_ack *extack)
 {
@@ -1933,7 +1740,7 @@ int mlx5_devlink_port_function_hw_addr_set(struct devlink *devlink,
 	int err = -EOPNOTSUPP;
 	u16 vport_num;
 
-	esw = mlx5_devlink_eswitch_get(devlink);
+	esw = mlx5_devlink_eswitch_get(port->devlink);
 	if (IS_ERR(esw)) {
 		NL_SET_ERR_MSG_MOD(extack, "Eswitch doesn't support set hw_addr");
 		return PTR_ERR(esw);
@@ -2049,110 +1856,6 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 	return err;
 }
 
-static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw)
-{
-	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
-	struct mlx5_vport *evport;
-	u32 max_guarantee = 0;
-	unsigned long i;
-
-	mlx5_esw_for_each_vport(esw, i, evport) {
-		if (!evport->enabled || evport->qos.min_rate < max_guarantee)
-			continue;
-		max_guarantee = evport->qos.min_rate;
-	}
-
-	if (max_guarantee)
-		return max_t(u32, max_guarantee / fw_max_bw_share, 1);
-	return 0;
-}
-
-static int normalize_vports_min_rate(struct mlx5_eswitch *esw)
-{
-	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
-	u32 divider = calculate_vports_min_rate_divider(esw);
-	struct mlx5_vport *evport;
-	u32 vport_max_rate;
-	u32 vport_min_rate;
-	unsigned long i;
-	u32 bw_share;
-	int err;
-
-	mlx5_esw_for_each_vport(esw, i, evport) {
-		if (!evport->enabled)
-			continue;
-		vport_min_rate = evport->qos.min_rate;
-		vport_max_rate = evport->qos.max_rate;
-		bw_share = 0;
-
-		if (divider)
-			bw_share = MLX5_RATE_TO_BW_SHARE(vport_min_rate,
-							 divider,
-							 fw_max_bw_share);
-
-		if (bw_share == evport->qos.bw_share)
-			continue;
-
-		err = esw_vport_qos_config(esw, evport, vport_max_rate,
-					   bw_share);
-		if (!err)
-			evport->qos.bw_share = bw_share;
-		else
-			return err;
-	}
-
-	return 0;
-}
-
-int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport,
-				u32 max_rate, u32 min_rate)
-{
-	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
-	u32 fw_max_bw_share;
-	u32 previous_min_rate;
-	bool min_rate_supported;
-	bool max_rate_supported;
-	int err = 0;
-
-	if (!mlx5_esw_allowed(esw))
-		return -EPERM;
-	if (IS_ERR(evport))
-		return PTR_ERR(evport);
-
-	fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
-	min_rate_supported = MLX5_CAP_QOS(esw->dev, esw_bw_share) &&
-				fw_max_bw_share >= MLX5_MIN_BW_SHARE;
-	max_rate_supported = MLX5_CAP_QOS(esw->dev, esw_rate_limit);
-
-	if ((min_rate && !min_rate_supported) || (max_rate && !max_rate_supported))
-		return -EOPNOTSUPP;
-
-	mutex_lock(&esw->state_lock);
-
-	if (min_rate == evport->qos.min_rate)
-		goto set_max_rate;
-
-	previous_min_rate = evport->qos.min_rate;
-	evport->qos.min_rate = min_rate;
-	err = normalize_vports_min_rate(esw);
-	if (err) {
-		evport->qos.min_rate = previous_min_rate;
-		goto unlock;
-	}
-
-set_max_rate:
-	if (max_rate == evport->qos.max_rate)
-		goto unlock;
-
-	err = esw_vport_qos_config(esw, evport, max_rate, evport->qos.bw_share);
-	if (!err)
-		evport->qos.max_rate = max_rate;
-
-unlock:
-	mutex_unlock(&esw->state_lock);
-	return err;
-}
-
 int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 				 u16 vport_num,
 				 struct ifla_vf_stats *vf_stats)
@@ -2366,10 +2069,23 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw)
  */
 void mlx5_esw_unlock(struct mlx5_eswitch *esw)
 {
+	if (!mlx5_esw_allowed(esw))
+		return;
 	up_write(&esw->mode_lock);
 }
 
 /**
+ * mlx5_esw_lock() - Take write lock on esw mode lock
+ * @esw: eswitch device.
+ */
+void mlx5_esw_lock(struct mlx5_eswitch *esw)
+{
+	if (!mlx5_esw_allowed(esw))
+		return;
+	down_write(&esw->mode_lock);
+}
+
+/**
  * mlx5_eswitch_get_total_vports - Get total vports of the eswitch
  *
  * @dev: Pointer to core device
@@ -2384,3 +2100,15 @@ u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev)
 	return mlx5_esw_allowed(esw) ? esw->total_vports : 0;
 }
 EXPORT_SYMBOL_GPL(mlx5_eswitch_get_total_vports);
+
+/**
+ * mlx5_eswitch_get_core_dev - Get the mdev device
+ * @esw : eswitch device.
+ *
+ * Return the mellanox core device which manages the eswitch.
+ */
+struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw)
+{
+	return mlx5_esw_allowed(esw) ? esw->dev : NULL;
+}
+EXPORT_SYMBOL(mlx5_eswitch_get_core_dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index d562edf5b0bc..2c7444101bb9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -46,7 +46,7 @@
 #include "lib/fs_chains.h"
 #include "sf/sf.h"
 #include "en/tc_ct.h"
-#include "esw/sample.h"
+#include "en/tc/sample.h"
 
 enum mlx5_mapped_obj_type {
 	MLX5_MAPPED_OBJ_CHAIN,
@@ -61,6 +61,7 @@ struct mlx5_mapped_obj {
 			u32 group_id;
 			u32 rate;
 			u32 trunc_size;
+			u32 tunnel_id;
 		} sample;
 	};
 };
@@ -75,17 +76,20 @@ struct mlx5_mapped_obj {
 #define MLX5_MAX_MC_PER_VPORT(dev) \
 	(1 << MLX5_CAP_GEN(dev, log_max_current_mc_list))
 
-#define MLX5_MIN_BW_SHARE 1
-
-#define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \
-	min_t(u32, max_t(u32, (rate) / (divider), MLX5_MIN_BW_SHARE), limit)
-
 #define mlx5_esw_has_fwd_fdb(dev) \
 	MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_to_table)
 
 #define esw_chains(esw) \
 	((esw)->fdb_table.offloads.esw_chains_priv)
 
+enum {
+	MAPPING_TYPE_CHAIN,
+	MAPPING_TYPE_TUNNEL,
+	MAPPING_TYPE_TUNNEL_ENC_OPTS,
+	MAPPING_TYPE_LABELS,
+	MAPPING_TYPE_ZONE,
+};
+
 struct vport_ingress {
 	struct mlx5_flow_table *acl;
 	struct mlx5_flow_handle *allow_rule;
@@ -124,6 +128,8 @@ struct vport_egress {
 		struct {
 			struct mlx5_flow_group *fwd_grp;
 			struct mlx5_flow_handle *fwd_rule;
+			struct mlx5_flow_handle *bounce_rule;
+			struct mlx5_flow_group *bounce_grp;
 		} offloads;
 	};
 };
@@ -150,8 +156,6 @@ enum mlx5_eswitch_vport_event {
 	MLX5_VPORT_PROMISC_CHANGE = BIT(3),
 };
 
-struct mlx5_esw_bridge;
-
 struct mlx5_vport {
 	struct mlx5_core_dev    *dev;
 	struct hlist_head       uc_list[MLX5_L2_ADDR_HASH_SIZE];
@@ -173,6 +177,7 @@ struct mlx5_vport {
 		u32             bw_share;
 		u32 min_rate;
 		u32 max_rate;
+		struct mlx5_esw_rate_group *group;
 	} qos;
 
 	u16 vport;
@@ -180,7 +185,6 @@ struct mlx5_vport {
 	enum mlx5_eswitch_vport_event enabled_events;
 	int index;
 	struct devlink_port *dl_port;
-	struct mlx5_esw_bridge *bridge;
 };
 
 struct mlx5_esw_indir_table;
@@ -302,7 +306,9 @@ struct mlx5_eswitch {
 
 	struct {
 		bool            enabled;
-		u32             root_tsar_id;
+		u32             root_tsar_ix;
+		struct mlx5_esw_rate_group *group0;
+		struct list_head groups; /* Protected by esw->state_lock */
 	} qos;
 
 	struct mlx5_esw_bridge_offloads *br_offloads;
@@ -315,6 +321,7 @@ struct mlx5_eswitch {
 		u32             large_group_num;
 	}  params;
 	struct blocking_notifier_head n_head;
+	struct lock_class_key mode_lock_key;
 };
 
 void esw_offloads_disable(struct mlx5_eswitch *esw);
@@ -327,8 +334,7 @@ int mlx5_esw_offloads_vport_metadata_set(struct mlx5_eswitch *esw, bool enable);
 u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw);
 void mlx5_esw_match_metadata_free(struct mlx5_eswitch *esw, u32 metadata);
 
-int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
-			       u32 rate_mbps);
+int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32 rate_mbps);
 
 /* E-Switch API */
 int mlx5_eswitch_init(struct mlx5_core_dev *dev);
@@ -351,6 +357,10 @@ int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
 				 u16 vport_num, bool setting);
 int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport,
 				u32 max_rate, u32 min_rate);
+int mlx5_esw_qos_vport_update_group(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *vport,
+				    struct mlx5_esw_rate_group *group,
+				    struct netlink_ext_ack *extack);
 int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting);
 int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting);
 int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
@@ -461,7 +471,6 @@ struct mlx5_esw_flow_attr {
 	} dests[MLX5_MAX_FLOW_FWD_VPORTS];
 	struct mlx5_rx_tun_attr *rx_tun_attr;
 	struct mlx5_pkt_reformat *decap_pkt_reformat;
-	struct mlx5_sample_attr *sample;
 };
 
 int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
@@ -475,12 +484,10 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
 					struct netlink_ext_ack *extack);
 int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink,
 					enum devlink_eswitch_encap_mode *encap);
-int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink,
-					   struct devlink_port *port,
+int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port,
 					   u8 *hw_addr, int *hw_addr_len,
 					   struct netlink_ext_ack *extack);
-int mlx5_devlink_port_function_hw_addr_set(struct devlink *devlink,
-					   struct devlink_port *port,
+int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port,
 					   const u8 *hw_addr, int hw_addr_len,
 					   struct netlink_ext_ack *extack);
 
@@ -699,11 +706,18 @@ void mlx5_esw_get(struct mlx5_core_dev *dev);
 void mlx5_esw_put(struct mlx5_core_dev *dev);
 int mlx5_esw_try_lock(struct mlx5_eswitch *esw);
 void mlx5_esw_unlock(struct mlx5_eswitch *esw);
+void mlx5_esw_lock(struct mlx5_eswitch *esw);
 
 void esw_vport_change_handle_locked(struct mlx5_vport *vport);
 
 bool mlx5_esw_offloads_controller_valid(const struct mlx5_eswitch *esw, u32 controller);
 
+int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw,
+					    struct mlx5_eswitch *slave_esw);
+void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw,
+					      struct mlx5_eswitch *slave_esw);
+int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw);
+
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
@@ -719,6 +733,9 @@ static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
+static inline void mlx5_esw_unlock(struct mlx5_eswitch *esw) { return; }
+static inline void mlx5_esw_lock(struct mlx5_eswitch *esw) { return; }
+
 static inline struct mlx5_flow_handle *
 esw_add_restore_rule(struct mlx5_eswitch *esw, u32 tag)
 {
@@ -731,6 +748,23 @@ mlx5_esw_vport_to_devlink_port_index(const struct mlx5_core_dev *dev,
 {
 	return vport_num;
 }
+
+static inline int
+mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw,
+					struct mlx5_eswitch *slave_esw)
+{
+	return 0;
+}
+
+static inline void
+mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw,
+					 struct mlx5_eswitch *slave_esw) {}
+
+static inline int
+mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw)
+{
+	return 0;
+}
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #endif /* __MLX5_ESWITCH_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 3bb71a186004..0d461e38add3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -187,12 +187,12 @@ esw_cleanup_decap_indir(struct mlx5_eswitch *esw,
 static int
 esw_setup_sampler_dest(struct mlx5_flow_destination *dest,
 		       struct mlx5_flow_act *flow_act,
-		       struct mlx5_esw_flow_attr *esw_attr,
+		       struct mlx5_flow_attr *attr,
 		       int i)
 {
 	flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 	dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER;
-	dest[i].sampler_id = esw_attr->sample->sampler_id;
+	dest[i].sampler_id = attr->sample_attr->sampler_id;
 
 	return 0;
 }
@@ -435,7 +435,7 @@ esw_setup_dests(struct mlx5_flow_destination *dest,
 		attr->flags |= MLX5_ESW_ATTR_FLAG_SRC_REWRITE;
 
 	if (attr->flags & MLX5_ESW_ATTR_FLAG_SAMPLE) {
-		esw_setup_sampler_dest(dest, flow_act, esw_attr, *i);
+		esw_setup_sampler_dest(dest, flow_act, attr, *i);
 		(*i)++;
 	} else if (attr->dest_ft) {
 		esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i);
@@ -540,10 +540,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		flow_act.modify_hdr = attr->modify_hdr;
 
-	/* esw_attr->sample is allocated only when there is a sample action */
-	if (esw_attr->sample && esw_attr->sample->sample_default_tbl) {
-		fdb = esw_attr->sample->sample_default_tbl;
-	} else if (split) {
+	if (split) {
 		fwd_attr.chain = attr->chain;
 		fwd_attr.prio = attr->prio;
 		fwd_attr.vport = esw_attr->in_rep->vport;
@@ -927,6 +924,7 @@ out:
 
 struct mlx5_flow_handle *
 mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
+				    struct mlx5_eswitch *from_esw,
 				    struct mlx5_eswitch_rep *rep,
 				    u32 sqn)
 {
@@ -945,10 +943,10 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
 	MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn);
 	/* source vport is the esw manager */
-	MLX5_SET(fte_match_set_misc, misc, source_port, rep->esw->manager_vport);
+	MLX5_SET(fte_match_set_misc, misc, source_port, from_esw->manager_vport);
 	if (MLX5_CAP_ESW(on_esw->dev, merged_eswitch))
 		MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
-			 MLX5_CAP_GEN(rep->esw->dev, vhca_id));
+			 MLX5_CAP_GEN(from_esw->dev, vhca_id));
 
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
 	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn);
@@ -964,6 +962,9 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
 	dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT;
+
 	flow_rule = mlx5_add_flow_rules(on_esw->fdb_table.offloads.slow_fdb,
 					spec, &flow_act, &dest, 1);
 	if (IS_ERR(flow_rule))
@@ -1614,7 +1615,18 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 		goto ns_err;
 	}
 
-	table_size = esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ +
+	/* To be strictly correct:
+	 *	MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ)
+	 * should be:
+	 *	esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ +
+	 *	peer_esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ
+	 * but as the peer device might not be in switchdev mode it's not
+	 * possible. We use the fact that by default FW sets max vfs and max sfs
+	 * to the same value on both devices. If it needs to be changed in the future note
+	 * the peer miss group should also be created based on the number of
+	 * total vports of the peer (currently is also uses esw->total_vports).
+	 */
+	table_size = MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ) +
 		MLX5_ESW_MISS_FLOWS + esw->total_vports + esw->esw_funcs.num_vfs;
 
 	/* create the slow path fdb with encap set, so further table instances
@@ -1671,7 +1683,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 			 source_eswitch_owner_vhca_id_valid, 1);
 	}
 
-	ix = esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ;
+	/* See comment above table_size calculation */
+	ix = MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ);
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix - 1);
 
@@ -2311,14 +2324,293 @@ void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num)
 		mlx5_esw_offloads_devlink_port_unregister(esw, vport_num);
 }
 
+static int esw_set_uplink_slave_ingress_root(struct mlx5_core_dev *master,
+					     struct mlx5_core_dev *slave)
+{
+	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)]   = {};
+	u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {};
+	struct mlx5_eswitch *esw;
+	struct mlx5_flow_root_namespace *root;
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_vport *vport;
+	int err;
+
+	MLX5_SET(set_flow_table_root_in, in, opcode,
+		 MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
+	MLX5_SET(set_flow_table_root_in, in, table_type, FS_FT_ESW_INGRESS_ACL);
+	MLX5_SET(set_flow_table_root_in, in, other_vport, 1);
+	MLX5_SET(set_flow_table_root_in, in, vport_number, MLX5_VPORT_UPLINK);
+
+	if (master) {
+		esw = master->priv.eswitch;
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+		MLX5_SET(set_flow_table_root_in, in, table_of_other_vport, 1);
+		MLX5_SET(set_flow_table_root_in, in, table_vport_number,
+			 MLX5_VPORT_UPLINK);
+
+		ns = mlx5_get_flow_vport_acl_namespace(master,
+						       MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+						       vport->index);
+		root = find_root(&ns->node);
+		mutex_lock(&root->chain_lock);
+
+		MLX5_SET(set_flow_table_root_in, in,
+			 table_eswitch_owner_vhca_id_valid, 1);
+		MLX5_SET(set_flow_table_root_in, in,
+			 table_eswitch_owner_vhca_id,
+			 MLX5_CAP_GEN(master, vhca_id));
+		MLX5_SET(set_flow_table_root_in, in, table_id,
+			 root->root_ft->id);
+	} else {
+		esw = slave->priv.eswitch;
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+		ns = mlx5_get_flow_vport_acl_namespace(slave,
+						       MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+						       vport->index);
+		root = find_root(&ns->node);
+		mutex_lock(&root->chain_lock);
+		MLX5_SET(set_flow_table_root_in, in, table_id, root->root_ft->id);
+	}
+
+	err = mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out));
+	mutex_unlock(&root->chain_lock);
+
+	return err;
+}
+
+static int esw_set_slave_root_fdb(struct mlx5_core_dev *master,
+				  struct mlx5_core_dev *slave)
+{
+	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)]   = {};
+	u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {};
+	struct mlx5_flow_root_namespace *root;
+	struct mlx5_flow_namespace *ns;
+	int err;
+
+	MLX5_SET(set_flow_table_root_in, in, opcode,
+		 MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
+	MLX5_SET(set_flow_table_root_in, in, table_type,
+		 FS_FT_FDB);
+
+	if (master) {
+		ns = mlx5_get_flow_namespace(master,
+					     MLX5_FLOW_NAMESPACE_FDB);
+		root = find_root(&ns->node);
+		mutex_lock(&root->chain_lock);
+		MLX5_SET(set_flow_table_root_in, in,
+			 table_eswitch_owner_vhca_id_valid, 1);
+		MLX5_SET(set_flow_table_root_in, in,
+			 table_eswitch_owner_vhca_id,
+			 MLX5_CAP_GEN(master, vhca_id));
+		MLX5_SET(set_flow_table_root_in, in, table_id,
+			 root->root_ft->id);
+	} else {
+		ns = mlx5_get_flow_namespace(slave,
+					     MLX5_FLOW_NAMESPACE_FDB);
+		root = find_root(&ns->node);
+		mutex_lock(&root->chain_lock);
+		MLX5_SET(set_flow_table_root_in, in, table_id,
+			 root->root_ft->id);
+	}
+
+	err = mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out));
+	mutex_unlock(&root->chain_lock);
+
+	return err;
+}
+
+static int __esw_set_master_egress_rule(struct mlx5_core_dev *master,
+					struct mlx5_core_dev *slave,
+					struct mlx5_vport *vport,
+					struct mlx5_flow_table *acl)
+{
+	struct mlx5_flow_handle *flow_rule = NULL;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+	void *misc;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			    misc_parameters);
+	MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_UPLINK);
+	MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
+		 MLX5_CAP_GEN(slave, vhca_id));
+
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+			 source_eswitch_owner_vhca_id);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+	dest.vport.num = slave->priv.eswitch->manager_vport;
+	dest.vport.vhca_id = MLX5_CAP_GEN(slave, vhca_id);
+	dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
+
+	flow_rule = mlx5_add_flow_rules(acl, spec, &flow_act,
+					&dest, 1);
+	if (IS_ERR(flow_rule))
+		err = PTR_ERR(flow_rule);
+	else
+		vport->egress.offloads.bounce_rule = flow_rule;
+
+	kvfree(spec);
+	return err;
+}
+
+static int esw_set_master_egress_rule(struct mlx5_core_dev *master,
+				      struct mlx5_core_dev *slave)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_eswitch *esw = master->priv.eswitch;
+	struct mlx5_flow_table_attr ft_attr = {
+		.max_fte = 1, .prio = 0, .level = 0,
+	};
+	struct mlx5_flow_namespace *egress_ns;
+	struct mlx5_flow_table *acl;
+	struct mlx5_flow_group *g;
+	struct mlx5_vport *vport;
+	void *match_criteria;
+	u32 *flow_group_in;
+	int err;
+
+	vport = mlx5_eswitch_get_vport(esw, esw->manager_vport);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	egress_ns = mlx5_get_flow_vport_acl_namespace(master,
+						      MLX5_FLOW_NAMESPACE_ESW_EGRESS,
+						      vport->index);
+	if (!egress_ns)
+		return -EINVAL;
+
+	if (vport->egress.acl)
+		return -EINVAL;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	acl = mlx5_create_vport_flow_table(egress_ns, &ft_attr, vport->vport);
+	if (IS_ERR(acl)) {
+		err = PTR_ERR(acl);
+		goto out;
+	}
+
+	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.source_port);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters.source_eswitch_owner_vhca_id);
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS);
+
+	MLX5_SET(create_flow_group_in, flow_group_in,
+		 source_eswitch_owner_vhca_id_valid, 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
+
+	g = mlx5_create_flow_group(acl, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		goto err_group;
+	}
+
+	err = __esw_set_master_egress_rule(master, slave, vport, acl);
+	if (err)
+		goto err_rule;
+
+	vport->egress.acl = acl;
+	vport->egress.offloads.bounce_grp = g;
+
+	kvfree(flow_group_in);
+
+	return 0;
+
+err_rule:
+	mlx5_destroy_flow_group(g);
+err_group:
+	mlx5_destroy_flow_table(acl);
+out:
+	kvfree(flow_group_in);
+	return err;
+}
+
+static void esw_unset_master_egress_rule(struct mlx5_core_dev *dev)
+{
+	struct mlx5_vport *vport;
+
+	vport = mlx5_eswitch_get_vport(dev->priv.eswitch,
+				       dev->priv.eswitch->manager_vport);
+
+	esw_acl_egress_ofld_cleanup(vport);
+}
+
+int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw,
+					    struct mlx5_eswitch *slave_esw)
+{
+	int err;
+
+	err = esw_set_uplink_slave_ingress_root(master_esw->dev,
+						slave_esw->dev);
+	if (err)
+		return -EINVAL;
+
+	err = esw_set_slave_root_fdb(master_esw->dev,
+				     slave_esw->dev);
+	if (err)
+		goto err_fdb;
+
+	err = esw_set_master_egress_rule(master_esw->dev,
+					 slave_esw->dev);
+	if (err)
+		goto err_acl;
+
+	return err;
+
+err_acl:
+	esw_set_slave_root_fdb(NULL, slave_esw->dev);
+
+err_fdb:
+	esw_set_uplink_slave_ingress_root(NULL, slave_esw->dev);
+
+	return err;
+}
+
+void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw,
+					      struct mlx5_eswitch *slave_esw)
+{
+	esw_unset_master_egress_rule(master_esw->dev);
+	esw_set_slave_root_fdb(NULL, slave_esw->dev);
+	esw_set_uplink_slave_ingress_root(NULL, slave_esw->dev);
+}
+
 #define ESW_OFFLOADS_DEVCOM_PAIR	(0)
 #define ESW_OFFLOADS_DEVCOM_UNPAIR	(1)
 
-static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw,
-				  struct mlx5_eswitch *peer_esw)
+static void mlx5_esw_offloads_rep_event_unpair(struct mlx5_eswitch *esw)
 {
+	const struct mlx5_eswitch_rep_ops *ops;
+	struct mlx5_eswitch_rep *rep;
+	unsigned long i;
+	u8 rep_type;
 
-	return esw_add_fdb_peer_miss_rules(esw, peer_esw->dev);
+	mlx5_esw_for_each_rep(esw, i, rep) {
+		rep_type = NUM_REP_TYPES;
+		while (rep_type--) {
+			ops = esw->offloads.rep_ops[rep_type];
+			if (atomic_read(&rep->rep_data[rep_type].state) == REP_LOADED &&
+			    ops->event)
+				ops->event(esw, rep, MLX5_SWITCHDEV_EVENT_UNPAIR, NULL);
+		}
+	}
 }
 
 static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw)
@@ -2326,9 +2618,42 @@ static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw)
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 	mlx5e_tc_clean_fdb_peer_flows(esw);
 #endif
+	mlx5_esw_offloads_rep_event_unpair(esw);
 	esw_del_fdb_peer_miss_rules(esw);
 }
 
+static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw,
+				  struct mlx5_eswitch *peer_esw)
+{
+	const struct mlx5_eswitch_rep_ops *ops;
+	struct mlx5_eswitch_rep *rep;
+	unsigned long i;
+	u8 rep_type;
+	int err;
+
+	err = esw_add_fdb_peer_miss_rules(esw, peer_esw->dev);
+	if (err)
+		return err;
+
+	mlx5_esw_for_each_rep(esw, i, rep) {
+		for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
+			ops = esw->offloads.rep_ops[rep_type];
+			if (atomic_read(&rep->rep_data[rep_type].state) == REP_LOADED &&
+			    ops->event) {
+				err = ops->event(esw, rep, MLX5_SWITCHDEV_EVENT_PAIR, peer_esw);
+				if (err)
+					goto err_out;
+			}
+		}
+	}
+
+	return 0;
+
+err_out:
+	mlx5_esw_offloads_unpair(esw);
+	return err;
+}
+
 static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw,
 					 struct mlx5_eswitch *peer_esw,
 					 bool pair)
@@ -2619,6 +2944,31 @@ static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
 	esw_vport_destroy_offloads_acl_tables(esw, vport);
 }
 
+int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw)
+{
+	struct mlx5_eswitch_rep *rep;
+	unsigned long i;
+	int ret;
+
+	if (!esw || esw->mode != MLX5_ESWITCH_OFFLOADS)
+		return 0;
+
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
+		return 0;
+
+	ret = mlx5_esw_offloads_rep_load(esw, MLX5_VPORT_UPLINK);
+	if (ret)
+		return ret;
+
+	mlx5_esw_for_each_rep(esw, i, rep) {
+		if (atomic_read(&rep->rep_data[REP_ETH].state) == REP_LOADED)
+			mlx5_esw_offloads_rep_load(esw, rep->vport);
+	}
+
+	return 0;
+}
+
 static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 {
 	struct mlx5_esw_indir_table *indir;
@@ -2788,6 +3138,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	struct mapping_ctx *reg_c0_obj_pool;
 	struct mlx5_vport *vport;
 	unsigned long i;
+	u64 mapping_id;
 	int err;
 
 	if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) &&
@@ -2811,9 +3162,13 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	if (err)
 		goto err_vport_metadata;
 
-	reg_c0_obj_pool = mapping_create(sizeof(struct mlx5_mapped_obj),
-					 ESW_REG_C0_USER_DATA_METADATA_MASK,
-					 true);
+	mapping_id = mlx5_query_nic_system_image_guid(esw->dev);
+
+	reg_c0_obj_pool = mapping_create_for_id(mapping_id, MAPPING_TYPE_CHAIN,
+						sizeof(struct mlx5_mapped_obj),
+						ESW_REG_C0_USER_DATA_METADATA_MASK,
+						true);
+
 	if (IS_ERR(reg_c0_obj_pool)) {
 		err = PTR_ERR(reg_c0_obj_pool);
 		goto err_pool;
@@ -2991,10 +3346,11 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 	if (esw_mode_from_devlink(mode, &mlx5_mode))
 		return -EINVAL;
 
+	mlx5_lag_disable_change(esw->dev);
 	err = mlx5_esw_try_lock(esw);
 	if (err < 0) {
 		NL_SET_ERR_MSG_MOD(extack, "Can't change mode, E-Switch is busy");
-		return err;
+		goto enable_lag;
 	}
 	cur_mlx5_mode = err;
 	err = 0;
@@ -3018,6 +3374,8 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 
 unlock:
 	mlx5_esw_unlock(esw);
+enable_lag:
+	mlx5_lag_enable_change(esw->dev);
 	return err;
 }
 
@@ -3091,8 +3449,11 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 
 	switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
 	case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
-		if (mode == DEVLINK_ESWITCH_INLINE_MODE_NONE)
+		if (mode == DEVLINK_ESWITCH_INLINE_MODE_NONE) {
+			err = 0;
 			goto out;
+		}
+
 		fallthrough;
 	case MLX5_CAP_INLINE_MODE_L2:
 		NL_SET_ERR_MSG_MOD(extack, "Inline mode can't be set");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index d713ae24d6b6..a1ac3a654962 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -27,7 +27,7 @@ static int pcie_core(struct notifier_block *, unsigned long, void *);
 static int forward_event(struct notifier_block *, unsigned long, void *);
 
 static struct mlx5_nb events_nbs_ref[] = {
-	/* Events to be proccessed by mlx5_core */
+	/* Events to be processed by mlx5_core */
 	{.nb.notifier_call = any_notifier,  .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY },
 	{.nb.notifier_call = temp_warn,     .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT },
 	{.nb.notifier_call = port_module,   .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index d5da4ab65766..306279b7f9e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -453,7 +453,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 
 	cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context);
 	MLX5_SET(cqc, cqc, log_cq_size, ilog2(cq_size));
-	MLX5_SET(cqc, cqc, c_eqn, eqn);
+	MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn);
 	MLX5_SET(cqc, cqc, uar_page, fdev->conn_res.uar->index);
 	MLX5_SET(cqc, cqc, log_page_size, conn->cq.wq_ctrl.buf.page_shift -
 			   MLX5_ADAPTER_PAGE_SHIFT);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index 0bba92cf5dc0..8ec148010d62 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -1516,7 +1516,7 @@ static int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 	mutex_lock(&fpga_xfrm->lock);
 
 	if (!fpga_xfrm->sa_ctx)
-		/* Unbounded xfrm, chane only sw attrs */
+		/* Unbounded xfrm, change only sw attrs */
 		goto change_sw_xfrm_attrs;
 
 	/* copy original hw sa */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 896a6c3dbdb7..7db8df64a60e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -152,17 +152,56 @@ static int mlx5_cmd_stub_destroy_ns(struct mlx5_flow_root_namespace *ns)
 	return 0;
 }
 
+static int mlx5_cmd_set_slave_root_fdb(struct mlx5_core_dev *master,
+				       struct mlx5_core_dev *slave,
+				       bool ft_id_valid,
+				       u32 ft_id)
+{
+	u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {};
+	struct mlx5_flow_root_namespace *root;
+	struct mlx5_flow_namespace *ns;
+
+	MLX5_SET(set_flow_table_root_in, in, opcode,
+		 MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
+	MLX5_SET(set_flow_table_root_in, in, table_type,
+		 FS_FT_FDB);
+	if (ft_id_valid) {
+		MLX5_SET(set_flow_table_root_in, in,
+			 table_eswitch_owner_vhca_id_valid, 1);
+		MLX5_SET(set_flow_table_root_in, in,
+			 table_eswitch_owner_vhca_id,
+			 MLX5_CAP_GEN(master, vhca_id));
+		MLX5_SET(set_flow_table_root_in, in, table_id,
+			 ft_id);
+	} else {
+		ns = mlx5_get_flow_namespace(slave,
+					     MLX5_FLOW_NAMESPACE_FDB);
+		root = find_root(&ns->node);
+		MLX5_SET(set_flow_table_root_in, in, table_id,
+			 root->root_ft->id);
+	}
+
+	return mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out));
+}
+
 static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 				   struct mlx5_flow_table *ft, u32 underlay_qpn,
 				   bool disconnect)
 {
 	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
+	int err;
 
 	if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
 	    underlay_qpn == 0)
 		return 0;
 
+	if (ft->type == FS_FT_FDB &&
+	    mlx5_lag_is_shared_fdb(dev) &&
+	    !mlx5_lag_is_master(dev))
+		return 0;
+
 	MLX5_SET(set_flow_table_root_in, in, opcode,
 		 MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
 	MLX5_SET(set_flow_table_root_in, in, table_type, ft->type);
@@ -177,7 +216,24 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 	MLX5_SET(set_flow_table_root_in, in, other_vport,
 		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
 
-	return mlx5_cmd_exec_in(dev, set_flow_table_root, in);
+	err = mlx5_cmd_exec_in(dev, set_flow_table_root, in);
+	if (!err &&
+	    ft->type == FS_FT_FDB &&
+	    mlx5_lag_is_shared_fdb(dev) &&
+	    mlx5_lag_is_master(dev)) {
+		err = mlx5_cmd_set_slave_root_fdb(dev,
+						  mlx5_lag_get_peer_mdev(dev),
+						  !disconnect, (!disconnect) ?
+						  ft->id : 0);
+		if (err && !disconnect) {
+			MLX5_SET(set_flow_table_root_in, in, op_mod, 0);
+			MLX5_SET(set_flow_table_root_in, in, table_id,
+				 ns->root_ft->id);
+			mlx5_cmd_exec_in(dev, set_flow_table_root, in);
+		}
+	}
+
+	return err;
 }
 
 static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index c0697e1b7118..9fe8e3c204d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -413,7 +413,7 @@ static bool check_valid_spec(const struct mlx5_flow_spec *spec)
 	return true;
 }
 
-static struct mlx5_flow_root_namespace *find_root(struct fs_node *node)
+struct mlx5_flow_root_namespace *find_root(struct fs_node *node)
 {
 	struct fs_node *root;
 	struct mlx5_flow_namespace *ns;
@@ -2343,7 +2343,7 @@ static int create_leaf_prios(struct mlx5_flow_namespace *ns, int prio,
 
 #define FLOW_TABLE_BIT_SZ 1
 #define GET_FLOW_TABLE_CAP(dev, offset) \
-	((be32_to_cpu(*((__be32 *)(dev->caps.hca_cur[MLX5_CAP_FLOW_TABLE]) +	\
+	((be32_to_cpu(*((__be32 *)(dev->caps.hca[MLX5_CAP_FLOW_TABLE]->cur) +	\
 			offset / 32)) >>					\
 	  (32 - FLOW_TABLE_BIT_SZ - (offset & 0x1f))) & FLOW_TABLE_BIT_SZ)
 static bool has_required_caps(struct mlx5_core_dev *dev, struct node_caps *caps)
@@ -2493,7 +2493,7 @@ static void set_prio_attrs_in_prio(struct fs_prio *prio, int acc_level)
 		acc_level_ns = set_prio_attrs_in_ns(ns, acc_level);
 
 		/* If this a prio with chains, and we can jump from one chain
-		 * (namepsace) to another, so we accumulate the levels
+		 * (namespace) to another, so we accumulate the levels
 		 */
 		if (prio->node.type == FS_TYPE_PRIO_CHAINS)
 			acc_level = acc_level_ns;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 7317cdeab661..98240badc342 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -294,6 +294,8 @@ void mlx5_fs_egress_acls_cleanup(struct mlx5_core_dev *dev);
 int mlx5_fs_ingress_acls_init(struct mlx5_core_dev *dev, int total_vports);
 void mlx5_fs_ingress_acls_cleanup(struct mlx5_core_dev *dev);
 
+struct mlx5_flow_root_namespace *find_root(struct fs_node *node);
+
 #define fs_get_obj(v, _node)  {v = container_of((_node), typeof(*v), node); }
 
 #define fs_list_for_each_entry(pos, root)		\
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 9abeb80ffa31..037e18dd4be0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -170,7 +170,7 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev)
 
 	/* The reset only needs to be issued by one PF. The health buffer is
 	 * shared between all functions, and will be cleared during a reset.
-	 * Check again to avoid a redundant 2nd reset. If the fatal erros was
+	 * Check again to avoid a redundant 2nd reset. If the fatal errors was
 	 * PCI related a reset won't help.
 	 */
 	fatal_error = mlx5_health_check_fatal_sensors(dev);
@@ -213,10 +213,6 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 	mutex_lock(&dev->intf_state_mutex);
 	if (!err_detected && dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
 		goto unlock;/* a previous error is still being handled */
-	if (dev->state == MLX5_DEVICE_STATE_UNINITIALIZED) {
-		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
-		goto unlock;
-	}
 
 	enter_error_state(dev, force);
 unlock:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index 0e487ec57d5c..0c8594c7df21 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -99,7 +99,9 @@ static void mlx5i_get_channels(struct net_device *dev,
 }
 
 static int mlx5i_set_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *coal)
+			      struct ethtool_coalesce *coal,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
 
@@ -107,7 +109,9 @@ static int mlx5i_set_coalesce(struct net_device *netdev,
 }
 
 static int mlx5i_get_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *coal)
+			      struct ethtool_coalesce *coal,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 7d7ed025db0d..67571e5040d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -50,7 +50,7 @@ static const struct net_device_ops mlx5i_netdev_ops = {
 	.ndo_init                = mlx5i_dev_init,
 	.ndo_uninit              = mlx5i_dev_cleanup,
 	.ndo_change_mtu          = mlx5i_change_mtu,
-	.ndo_do_ioctl            = mlx5i_ioctl,
+	.ndo_eth_ioctl            = mlx5i_ioctl,
 };
 
 /* IPoIB mlx5 netdev profile */
@@ -314,8 +314,7 @@ static void mlx5i_cleanup_tx(struct mlx5e_priv *priv)
 
 static int mlx5i_create_flow_steering(struct mlx5e_priv *priv)
 {
-	struct ttc_params ttc_params = {};
-	int tt, err;
+	int err;
 
 	priv->fs.ns = mlx5_get_flow_namespace(priv->mdev,
 					       MLX5_FLOW_NAMESPACE_KERNEL);
@@ -330,33 +329,15 @@ static int mlx5i_create_flow_steering(struct mlx5e_priv *priv)
 		priv->netdev->hw_features &= ~NETIF_F_NTUPLE;
 	}
 
-	mlx5e_set_ttc_basic_params(priv, &ttc_params);
-	mlx5e_set_inner_ttc_ft_params(&ttc_params);
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
-		ttc_params.indir_tirn[tt] = priv->inner_indir_tir[tt].tirn;
-
-	err = mlx5e_create_inner_ttc_table(priv, &ttc_params, &priv->fs.inner_ttc);
-	if (err) {
-		netdev_err(priv->netdev, "Failed to create inner ttc table, err=%d\n",
-			   err);
-		goto err_destroy_arfs_tables;
-	}
-
-	mlx5e_set_ttc_ft_params(&ttc_params);
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
-		ttc_params.indir_tirn[tt] = priv->indir_tir[tt].tirn;
-
-	err = mlx5e_create_ttc_table(priv, &ttc_params, &priv->fs.ttc);
+	err = mlx5e_create_ttc_table(priv);
 	if (err) {
 		netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n",
 			   err);
-		goto err_destroy_inner_ttc_table;
+		goto err_destroy_arfs_tables;
 	}
 
 	return 0;
 
-err_destroy_inner_ttc_table:
-	mlx5e_destroy_inner_ttc_table(priv, &priv->fs.inner_ttc);
 err_destroy_arfs_tables:
 	mlx5e_arfs_destroy_tables(priv);
 
@@ -365,17 +346,20 @@ err_destroy_arfs_tables:
 
 static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv)
 {
-	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
-	mlx5e_destroy_inner_ttc_table(priv, &priv->fs.inner_ttc);
+	mlx5e_destroy_ttc_table(priv);
 	mlx5e_arfs_destroy_tables(priv);
 }
 
 static int mlx5i_init_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 max_nch = priv->max_nch;
+	struct mlx5e_lro_param lro_param;
 	int err;
 
+	priv->rx_res = mlx5e_rx_res_alloc();
+	if (!priv->rx_res)
+		return -ENOMEM;
+
 	mlx5e_create_q_counters(priv);
 
 	err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
@@ -384,54 +368,38 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 		goto err_destroy_q_counters;
 	}
 
-	err = mlx5e_create_indirect_rqt(priv);
+	lro_param = mlx5e_get_lro_param(&priv->channels.params);
+	err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0,
+				priv->max_nch, priv->drop_rq.rqn, &lro_param,
+				priv->channels.params.num_channels);
 	if (err)
 		goto err_close_drop_rq;
 
-	err = mlx5e_create_direct_rqts(priv, priv->direct_tir, max_nch);
-	if (err)
-		goto err_destroy_indirect_rqts;
-
-	err = mlx5e_create_indirect_tirs(priv, true);
-	if (err)
-		goto err_destroy_direct_rqts;
-
-	err = mlx5e_create_direct_tirs(priv, priv->direct_tir, max_nch);
-	if (err)
-		goto err_destroy_indirect_tirs;
-
 	err = mlx5i_create_flow_steering(priv);
 	if (err)
-		goto err_destroy_direct_tirs;
+		goto err_destroy_rx_res;
 
 	return 0;
 
-err_destroy_direct_tirs:
-	mlx5e_destroy_direct_tirs(priv, priv->direct_tir, max_nch);
-err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv);
-err_destroy_direct_rqts:
-	mlx5e_destroy_direct_rqts(priv, priv->direct_tir, max_nch);
-err_destroy_indirect_rqts:
-	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+err_destroy_rx_res:
+	mlx5e_rx_res_destroy(priv->rx_res);
 err_close_drop_rq:
 	mlx5e_close_drop_rq(&priv->drop_rq);
 err_destroy_q_counters:
 	mlx5e_destroy_q_counters(priv);
+	mlx5e_rx_res_free(priv->rx_res);
+	priv->rx_res = NULL;
 	return err;
 }
 
 static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
 {
-	u16 max_nch = priv->max_nch;
-
 	mlx5i_destroy_flow_steering(priv);
-	mlx5e_destroy_direct_tirs(priv, priv->direct_tir, max_nch);
-	mlx5e_destroy_indirect_tirs(priv);
-	mlx5e_destroy_direct_rqts(priv, priv->direct_tir, max_nch);
-	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+	mlx5e_rx_res_destroy(priv->rx_res);
 	mlx5e_close_drop_rq(&priv->drop_rq);
 	mlx5e_destroy_q_counters(priv);
+	mlx5e_rx_res_free(priv->rx_res);
+	priv->rx_res = NULL;
 }
 
 /* The stats groups order is opposite to the update_stats() order calls */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index 18ee21b06a00..5308f23702bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -149,7 +149,7 @@ static const struct net_device_ops mlx5i_pkey_netdev_ops = {
 	.ndo_get_stats64         = mlx5i_get_stats,
 	.ndo_uninit              = mlx5i_pkey_dev_cleanup,
 	.ndo_change_mtu          = mlx5i_pkey_change_mtu,
-	.ndo_do_ioctl            = mlx5i_pkey_ioctl,
+	.ndo_eth_ioctl            = mlx5i_pkey_ioctl,
 };
 
 /* Child NDOs */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 5c043c5cc403..49ca57c6d31d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -32,7 +32,9 @@
 
 #include <linux/netdevice.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/eswitch.h>
 #include <linux/mlx5/vport.h>
+#include "lib/devcom.h"
 #include "mlx5_core.h"
 #include "eswitch.h"
 #include "lag.h"
@@ -45,7 +47,7 @@
 static DEFINE_SPINLOCK(lag_lock);
 
 static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1,
-			       u8 remap_port2)
+			       u8 remap_port2, bool shared_fdb)
 {
 	u32 in[MLX5_ST_SZ_DW(create_lag_in)] = {};
 	void *lag_ctx = MLX5_ADDR_OF(create_lag_in, in, ctx);
@@ -54,6 +56,7 @@ static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1,
 
 	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1);
 	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2);
+	MLX5_SET(lagc, lag_ctx, fdb_selection_mode, shared_fdb);
 
 	return mlx5_cmd_exec_in(dev, create_lag, in);
 }
@@ -224,35 +227,59 @@ void mlx5_modify_lag(struct mlx5_lag *ldev,
 }
 
 static int mlx5_create_lag(struct mlx5_lag *ldev,
-			   struct lag_tracker *tracker)
+			   struct lag_tracker *tracker,
+			   bool shared_fdb)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev;
+	u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {};
 	int err;
 
 	mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[MLX5_LAG_P1],
 				       &ldev->v2p_map[MLX5_LAG_P2]);
 
-	mlx5_core_info(dev0, "lag map port 1:%d port 2:%d",
-		       ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2]);
+	mlx5_core_info(dev0, "lag map port 1:%d port 2:%d shared_fdb:%d",
+		       ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2],
+		       shared_fdb);
 
 	err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[MLX5_LAG_P1],
-				  ldev->v2p_map[MLX5_LAG_P2]);
-	if (err)
+				  ldev->v2p_map[MLX5_LAG_P2], shared_fdb);
+	if (err) {
 		mlx5_core_err(dev0,
 			      "Failed to create LAG (%d)\n",
 			      err);
+		return err;
+	}
+
+	if (shared_fdb) {
+		err = mlx5_eswitch_offloads_config_single_fdb(dev0->priv.eswitch,
+							      dev1->priv.eswitch);
+		if (err)
+			mlx5_core_err(dev0, "Can't enable single FDB mode\n");
+		else
+			mlx5_core_info(dev0, "Operation mode is single FDB\n");
+	}
+
+	if (err) {
+		MLX5_SET(destroy_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_LAG);
+		if (mlx5_cmd_exec_in(dev0, destroy_lag, in))
+			mlx5_core_err(dev0,
+				      "Failed to deactivate RoCE LAG; driver restart required\n");
+	}
+
 	return err;
 }
 
 int mlx5_activate_lag(struct mlx5_lag *ldev,
 		      struct lag_tracker *tracker,
-		      u8 flags)
+		      u8 flags,
+		      bool shared_fdb)
 {
 	bool roce_lag = !!(flags & MLX5_LAG_FLAG_ROCE);
 	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
 	int err;
 
-	err = mlx5_create_lag(ldev, tracker);
+	err = mlx5_create_lag(ldev, tracker, shared_fdb);
 	if (err) {
 		if (roce_lag) {
 			mlx5_core_err(dev0,
@@ -266,6 +293,7 @@ int mlx5_activate_lag(struct mlx5_lag *ldev,
 	}
 
 	ldev->flags |= flags;
+	ldev->shared_fdb = shared_fdb;
 	return 0;
 }
 
@@ -277,6 +305,13 @@ static int mlx5_deactivate_lag(struct mlx5_lag *ldev)
 	int err;
 
 	ldev->flags &= ~MLX5_LAG_MODE_FLAGS;
+	mlx5_lag_mp_reset(ldev);
+
+	if (ldev->shared_fdb) {
+		mlx5_eswitch_offloads_destroy_single_fdb(ldev->pf[MLX5_LAG_P1].dev->priv.eswitch,
+							 ldev->pf[MLX5_LAG_P2].dev->priv.eswitch);
+		ldev->shared_fdb = false;
+	}
 
 	MLX5_SET(destroy_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_LAG);
 	err = mlx5_cmd_exec_in(dev0, destroy_lag, in);
@@ -333,6 +368,10 @@ static void mlx5_lag_remove_devices(struct mlx5_lag *ldev)
 		if (!ldev->pf[i].dev)
 			continue;
 
+		if (ldev->pf[i].dev->priv.flags &
+		    MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)
+			continue;
+
 		ldev->pf[i].dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
 		mlx5_rescan_drivers_locked(ldev->pf[i].dev);
 	}
@@ -342,12 +381,15 @@ static void mlx5_disable_lag(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
 	struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev;
+	bool shared_fdb = ldev->shared_fdb;
 	bool roce_lag;
 	int err;
 
 	roce_lag = __mlx5_lag_is_roce(ldev);
 
-	if (roce_lag) {
+	if (shared_fdb) {
+		mlx5_lag_remove_devices(ldev);
+	} else if (roce_lag) {
 		if (!(dev0->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) {
 			dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
 			mlx5_rescan_drivers_locked(dev0);
@@ -359,8 +401,34 @@ static void mlx5_disable_lag(struct mlx5_lag *ldev)
 	if (err)
 		return;
 
-	if (roce_lag)
+	if (shared_fdb || roce_lag)
 		mlx5_lag_add_devices(ldev);
+
+	if (shared_fdb) {
+		if (!(dev0->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV))
+			mlx5_eswitch_reload_reps(dev0->priv.eswitch);
+		if (!(dev1->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV))
+			mlx5_eswitch_reload_reps(dev1->priv.eswitch);
+	}
+}
+
+static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev)
+{
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev;
+
+	if (is_mdev_switchdev_mode(dev0) &&
+	    is_mdev_switchdev_mode(dev1) &&
+	    mlx5_eswitch_vport_match_metadata_enabled(dev0->priv.eswitch) &&
+	    mlx5_eswitch_vport_match_metadata_enabled(dev1->priv.eswitch) &&
+	    mlx5_devcom_is_paired(dev0->priv.devcom,
+				  MLX5_DEVCOM_ESW_OFFLOADS) &&
+	    MLX5_CAP_GEN(dev1, lag_native_fdb_selection) &&
+	    MLX5_CAP_ESW(dev1, root_ft_on_other_esw) &&
+	    MLX5_CAP_ESW(dev0, esw_shared_ingress_acl))
+		return true;
+
+	return false;
 }
 
 static void mlx5_do_bond(struct mlx5_lag *ldev)
@@ -371,14 +439,17 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	bool do_bond, roce_lag;
 	int err;
 
-	if (!mlx5_lag_is_ready(ldev))
-		return;
-
-	tracker = ldev->tracker;
+	if (!mlx5_lag_is_ready(ldev)) {
+		do_bond = false;
+	} else {
+		tracker = ldev->tracker;
 
-	do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev);
+		do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev);
+	}
 
 	if (do_bond && !__mlx5_lag_is_active(ldev)) {
+		bool shared_fdb = mlx5_shared_fdb_supported(ldev);
+
 		roce_lag = !mlx5_sriov_is_enabled(dev0) &&
 			   !mlx5_sriov_is_enabled(dev1);
 
@@ -388,23 +459,40 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 			   dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE;
 #endif
 
-		if (roce_lag)
+		if (shared_fdb || roce_lag)
 			mlx5_lag_remove_devices(ldev);
 
 		err = mlx5_activate_lag(ldev, &tracker,
 					roce_lag ? MLX5_LAG_FLAG_ROCE :
-					MLX5_LAG_FLAG_SRIOV);
+						   MLX5_LAG_FLAG_SRIOV,
+					shared_fdb);
 		if (err) {
-			if (roce_lag)
+			if (shared_fdb || roce_lag)
 				mlx5_lag_add_devices(ldev);
 
 			return;
-		}
-
-		if (roce_lag) {
+		} else if (roce_lag) {
 			dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
 			mlx5_rescan_drivers_locked(dev0);
 			mlx5_nic_vport_enable_roce(dev1);
+		} else if (shared_fdb) {
+			dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
+			mlx5_rescan_drivers_locked(dev0);
+
+			err = mlx5_eswitch_reload_reps(dev0->priv.eswitch);
+			if (!err)
+				err = mlx5_eswitch_reload_reps(dev1->priv.eswitch);
+
+			if (err) {
+				dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
+				mlx5_rescan_drivers_locked(dev0);
+				mlx5_deactivate_lag(ldev);
+				mlx5_lag_add_devices(ldev);
+				mlx5_eswitch_reload_reps(dev0->priv.eswitch);
+				mlx5_eswitch_reload_reps(dev1->priv.eswitch);
+				mlx5_core_err(dev0, "Failed to enable lag\n");
+				return;
+			}
 		}
 	} else if (do_bond && __mlx5_lag_is_active(ldev)) {
 		mlx5_modify_lag(ldev, &tracker);
@@ -418,21 +506,48 @@ static void mlx5_queue_bond_work(struct mlx5_lag *ldev, unsigned long delay)
 	queue_delayed_work(ldev->wq, &ldev->bond_work, delay);
 }
 
+static void mlx5_lag_lock_eswitches(struct mlx5_core_dev *dev0,
+				    struct mlx5_core_dev *dev1)
+{
+	if (dev0)
+		mlx5_esw_lock(dev0->priv.eswitch);
+	if (dev1)
+		mlx5_esw_lock(dev1->priv.eswitch);
+}
+
+static void mlx5_lag_unlock_eswitches(struct mlx5_core_dev *dev0,
+				      struct mlx5_core_dev *dev1)
+{
+	if (dev1)
+		mlx5_esw_unlock(dev1->priv.eswitch);
+	if (dev0)
+		mlx5_esw_unlock(dev0->priv.eswitch);
+}
+
 static void mlx5_do_bond_work(struct work_struct *work)
 {
 	struct delayed_work *delayed_work = to_delayed_work(work);
 	struct mlx5_lag *ldev = container_of(delayed_work, struct mlx5_lag,
 					     bond_work);
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev;
 	int status;
 
 	status = mlx5_dev_list_trylock();
 	if (!status) {
-		/* 1 sec delay. */
 		mlx5_queue_bond_work(ldev, HZ);
 		return;
 	}
 
+	if (ldev->mode_changes_in_progress) {
+		mlx5_dev_list_unlock();
+		mlx5_queue_bond_work(ldev, HZ);
+		return;
+	}
+
+	mlx5_lag_lock_eswitches(dev0, dev1);
 	mlx5_do_bond(ldev);
+	mlx5_lag_unlock_eswitches(dev0, dev1);
 	mlx5_dev_list_unlock();
 }
 
@@ -630,7 +745,7 @@ static void mlx5_ldev_remove_mdev(struct mlx5_lag *ldev,
 }
 
 /* Must be called with intf_mutex held */
-static void __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev)
+static int __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev = NULL;
 	struct mlx5_core_dev *tmp_dev;
@@ -638,7 +753,7 @@ static void __mlx5_lag_dev_add_mdev(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) != MLX5_MAX_PORTS)
-		return;
+		return 0;
 
 	tmp_dev = mlx5_get_next_phys_dev(dev);
 	if (tmp_dev)
@@ -648,15 +763,17 @@ static void __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev)
 		ldev = mlx5_lag_dev_alloc(dev);
 		if (!ldev) {
 			mlx5_core_err(dev, "Failed to alloc lag dev\n");
-			return;
+			return 0;
 		}
 	} else {
+		if (ldev->mode_changes_in_progress)
+			return -EAGAIN;
 		mlx5_ldev_get(ldev);
 	}
 
 	mlx5_ldev_add_mdev(ldev, dev);
 
-	return;
+	return 0;
 }
 
 void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev)
@@ -667,7 +784,13 @@ void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev)
 	if (!ldev)
 		return;
 
+recheck:
 	mlx5_dev_list_lock();
+	if (ldev->mode_changes_in_progress) {
+		mlx5_dev_list_unlock();
+		msleep(100);
+		goto recheck;
+	}
 	mlx5_ldev_remove_mdev(ldev, dev);
 	mlx5_dev_list_unlock();
 	mlx5_ldev_put(ldev);
@@ -675,8 +798,16 @@ void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev)
 
 void mlx5_lag_add_mdev(struct mlx5_core_dev *dev)
 {
+	int err;
+
+recheck:
 	mlx5_dev_list_lock();
-	__mlx5_lag_dev_add_mdev(dev);
+	err = __mlx5_lag_dev_add_mdev(dev);
+	if (err) {
+		mlx5_dev_list_unlock();
+		msleep(100);
+		goto recheck;
+	}
 	mlx5_dev_list_unlock();
 }
 
@@ -690,11 +821,11 @@ void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev,
 	if (!ldev)
 		return;
 
-	if (__mlx5_lag_is_active(ldev))
-		mlx5_disable_lag(ldev);
-
 	mlx5_ldev_remove_netdev(ldev, netdev);
 	ldev->flags &= ~MLX5_LAG_FLAG_READY;
+
+	if (__mlx5_lag_is_active(ldev))
+		mlx5_queue_bond_work(ldev, 0);
 }
 
 /* Must be called with intf_mutex held */
@@ -716,6 +847,7 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev,
 
 	if (i >= MLX5_MAX_PORTS)
 		ldev->flags |= MLX5_LAG_FLAG_READY;
+	mlx5_queue_bond_work(ldev, 0);
 }
 
 bool mlx5_lag_is_roce(struct mlx5_core_dev *dev)
@@ -746,6 +878,21 @@ bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_lag_is_active);
 
+bool mlx5_lag_is_master(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev;
+	bool res;
+
+	spin_lock(&lag_lock);
+	ldev = mlx5_lag_dev(dev);
+	res = ldev && __mlx5_lag_is_active(ldev) &&
+		dev == ldev->pf[MLX5_LAG_P1].dev;
+	spin_unlock(&lag_lock);
+
+	return res;
+}
+EXPORT_SYMBOL(mlx5_lag_is_master);
+
 bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
@@ -760,19 +907,50 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_lag_is_sriov);
 
-void mlx5_lag_update(struct mlx5_core_dev *dev)
+bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev;
+	bool res;
+
+	spin_lock(&lag_lock);
+	ldev = mlx5_lag_dev(dev);
+	res = ldev && __mlx5_lag_is_sriov(ldev) && ldev->shared_fdb;
+	spin_unlock(&lag_lock);
+
+	return res;
+}
+EXPORT_SYMBOL(mlx5_lag_is_shared_fdb);
+
+void mlx5_lag_disable_change(struct mlx5_core_dev *dev)
 {
+	struct mlx5_core_dev *dev0;
+	struct mlx5_core_dev *dev1;
 	struct mlx5_lag *ldev;
 
 	mlx5_dev_list_lock();
+
 	ldev = mlx5_lag_dev(dev);
-	if (!ldev)
-		goto unlock;
+	dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	dev1 = ldev->pf[MLX5_LAG_P2].dev;
 
-	mlx5_do_bond(ldev);
+	ldev->mode_changes_in_progress++;
+	if (__mlx5_lag_is_active(ldev)) {
+		mlx5_lag_lock_eswitches(dev0, dev1);
+		mlx5_disable_lag(ldev);
+		mlx5_lag_unlock_eswitches(dev0, dev1);
+	}
+	mlx5_dev_list_unlock();
+}
 
-unlock:
+void mlx5_lag_enable_change(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev;
+
+	mlx5_dev_list_lock();
+	ldev = mlx5_lag_dev(dev);
+	ldev->mode_changes_in_progress--;
 	mlx5_dev_list_unlock();
+	mlx5_queue_bond_work(ldev, 0);
 }
 
 struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
@@ -827,6 +1005,26 @@ unlock:
 }
 EXPORT_SYMBOL(mlx5_lag_get_slave_port);
 
+struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_dev *peer_dev = NULL;
+	struct mlx5_lag *ldev;
+
+	spin_lock(&lag_lock);
+	ldev = mlx5_lag_dev(dev);
+	if (!ldev)
+		goto unlock;
+
+	peer_dev = ldev->pf[MLX5_LAG_P1].dev == dev ?
+			   ldev->pf[MLX5_LAG_P2].dev :
+			   ldev->pf[MLX5_LAG_P1].dev;
+
+unlock:
+	spin_unlock(&lag_lock);
+	return peer_dev;
+}
+EXPORT_SYMBOL(mlx5_lag_get_peer_mdev);
+
 int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 				 u64 *values,
 				 int num_counters,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h
index 191392c37558..d4bae528954e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h
@@ -39,6 +39,8 @@ struct lag_tracker {
  */
 struct mlx5_lag {
 	u8                        flags;
+	int			  mode_changes_in_progress;
+	bool			  shared_fdb;
 	u8                        v2p_map[MLX5_MAX_PORTS];
 	struct kref               ref;
 	struct lag_func           pf[MLX5_MAX_PORTS];
@@ -71,7 +73,8 @@ void mlx5_modify_lag(struct mlx5_lag *ldev,
 		     struct lag_tracker *tracker);
 int mlx5_activate_lag(struct mlx5_lag *ldev,
 		      struct lag_tracker *tracker,
-		      u8 flags);
+		      u8 flags,
+		      bool shared_fdb);
 int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 				struct net_device *ndev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
index c4bf8b679541..f239b352a58a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
@@ -161,7 +161,7 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev,
 		struct lag_tracker tracker;
 
 		tracker = ldev->tracker;
-		mlx5_activate_lag(ldev, &tracker, MLX5_LAG_FLAG_MULTIPATH);
+		mlx5_activate_lag(ldev, &tracker, MLX5_LAG_FLAG_MULTIPATH, false);
 	}
 
 	mlx5_lag_set_port_affinity(ldev, MLX5_LAG_NORMAL_AFFINITY);
@@ -302,6 +302,14 @@ static int mlx5_lag_fib_event(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
+void mlx5_lag_mp_reset(struct mlx5_lag *ldev)
+{
+	/* Clear mfi, as it might become stale when a route delete event
+	 * has been missed, see mlx5_lag_fib_route_event().
+	 */
+	ldev->lag_mp.mfi = NULL;
+}
+
 int mlx5_lag_mp_init(struct mlx5_lag *ldev)
 {
 	struct lag_mp *mp = &ldev->lag_mp;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
index 258ac7b2964e..729c839397a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
@@ -21,11 +21,13 @@ struct lag_mp {
 
 #ifdef CONFIG_MLX5_ESWITCH
 
+void mlx5_lag_mp_reset(struct mlx5_lag *ldev);
 int mlx5_lag_mp_init(struct mlx5_lag *ldev);
 void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev);
 
 #else /* CONFIG_MLX5_ESWITCH */
 
+static inline void mlx5_lag_mp_reset(struct mlx5_lag *ldev) {};
 static inline int mlx5_lag_mp_init(struct mlx5_lag *ldev) { return 0; }
 static inline void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) {}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index ce696d523493..ffac8a0e7a23 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -749,7 +749,7 @@ static int mlx5_pps_event(struct notifier_block *nb,
 		} else {
 			ptp_event.type = PTP_CLOCK_EXTTS;
 		}
-		/* TODOL clock->ptp can be NULL if ptp_clock_register failes */
+		/* TODOL clock->ptp can be NULL if ptp_clock_register fails */
 		ptp_clock_event(clock->ptp, &ptp_event);
 		break;
 	case PTP_PF_PEROUT:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
new file mode 100644
index 000000000000..749d17c0057d
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
@@ -0,0 +1,602 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2021 NVIDIA CORPORATION & AFFILIATES.
+
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/mlx5/fs.h>
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+#include "lib/fs_ttc.h"
+
+#define MLX5_TTC_NUM_GROUPS	3
+#define MLX5_TTC_GROUP1_SIZE	(BIT(3) + MLX5_NUM_TUNNEL_TT)
+#define MLX5_TTC_GROUP2_SIZE	 BIT(1)
+#define MLX5_TTC_GROUP3_SIZE	 BIT(0)
+#define MLX5_TTC_TABLE_SIZE	(MLX5_TTC_GROUP1_SIZE +\
+				 MLX5_TTC_GROUP2_SIZE +\
+				 MLX5_TTC_GROUP3_SIZE)
+
+#define MLX5_INNER_TTC_NUM_GROUPS	3
+#define MLX5_INNER_TTC_GROUP1_SIZE	BIT(3)
+#define MLX5_INNER_TTC_GROUP2_SIZE	BIT(1)
+#define MLX5_INNER_TTC_GROUP3_SIZE	BIT(0)
+#define MLX5_INNER_TTC_TABLE_SIZE	(MLX5_INNER_TTC_GROUP1_SIZE +\
+					 MLX5_INNER_TTC_GROUP2_SIZE +\
+					 MLX5_INNER_TTC_GROUP3_SIZE)
+
+/* L3/L4 traffic type classifier */
+struct mlx5_ttc_table {
+	int num_groups;
+	struct mlx5_flow_table *t;
+	struct mlx5_flow_group **g;
+	struct mlx5_ttc_rule rules[MLX5_NUM_TT];
+	struct mlx5_flow_handle *tunnel_rules[MLX5_NUM_TUNNEL_TT];
+};
+
+struct mlx5_flow_table *mlx5_get_ttc_flow_table(struct mlx5_ttc_table *ttc)
+{
+	return ttc->t;
+}
+
+static void mlx5_cleanup_ttc_rules(struct mlx5_ttc_table *ttc)
+{
+	int i;
+
+	for (i = 0; i < MLX5_NUM_TT; i++) {
+		if (!IS_ERR_OR_NULL(ttc->rules[i].rule)) {
+			mlx5_del_flow_rules(ttc->rules[i].rule);
+			ttc->rules[i].rule = NULL;
+		}
+	}
+
+	for (i = 0; i < MLX5_NUM_TUNNEL_TT; i++) {
+		if (!IS_ERR_OR_NULL(ttc->tunnel_rules[i])) {
+			mlx5_del_flow_rules(ttc->tunnel_rules[i]);
+			ttc->tunnel_rules[i] = NULL;
+		}
+	}
+}
+
+struct mlx5_etype_proto {
+	u16 etype;
+	u8 proto;
+};
+
+static struct mlx5_etype_proto ttc_rules[] = {
+	[MLX5_TT_IPV4_TCP] = {
+		.etype = ETH_P_IP,
+		.proto = IPPROTO_TCP,
+	},
+	[MLX5_TT_IPV6_TCP] = {
+		.etype = ETH_P_IPV6,
+		.proto = IPPROTO_TCP,
+	},
+	[MLX5_TT_IPV4_UDP] = {
+		.etype = ETH_P_IP,
+		.proto = IPPROTO_UDP,
+	},
+	[MLX5_TT_IPV6_UDP] = {
+		.etype = ETH_P_IPV6,
+		.proto = IPPROTO_UDP,
+	},
+	[MLX5_TT_IPV4_IPSEC_AH] = {
+		.etype = ETH_P_IP,
+		.proto = IPPROTO_AH,
+	},
+	[MLX5_TT_IPV6_IPSEC_AH] = {
+		.etype = ETH_P_IPV6,
+		.proto = IPPROTO_AH,
+	},
+	[MLX5_TT_IPV4_IPSEC_ESP] = {
+		.etype = ETH_P_IP,
+		.proto = IPPROTO_ESP,
+	},
+	[MLX5_TT_IPV6_IPSEC_ESP] = {
+		.etype = ETH_P_IPV6,
+		.proto = IPPROTO_ESP,
+	},
+	[MLX5_TT_IPV4] = {
+		.etype = ETH_P_IP,
+		.proto = 0,
+	},
+	[MLX5_TT_IPV6] = {
+		.etype = ETH_P_IPV6,
+		.proto = 0,
+	},
+	[MLX5_TT_ANY] = {
+		.etype = 0,
+		.proto = 0,
+	},
+};
+
+static struct mlx5_etype_proto ttc_tunnel_rules[] = {
+	[MLX5_TT_IPV4_GRE] = {
+		.etype = ETH_P_IP,
+		.proto = IPPROTO_GRE,
+	},
+	[MLX5_TT_IPV6_GRE] = {
+		.etype = ETH_P_IPV6,
+		.proto = IPPROTO_GRE,
+	},
+	[MLX5_TT_IPV4_IPIP] = {
+		.etype = ETH_P_IP,
+		.proto = IPPROTO_IPIP,
+	},
+	[MLX5_TT_IPV6_IPIP] = {
+		.etype = ETH_P_IPV6,
+		.proto = IPPROTO_IPIP,
+	},
+	[MLX5_TT_IPV4_IPV6] = {
+		.etype = ETH_P_IP,
+		.proto = IPPROTO_IPV6,
+	},
+	[MLX5_TT_IPV6_IPV6] = {
+		.etype = ETH_P_IPV6,
+		.proto = IPPROTO_IPV6,
+	},
+
+};
+
+u8 mlx5_get_proto_by_tunnel_type(enum mlx5_tunnel_types tt)
+{
+	return ttc_tunnel_rules[tt].proto;
+}
+
+static bool mlx5_tunnel_proto_supported_rx(struct mlx5_core_dev *mdev,
+					   u8 proto_type)
+{
+	switch (proto_type) {
+	case IPPROTO_GRE:
+		return MLX5_CAP_ETH(mdev, tunnel_stateless_gre);
+	case IPPROTO_IPIP:
+	case IPPROTO_IPV6:
+		return (MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip) ||
+			MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip_rx));
+	default:
+		return false;
+	}
+}
+
+static bool mlx5_tunnel_any_rx_proto_supported(struct mlx5_core_dev *mdev)
+{
+	int tt;
+
+	for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) {
+		if (mlx5_tunnel_proto_supported_rx(mdev,
+						   ttc_tunnel_rules[tt].proto))
+			return true;
+	}
+	return false;
+}
+
+bool mlx5_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev)
+{
+	return (mlx5_tunnel_any_rx_proto_supported(mdev) &&
+		MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
+					  ft_field_support.inner_ip_version));
+}
+
+static u8 mlx5_etype_to_ipv(u16 ethertype)
+{
+	if (ethertype == ETH_P_IP)
+		return 4;
+
+	if (ethertype == ETH_P_IPV6)
+		return 6;
+
+	return 0;
+}
+
+static struct mlx5_flow_handle *
+mlx5_generate_ttc_rule(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft,
+		       struct mlx5_flow_destination *dest, u16 etype, u8 proto)
+{
+	int match_ipv_outer =
+		MLX5_CAP_FLOWTABLE_NIC_RX(dev,
+					  ft_field_support.outer_ip_version);
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+	u8 ipv;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return ERR_PTR(-ENOMEM);
+
+	if (proto) {
+		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol);
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, proto);
+	}
+
+	ipv = mlx5_etype_to_ipv(etype);
+	if (match_ipv_outer && ipv) {
+		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_version);
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_version, ipv);
+	} else if (etype) {
+		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ethertype);
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype);
+	}
+
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(dev, "%s: add rule failed\n", __func__);
+	}
+
+	kvfree(spec);
+	return err ? ERR_PTR(err) : rule;
+}
+
+static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev,
+					 struct ttc_params *params,
+					 struct mlx5_ttc_table *ttc)
+{
+	struct mlx5_flow_handle **trules;
+	struct mlx5_ttc_rule *rules;
+	struct mlx5_flow_table *ft;
+	int tt;
+	int err;
+
+	ft = ttc->t;
+	rules = ttc->rules;
+	for (tt = 0; tt < MLX5_NUM_TT; tt++) {
+		struct mlx5_ttc_rule *rule = &rules[tt];
+
+		rule->rule = mlx5_generate_ttc_rule(dev, ft, &params->dests[tt],
+						    ttc_rules[tt].etype,
+						    ttc_rules[tt].proto);
+		if (IS_ERR(rule->rule)) {
+			err = PTR_ERR(rule->rule);
+			rule->rule = NULL;
+			goto del_rules;
+		}
+		rule->default_dest = params->dests[tt];
+	}
+
+	if (!params->inner_ttc || !mlx5_tunnel_inner_ft_supported(dev))
+		return 0;
+
+	trules    = ttc->tunnel_rules;
+	for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) {
+		if (!mlx5_tunnel_proto_supported_rx(dev,
+						    ttc_tunnel_rules[tt].proto))
+			continue;
+		trules[tt] = mlx5_generate_ttc_rule(dev, ft,
+						    &params->tunnel_dests[tt],
+						    ttc_tunnel_rules[tt].etype,
+						    ttc_tunnel_rules[tt].proto);
+		if (IS_ERR(trules[tt])) {
+			err = PTR_ERR(trules[tt]);
+			trules[tt] = NULL;
+			goto del_rules;
+		}
+	}
+
+	return 0;
+
+del_rules:
+	mlx5_cleanup_ttc_rules(ttc);
+	return err;
+}
+
+static int mlx5_create_ttc_table_groups(struct mlx5_ttc_table *ttc,
+					bool use_ipv)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	int ix = 0;
+	u32 *in;
+	int err;
+	u8 *mc;
+
+	ttc->g = kcalloc(MLX5_TTC_NUM_GROUPS, sizeof(*ttc->g), GFP_KERNEL);
+	if (!ttc->g)
+		return -ENOMEM;
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in) {
+		kfree(ttc->g);
+		ttc->g = NULL;
+		return -ENOMEM;
+	}
+
+	/* L4 Group */
+	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+	MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol);
+	if (use_ipv)
+		MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_version);
+	else
+		MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype);
+	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5_TTC_GROUP1_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
+	if (IS_ERR(ttc->g[ttc->num_groups]))
+		goto err;
+	ttc->num_groups++;
+
+	/* L3 Group */
+	MLX5_SET(fte_match_param, mc, outer_headers.ip_protocol, 0);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5_TTC_GROUP2_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
+	if (IS_ERR(ttc->g[ttc->num_groups]))
+		goto err;
+	ttc->num_groups++;
+
+	/* Any Group */
+	memset(in, 0, inlen);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5_TTC_GROUP3_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
+	if (IS_ERR(ttc->g[ttc->num_groups]))
+		goto err;
+	ttc->num_groups++;
+
+	kvfree(in);
+	return 0;
+
+err:
+	err = PTR_ERR(ttc->g[ttc->num_groups]);
+	ttc->g[ttc->num_groups] = NULL;
+	kvfree(in);
+
+	return err;
+}
+
+static struct mlx5_flow_handle *
+mlx5_generate_inner_ttc_rule(struct mlx5_core_dev *dev,
+			     struct mlx5_flow_table *ft,
+			     struct mlx5_flow_destination *dest,
+			     u16 etype, u8 proto)
+{
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+	u8 ipv;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return ERR_PTR(-ENOMEM);
+
+	ipv = mlx5_etype_to_ipv(etype);
+	if (etype && ipv) {
+		spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS;
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_version);
+		MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_version, ipv);
+	}
+
+	if (proto) {
+		spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS;
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_protocol);
+		MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_protocol, proto);
+	}
+
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(dev, "%s: add inner TTC rule failed\n", __func__);
+	}
+
+	kvfree(spec);
+	return err ? ERR_PTR(err) : rule;
+}
+
+static int mlx5_generate_inner_ttc_table_rules(struct mlx5_core_dev *dev,
+					       struct ttc_params *params,
+					       struct mlx5_ttc_table *ttc)
+{
+	struct mlx5_ttc_rule *rules;
+	struct mlx5_flow_table *ft;
+	int err;
+	int tt;
+
+	ft = ttc->t;
+	rules = ttc->rules;
+
+	for (tt = 0; tt < MLX5_NUM_TT; tt++) {
+		struct mlx5_ttc_rule *rule = &rules[tt];
+
+		rule->rule = mlx5_generate_inner_ttc_rule(dev, ft,
+							  &params->dests[tt],
+							  ttc_rules[tt].etype,
+							  ttc_rules[tt].proto);
+		if (IS_ERR(rule->rule)) {
+			err = PTR_ERR(rule->rule);
+			rule->rule = NULL;
+			goto del_rules;
+		}
+		rule->default_dest = params->dests[tt];
+	}
+
+	return 0;
+
+del_rules:
+
+	mlx5_cleanup_ttc_rules(ttc);
+	return err;
+}
+
+static int mlx5_create_inner_ttc_table_groups(struct mlx5_ttc_table *ttc)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	int ix = 0;
+	u32 *in;
+	int err;
+	u8 *mc;
+
+	ttc->g = kcalloc(MLX5_INNER_TTC_NUM_GROUPS, sizeof(*ttc->g),
+			 GFP_KERNEL);
+	if (!ttc->g)
+		return -ENOMEM;
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in) {
+		kfree(ttc->g);
+		ttc->g = NULL;
+		return -ENOMEM;
+	}
+
+	/* L4 Group */
+	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+	MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_protocol);
+	MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_version);
+	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_INNER_HEADERS);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5_INNER_TTC_GROUP1_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
+	if (IS_ERR(ttc->g[ttc->num_groups]))
+		goto err;
+	ttc->num_groups++;
+
+	/* L3 Group */
+	MLX5_SET(fte_match_param, mc, inner_headers.ip_protocol, 0);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5_INNER_TTC_GROUP2_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
+	if (IS_ERR(ttc->g[ttc->num_groups]))
+		goto err;
+	ttc->num_groups++;
+
+	/* Any Group */
+	memset(in, 0, inlen);
+	MLX5_SET_CFG(in, start_flow_index, ix);
+	ix += MLX5_INNER_TTC_GROUP3_SIZE;
+	MLX5_SET_CFG(in, end_flow_index, ix - 1);
+	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
+	if (IS_ERR(ttc->g[ttc->num_groups]))
+		goto err;
+	ttc->num_groups++;
+
+	kvfree(in);
+	return 0;
+
+err:
+	err = PTR_ERR(ttc->g[ttc->num_groups]);
+	ttc->g[ttc->num_groups] = NULL;
+	kvfree(in);
+
+	return err;
+}
+
+struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
+						   struct ttc_params *params)
+{
+	struct mlx5_ttc_table *ttc;
+	int err;
+
+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
+	WARN_ON_ONCE(params->ft_attr.max_fte);
+	params->ft_attr.max_fte = MLX5_INNER_TTC_TABLE_SIZE;
+	ttc->t = mlx5_create_flow_table(params->ns, &params->ft_attr);
+	if (IS_ERR(ttc->t)) {
+		err = PTR_ERR(ttc->t);
+		kvfree(ttc);
+		return ERR_PTR(err);
+	}
+
+	err = mlx5_create_inner_ttc_table_groups(ttc);
+	if (err)
+		goto destroy_ft;
+
+	err = mlx5_generate_inner_ttc_table_rules(dev, params, ttc);
+	if (err)
+		goto destroy_ft;
+
+	return ttc;
+
+destroy_ft:
+	mlx5_destroy_ttc_table(ttc);
+	return ERR_PTR(err);
+}
+
+void mlx5_destroy_ttc_table(struct mlx5_ttc_table *ttc)
+{
+	int i;
+
+	mlx5_cleanup_ttc_rules(ttc);
+	for (i = ttc->num_groups - 1; i >= 0; i--) {
+		if (!IS_ERR_OR_NULL(ttc->g[i]))
+			mlx5_destroy_flow_group(ttc->g[i]);
+		ttc->g[i] = NULL;
+	}
+
+	kfree(ttc->g);
+	mlx5_destroy_flow_table(ttc->t);
+	kvfree(ttc);
+}
+
+struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
+					     struct ttc_params *params)
+{
+	bool match_ipv_outer =
+		MLX5_CAP_FLOWTABLE_NIC_RX(dev,
+					  ft_field_support.outer_ip_version);
+	struct mlx5_ttc_table *ttc;
+	int err;
+
+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
+	WARN_ON_ONCE(params->ft_attr.max_fte);
+	params->ft_attr.max_fte = MLX5_TTC_TABLE_SIZE;
+	ttc->t = mlx5_create_flow_table(params->ns, &params->ft_attr);
+	if (IS_ERR(ttc->t)) {
+		err = PTR_ERR(ttc->t);
+		kvfree(ttc);
+		return ERR_PTR(err);
+	}
+
+	err = mlx5_create_ttc_table_groups(ttc, match_ipv_outer);
+	if (err)
+		goto destroy_ft;
+
+	err = mlx5_generate_ttc_table_rules(dev, params, ttc);
+	if (err)
+		goto destroy_ft;
+
+	return ttc;
+
+destroy_ft:
+	mlx5_destroy_ttc_table(ttc);
+	return ERR_PTR(err);
+}
+
+int mlx5_ttc_fwd_dest(struct mlx5_ttc_table *ttc, enum mlx5_traffic_types type,
+		      struct mlx5_flow_destination *new_dest)
+{
+	return mlx5_modify_rule_destination(ttc->rules[type].rule, new_dest,
+					    NULL);
+}
+
+struct mlx5_flow_destination
+mlx5_ttc_get_default_dest(struct mlx5_ttc_table *ttc,
+			  enum mlx5_traffic_types type)
+{
+	struct mlx5_flow_destination *dest = &ttc->rules[type].default_dest;
+
+	WARN_ONCE(dest->type != MLX5_FLOW_DESTINATION_TYPE_TIR,
+		  "TTC[%d] default dest is not setup yet", type);
+
+	return *dest;
+}
+
+int mlx5_ttc_fwd_default_dest(struct mlx5_ttc_table *ttc,
+			      enum mlx5_traffic_types type)
+{
+	struct mlx5_flow_destination dest = mlx5_ttc_get_default_dest(ttc, type);
+
+	return mlx5_ttc_fwd_dest(ttc, type, &dest);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
new file mode 100644
index 000000000000..ce95be8f8382
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies. */
+
+#ifndef __ML5_FS_TTC_H__
+#define __ML5_FS_TTC_H__
+
+#include <linux/mlx5/fs.h>
+
+enum mlx5_traffic_types {
+	MLX5_TT_IPV4_TCP,
+	MLX5_TT_IPV6_TCP,
+	MLX5_TT_IPV4_UDP,
+	MLX5_TT_IPV6_UDP,
+	MLX5_TT_IPV4_IPSEC_AH,
+	MLX5_TT_IPV6_IPSEC_AH,
+	MLX5_TT_IPV4_IPSEC_ESP,
+	MLX5_TT_IPV6_IPSEC_ESP,
+	MLX5_TT_IPV4,
+	MLX5_TT_IPV6,
+	MLX5_TT_ANY,
+	MLX5_NUM_TT,
+	MLX5_NUM_INDIR_TIRS = MLX5_TT_ANY,
+};
+
+enum mlx5_tunnel_types {
+	MLX5_TT_IPV4_GRE,
+	MLX5_TT_IPV6_GRE,
+	MLX5_TT_IPV4_IPIP,
+	MLX5_TT_IPV6_IPIP,
+	MLX5_TT_IPV4_IPV6,
+	MLX5_TT_IPV6_IPV6,
+	MLX5_NUM_TUNNEL_TT,
+};
+
+struct mlx5_ttc_rule {
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_destination default_dest;
+};
+
+struct mlx5_ttc_table;
+
+struct ttc_params {
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_flow_table_attr ft_attr;
+	struct mlx5_flow_destination dests[MLX5_NUM_TT];
+	bool   inner_ttc;
+	struct mlx5_flow_destination tunnel_dests[MLX5_NUM_TUNNEL_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,
+					     struct ttc_params *params);
+void mlx5_destroy_ttc_table(struct mlx5_ttc_table *ttc);
+
+struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
+						   struct ttc_params *params);
+
+int mlx5_ttc_fwd_dest(struct mlx5_ttc_table *ttc, enum mlx5_traffic_types type,
+		      struct mlx5_flow_destination *new_dest);
+struct mlx5_flow_destination
+mlx5_ttc_get_default_dest(struct mlx5_ttc_table *ttc,
+			  enum mlx5_traffic_types type);
+int mlx5_ttc_fwd_default_dest(struct mlx5_ttc_table *ttc,
+			      enum mlx5_traffic_types type);
+
+bool mlx5_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev);
+u8 mlx5_get_proto_by_tunnel_type(enum mlx5_tunnel_types tt);
+
+#endif /* __MLX5_FS_TTC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
index 38084400ee8f..e3b0a131c3e1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
@@ -40,7 +40,7 @@
 
 struct mlx5_vxlan {
 	struct mlx5_core_dev		*mdev;
-	/* max_num_ports is usuallly 4, 16 buckets is more than enough */
+	/* max_num_ports is usually 4, 16 buckets is more than enough */
 	DECLARE_HASHTABLE(htable, 4);
 	struct mutex                    sync_lock; /* sync add/del port HW operations */
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c84ad87c99bb..79482824c64f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -252,28 +252,16 @@ static int set_dma_caps(struct pci_dev *pdev)
 {
 	int err;
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (err) {
 		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask\n");
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
 			dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting\n");
 			return err;
 		}
 	}
 
-	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (err) {
-		dev_warn(&pdev->dev,
-			 "Warning: couldn't set 64-bit consistent PCI DMA mask\n");
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (err) {
-			dev_err(&pdev->dev,
-				"Can't set consistent PCI DMA mask, aborting\n");
-			return err;
-		}
-	}
-
 	dma_set_max_seg_size(&pdev->dev, 2u * 1024 * 1024 * 1024);
 	return err;
 }
@@ -389,11 +377,11 @@ static int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev,
 
 	switch (cap_mode) {
 	case HCA_CAP_OPMOD_GET_MAX:
-		memcpy(dev->caps.hca_max[cap_type], hca_caps,
+		memcpy(dev->caps.hca[cap_type]->max, hca_caps,
 		       MLX5_UN_SZ_BYTES(hca_cap_union));
 		break;
 	case HCA_CAP_OPMOD_GET_CUR:
-		memcpy(dev->caps.hca_cur[cap_type], hca_caps,
+		memcpy(dev->caps.hca[cap_type]->cur, hca_caps,
 		       MLX5_UN_SZ_BYTES(hca_cap_union));
 		break;
 	default:
@@ -469,7 +457,7 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 		return err;
 
 	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability);
-	memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ODP],
+	memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ODP]->cur,
 	       MLX5_ST_SZ_BYTES(odp_cap));
 
 #define ODP_CAP_SET_MAX(dev, field)                                            \
@@ -514,7 +502,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 
 	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx,
 				   capability);
-	memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_GENERAL],
+	memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_GENERAL]->cur,
 	       MLX5_ST_SZ_BYTES(cmd_hca_cap));
 
 	mlx5_core_dbg(dev, "Current Pkey table size %d Setting new size %d\n",
@@ -596,7 +584,7 @@ static int handle_hca_cap_roce(struct mlx5_core_dev *dev, void *set_ctx)
 		return 0;
 
 	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability);
-	memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ROCE],
+	memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ROCE]->cur,
 	       MLX5_ST_SZ_BYTES(roce_cap));
 	MLX5_SET(roce_cap, set_hca_cap, sw_r_roce_src_udp_port, 1);
 
@@ -748,14 +736,12 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
 static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 			 const struct pci_device_id *id)
 {
-	struct mlx5_priv *priv = &dev->priv;
 	int err = 0;
 
 	mutex_init(&dev->pci_status_mutex);
 	pci_set_drvdata(dev->pdev, dev);
 
 	dev->bar_addr = pci_resource_start(pdev, 0);
-	priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev));
 
 	err = mlx5_pci_enable_device(dev);
 	if (err) {
@@ -1179,6 +1165,7 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_ec;
 	}
 
+	mlx5_lag_add_mdev(dev);
 	err = mlx5_sriov_attach(dev);
 	if (err) {
 		mlx5_core_err(dev, "sriov init failed %d\n", err);
@@ -1186,11 +1173,11 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 	}
 
 	mlx5_sf_dev_table_create(dev);
-	mlx5_lag_add_mdev(dev);
 
 	return 0;
 
 err_sriov:
+	mlx5_lag_remove_mdev(dev);
 	mlx5_ec_cleanup(dev);
 err_ec:
 	mlx5_sf_hw_table_destroy(dev);
@@ -1222,9 +1209,9 @@ err_irq_table:
 
 static void mlx5_unload(struct mlx5_core_dev *dev)
 {
-	mlx5_lag_remove_mdev(dev);
 	mlx5_sf_dev_table_destroy(dev);
 	mlx5_sriov_detach(dev);
+	mlx5_lag_remove_mdev(dev);
 	mlx5_ec_cleanup(dev);
 	mlx5_sf_hw_table_destroy(dev);
 	mlx5_vhca_event_stop(dev);
@@ -1248,11 +1235,6 @@ int mlx5_init_one(struct mlx5_core_dev *dev)
 	int err = 0;
 
 	mutex_lock(&dev->intf_state_mutex);
-	if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
-		mlx5_core_warn(dev, "interface is up, NOP\n");
-		goto out;
-	}
-	/* remove any previous indication of internal error */
 	dev->state = MLX5_DEVICE_STATE_UP;
 
 	err = mlx5_function_setup(dev, true);
@@ -1271,7 +1253,7 @@ int mlx5_init_one(struct mlx5_core_dev *dev)
 
 	set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
 
-	err = mlx5_devlink_register(priv_to_devlink(dev), dev->device);
+	err = mlx5_devlink_register(priv_to_devlink(dev));
 	if (err)
 		goto err_devlink_reg;
 
@@ -1293,7 +1275,6 @@ function_teardown:
 	mlx5_function_teardown(dev, true);
 err_function:
 	dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
-out:
 	mutex_unlock(&dev->intf_state_mutex);
 	return err;
 }
@@ -1380,6 +1361,60 @@ out:
 	mutex_unlock(&dev->intf_state_mutex);
 }
 
+static const int types[] = {
+	MLX5_CAP_GENERAL,
+	MLX5_CAP_GENERAL_2,
+	MLX5_CAP_ETHERNET_OFFLOADS,
+	MLX5_CAP_IPOIB_ENHANCED_OFFLOADS,
+	MLX5_CAP_ODP,
+	MLX5_CAP_ATOMIC,
+	MLX5_CAP_ROCE,
+	MLX5_CAP_IPOIB_OFFLOADS,
+	MLX5_CAP_FLOW_TABLE,
+	MLX5_CAP_ESWITCH_FLOW_TABLE,
+	MLX5_CAP_ESWITCH,
+	MLX5_CAP_VECTOR_CALC,
+	MLX5_CAP_QOS,
+	MLX5_CAP_DEBUG,
+	MLX5_CAP_DEV_MEM,
+	MLX5_CAP_DEV_EVENT,
+	MLX5_CAP_TLS,
+	MLX5_CAP_VDPA_EMULATION,
+	MLX5_CAP_IPSEC,
+};
+
+static void mlx5_hca_caps_free(struct mlx5_core_dev *dev)
+{
+	int type;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(types); i++) {
+		type = types[i];
+		kfree(dev->caps.hca[type]);
+	}
+}
+
+static int mlx5_hca_caps_alloc(struct mlx5_core_dev *dev)
+{
+	struct mlx5_hca_cap *cap;
+	int type;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(types); i++) {
+		cap = kzalloc(sizeof(*cap), GFP_KERNEL);
+		if (!cap)
+			goto err;
+		type = types[i];
+		dev->caps.hca[type] = cap;
+	}
+
+	return 0;
+
+err:
+	mlx5_hca_caps_free(dev);
+	return -ENOMEM;
+}
+
 int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 {
 	struct mlx5_priv *priv = &dev->priv;
@@ -1399,6 +1434,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	mutex_init(&priv->pgdir_mutex);
 	INIT_LIST_HEAD(&priv->pgdir_list);
 
+	priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev));
 	priv->dbg_root = debugfs_create_dir(dev_name(dev->device),
 					    mlx5_debugfs_root);
 	INIT_LIST_HEAD(&priv->traps);
@@ -1415,8 +1451,14 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	if (err)
 		goto err_adev_init;
 
+	err = mlx5_hca_caps_alloc(dev);
+	if (err)
+		goto err_hca_caps;
+
 	return 0;
 
+err_hca_caps:
+	mlx5_adev_cleanup(dev);
 err_adev_init:
 	mlx5_pagealloc_cleanup(dev);
 err_pagealloc_init:
@@ -1435,6 +1477,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 
+	mlx5_hca_caps_free(dev);
 	mlx5_adev_cleanup(dev);
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_health_cleanup(dev);
@@ -1452,7 +1495,7 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct devlink *devlink;
 	int err;
 
-	devlink = mlx5_devlink_alloc();
+	devlink = mlx5_devlink_alloc(&pdev->dev);
 	if (!devlink) {
 		dev_err(&pdev->dev, "devlink alloc failed\n");
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index da365b8f0141..230eab7e3bc9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -168,6 +168,8 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, struct net_device *netdev);
 void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev, struct net_device *netdev);
 void mlx5_lag_add_mdev(struct mlx5_core_dev *dev);
 void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev);
+void mlx5_lag_disable_change(struct mlx5_core_dev *dev);
+void mlx5_lag_enable_change(struct mlx5_core_dev *dev);
 
 int mlx5_events_init(struct mlx5_core_dev *dev);
 void mlx5_events_cleanup(struct mlx5_core_dev *dev);
@@ -275,4 +277,9 @@ static inline u32 mlx5_sriov_get_vf_total_msix(struct pci_dev *pdev)
 
 	return MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix);
 }
+
+bool mlx5_eth_supported(struct mlx5_core_dev *dev);
+bool mlx5_rdma_supported(struct mlx5_core_dev *dev);
+bool mlx5_vnet_supported(struct mlx5_core_dev *dev);
+
 #endif /* __MLX5_CORE_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 3465b363fc2f..c79a10b3454d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -18,7 +18,7 @@
 
 #define MLX5_SFS_PER_CTRL_IRQ 64
 #define MLX5_IRQ_CTRL_SF_MAX 8
-/* min num of vectores for SFs to be enabled */
+/* min num of vectors for SFs to be enabled */
 #define MLX5_IRQ_VEC_COMP_BASE_SF 2
 
 #define MLX5_EQ_SHARE_IRQ_MAX_COMP (8)
@@ -28,13 +28,13 @@
 #define MLX5_EQ_REFS_PER_IRQ (2)
 
 struct mlx5_irq {
-	u32 index;
 	struct atomic_notifier_head nh;
 	cpumask_var_t mask;
 	char name[MLX5_MAX_IRQ_NAME];
-	struct kref kref;
-	int irqn;
 	struct mlx5_irq_pool *pool;
+	int refcount;
+	u32 index;
+	int irqn;
 };
 
 struct mlx5_irq_pool {
@@ -138,9 +138,8 @@ out:
 	return ret;
 }
 
-static void irq_release(struct kref *kref)
+static void irq_release(struct mlx5_irq *irq)
 {
-	struct mlx5_irq *irq = container_of(kref, struct mlx5_irq, kref);
 	struct mlx5_irq_pool *pool = irq->pool;
 
 	xa_erase(&pool->irqs, irq->index);
@@ -159,10 +158,31 @@ static void irq_put(struct mlx5_irq *irq)
 	struct mlx5_irq_pool *pool = irq->pool;
 
 	mutex_lock(&pool->lock);
-	kref_put(&irq->kref, irq_release);
+	irq->refcount--;
+	if (!irq->refcount)
+		irq_release(irq);
 	mutex_unlock(&pool->lock);
 }
 
+static int irq_get_locked(struct mlx5_irq *irq)
+{
+	lockdep_assert_held(&irq->pool->lock);
+	if (WARN_ON_ONCE(!irq->refcount))
+		return 0;
+	irq->refcount++;
+	return 1;
+}
+
+static int irq_get(struct mlx5_irq *irq)
+{
+	int err;
+
+	mutex_lock(&irq->pool->lock);
+	err = irq_get_locked(irq);
+	mutex_unlock(&irq->pool->lock);
+	return err;
+}
+
 static irqreturn_t irq_int_handler(int irq, void *nh)
 {
 	atomic_notifier_call_chain(nh, 0, NULL);
@@ -215,7 +235,7 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i)
 		goto err_cpumask;
 	}
 	irq->pool = pool;
-	kref_init(&irq->kref);
+	irq->refcount = 1;
 	irq->index = i;
 	err = xa_err(xa_store(&pool->irqs, irq->index, irq, GFP_KERNEL));
 	if (err) {
@@ -235,18 +255,18 @@ err_req_irq:
 
 int mlx5_irq_attach_nb(struct mlx5_irq *irq, struct notifier_block *nb)
 {
-	int err;
+	int ret;
 
-	err = kref_get_unless_zero(&irq->kref);
-	if (WARN_ON_ONCE(!err))
+	ret = irq_get(irq);
+	if (!ret)
 		/* Something very bad happens here, we are enabling EQ
 		 * on non-existing IRQ.
 		 */
 		return -ENOENT;
-	err = atomic_notifier_chain_register(&irq->nh, nb);
-	if (err)
+	ret = atomic_notifier_chain_register(&irq->nh, nb);
+	if (ret)
 		irq_put(irq);
-	return err;
+	return ret;
 }
 
 int mlx5_irq_detach_nb(struct mlx5_irq *irq, struct notifier_block *nb)
@@ -304,10 +324,9 @@ static struct mlx5_irq *irq_pool_find_least_loaded(struct mlx5_irq_pool *pool,
 	xa_for_each_range(&pool->irqs, index, iter, start, end) {
 		if (!cpumask_equal(iter->mask, affinity))
 			continue;
-		if (kref_read(&iter->kref) < pool->min_threshold)
+		if (iter->refcount < pool->min_threshold)
 			return iter;
-		if (!irq || kref_read(&iter->kref) <
-		    kref_read(&irq->kref))
+		if (!irq || iter->refcount < irq->refcount)
 			irq = iter;
 	}
 	return irq;
@@ -322,7 +341,7 @@ static struct mlx5_irq *irq_pool_request_affinity(struct mlx5_irq_pool *pool,
 	mutex_lock(&pool->lock);
 	least_loaded_irq = irq_pool_find_least_loaded(pool, affinity);
 	if (least_loaded_irq &&
-	    kref_read(&least_loaded_irq->kref) < pool->min_threshold)
+	    least_loaded_irq->refcount < pool->min_threshold)
 		goto out;
 	new_irq = irq_pool_create_irq(pool, affinity);
 	if (IS_ERR(new_irq)) {
@@ -340,11 +359,11 @@ static struct mlx5_irq *irq_pool_request_affinity(struct mlx5_irq_pool *pool,
 	least_loaded_irq = new_irq;
 	goto unlock;
 out:
-	kref_get(&least_loaded_irq->kref);
-	if (kref_read(&least_loaded_irq->kref) > pool->max_threshold)
+	irq_get_locked(least_loaded_irq);
+	if (least_loaded_irq->refcount > pool->max_threshold)
 		mlx5_core_dbg(pool->dev, "IRQ %u overloaded, pool_name: %s, %u EQs on this irq\n",
 			      least_loaded_irq->irqn, pool->name,
-			      kref_read(&least_loaded_irq->kref) / MLX5_EQ_REFS_PER_IRQ);
+			      least_loaded_irq->refcount / MLX5_EQ_REFS_PER_IRQ);
 unlock:
 	mutex_unlock(&pool->lock);
 	return least_loaded_irq;
@@ -360,7 +379,7 @@ irq_pool_request_vector(struct mlx5_irq_pool *pool, int vecidx,
 	mutex_lock(&pool->lock);
 	irq = xa_load(&pool->irqs, vecidx);
 	if (irq) {
-		kref_get(&irq->kref);
+		irq_get_locked(irq);
 		goto unlock;
 	}
 	irq = irq_request(pool, vecidx);
@@ -427,7 +446,7 @@ out:
 		return irq;
 	mlx5_core_dbg(dev, "irq %u mapped to cpu %*pbl, %u EQs on this irq\n",
 		      irq->irqn, cpumask_pr_args(affinity),
-		      kref_read(&irq->kref) / MLX5_EQ_REFS_PER_IRQ);
+		      irq->refcount / MLX5_EQ_REFS_PER_IRQ);
 	return irq;
 }
 
@@ -459,8 +478,12 @@ 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
+	 * freeing all the IRQs, fast teardown for example. Hence, free the irqs
+	 * which might not have been freed.
+	 */
 	xa_for_each(&pool->irqs, index, irq)
-		irq_release(&irq->kref);
+		irq_release(irq);
 	xa_destroy(&pool->irqs);
 	mutex_destroy(&pool->lock);
 	kvfree(pool);
@@ -483,7 +506,7 @@ static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pf_vec)
 	if (!mlx5_sf_max_functions(dev))
 		return 0;
 	if (sf_vec < MLX5_IRQ_VEC_COMP_BASE_SF) {
-		mlx5_core_err(dev, "Not enough IRQs for SFs. SF may run at lower performance\n");
+		mlx5_core_dbg(dev, "Not enught IRQs for SFs. SF may run at lower performance\n");
 		return 0;
 	}
 
@@ -601,7 +624,7 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev)
 		return;
 
 	/* There are cases where IRQs still will be in used when we reaching
-	 * to here. Hence, making sure all the irqs are realeased.
+	 * to here. Hence, making sure all the irqs are released.
 	 */
 	irq_pools_destroy(table);
 	pci_free_irq_vectors(dev->pdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index fa0288afc0dd..871c2fbe18d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -39,7 +39,7 @@ static ssize_t sfnum_show(struct device *dev, struct device_attribute *attr, cha
 	struct auxiliary_device *adev = container_of(dev, struct auxiliary_device, dev);
 	struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", sf_dev->sfnum);
+	return sysfs_emit(buf, "%u\n", sf_dev->sfnum);
 }
 static DEVICE_ATTR_RO(sfnum);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
index 42c8ee03fe3e..052f48068dc1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
@@ -14,7 +14,7 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia
 	struct devlink *devlink;
 	int err;
 
-	devlink = mlx5_devlink_alloc();
+	devlink = mlx5_devlink_alloc(&adev->dev);
 	if (!devlink)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index 1be048769309..13891fdc607e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -164,12 +164,12 @@ static bool mlx5_sf_is_active(const struct mlx5_sf *sf)
 	return sf->hw_state == MLX5_VHCA_STATE_ACTIVE || sf->hw_state == MLX5_VHCA_STATE_IN_USE;
 }
 
-int mlx5_devlink_sf_port_fn_state_get(struct devlink *devlink, struct devlink_port *dl_port,
+int mlx5_devlink_sf_port_fn_state_get(struct devlink_port *dl_port,
 				      enum devlink_port_fn_state *state,
 				      enum devlink_port_fn_opstate *opstate,
 				      struct netlink_ext_ack *extack)
 {
-	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	struct mlx5_core_dev *dev = devlink_priv(dl_port->devlink);
 	struct mlx5_sf_table *table;
 	struct mlx5_sf *sf;
 	int err = 0;
@@ -248,11 +248,11 @@ out:
 	return err;
 }
 
-int mlx5_devlink_sf_port_fn_state_set(struct devlink *devlink, struct devlink_port *dl_port,
+int mlx5_devlink_sf_port_fn_state_set(struct devlink_port *dl_port,
 				      enum devlink_port_fn_state state,
 				      struct netlink_ext_ack *extack)
 {
-	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	struct mlx5_core_dev *dev = devlink_priv(dl_port->devlink);
 	struct mlx5_sf_table *table;
 	struct mlx5_sf *sf;
 	int err;
@@ -476,7 +476,7 @@ static void mlx5_sf_table_disable(struct mlx5_sf_table *table)
 		return;
 
 	/* Balances with refcount_set; drop the reference so that new user cmd cannot start
-	 * and new vhca event handler cannnot run.
+	 * and new vhca event handler cannot run.
 	 */
 	mlx5_sf_table_put(table);
 	wait_for_completion(&table->disable_complete);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
index 81ce13b19ee8..3a480e06ecc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
@@ -24,11 +24,11 @@ int mlx5_devlink_sf_port_new(struct devlink *devlink,
 			     unsigned int *new_port_index);
 int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index,
 			     struct netlink_ext_ack *extack);
-int mlx5_devlink_sf_port_fn_state_get(struct devlink *devlink, struct devlink_port *dl_port,
+int mlx5_devlink_sf_port_fn_state_get(struct devlink_port *dl_port,
 				      enum devlink_port_fn_state *state,
 				      enum devlink_port_fn_opstate *opstate,
 				      struct netlink_ext_ack *extack);
-int mlx5_devlink_sf_port_fn_state_set(struct devlink *devlink, struct devlink_port *dl_port,
+int mlx5_devlink_sf_port_fn_state_set(struct devlink_port *dl_port,
 				      enum devlink_port_fn_state state,
 				      struct netlink_ext_ack *extack);
 #else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 6475ba35cf6b..a5b9f65db23c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -18,12 +18,39 @@ enum dr_action_valid_state {
 	DR_ACTION_STATE_ENCAP,
 	DR_ACTION_STATE_DECAP,
 	DR_ACTION_STATE_MODIFY_HDR,
-	DR_ACTION_STATE_MODIFY_VLAN,
+	DR_ACTION_STATE_POP_VLAN,
+	DR_ACTION_STATE_PUSH_VLAN,
 	DR_ACTION_STATE_NON_TERM,
 	DR_ACTION_STATE_TERM,
 	DR_ACTION_STATE_MAX,
 };
 
+static const char * const action_type_to_str[] = {
+	[DR_ACTION_TYP_TNL_L2_TO_L2] = "DR_ACTION_TYP_TNL_L2_TO_L2",
+	[DR_ACTION_TYP_L2_TO_TNL_L2] = "DR_ACTION_TYP_L2_TO_TNL_L2",
+	[DR_ACTION_TYP_TNL_L3_TO_L2] = "DR_ACTION_TYP_TNL_L3_TO_L2",
+	[DR_ACTION_TYP_L2_TO_TNL_L3] = "DR_ACTION_TYP_L2_TO_TNL_L3",
+	[DR_ACTION_TYP_DROP] = "DR_ACTION_TYP_DROP",
+	[DR_ACTION_TYP_QP] = "DR_ACTION_TYP_QP",
+	[DR_ACTION_TYP_FT] = "DR_ACTION_TYP_FT",
+	[DR_ACTION_TYP_CTR] = "DR_ACTION_TYP_CTR",
+	[DR_ACTION_TYP_TAG] = "DR_ACTION_TYP_TAG",
+	[DR_ACTION_TYP_MODIFY_HDR] = "DR_ACTION_TYP_MODIFY_HDR",
+	[DR_ACTION_TYP_VPORT] = "DR_ACTION_TYP_VPORT",
+	[DR_ACTION_TYP_POP_VLAN] = "DR_ACTION_TYP_POP_VLAN",
+	[DR_ACTION_TYP_PUSH_VLAN] = "DR_ACTION_TYP_PUSH_VLAN",
+	[DR_ACTION_TYP_INSERT_HDR] = "DR_ACTION_TYP_INSERT_HDR",
+	[DR_ACTION_TYP_REMOVE_HDR] = "DR_ACTION_TYP_REMOVE_HDR",
+	[DR_ACTION_TYP_MAX] = "DR_ACTION_UNKNOWN",
+};
+
+static const char *dr_action_id_to_str(enum mlx5dr_action_type action_id)
+{
+	if (action_id > DR_ACTION_TYP_MAX)
+		action_id = DR_ACTION_TYP_MAX;
+	return action_type_to_str[action_id];
+}
+
 static const enum dr_action_valid_state
 next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] = {
 	[DR_ACTION_DOMAIN_NIC_INGRESS] = {
@@ -39,8 +66,10 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_REMOVE_HDR]	= DR_ACTION_STATE_DECAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
-			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
 		},
 		[DR_ACTION_STATE_DECAP] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
@@ -53,7 +82,8 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
-			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
 		},
 		[DR_ACTION_STATE_ENCAP] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
@@ -73,20 +103,31 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
 		},
-		[DR_ACTION_STATE_MODIFY_VLAN] = {
+		[DR_ACTION_STATE_POP_VLAN] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_QP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_SAMPLER]		= DR_ACTION_STATE_TERM,
-			[DR_ACTION_TYP_TAG]		= DR_ACTION_STATE_MODIFY_VLAN,
-			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_MODIFY_VLAN,
-			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_TAG]		= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 		},
+		[DR_ACTION_STATE_PUSH_VLAN] = {
+			[DR_ACTION_TYP_QP]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_SAMPLER]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_TAG]		= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+		},
 		[DR_ACTION_STATE_NON_TERM] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_QP]		= DR_ACTION_STATE_TERM,
@@ -99,8 +140,10 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_REMOVE_HDR]	= DR_ACTION_STATE_DECAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
-			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
 		},
 		[DR_ACTION_STATE_TERM] = {
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_TERM,
@@ -115,8 +158,16 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_REMOVE_HDR]	= DR_ACTION_STATE_DECAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
-			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
+		},
+		[DR_ACTION_STATE_DECAP] = {
+			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_SAMPLER]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_DECAP,
 		},
 		[DR_ACTION_STATE_ENCAP] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
@@ -132,14 +183,25 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
-			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
+		},
+		[DR_ACTION_STATE_POP_VLAN] = {
+			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_SAMPLER]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 		},
-		[DR_ACTION_STATE_MODIFY_VLAN] = {
+		[DR_ACTION_STATE_PUSH_VLAN] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_SAMPLER]		= DR_ACTION_STATE_TERM,
-			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_MODIFY_VLAN,
-			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
@@ -152,8 +214,10 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_REMOVE_HDR]	= DR_ACTION_STATE_DECAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
-			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
 		},
 		[DR_ACTION_STATE_TERM] = {
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_TERM,
@@ -170,8 +234,10 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_REMOVE_HDR]	= DR_ACTION_STATE_DECAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
-			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 		},
 		[DR_ACTION_STATE_DECAP] = {
@@ -180,11 +246,12 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_DECAP,
 			[DR_ACTION_TYP_SAMPLER]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
-			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
 		},
 		[DR_ACTION_STATE_ENCAP] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
@@ -203,13 +270,26 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
 		},
-		[DR_ACTION_STATE_MODIFY_VLAN] = {
+		[DR_ACTION_STATE_POP_VLAN] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_SAMPLER]		= DR_ACTION_STATE_TERM,
-			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
-			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
+		},
+		[DR_ACTION_STATE_PUSH_VLAN] = {
+			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_SAMPLER]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_PUSH_VLAN,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
@@ -226,8 +306,10 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_REMOVE_HDR]	= DR_ACTION_STATE_DECAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
-			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 		},
 		[DR_ACTION_STATE_TERM] = {
@@ -244,8 +326,17 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
-			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_REMOVE_HDR]	= DR_ACTION_STATE_DECAP,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
+		},
+		[DR_ACTION_STATE_DECAP] = {
+			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_DECAP,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_SAMPLER]		= DR_ACTION_STATE_TERM,
 		},
 		[DR_ACTION_STATE_ENCAP] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
@@ -262,15 +353,27 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
-			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
+		},
+		[DR_ACTION_STATE_POP_VLAN] = {
+			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_SAMPLER]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 		},
-		[DR_ACTION_STATE_MODIFY_VLAN] = {
+		[DR_ACTION_STATE_PUSH_VLAN] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_SAMPLER]		= DR_ACTION_STATE_TERM,
-			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
-			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_PUSH_VLAN,
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
@@ -285,7 +388,9 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
-			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
+			[DR_ACTION_TYP_REMOVE_HDR]	= DR_ACTION_STATE_DECAP,
+			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_PUSH_VLAN,
+			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_POP_VLAN,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 		},
 		[DR_ACTION_STATE_TERM] = {
@@ -314,6 +419,9 @@ dr_action_reformat_to_action_type(enum mlx5dr_action_reformat_type reformat_type
 	case DR_ACTION_REFORMAT_TYP_INSERT_HDR:
 		*action_type = DR_ACTION_TYP_INSERT_HDR;
 		break;
+	case DR_ACTION_REFORMAT_TYP_REMOVE_HDR:
+		*action_type = DR_ACTION_TYP_REMOVE_HDR;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -326,7 +434,7 @@ dr_action_reformat_to_action_type(enum mlx5dr_action_reformat_type reformat_type
  * the new size of the STEs array, rule with actions.
  */
 static void dr_actions_apply(struct mlx5dr_domain *dmn,
-			     enum mlx5dr_ste_entry_type ste_type,
+			     enum mlx5dr_domain_nic_type nic_type,
 			     u8 *action_type_set,
 			     u8 *last_ste,
 			     struct mlx5dr_ste_actions_attr *attr,
@@ -335,7 +443,7 @@ static void dr_actions_apply(struct mlx5dr_domain *dmn,
 	struct mlx5dr_ste_ctx *ste_ctx = dmn->ste_ctx;
 	u32 added_stes = 0;
 
-	if (ste_type == MLX5DR_STE_TYPE_RX)
+	if (nic_type == DR_DOMAIN_NIC_TYPE_RX)
 		mlx5dr_ste_set_actions_rx(ste_ctx, dmn, action_type_set,
 					  last_ste, attr, &added_stes);
 	else
@@ -347,7 +455,7 @@ static void dr_actions_apply(struct mlx5dr_domain *dmn,
 
 static enum dr_action_domain
 dr_action_get_action_domain(enum mlx5dr_domain_type domain,
-			    enum mlx5dr_ste_entry_type ste_type)
+			    enum mlx5dr_domain_nic_type nic_type)
 {
 	switch (domain) {
 	case MLX5DR_DOMAIN_TYPE_NIC_RX:
@@ -355,7 +463,7 @@ dr_action_get_action_domain(enum mlx5dr_domain_type domain,
 	case MLX5DR_DOMAIN_TYPE_NIC_TX:
 		return DR_ACTION_DOMAIN_NIC_EGRESS;
 	case MLX5DR_DOMAIN_TYPE_FDB:
-		if (ste_type == MLX5DR_STE_TYPE_RX)
+		if (nic_type == DR_DOMAIN_NIC_TYPE_RX)
 			return DR_ACTION_DOMAIN_FDB_INGRESS;
 		return DR_ACTION_DOMAIN_FDB_EGRESS;
 	default:
@@ -421,6 +529,18 @@ static int dr_action_handle_cs_recalc(struct mlx5dr_domain *dmn,
 	return 0;
 }
 
+static void dr_action_print_sequence(struct mlx5dr_domain *dmn,
+				     struct mlx5dr_action *actions[],
+				     int last_idx)
+{
+	int i;
+
+	for (i = 0; i <= last_idx; i++)
+		mlx5dr_err(dmn, "< %s (%d) > ",
+			   dr_action_id_to_str(actions[i]->action_type),
+			   actions[i]->action_type);
+}
+
 #define WITH_VLAN_NUM_HW_ACTIONS 6
 
 int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
@@ -431,7 +551,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 				 u32 *new_hw_ste_arr_sz)
 {
 	struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn;
-	bool rx_rule = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX;
+	bool rx_rule = nic_dmn->type == DR_DOMAIN_NIC_TYPE_RX;
 	struct mlx5dr_domain *dmn = matcher->tbl->dmn;
 	u8 action_type_set[DR_ACTION_TYP_MAX] = {};
 	struct mlx5dr_ste_actions_attr attr = {};
@@ -445,7 +565,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 	attr.gvmi = dmn->info.caps.gvmi;
 	attr.hit_gvmi = dmn->info.caps.gvmi;
 	attr.final_icm_addr = nic_dmn->default_icm_addr;
-	action_domain = dr_action_get_action_domain(dmn->type, nic_dmn->ste_type);
+	action_domain = dr_action_get_action_domain(dmn->type, nic_dmn->type);
 
 	for (i = 0; i < num_actions; i++) {
 		struct mlx5dr_action_dest_tbl *dest_tbl;
@@ -467,11 +587,11 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 				if (dest_tbl->tbl->dmn != dmn) {
 					mlx5dr_err(dmn,
 						   "Destination table belongs to a different domain\n");
-					goto out_invalid_arg;
+					return -EINVAL;
 				}
 				if (dest_tbl->tbl->level <= matcher->tbl->level) {
-					mlx5_core_warn_once(dmn->mdev,
-							    "Connecting table to a lower/same level destination table\n");
+					mlx5_core_dbg_once(dmn->mdev,
+							   "Connecting table to a lower/same level destination table\n");
 					mlx5dr_dbg(dmn,
 						   "Connecting table at level %d to a destination table at level %d\n",
 						   matcher->tbl->level,
@@ -509,7 +629,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 			break;
 		case DR_ACTION_TYP_QP:
 			mlx5dr_info(dmn, "Domain doesn't support QP\n");
-			goto out_invalid_arg;
+			return -EOPNOTSUPP;
 		case DR_ACTION_TYP_CTR:
 			attr.ctr_id = action->ctr->ctr_id +
 				action->ctr->offeset;
@@ -536,7 +656,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 			if (rx_rule &&
 			    !(dmn->ste_ctx->actions_caps & DR_STE_CTX_ACTION_CAP_RX_ENCAP)) {
 				mlx5dr_info(dmn, "Device doesn't support Encap on RX\n");
-				goto out_invalid_arg;
+				return -EOPNOTSUPP;
 			}
 			attr.reformat.size = action->reformat->size;
 			attr.reformat.id = action->reformat->id;
@@ -549,48 +669,66 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 			attr.hit_gvmi = action->vport->caps->vhca_gvmi;
 			dest_action = action;
 			if (rx_rule) {
-				/* Loopback on WIRE vport is not supported */
-				if (action->vport->caps->num == WIRE_PORT)
-					goto out_invalid_arg;
-
+				if (action->vport->caps->num == WIRE_PORT) {
+					mlx5dr_dbg(dmn, "Device doesn't support Loopback on WIRE vport\n");
+					return -EOPNOTSUPP;
+				}
 				attr.final_icm_addr = action->vport->caps->icm_address_rx;
 			} else {
 				attr.final_icm_addr = action->vport->caps->icm_address_tx;
 			}
 			break;
 		case DR_ACTION_TYP_POP_VLAN:
+			if (!rx_rule && !(dmn->ste_ctx->actions_caps &
+					  DR_STE_CTX_ACTION_CAP_TX_POP)) {
+				mlx5dr_dbg(dmn, "Device doesn't support POP VLAN action on TX\n");
+				return -EOPNOTSUPP;
+			}
+
 			max_actions_type = MLX5DR_MAX_VLANS;
 			attr.vlans.count++;
 			break;
 		case DR_ACTION_TYP_PUSH_VLAN:
+			if (rx_rule && !(dmn->ste_ctx->actions_caps &
+					 DR_STE_CTX_ACTION_CAP_RX_PUSH)) {
+				mlx5dr_dbg(dmn, "Device doesn't support PUSH VLAN action on RX\n");
+				return -EOPNOTSUPP;
+			}
+
 			max_actions_type = MLX5DR_MAX_VLANS;
-			if (attr.vlans.count == MLX5DR_MAX_VLANS)
+			if (attr.vlans.count == MLX5DR_MAX_VLANS) {
+				mlx5dr_dbg(dmn, "Max VLAN push/pop count exceeded\n");
 				return -EINVAL;
+			}
 
 			attr.vlans.headers[attr.vlans.count++] = action->push_vlan->vlan_hdr;
 			break;
 		case DR_ACTION_TYP_INSERT_HDR:
+		case DR_ACTION_TYP_REMOVE_HDR:
 			attr.reformat.size = action->reformat->size;
 			attr.reformat.id = action->reformat->id;
 			attr.reformat.param_0 = action->reformat->param_0;
 			attr.reformat.param_1 = action->reformat->param_1;
 			break;
 		default:
-			goto out_invalid_arg;
+			mlx5dr_err(dmn, "Unsupported action type %d\n", action_type);
+			return -EINVAL;
 		}
 
 		/* Check action duplication */
 		if (++action_type_set[action_type] > max_actions_type) {
 			mlx5dr_err(dmn, "Action type %d supports only max %d time(s)\n",
 				   action_type, max_actions_type);
-			goto out_invalid_arg;
+			return -EINVAL;
 		}
 
 		/* Check action state machine is valid */
 		if (dr_action_validate_and_get_next_state(action_domain,
 							  action_type,
 							  &state)) {
-			mlx5dr_err(dmn, "Invalid action sequence provided\n");
+			mlx5dr_err(dmn, "Invalid action (gvmi: %d, is_rx: %d) sequence provided:",
+				   attr.gvmi, rx_rule);
+			dr_action_print_sequence(dmn, actions, i);
 			return -EOPNOTSUPP;
 		}
 	}
@@ -614,16 +752,13 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 	}
 
 	dr_actions_apply(dmn,
-			 nic_dmn->ste_type,
+			 nic_dmn->type,
 			 action_type_set,
 			 last_ste,
 			 &attr,
 			 new_hw_ste_arr_sz);
 
 	return 0;
-
-out_invalid_arg:
-	return -EINVAL;
 }
 
 static unsigned int action_size[DR_ACTION_TYP_MAX] = {
@@ -638,6 +773,7 @@ static unsigned int action_size[DR_ACTION_TYP_MAX] = {
 	[DR_ACTION_TYP_VPORT]        = sizeof(struct mlx5dr_action_vport),
 	[DR_ACTION_TYP_PUSH_VLAN]    = sizeof(struct mlx5dr_action_push_vlan),
 	[DR_ACTION_TYP_INSERT_HDR]   = sizeof(struct mlx5dr_action_reformat),
+	[DR_ACTION_TYP_REMOVE_HDR]   = sizeof(struct mlx5dr_action_reformat),
 	[DR_ACTION_TYP_SAMPLER]      = sizeof(struct mlx5dr_action_sampler),
 };
 
@@ -709,7 +845,8 @@ dec_ref:
 struct mlx5dr_action *
 mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn,
 				   struct mlx5dr_action_dest *dests,
-				   u32 num_of_dests)
+				   u32 num_of_dests,
+				   bool ignore_flow_level)
 {
 	struct mlx5dr_cmd_flow_destination_hw_info *hw_dests;
 	struct mlx5dr_action **ref_actions;
@@ -776,7 +913,8 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn,
 				      num_of_dests,
 				      reformat_req,
 				      &action->dest_tbl->fw_tbl.id,
-				      &action->dest_tbl->fw_tbl.group_id);
+				      &action->dest_tbl->fw_tbl.group_id,
+				      ignore_flow_level);
 	if (ret)
 		goto free_action;
 
@@ -884,11 +1022,23 @@ dr_action_verify_reformat_params(enum mlx5dr_action_type reformat_type,
 				 size_t data_sz,
 				 void *data)
 {
-	if ((!data && data_sz) || (data && !data_sz) ||
-	    ((reformat_param_0 || reformat_param_1) &&
-	     reformat_type != DR_ACTION_TYP_INSERT_HDR) ||
-	    reformat_type > DR_ACTION_TYP_INSERT_HDR) {
-		mlx5dr_dbg(dmn, "Invalid reformat parameter!\n");
+	if (reformat_type == DR_ACTION_TYP_INSERT_HDR) {
+		if ((!data && data_sz) || (data && !data_sz) ||
+		    MLX5_CAP_GEN_2(dmn->mdev, max_reformat_insert_size) < data_sz ||
+		    MLX5_CAP_GEN_2(dmn->mdev, max_reformat_insert_offset) < reformat_param_1) {
+			mlx5dr_dbg(dmn, "Invalid reformat parameters for INSERT_HDR\n");
+			goto out_err;
+		}
+	} else if (reformat_type == DR_ACTION_TYP_REMOVE_HDR) {
+		if (data ||
+		    MLX5_CAP_GEN_2(dmn->mdev, max_reformat_remove_size) < data_sz ||
+		    MLX5_CAP_GEN_2(dmn->mdev, max_reformat_remove_offset) < reformat_param_1) {
+			mlx5dr_dbg(dmn, "Invalid reformat parameters for REMOVE_HDR\n");
+			goto out_err;
+		}
+	} else if (reformat_param_0 || reformat_param_1 ||
+		   reformat_type > DR_ACTION_TYP_REMOVE_HDR) {
+		mlx5dr_dbg(dmn, "Invalid reformat parameters\n");
 		goto out_err;
 	}
 
@@ -987,7 +1137,6 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn,
 		return 0;
 	}
 	case DR_ACTION_TYP_INSERT_HDR:
-	{
 		ret = mlx5dr_cmd_create_reformat_ctx(dmn->mdev,
 						     MLX5_REFORMAT_TYPE_INSERT_HDR,
 						     reformat_param_0,
@@ -1002,7 +1151,12 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn,
 		action->reformat->param_0 = reformat_param_0;
 		action->reformat->param_1 = reformat_param_1;
 		return 0;
-	}
+	case DR_ACTION_TYP_REMOVE_HDR:
+		action->reformat->id = 0;
+		action->reformat->size = data_sz;
+		action->reformat->param_0 = reformat_param_0;
+		action->reformat->param_1 = reformat_param_1;
+		return 0;
 	default:
 		mlx5dr_info(dmn, "Reformat type is not supported %d\n", action->action_type);
 		return -EINVAL;
@@ -1658,6 +1812,7 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action)
 		}
 		break;
 	case DR_ACTION_TYP_TNL_L2_TO_L2:
+	case DR_ACTION_TYP_REMOVE_HDR:
 		refcount_dec(&action->reformat->dmn->refcount);
 		break;
 	case DR_ACTION_TYP_TNL_L3_TO_L2:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
index 54e1f5438bbe..56307283bf9b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
@@ -655,6 +655,7 @@ int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(set_fte_in, in, table_type, ft->type);
 	MLX5_SET(set_fte_in, in, table_id, ft->id);
 	MLX5_SET(set_fte_in, in, flow_index, fte->index);
+	MLX5_SET(set_fte_in, in, ignore_flow_level, fte->ignore_flow_level);
 	if (ft->vport) {
 		MLX5_SET(set_fte_in, in, vport_number, ft->vport);
 		MLX5_SET(set_fte_in, in, other_vport, 1);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
index 7091b1be84ef..0fe159809ba1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
@@ -245,7 +245,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev,
 			return -ENOTSUPP;
 
 		dmn->info.supp_sw_steering = true;
-		dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX;
+		dmn->info.rx.type = DR_DOMAIN_NIC_TYPE_RX;
 		dmn->info.rx.default_icm_addr = dmn->info.caps.nic_rx_drop_address;
 		dmn->info.rx.drop_icm_addr = dmn->info.caps.nic_rx_drop_address;
 		break;
@@ -254,7 +254,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev,
 			return -ENOTSUPP;
 
 		dmn->info.supp_sw_steering = true;
-		dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX;
+		dmn->info.tx.type = DR_DOMAIN_NIC_TYPE_TX;
 		dmn->info.tx.default_icm_addr = dmn->info.caps.nic_tx_allow_address;
 		dmn->info.tx.drop_icm_addr = dmn->info.caps.nic_tx_drop_address;
 		break;
@@ -265,8 +265,8 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev,
 		if (!DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, fdb))
 			return -ENOTSUPP;
 
-		dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX;
-		dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX;
+		dmn->info.rx.type = DR_DOMAIN_NIC_TYPE_RX;
+		dmn->info.tx.type = DR_DOMAIN_NIC_TYPE_TX;
 		vport_cap = mlx5dr_get_vport_cap(&dmn->info.caps, 0);
 		if (!vport_cap) {
 			mlx5dr_err(dmn, "Failed to get esw manager vport\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
index 7ccfd40586ce..0d6f86eb248b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
@@ -103,7 +103,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn,
 			    int num_dest,
 			    bool reformat_req,
 			    u32 *tbl_id,
-			    u32 *group_id)
+			    u32 *group_id,
+			    bool ignore_flow_level)
 {
 	struct mlx5dr_cmd_create_flow_table_attr ft_attr = {};
 	struct mlx5dr_cmd_fte_info fte_info = {};
@@ -137,6 +138,7 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn,
 	fte_info.dests_size = num_dest;
 	fte_info.val = val;
 	fte_info.dest_arr = dest;
+	fte_info.ignore_flow_level = ignore_flow_level;
 
 	ret = mlx5dr_cmd_set_fte(dmn->mdev, 0, 0, &ft_info, *group_id, &fte_info);
 	if (ret) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
index 6f6191d1d5a6..b5409cc021d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
@@ -396,13 +396,14 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 	struct mlx5dr_domain *dmn = matcher->tbl->dmn;
 	struct mlx5dr_ste_ctx *ste_ctx = dmn->ste_ctx;
 	struct mlx5dr_match_param mask = {};
+	bool allow_empty_match = false;
 	struct mlx5dr_ste_build *sb;
 	bool inner, rx;
 	int idx = 0;
 	int ret, i;
 
 	sb = nic_matcher->ste_builder_arr[outer_ipv][inner_ipv];
-	rx = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX;
+	rx = nic_dmn->type == DR_DOMAIN_NIC_TYPE_RX;
 
 	/* Create a temporary mask to track and clear used mask fields */
 	if (matcher->match_criteria & DR_MATCHER_CRITERIA_OUTER)
@@ -428,6 +429,16 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 	if (ret)
 		return ret;
 
+	/* Optimize RX pipe by reducing source port match, since
+	 * the FDB RX part is connected only to the wire.
+	 */
+	if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB &&
+	    rx && mask.misc.source_port) {
+		mask.misc.source_port = 0;
+		mask.misc.source_eswitch_owner_vhca_id = 0;
+		allow_empty_match = true;
+	}
+
 	/* Outer */
 	if (matcher->match_criteria & (DR_MATCHER_CRITERIA_OUTER |
 				       DR_MATCHER_CRITERIA_MISC |
@@ -619,7 +630,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 	}
 
 	/* Empty matcher, takes all */
-	if (matcher->match_criteria == DR_MATCHER_CRITERIA_EMPTY)
+	if ((!idx && allow_empty_match) ||
+	    matcher->match_criteria == DR_MATCHER_CRITERIA_EMPTY)
 		mlx5dr_ste_build_empty_always_hit(&sb[idx++], rx);
 
 	if (idx == 0) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index 43356fad53de..aca80efc28fa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -81,6 +81,7 @@ dr_rule_create_collision_entry(struct mlx5dr_matcher *matcher,
 	}
 
 	ste->ste_chain_location = orig_ste->ste_chain_location;
+	ste->htbl->pointing_ste = orig_ste->htbl->pointing_ste;
 
 	/* In collision entry, all members share the same miss_list_head */
 	ste->htbl->miss_list = mlx5dr_ste_get_miss_list(orig_ste);
@@ -185,6 +186,9 @@ dr_rule_rehash_handle_collision(struct mlx5dr_matcher *matcher,
 	if (!new_ste)
 		return NULL;
 
+	/* Update collision pointing STE */
+	new_ste->htbl->pointing_ste = col_ste->htbl->pointing_ste;
+
 	/* In collision entry, all members share the same miss_list_head */
 	new_ste->htbl->miss_list = mlx5dr_ste_get_miss_list(col_ste);
 
@@ -212,7 +216,7 @@ static void dr_rule_rehash_copy_ste_ctrl(struct mlx5dr_matcher *matcher,
 	new_ste->next_htbl = cur_ste->next_htbl;
 	new_ste->ste_chain_location = cur_ste->ste_chain_location;
 
-	if (!mlx5dr_ste_is_last_in_rule(nic_matcher, new_ste->ste_chain_location))
+	if (new_ste->next_htbl)
 		new_ste->next_htbl->pointing_ste = new_ste;
 
 	/* We need to copy the refcount since this ste
@@ -220,10 +224,8 @@ static void dr_rule_rehash_copy_ste_ctrl(struct mlx5dr_matcher *matcher,
 	 */
 	new_ste->refcount = cur_ste->refcount;
 
-	/* Link old STEs rule_mem list to the new ste */
-	mlx5dr_rule_update_rule_member(cur_ste, new_ste);
-	INIT_LIST_HEAD(&new_ste->rule_list);
-	list_splice_tail_init(&cur_ste->rule_list, &new_ste->rule_list);
+	/* Link old STEs rule to the new ste */
+	mlx5dr_rule_set_last_member(cur_ste->rule_rx_tx, new_ste, false);
 }
 
 static struct mlx5dr_ste *
@@ -404,7 +406,7 @@ dr_rule_rehash_htbl(struct mlx5dr_rule *rule,
 	info.miss_icm_addr = nic_matcher->e_anchor->chunk->icm_addr;
 	mlx5dr_ste_set_formatted_ste(dmn->ste_ctx,
 				     dmn->info.caps.gvmi,
-				     nic_dmn,
+				     nic_dmn->type,
 				     new_htbl,
 				     formatted_ste,
 				     &info);
@@ -581,34 +583,66 @@ free_action_members:
 	return -ENOMEM;
 }
 
-/* While the pointer of ste is no longer valid, like while moving ste to be
- * the first in the miss_list, and to be in the origin table,
- * all rule-members that are attached to this ste should update their ste member
- * to the new pointer
- */
-void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *ste,
-				    struct mlx5dr_ste *new_ste)
+void mlx5dr_rule_set_last_member(struct mlx5dr_rule_rx_tx *nic_rule,
+				 struct mlx5dr_ste *ste,
+				 bool force)
 {
-	struct mlx5dr_rule_member *rule_mem;
+	/* Update rule member is usually done for the last STE or during rule
+	 * creation to recover from mid-creation failure (for this peruse the
+	 * force flag is used)
+	 */
+	if (ste->next_htbl && !force)
+		return;
 
-	list_for_each_entry(rule_mem, &ste->rule_list, use_ste_list)
-		rule_mem->ste = new_ste;
+	/* Update is required since each rule keeps track of its last STE */
+	ste->rule_rx_tx = nic_rule;
+	nic_rule->last_rule_ste = ste;
+}
+
+static struct mlx5dr_ste *dr_rule_get_pointed_ste(struct mlx5dr_ste *curr_ste)
+{
+	struct mlx5dr_ste *first_ste;
+
+	first_ste = list_first_entry(mlx5dr_ste_get_miss_list(curr_ste),
+				     struct mlx5dr_ste, miss_list_node);
+
+	return first_ste->htbl->pointing_ste;
+}
+
+int mlx5dr_rule_get_reverse_rule_members(struct mlx5dr_ste **ste_arr,
+					 struct mlx5dr_ste *curr_ste,
+					 int *num_of_stes)
+{
+	bool first = false;
+
+	*num_of_stes = 0;
+
+	if (!curr_ste)
+		return -ENOENT;
+
+	/* Iterate from last to first */
+	while (!first) {
+		first = curr_ste->ste_chain_location == 1;
+		ste_arr[*num_of_stes] = curr_ste;
+		*num_of_stes += 1;
+		curr_ste = dr_rule_get_pointed_ste(curr_ste);
+	}
+
+	return 0;
 }
 
 static void dr_rule_clean_rule_members(struct mlx5dr_rule *rule,
 				       struct mlx5dr_rule_rx_tx *nic_rule)
 {
-	struct mlx5dr_rule_member *rule_mem;
-	struct mlx5dr_rule_member *tmp_mem;
+	struct mlx5dr_ste *ste_arr[DR_RULE_MAX_STES + DR_ACTION_MAX_STES];
+	struct mlx5dr_ste *curr_ste = nic_rule->last_rule_ste;
+	int i;
 
-	if (list_empty(&nic_rule->rule_members_list))
+	if (mlx5dr_rule_get_reverse_rule_members(ste_arr, curr_ste, &i))
 		return;
-	list_for_each_entry_safe(rule_mem, tmp_mem, &nic_rule->rule_members_list, list) {
-		list_del(&rule_mem->list);
-		list_del(&rule_mem->use_ste_list);
-		mlx5dr_ste_put(rule_mem->ste, rule->matcher, nic_rule->nic_matcher);
-		kvfree(rule_mem);
-	}
+
+	while (i--)
+		mlx5dr_ste_put(ste_arr[i], rule->matcher, nic_rule->nic_matcher);
 }
 
 static u16 dr_get_bits_per_mask(u16 byte_mask)
@@ -628,43 +662,25 @@ static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl,
 				      struct mlx5dr_domain_rx_tx *nic_dmn)
 {
 	struct mlx5dr_ste_htbl_ctrl *ctrl = &htbl->ctrl;
+	int threshold;
 
 	if (dmn->info.max_log_sw_icm_sz <= htbl->chunk_size)
 		return false;
 
-	if (!ctrl->may_grow)
+	if (!mlx5dr_ste_htbl_may_grow(htbl))
 		return false;
 
 	if (dr_get_bits_per_mask(htbl->byte_mask) * BITS_PER_BYTE <= htbl->chunk_size)
 		return false;
 
-	if (ctrl->num_of_collisions >= ctrl->increase_threshold &&
-	    (ctrl->num_of_valid_entries - ctrl->num_of_collisions) >= ctrl->increase_threshold)
+	threshold = mlx5dr_ste_htbl_increase_threshold(htbl);
+	if (ctrl->num_of_collisions >= threshold &&
+	    (ctrl->num_of_valid_entries - ctrl->num_of_collisions) >= threshold)
 		return true;
 
 	return false;
 }
 
-static int dr_rule_add_member(struct mlx5dr_rule_rx_tx *nic_rule,
-			      struct mlx5dr_ste *ste)
-{
-	struct mlx5dr_rule_member *rule_mem;
-
-	rule_mem = kvzalloc(sizeof(*rule_mem), GFP_KERNEL);
-	if (!rule_mem)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&rule_mem->list);
-	INIT_LIST_HEAD(&rule_mem->use_ste_list);
-
-	rule_mem->ste = ste;
-	list_add_tail(&rule_mem->list, &nic_rule->rule_members_list);
-
-	list_add_tail(&rule_mem->use_ste_list, &ste->rule_list);
-
-	return 0;
-}
-
 static int dr_rule_handle_action_stes(struct mlx5dr_rule *rule,
 				      struct mlx5dr_rule_rx_tx *nic_rule,
 				      struct list_head *send_ste_list,
@@ -679,15 +695,13 @@ static int dr_rule_handle_action_stes(struct mlx5dr_rule *rule,
 	struct mlx5dr_domain *dmn = matcher->tbl->dmn;
 	u8 *curr_hw_ste, *prev_hw_ste;
 	struct mlx5dr_ste *action_ste;
-	int i, k, ret;
+	int i, k;
 
 	/* Two cases:
 	 * 1. num_of_builders is equal to new_hw_ste_arr_sz, the action in the ste
 	 * 2. num_of_builders is less then new_hw_ste_arr_sz, new ste was added
 	 *    to support the action.
 	 */
-	if (num_of_builders == new_hw_ste_arr_sz)
-		return 0;
 
 	for (i = num_of_builders, k = 0; i < new_hw_ste_arr_sz; i++, k++) {
 		curr_hw_ste = hw_ste_arr + i * DR_STE_SIZE;
@@ -700,6 +714,10 @@ static int dr_rule_handle_action_stes(struct mlx5dr_rule *rule,
 
 		mlx5dr_ste_get(action_ste);
 
+		action_ste->htbl->pointing_ste = last_ste;
+		last_ste->next_htbl = action_ste->htbl;
+		last_ste = action_ste;
+
 		/* While free ste we go over the miss list, so add this ste to the list */
 		list_add_tail(&action_ste->miss_list_node,
 			      mlx5dr_ste_get_miss_list(action_ste));
@@ -713,21 +731,19 @@ static int dr_rule_handle_action_stes(struct mlx5dr_rule *rule,
 		mlx5dr_ste_set_hit_addr_by_next_htbl(dmn->ste_ctx,
 						     prev_hw_ste,
 						     action_ste->htbl);
-		ret = dr_rule_add_member(nic_rule, action_ste);
-		if (ret) {
-			mlx5dr_dbg(dmn, "Failed adding rule member\n");
-			goto free_ste_info;
-		}
+
+		mlx5dr_rule_set_last_member(nic_rule, action_ste, true);
+
 		mlx5dr_send_fill_and_append_ste_send_info(action_ste, DR_STE_SIZE, 0,
 							  curr_hw_ste,
 							  ste_info_arr[k],
 							  send_ste_list, false);
 	}
 
+	last_ste->next_htbl = NULL;
+
 	return 0;
 
-free_ste_info:
-	kfree(ste_info_arr[k]);
 err_exit:
 	mlx5dr_ste_put(action_ste, matcher, nic_matcher);
 	return -ENOMEM;
@@ -846,9 +862,9 @@ again:
 			new_htbl = dr_rule_rehash(rule, nic_rule, cur_htbl,
 						  ste_location, send_ste_list);
 			if (!new_htbl) {
-				mlx5dr_htbl_put(cur_htbl);
 				mlx5dr_err(dmn, "Failed creating rehash table, htbl-log_size: %d\n",
 					   cur_htbl->chunk_size);
+				mlx5dr_htbl_put(cur_htbl);
 			} else {
 				cur_htbl = new_htbl;
 			}
@@ -1015,12 +1031,12 @@ static enum mlx5dr_ipv dr_rule_get_ipv(struct mlx5dr_match_spec *spec)
 }
 
 static bool dr_rule_skip(enum mlx5dr_domain_type domain,
-			 enum mlx5dr_ste_entry_type ste_type,
+			 enum mlx5dr_domain_nic_type nic_type,
 			 struct mlx5dr_match_param *mask,
 			 struct mlx5dr_match_param *value,
 			 u32 flow_source)
 {
-	bool rx = ste_type == MLX5DR_STE_TYPE_RX;
+	bool rx = nic_type == DR_DOMAIN_NIC_TYPE_RX;
 
 	if (domain != MLX5DR_DOMAIN_TYPE_FDB)
 		return false;
@@ -1065,9 +1081,7 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
 	nic_matcher = nic_rule->nic_matcher;
 	nic_dmn = nic_matcher->nic_tbl->nic_dmn;
 
-	INIT_LIST_HEAD(&nic_rule->rule_members_list);
-
-	if (dr_rule_skip(dmn->type, nic_dmn->ste_type, &matcher->mask, param,
+	if (dr_rule_skip(dmn->type, nic_dmn->type, &matcher->mask, param,
 			 rule->flow_source))
 		return 0;
 
@@ -1121,14 +1135,8 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
 
 		cur_htbl = ste->next_htbl;
 
-		/* Keep all STEs in the rule struct */
-		ret = dr_rule_add_member(nic_rule, ste);
-		if (ret) {
-			mlx5dr_dbg(dmn, "Failed adding rule member index %d\n", i);
-			goto free_ste;
-		}
-
 		mlx5dr_ste_get(ste);
+		mlx5dr_rule_set_last_member(nic_rule, ste, true);
 	}
 
 	/* Connect actions */
@@ -1153,8 +1161,6 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
 
 	return 0;
 
-free_ste:
-	mlx5dr_ste_put(ste, matcher, nic_matcher);
 free_rule:
 	dr_rule_clean_rule_members(rule, nic_rule);
 	/* Clean all ste_info's */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 9df0e73d1c35..bfb14b4b1906 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -325,10 +325,14 @@ static int dr_handle_pending_wc(struct mlx5dr_domain *dmn,
 
 	do {
 		ne = dr_poll_cq(send_ring->cq, 1);
-		if (ne < 0)
+		if (unlikely(ne < 0)) {
+			mlx5_core_warn_once(dmn->mdev, "SMFS QPN 0x%x is disabled/limited",
+					    send_ring->qp->qpn);
+			send_ring->err_state = true;
 			return ne;
-		else if (ne == 1)
+		} else if (ne == 1) {
 			send_ring->pending_wqe -= send_ring->signal_th;
+		}
 	} while (is_drain && send_ring->pending_wqe);
 
 	return 0;
@@ -361,6 +365,14 @@ static int dr_postsend_icm_data(struct mlx5dr_domain *dmn,
 	u32 buff_offset;
 	int ret;
 
+	if (unlikely(dmn->mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR ||
+		     send_ring->err_state)) {
+		mlx5_core_dbg_once(dmn->mdev,
+				   "Skipping post send: QP err state: %d, device state: %d\n",
+				   send_ring->err_state, dmn->mdev->state);
+		return 0;
+	}
+
 	spin_lock(&send_ring->lock);
 
 	ret = dr_handle_pending_wc(dmn, send_ring);
@@ -620,6 +632,7 @@ static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev,
 
 	MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt);
 	MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry);
+	MLX5_SET(qpc, qpc, primary_address_path.ack_timeout, 0x8); /* ~1ms */
 
 	MLX5_SET(rtr2rts_qp_in, in, opcode, MLX5_CMD_OP_RTR2RTS_QP);
 	MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->qpn);
@@ -789,7 +802,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 
 	cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context);
 	MLX5_SET(cqc, cqc, log_cq_size, ilog2(ncqe));
-	MLX5_SET(cqc, cqc, c_eqn, eqn);
+	MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn);
 	MLX5_SET(cqc, cqc, uar_page, uar->index);
 	MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
 		 MLX5_ADAPTER_PAGE_SHIFT);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
index 9b1529137cba..1cdfe4fccc7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
@@ -172,9 +172,6 @@ static void dr_ste_replace(struct mlx5dr_ste *dst, struct mlx5dr_ste *src)
 		dst->next_htbl->pointing_ste = dst;
 
 	dst->refcount = src->refcount;
-
-	INIT_LIST_HEAD(&dst->rule_list);
-	list_splice_tail_init(&src->rule_list, &dst->rule_list);
 }
 
 /* Free ste which is the head and the only one in miss_list */
@@ -233,12 +230,12 @@ dr_ste_replace_head_ste(struct mlx5dr_matcher_rx_tx *nic_matcher,
 	/* Remove from the miss_list the next_ste before copy */
 	list_del_init(&next_ste->miss_list_node);
 
-	/* All rule-members that use next_ste should know about that */
-	mlx5dr_rule_update_rule_member(next_ste, ste);
-
 	/* Move data from next into ste */
 	dr_ste_replace(ste, next_ste);
 
+	/* Update the rule on STE change */
+	mlx5dr_rule_set_last_member(next_ste->rule_rx_tx, ste, false);
+
 	/* Copy all 64 hw_ste bytes */
 	memcpy(hw_ste, ste->hw_ste, DR_STE_SIZE_REDUCED);
 	sb_idx = ste->ste_chain_location - 1;
@@ -382,14 +379,15 @@ void mlx5dr_ste_prepare_for_postsend(struct mlx5dr_ste_ctx *ste_ctx,
 /* Init one ste as a pattern for ste data array */
 void mlx5dr_ste_set_formatted_ste(struct mlx5dr_ste_ctx *ste_ctx,
 				  u16 gvmi,
-				  struct mlx5dr_domain_rx_tx *nic_dmn,
+				  enum mlx5dr_domain_nic_type nic_type,
 				  struct mlx5dr_ste_htbl *htbl,
 				  u8 *formatted_ste,
 				  struct mlx5dr_htbl_connect_info *connect_info)
 {
+	bool is_rx = nic_type == DR_DOMAIN_NIC_TYPE_RX;
 	struct mlx5dr_ste ste = {};
 
-	ste_ctx->ste_init(formatted_ste, htbl->lu_type, nic_dmn->ste_type, gvmi);
+	ste_ctx->ste_init(formatted_ste, htbl->lu_type, is_rx, gvmi);
 	ste.hw_ste = formatted_ste;
 
 	if (connect_info->type == CONNECT_HIT)
@@ -408,7 +406,7 @@ int mlx5dr_ste_htbl_init_and_postsend(struct mlx5dr_domain *dmn,
 
 	mlx5dr_ste_set_formatted_ste(dmn->ste_ctx,
 				     dmn->info.caps.gvmi,
-				     nic_dmn,
+				     nic_dmn->type,
 				     htbl,
 				     formatted_ste,
 				     connect_info);
@@ -466,21 +464,6 @@ free_table:
 	return -ENOENT;
 }
 
-static void dr_ste_set_ctrl(struct mlx5dr_ste_htbl *htbl)
-{
-	struct mlx5dr_ste_htbl_ctrl *ctrl = &htbl->ctrl;
-	int num_of_entries;
-
-	htbl->ctrl.may_grow = true;
-
-	if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1 || !htbl->byte_mask)
-		htbl->ctrl.may_grow = false;
-
-	/* Threshold is 50%, one is added to table of size 1 */
-	num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(htbl->chunk_size);
-	ctrl->increase_threshold = (num_of_entries + 1) / 2;
-}
-
 struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool,
 					      enum mlx5dr_icm_chunk_size chunk_size,
 					      u16 lu_type, u16 byte_mask)
@@ -513,11 +496,9 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool,
 		ste->refcount = 0;
 		INIT_LIST_HEAD(&ste->miss_list_node);
 		INIT_LIST_HEAD(&htbl->miss_list[i]);
-		INIT_LIST_HEAD(&ste->rule_list);
 	}
 
 	htbl->chunk_size = chunk_size;
-	dr_ste_set_ctrl(htbl);
 	return htbl;
 
 out_free_htbl:
@@ -649,6 +630,7 @@ int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher,
 			     u8 *ste_arr)
 {
 	struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn;
+	bool is_rx = nic_dmn->type == DR_DOMAIN_NIC_TYPE_RX;
 	struct mlx5dr_domain *dmn = matcher->tbl->dmn;
 	struct mlx5dr_ste_ctx *ste_ctx = dmn->ste_ctx;
 	struct mlx5dr_ste_build *sb;
@@ -663,7 +645,7 @@ int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher,
 	for (i = 0; i < nic_matcher->num_of_builders; i++) {
 		ste_ctx->ste_init(ste_arr,
 				  sb->lu_type,
-				  nic_dmn->ste_type,
+				  is_rx,
 				  dmn->info.caps.gvmi);
 
 		mlx5dr_ste_set_bit_mask(ste_arr, sb->bit_mask);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h
index 12a8bbbf944b..2d52d065dc8b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h
@@ -146,7 +146,7 @@ struct mlx5dr_ste_ctx {
 
 	/* Getters and Setters */
 	void (*ste_init)(u8 *hw_ste_p, u16 lu_type,
-			 u8 entry_type, u16 gvmi);
+			 bool is_rx, u16 gvmi);
 	void (*set_next_lu_type)(u8 *hw_ste_p, u16 lu_type);
 	u16  (*get_next_lu_type)(u8 *hw_ste_p);
 	void (*set_miss_addr)(u8 *hw_ste_p, u64 miss_addr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c
index e4dd4eed5aee..9c704bce3c12 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c
@@ -8,6 +8,12 @@
 #define SVLAN_ETHERTYPE		0x88a8
 #define DR_STE_ENABLE_FLOW_TAG	BIT(31)
 
+enum dr_ste_v0_entry_type {
+	DR_STE_TYPE_TX          = 1,
+	DR_STE_TYPE_RX          = 2,
+	DR_STE_TYPE_MODIFY_PKT  = 6,
+};
+
 enum dr_ste_v0_action_tunl {
 	DR_STE_TUNL_ACTION_NONE		= 0,
 	DR_STE_TUNL_ACTION_ENABLE	= 1,
@@ -292,8 +298,8 @@ static void dr_ste_v0_set_hit_addr(u8 *hw_ste_p, u64 icm_addr, u32 ht_size)
 	MLX5_SET(ste_general, hw_ste_p, next_table_base_31_5_size, index);
 }
 
-static void dr_ste_v0_init(u8 *hw_ste_p, u16 lu_type,
-			   u8 entry_type, u16 gvmi)
+static void dr_ste_v0_init_full(u8 *hw_ste_p, u16 lu_type,
+				enum dr_ste_v0_entry_type entry_type, u16 gvmi)
 {
 	dr_ste_v0_set_entry_type(hw_ste_p, entry_type);
 	dr_ste_v0_set_lu_type(hw_ste_p, lu_type);
@@ -307,6 +313,15 @@ static void dr_ste_v0_init(u8 *hw_ste_p, u16 lu_type,
 	MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_63_48, gvmi);
 }
 
+static void dr_ste_v0_init(u8 *hw_ste_p, u16 lu_type,
+			   bool is_rx, u16 gvmi)
+{
+	enum dr_ste_v0_entry_type entry_type;
+
+	entry_type = is_rx ? DR_STE_TYPE_RX : DR_STE_TYPE_TX;
+	dr_ste_v0_init_full(hw_ste_p, lu_type, entry_type, gvmi);
+}
+
 static void dr_ste_v0_rx_set_flow_tag(u8 *hw_ste_p, u32 flow_tag)
 {
 	MLX5_SET(ste_rx_steering_mult, hw_ste_p, qp_list_pointer,
@@ -380,13 +395,13 @@ static void dr_ste_v0_set_rewrite_actions(u8 *hw_ste_p, u16 num_of_actions,
 
 static void dr_ste_v0_arr_init_next(u8 **last_ste,
 				    u32 *added_stes,
-				    enum mlx5dr_ste_entry_type entry_type,
+				    enum dr_ste_v0_entry_type entry_type,
 				    u16 gvmi)
 {
 	(*added_stes)++;
 	*last_ste += DR_STE_SIZE;
-	dr_ste_v0_init(*last_ste, MLX5DR_STE_LU_TYPE_DONT_CARE,
-		       entry_type, gvmi);
+	dr_ste_v0_init_full(*last_ste, MLX5DR_STE_LU_TYPE_DONT_CARE,
+			    entry_type, gvmi);
 }
 
 static void
@@ -404,7 +419,7 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn,
 	 * modify headers for outer headers only
 	 */
 	if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) {
-		dr_ste_v0_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT);
+		dr_ste_v0_set_entry_type(last_ste, DR_STE_TYPE_MODIFY_PKT);
 		dr_ste_v0_set_rewrite_actions(last_ste,
 					      attr->modify_actions,
 					      attr->modify_index);
@@ -417,7 +432,7 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn,
 			if (i || action_type_set[DR_ACTION_TYP_MODIFY_HDR])
 				dr_ste_v0_arr_init_next(&last_ste,
 							added_stes,
-							MLX5DR_STE_TYPE_TX,
+							DR_STE_TYPE_TX,
 							attr->gvmi);
 
 			dr_ste_v0_set_tx_push_vlan(last_ste,
@@ -435,7 +450,7 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn,
 		    action_type_set[DR_ACTION_TYP_PUSH_VLAN])
 			dr_ste_v0_arr_init_next(&last_ste,
 						added_stes,
-						MLX5DR_STE_TYPE_TX,
+						DR_STE_TYPE_TX,
 						attr->gvmi);
 
 		dr_ste_v0_set_tx_encap(last_ste,
@@ -469,7 +484,7 @@ dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn,
 		dr_ste_v0_set_counter_id(last_ste, attr->ctr_id);
 
 	if (action_type_set[DR_ACTION_TYP_TNL_L3_TO_L2]) {
-		dr_ste_v0_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT);
+		dr_ste_v0_set_entry_type(last_ste, DR_STE_TYPE_MODIFY_PKT);
 		dr_ste_v0_set_rx_decap_l3(last_ste, attr->decap_with_vlan);
 		dr_ste_v0_set_rewrite_actions(last_ste,
 					      attr->decap_actions,
@@ -488,7 +503,7 @@ dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn,
 			    action_type_set[DR_ACTION_TYP_TNL_L3_TO_L2])
 				dr_ste_v0_arr_init_next(&last_ste,
 							added_stes,
-							MLX5DR_STE_TYPE_RX,
+							DR_STE_TYPE_RX,
 							attr->gvmi);
 
 			dr_ste_v0_set_rx_pop_vlan(last_ste);
@@ -496,13 +511,13 @@ dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn,
 	}
 
 	if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) {
-		if (dr_ste_v0_get_entry_type(last_ste) == MLX5DR_STE_TYPE_MODIFY_PKT)
+		if (dr_ste_v0_get_entry_type(last_ste) == DR_STE_TYPE_MODIFY_PKT)
 			dr_ste_v0_arr_init_next(&last_ste,
 						added_stes,
-						MLX5DR_STE_TYPE_MODIFY_PKT,
+						DR_STE_TYPE_MODIFY_PKT,
 						attr->gvmi);
 		else
-			dr_ste_v0_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT);
+			dr_ste_v0_set_entry_type(last_ste, DR_STE_TYPE_MODIFY_PKT);
 
 		dr_ste_v0_set_rewrite_actions(last_ste,
 					      attr->modify_actions,
@@ -510,10 +525,10 @@ dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn,
 	}
 
 	if (action_type_set[DR_ACTION_TYP_TAG]) {
-		if (dr_ste_v0_get_entry_type(last_ste) == MLX5DR_STE_TYPE_MODIFY_PKT)
+		if (dr_ste_v0_get_entry_type(last_ste) == DR_STE_TYPE_MODIFY_PKT)
 			dr_ste_v0_arr_init_next(&last_ste,
 						added_stes,
-						MLX5DR_STE_TYPE_RX,
+						DR_STE_TYPE_RX,
 						attr->gvmi);
 
 		dr_ste_v0_rx_set_flow_tag(last_ste, attr->flow_tag);
@@ -1157,6 +1172,7 @@ dr_ste_v0_build_eth_ipv6_l3_l4_tag(struct mlx5dr_match_param *value,
 				   u8 *tag)
 {
 	struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+	struct mlx5dr_match_misc *misc = &value->misc;
 
 	DR_STE_SET_TAG(eth_l4, tag, dst_port, spec, tcp_dport);
 	DR_STE_SET_TAG(eth_l4, tag, src_port, spec, tcp_sport);
@@ -1168,6 +1184,11 @@ dr_ste_v0_build_eth_ipv6_l3_l4_tag(struct mlx5dr_match_param *value,
 	DR_STE_SET_TAG(eth_l4, tag, ecn, spec, ip_ecn);
 	DR_STE_SET_TAG(eth_l4, tag, ipv6_hop_limit, spec, ttl_hoplimit);
 
+	if (sb->inner)
+		DR_STE_SET_TAG(eth_l4, tag, flow_label, misc, inner_ipv6_flow_label);
+	else
+		DR_STE_SET_TAG(eth_l4, tag, flow_label, misc, outer_ipv6_flow_label);
+
 	if (spec->tcp_flags) {
 		DR_STE_SET_TCP_FLAGS(eth_l4, tag, spec);
 		spec->tcp_flags = 0;
@@ -1772,7 +1793,7 @@ dr_ste_v0_build_flex_parser_tnl_geneve_tlv_opt_init(struct mlx5dr_ste_build *sb,
 
 static int dr_ste_v0_build_flex_parser_tnl_gtpu_tag(struct mlx5dr_match_param *value,
 						    struct mlx5dr_ste_build *sb,
-						    uint8_t *tag)
+						    u8 *tag)
 {
 	struct mlx5dr_match_misc3 *misc3 = &value->misc3;
 
@@ -1802,7 +1823,7 @@ static void dr_ste_v0_build_flex_parser_tnl_gtpu_init(struct mlx5dr_ste_build *s
 static int
 dr_ste_v0_build_tnl_gtpu_flex_parser_0_tag(struct mlx5dr_match_param *value,
 					   struct mlx5dr_ste_build *sb,
-					   uint8_t *tag)
+					   u8 *tag)
 {
 	if (dr_is_flex_parser_0_id(sb->caps->flex_parser_id_gtpu_dw_0))
 		DR_STE_SET_FLEX_PARSER_FIELD(tag, gtpu_dw_0, sb->caps, &value->misc3);
@@ -1829,7 +1850,7 @@ dr_ste_v0_build_tnl_gtpu_flex_parser_0_init(struct mlx5dr_ste_build *sb,
 static int
 dr_ste_v0_build_tnl_gtpu_flex_parser_1_tag(struct mlx5dr_match_param *value,
 					   struct mlx5dr_ste_build *sb,
-					   uint8_t *tag)
+					   u8 *tag)
 {
 	if (dr_is_flex_parser_1_id(sb->caps->flex_parser_id_gtpu_dw_0))
 		DR_STE_SET_FLEX_PARSER_FIELD(tag, gtpu_dw_0, sb->caps, &value->misc3);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
index 4aaca8eb7597..b2481c99da79 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
@@ -322,7 +322,7 @@ static void dr_ste_v1_set_hit_addr(u8 *hw_ste_p, u64 icm_addr, u32 ht_size)
 }
 
 static void dr_ste_v1_init(u8 *hw_ste_p, u16 lu_type,
-			   u8 entry_type, u16 gvmi)
+			   bool is_rx, u16 gvmi)
 {
 	dr_ste_v1_set_lu_type(hw_ste_p, lu_type);
 	dr_ste_v1_set_next_lu_type(hw_ste_p, MLX5DR_STE_LU_TYPE_DONT_CARE);
@@ -402,8 +402,23 @@ 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_tx_push_vlan(u8 *hw_ste_p, u8 *d_action,
-				       u32 vlan_hdr)
+static 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);
+	MLX5_SET(ste_single_action_remove_header_size_v1, s_action, start_anchor, anchor);
+
+	/* The hardware expects here size and offset in words (2 byte) */
+	MLX5_SET(ste_single_action_remove_header_size_v1, s_action, remove_size, size / 2);
+	MLX5_SET(ste_single_action_remove_header_size_v1, s_action, start_offset, offset / 2);
+
+	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)
 {
 	MLX5_SET(ste_double_action_insert_with_inline_v1, d_action,
 		 action_id, DR_STE_V1_ACTION_ID_INSERT_INLINE);
@@ -416,7 +431,7 @@ static void dr_ste_v1_set_tx_push_vlan(u8 *hw_ste_p, u8 *d_action,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_rx_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num)
+static 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);
@@ -503,13 +518,28 @@ static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 {
 	u8 *action = MLX5_ADDR_OF(ste_match_bwc_v1, last_ste, action);
 	u8 action_sz = DR_STE_ACTION_DOUBLE_SZ;
+	bool allow_modify_hdr = true;
 	bool allow_encap = true;
 
+	if (action_type_set[DR_ACTION_TYP_POP_VLAN]) {
+		if (action_sz < DR_STE_ACTION_SINGLE_SZ) {
+			dr_ste_v1_arr_init_next_match(&last_ste, added_stes,
+						      attr->gvmi);
+			action = MLX5_ADDR_OF(ste_mask_and_match_v1,
+					      last_ste, action);
+			action_sz = DR_STE_ACTION_TRIPLE_SZ;
+		}
+		dr_ste_v1_set_pop_vlan(last_ste, action, attr->vlans.count);
+		action_sz -= DR_STE_ACTION_SINGLE_SZ;
+		action += DR_STE_ACTION_SINGLE_SZ;
+		allow_modify_hdr = false;
+	}
+
 	if (action_type_set[DR_ACTION_TYP_CTR])
 		dr_ste_v1_set_counter_id(last_ste, attr->ctr_id);
 
 	if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) {
-		if (action_sz < DR_STE_ACTION_DOUBLE_SZ) {
+		if (!allow_modify_hdr || action_sz < DR_STE_ACTION_DOUBLE_SZ) {
 			dr_ste_v1_arr_init_next_match(&last_ste, added_stes,
 						      attr->gvmi);
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1,
@@ -534,7 +564,8 @@ static 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_tx_push_vlan(last_ste, action, attr->vlans.headers[i]);
+			dr_ste_v1_set_push_vlan(last_ste, action,
+						attr->vlans.headers[i]);
 			action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 			action += DR_STE_ACTION_DOUBLE_SZ;
 		}
@@ -579,6 +610,18 @@ static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 					 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]) {
+		if (action_sz < DR_STE_ACTION_SINGLE_SZ) {
+			dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi);
+			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);
+		action_sz -= DR_STE_ACTION_SINGLE_SZ;
+		action += DR_STE_ACTION_SINGLE_SZ;
 	}
 
 	dr_ste_v1_set_hit_gvmi(last_ste, attr->hit_gvmi);
@@ -635,7 +678,7 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 			allow_ctr = false;
 		}
 
-		dr_ste_v1_set_rx_pop_vlan(last_ste, action, attr->vlans.count);
+		dr_ste_v1_set_pop_vlan(last_ste, action, attr->vlans.count);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 	}
@@ -656,6 +699,26 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 		action += DR_STE_ACTION_DOUBLE_SZ;
 	}
 
+	if (action_type_set[DR_ACTION_TYP_PUSH_VLAN]) {
+		int i;
+
+		for (i = 0; i < attr->vlans.count; i++) {
+			if (action_sz < DR_STE_ACTION_DOUBLE_SZ ||
+			    !allow_modify_hdr) {
+				dr_ste_v1_arr_init_next_match(&last_ste,
+							      added_stes,
+							      attr->gvmi);
+				action = MLX5_ADDR_OF(ste_mask_and_match_v1,
+						      last_ste, action);
+				action_sz = DR_STE_ACTION_TRIPLE_SZ;
+			}
+			dr_ste_v1_set_push_vlan(last_ste, action,
+						attr->vlans.headers[i]);
+			action_sz -= DR_STE_ACTION_DOUBLE_SZ;
+			action += DR_STE_ACTION_DOUBLE_SZ;
+		}
+	}
+
 	if (action_type_set[DR_ACTION_TYP_CTR]) {
 		/* Counter action set after decap and before insert_hdr
 		 * to exclude decaped / encaped header respectively.
@@ -714,6 +777,20 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 		action += DR_STE_ACTION_DOUBLE_SZ;
 		allow_modify_hdr = false;
+	} else if (action_type_set[DR_ACTION_TYP_REMOVE_HDR]) {
+		if (action_sz < DR_STE_ACTION_SINGLE_SZ) {
+			dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi);
+			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
+			action_sz = DR_STE_ACTION_TRIPLE_SZ;
+			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);
+		action_sz -= DR_STE_ACTION_SINGLE_SZ;
+		action += DR_STE_ACTION_SINGLE_SZ;
 	}
 
 	dr_ste_v1_set_hit_gvmi(last_ste, attr->hit_gvmi);
@@ -1844,7 +1921,7 @@ dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_init(struct mlx5dr_ste_build *sb,
 
 static int dr_ste_v1_build_flex_parser_tnl_gtpu_tag(struct mlx5dr_match_param *value,
 						    struct mlx5dr_ste_build *sb,
-						    uint8_t *tag)
+						    u8 *tag)
 {
 	struct mlx5dr_match_misc3 *misc3 = &value->misc3;
 
@@ -1868,7 +1945,7 @@ static void dr_ste_v1_build_flex_parser_tnl_gtpu_init(struct mlx5dr_ste_build *s
 static int
 dr_ste_v1_build_tnl_gtpu_flex_parser_0_tag(struct mlx5dr_match_param *value,
 					   struct mlx5dr_ste_build *sb,
-					   uint8_t *tag)
+					   u8 *tag)
 {
 	if (dr_is_flex_parser_0_id(sb->caps->flex_parser_id_gtpu_dw_0))
 		DR_STE_SET_FLEX_PARSER_FIELD(tag, gtpu_dw_0, sb->caps, &value->misc3);
@@ -1895,7 +1972,7 @@ dr_ste_v1_build_tnl_gtpu_flex_parser_0_init(struct mlx5dr_ste_build *sb,
 static int
 dr_ste_v1_build_tnl_gtpu_flex_parser_1_tag(struct mlx5dr_match_param *value,
 					   struct mlx5dr_ste_build *sb,
-					   uint8_t *tag)
+					   u8 *tag)
 {
 	if (dr_is_flex_parser_1_id(sb->caps->flex_parser_id_gtpu_dw_0))
 		DR_STE_SET_FLEX_PARSER_FIELD(tag, gtpu_dw_0, sb->caps, &value->misc3);
@@ -1960,7 +2037,9 @@ struct mlx5dr_ste_ctx ste_ctx_v1 = {
 	.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_RX_ENCAP,
+	.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_v1_action_modify_field_arr),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index f5e93fa87aff..b20e8aabb861 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -83,15 +83,14 @@ enum {
 	DR_STE_SIZE_CTRL = 32,
 	DR_STE_SIZE_TAG = 16,
 	DR_STE_SIZE_MASK = 16,
-};
-
-enum {
 	DR_STE_SIZE_REDUCED = DR_STE_SIZE - DR_STE_SIZE_MASK,
 };
 
 enum mlx5dr_ste_ctx_action_cap {
 	DR_STE_CTX_ACTION_CAP_NONE = 0,
-	DR_STE_CTX_ACTION_CAP_RX_ENCAP = 1 << 0,
+	DR_STE_CTX_ACTION_CAP_TX_POP   = 1 << 0,
+	DR_STE_CTX_ACTION_CAP_RX_PUSH  = 1 << 1,
+	DR_STE_CTX_ACTION_CAP_RX_ENCAP = 1 << 2,
 };
 
 enum {
@@ -124,6 +123,7 @@ enum mlx5dr_action_type {
 	DR_ACTION_TYP_POP_VLAN,
 	DR_ACTION_TYP_PUSH_VLAN,
 	DR_ACTION_TYP_INSERT_HDR,
+	DR_ACTION_TYP_REMOVE_HDR,
 	DR_ACTION_TYP_SAMPLER,
 	DR_ACTION_TYP_MAX,
 };
@@ -140,6 +140,7 @@ struct mlx5dr_icm_buddy_mem;
 struct mlx5dr_ste_htbl;
 struct mlx5dr_match_param;
 struct mlx5dr_cmd_caps;
+struct mlx5dr_rule_rx_tx;
 struct mlx5dr_matcher_rx_tx;
 struct mlx5dr_ste_ctx;
 
@@ -151,14 +152,14 @@ struct mlx5dr_ste {
 	/* attached to the miss_list head at each htbl entry */
 	struct list_head miss_list_node;
 
-	/* each rule member that uses this ste attached here */
-	struct list_head rule_list;
-
 	/* this ste is member of htbl */
 	struct mlx5dr_ste_htbl *htbl;
 
 	struct mlx5dr_ste_htbl *next_htbl;
 
+	/* The rule this STE belongs to */
+	struct mlx5dr_rule_rx_tx *rule_rx_tx;
+
 	/* this ste is part of a rule, located in ste's chain */
 	u8 ste_chain_location;
 };
@@ -171,8 +172,6 @@ struct mlx5dr_ste_htbl_ctrl {
 
 	/* total number of collisions entries attached to this table */
 	unsigned int num_of_collisions;
-	unsigned int increase_threshold;
-	u8 may_grow:1;
 };
 
 struct mlx5dr_ste_htbl {
@@ -804,10 +803,15 @@ struct mlx5dr_cmd_caps {
 	u8 isolate_vl_tc:1;
 };
 
+enum mlx5dr_domain_nic_type {
+	DR_DOMAIN_NIC_TYPE_RX,
+	DR_DOMAIN_NIC_TYPE_TX,
+};
+
 struct mlx5dr_domain_rx_tx {
 	u64 drop_icm_addr;
 	u64 default_icm_addr;
-	enum mlx5dr_ste_entry_type ste_type;
+	enum mlx5dr_domain_nic_type type;
 	struct mutex mutex; /* protect rx/tx domain */
 };
 
@@ -885,14 +889,6 @@ struct mlx5dr_matcher {
 	struct mlx5dv_flow_matcher *dv_matcher;
 };
 
-struct mlx5dr_rule_member {
-	struct mlx5dr_ste *ste;
-	/* attached to mlx5dr_rule via this */
-	struct list_head list;
-	/* attached to mlx5dr_ste via this */
-	struct list_head use_ste_list;
-};
-
 struct mlx5dr_ste_action_modify_field {
 	u16 hw_field;
 	u8 start;
@@ -993,8 +989,8 @@ struct mlx5dr_htbl_connect_info {
 };
 
 struct mlx5dr_rule_rx_tx {
-	struct list_head rule_members_list;
 	struct mlx5dr_matcher_rx_tx *nic_matcher;
+	struct mlx5dr_ste *last_rule_ste;
 };
 
 struct mlx5dr_rule {
@@ -1005,8 +1001,12 @@ struct mlx5dr_rule {
 	u32 flow_source;
 };
 
-void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *new_ste,
-				    struct mlx5dr_ste *ste);
+void mlx5dr_rule_set_last_member(struct mlx5dr_rule_rx_tx *nic_rule,
+				 struct mlx5dr_ste *ste,
+				 bool force);
+int mlx5dr_rule_get_reverse_rule_members(struct mlx5dr_ste **ste_arr,
+					 struct mlx5dr_ste *curr_ste,
+					 int *num_of_stes);
 
 struct mlx5dr_icm_chunk {
 	struct mlx5dr_icm_buddy_mem *buddy_mem;
@@ -1083,6 +1083,25 @@ mlx5dr_icm_pool_chunk_size_to_byte(enum mlx5dr_icm_chunk_size chunk_size,
 	return entry_size * num_of_entries;
 }
 
+static inline int
+mlx5dr_ste_htbl_increase_threshold(struct mlx5dr_ste_htbl *htbl)
+{
+	int num_of_entries =
+		mlx5dr_icm_pool_chunk_size_to_entries(htbl->chunk_size);
+
+	/* Threshold is 50%, one is added to table of size 1 */
+	return (num_of_entries + 1) / 2;
+}
+
+static inline bool
+mlx5dr_ste_htbl_may_grow(struct mlx5dr_ste_htbl *htbl)
+{
+	if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1 || !htbl->byte_mask)
+		return false;
+
+	return true;
+}
+
 static inline struct mlx5dr_cmd_vport_cap *
 mlx5dr_get_vport_cap(struct mlx5dr_cmd_caps *caps, u32 vport)
 {
@@ -1216,7 +1235,7 @@ int mlx5dr_ste_htbl_init_and_postsend(struct mlx5dr_domain *dmn,
 				      bool update_hw_ste);
 void mlx5dr_ste_set_formatted_ste(struct mlx5dr_ste_ctx *ste_ctx,
 				  u16 gvmi,
-				  struct mlx5dr_domain_rx_tx *nic_dmn,
+				  enum mlx5dr_domain_nic_type nic_type,
 				  struct mlx5dr_ste_htbl *htbl,
 				  u8 *formatted_ste,
 				  struct mlx5dr_htbl_connect_info *connect_info);
@@ -1282,6 +1301,7 @@ struct mlx5dr_send_ring {
 	u8 sync_buff[MIN_READ_SYNC];
 	struct mlx5dr_mr *sync_mr;
 	spinlock_t lock; /* Protect the data path of the send ring */
+	bool err_state; /* send_ring is not usable in err state */
 };
 
 int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn);
@@ -1333,6 +1353,7 @@ struct mlx5dr_cmd_fte_info {
 	u32 *val;
 	struct mlx5_flow_act action;
 	struct mlx5dr_cmd_flow_destination_hw_info *dest_arr;
+	bool ignore_flow_level;
 };
 
 int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev,
@@ -1362,7 +1383,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn,
 			    int num_dest,
 			    bool reformat_req,
 			    u32 *tbl_id,
-			    u32 *group_id);
+			    u32 *group_id,
+			    bool ignore_flow_level);
 void mlx5dr_fw_destroy_md_tbl(struct mlx5dr_domain *dmn, u32 tbl_id,
 			      u32 group_id);
 #endif  /* _DR_TYPES_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index d5926dd7e972..7e58f4e594b7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -133,6 +133,9 @@ static int mlx5_cmd_dr_modify_flow_table(struct mlx5_flow_root_namespace *ns,
 					 struct mlx5_flow_table *ft,
 					 struct mlx5_flow_table *next_ft)
 {
+	if (mlx5_dr_is_fw_table(ft->flags))
+		return mlx5_fs_cmd_get_fw_cmds()->modify_flow_table(ns, ft, next_ft);
+
 	return set_miss_action(ns, ft, next_ft);
 }
 
@@ -487,9 +490,13 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 
 		actions[num_actions++] = term_actions->dest;
 	} else if (num_term_actions > 1) {
+		bool ignore_flow_level =
+			!!(fte->action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL);
+
 		tmp_action = mlx5dr_action_create_mult_dest_tbl(domain,
 								term_actions,
-								num_term_actions);
+								num_term_actions,
+								ignore_flow_level);
 		if (!tmp_action) {
 			err = -EOPNOTSUPP;
 			goto free_actions;
@@ -557,6 +564,9 @@ static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns
 	case MLX5_REFORMAT_TYPE_INSERT_HDR:
 		dr_reformat = DR_ACTION_REFORMAT_TYP_INSERT_HDR;
 		break;
+	case MLX5_REFORMAT_TYPE_REMOVE_HDR:
+		dr_reformat = DR_ACTION_REFORMAT_TYP_REMOVE_HDR;
+		break;
 	default:
 		mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n",
 			      params->type);
@@ -615,15 +625,6 @@ static void mlx5_cmd_dr_modify_header_dealloc(struct mlx5_flow_root_namespace *n
 	mlx5dr_action_destroy(modify_hdr->action.dr_action);
 }
 
-static int mlx5_cmd_dr_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)
-{
-	return -EOPNOTSUPP;
-}
-
 static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns,
 				  struct mlx5_flow_table *ft,
 				  struct fs_fte *fte)
@@ -648,6 +649,36 @@ static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns,
 	return 0;
 }
 
+static int mlx5_cmd_dr_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)
+{
+	struct fs_fte fte_tmp = {};
+	int ret;
+
+	if (mlx5_dr_is_fw_table(ft->flags))
+		return mlx5_fs_cmd_get_fw_cmds()->update_fte(ns, ft, group, modify_mask, fte);
+
+	/* Backup current dr rule details */
+	fte_tmp.fs_dr_rule = fte->fs_dr_rule;
+	memset(&fte->fs_dr_rule, 0, sizeof(struct mlx5_fs_dr_rule));
+
+	/* First add the new updated rule, then delete the old rule */
+	ret = mlx5_cmd_dr_create_fte(ns, ft, group, fte);
+	if (ret)
+		goto restore_fte;
+
+	ret = mlx5_cmd_dr_delete_fte(ns, ft, &fte_tmp);
+	WARN_ONCE(ret, "dr update fte duplicate rule deletion failed\n");
+	return ret;
+
+restore_fte:
+	fte->fs_dr_rule = fte_tmp.fs_dr_rule;
+	return ret;
+}
+
 static int mlx5_cmd_dr_set_peer(struct mlx5_flow_root_namespace *ns,
 				struct mlx5_flow_root_namespace *peer_ns)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
index 9643ee647f57..d2a937f69784 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
@@ -8,12 +8,6 @@ enum {
 	MLX5DR_STE_LU_TYPE_DONT_CARE			= 0x0f,
 };
 
-enum mlx5dr_ste_entry_type {
-	MLX5DR_STE_TYPE_TX		= 1,
-	MLX5DR_STE_TYPE_RX		= 2,
-	MLX5DR_STE_TYPE_MODIFY_PKT	= 6,
-};
-
 struct mlx5_ifc_ste_general_bits {
 	u8         entry_type[0x4];
 	u8         reserved_at_4[0x4];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
index bbfe101d4e57..c5a8b1601999 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
@@ -27,6 +27,7 @@ enum mlx5dr_action_reformat_type {
 	DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2,
 	DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3,
 	DR_ACTION_REFORMAT_TYP_INSERT_HDR,
+	DR_ACTION_REFORMAT_TYP_REMOVE_HDR,
 };
 
 struct mlx5dr_match_parameters {
@@ -94,7 +95,8 @@ mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain,
 struct mlx5dr_action *
 mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn,
 				   struct mlx5dr_action_dest *dests,
-				   u32 num_of_dests);
+				   u32 num_of_dests,
+				   bool ignore_flow_level);
 
 struct mlx5dr_action *mlx5dr_action_create_drop(void);
 
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 a0a059e0154f..3e85b17f5857 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
@@ -199,7 +199,7 @@ static int mlxbf_gige_stop(struct net_device *netdev)
 	return 0;
 }
 
-static int mlxbf_gige_do_ioctl(struct net_device *netdev,
+static int mlxbf_gige_eth_ioctl(struct net_device *netdev,
 			       struct ifreq *ifr, int cmd)
 {
 	if (!(netif_running(netdev)))
@@ -253,7 +253,7 @@ static const struct net_device_ops mlxbf_gige_netdev_ops = {
 	.ndo_start_xmit		= mlxbf_gige_start_xmit,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= mlxbf_gige_do_ioctl,
+	.ndo_eth_ioctl		= mlxbf_gige_eth_ioctl,
 	.ndo_set_rx_mode        = mlxbf_gige_set_rx_mode,
 	.ndo_get_stats64        = mlxbf_gige_get_stats64,
 };
@@ -269,9 +269,6 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
 {
 	struct phy_device *phydev;
 	struct net_device *netdev;
-	struct resource *mac_res;
-	struct resource *llu_res;
-	struct resource *plu_res;
 	struct mlxbf_gige *priv;
 	void __iomem *llu_base;
 	void __iomem *plu_base;
@@ -280,27 +277,15 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
 	int addr;
 	int err;
 
-	mac_res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_MAC);
-	if (!mac_res)
-		return -ENXIO;
-
-	base = devm_ioremap_resource(&pdev->dev, mac_res);
+	base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MAC);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
-	llu_res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_LLU);
-	if (!llu_res)
-		return -ENXIO;
-
-	llu_base = devm_ioremap_resource(&pdev->dev, llu_res);
+	llu_base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_LLU);
 	if (IS_ERR(llu_base))
 		return PTR_ERR(llu_base);
 
-	plu_res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_PLU);
-	if (!plu_res)
-		return -ENXIO;
-
-	plu_base = devm_ioremap_resource(&pdev->dev, plu_res);
+	plu_base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_PLU);
 	if (IS_ERR(plu_base))
 		return PTR_ERR(plu_base);
 
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c
index e32dd34fdcc0..7905179a9575 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c
@@ -145,14 +145,9 @@ static int mlxbf_gige_mdio_write(struct mii_bus *bus, int phy_add,
 int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv)
 {
 	struct device *dev = &pdev->dev;
-	struct resource *res;
 	int ret;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_MDIO9);
-	if (!res)
-		return -ENODEV;
-
-	priv->mdio_io = devm_ioremap_resource(dev, res);
+	priv->mdio_io = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MDIO9);
 	if (IS_ERR(priv->mdio_io))
 		return PTR_ERR(priv->mdio_io);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index 12871c8dc7c1..d1ae248e125c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -58,10 +58,10 @@ config MLXSW_SPECTRUM
 	depends on NET_IPGRE || NET_IPGRE=n
 	depends on IPV6_GRE || IPV6_GRE=n
 	depends on VXLAN || VXLAN=n
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select GENERIC_ALLOCATOR
 	select PARMAN
 	select OBJAGG
-	imply PTP_1588_CLOCK
 	select NET_PTP_CLASSIFY if PTP_1588_CLOCK
 	default m
 	help
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index e775f08fb464..f080fab3de2b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1927,7 +1927,8 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 
 	if (!reload) {
 		alloc_size = sizeof(*mlxsw_core) + mlxsw_driver->priv_size;
-		devlink = devlink_alloc(&mlxsw_devlink_ops, alloc_size);
+		devlink = devlink_alloc(&mlxsw_devlink_ops, alloc_size,
+					mlxsw_bus_info->dev);
 		if (!devlink) {
 			err = -ENOMEM;
 			goto err_devlink_alloc;
@@ -1974,7 +1975,7 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 		goto err_emad_init;
 
 	if (!reload) {
-		err = devlink_register(devlink, mlxsw_bus_info->dev);
+		err = devlink_register(devlink);
 		if (err)
 			goto err_devlink_register;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 88699e678544..250c5a24264d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1207,7 +1207,7 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
 	.ndo_vlan_rx_kill_vid	= mlxsw_sp_port_kill_vid,
 	.ndo_set_features	= mlxsw_sp_set_features,
 	.ndo_get_devlink_port	= mlxsw_sp_port_get_devlink_port,
-	.ndo_do_ioctl		= mlxsw_sp_port_ioctl,
+	.ndo_eth_ioctl		= mlxsw_sp_port_ioctl,
 };
 
 static int
@@ -2717,6 +2717,22 @@ mlxsw_sp_sample_trigger_params_unset(struct mlxsw_sp *mlxsw_sp,
 static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
 				    unsigned long event, void *ptr);
 
+#define MLXSW_SP_DEFAULT_PARSING_DEPTH 96
+#define MLXSW_SP_INCREASED_PARSING_DEPTH 128
+#define MLXSW_SP_DEFAULT_VXLAN_UDP_DPORT 4789
+
+static void mlxsw_sp_parsing_init(struct mlxsw_sp *mlxsw_sp)
+{
+	mlxsw_sp->parsing.parsing_depth = MLXSW_SP_DEFAULT_PARSING_DEPTH;
+	mlxsw_sp->parsing.vxlan_udp_dport = MLXSW_SP_DEFAULT_VXLAN_UDP_DPORT;
+	mutex_init(&mlxsw_sp->parsing.lock);
+}
+
+static void mlxsw_sp_parsing_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	mutex_destroy(&mlxsw_sp->parsing.lock);
+}
+
 static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 			 const struct mlxsw_bus_info *mlxsw_bus_info,
 			 struct netlink_ext_ack *extack)
@@ -2727,6 +2743,7 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->core = mlxsw_core;
 	mlxsw_sp->bus_info = mlxsw_bus_info;
 
+	mlxsw_sp_parsing_init(mlxsw_sp);
 	mlxsw_core_emad_string_tlv_enable(mlxsw_core);
 
 	err = mlxsw_sp_base_mac_get(mlxsw_sp);
@@ -2926,6 +2943,7 @@ err_policers_init:
 	mlxsw_sp_fids_fini(mlxsw_sp);
 err_fids_init:
 	mlxsw_sp_kvdl_fini(mlxsw_sp);
+	mlxsw_sp_parsing_fini(mlxsw_sp);
 	return err;
 }
 
@@ -3046,6 +3064,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 	mlxsw_sp_policers_fini(mlxsw_sp);
 	mlxsw_sp_fids_fini(mlxsw_sp);
 	mlxsw_sp_kvdl_fini(mlxsw_sp);
+	mlxsw_sp_parsing_fini(mlxsw_sp);
 }
 
 /* Per-FID flood tables are used for both "true" 802.1D FIDs and emulated
@@ -3611,6 +3630,69 @@ void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port)
 	dev_put(mlxsw_sp_port->dev);
 }
 
+int mlxsw_sp_parsing_depth_inc(struct mlxsw_sp *mlxsw_sp)
+{
+	char mprs_pl[MLXSW_REG_MPRS_LEN];
+	int err = 0;
+
+	mutex_lock(&mlxsw_sp->parsing.lock);
+
+	if (refcount_inc_not_zero(&mlxsw_sp->parsing.parsing_depth_ref))
+		goto out_unlock;
+
+	mlxsw_reg_mprs_pack(mprs_pl, MLXSW_SP_INCREASED_PARSING_DEPTH,
+			    mlxsw_sp->parsing.vxlan_udp_dport);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl);
+	if (err)
+		goto out_unlock;
+
+	mlxsw_sp->parsing.parsing_depth = MLXSW_SP_INCREASED_PARSING_DEPTH;
+	refcount_set(&mlxsw_sp->parsing.parsing_depth_ref, 1);
+
+out_unlock:
+	mutex_unlock(&mlxsw_sp->parsing.lock);
+	return err;
+}
+
+void mlxsw_sp_parsing_depth_dec(struct mlxsw_sp *mlxsw_sp)
+{
+	char mprs_pl[MLXSW_REG_MPRS_LEN];
+
+	mutex_lock(&mlxsw_sp->parsing.lock);
+
+	if (!refcount_dec_and_test(&mlxsw_sp->parsing.parsing_depth_ref))
+		goto out_unlock;
+
+	mlxsw_reg_mprs_pack(mprs_pl, MLXSW_SP_DEFAULT_PARSING_DEPTH,
+			    mlxsw_sp->parsing.vxlan_udp_dport);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl);
+	mlxsw_sp->parsing.parsing_depth = MLXSW_SP_DEFAULT_PARSING_DEPTH;
+
+out_unlock:
+	mutex_unlock(&mlxsw_sp->parsing.lock);
+}
+
+int mlxsw_sp_parsing_vxlan_udp_dport_set(struct mlxsw_sp *mlxsw_sp,
+					 __be16 udp_dport)
+{
+	char mprs_pl[MLXSW_REG_MPRS_LEN];
+	int err;
+
+	mutex_lock(&mlxsw_sp->parsing.lock);
+
+	mlxsw_reg_mprs_pack(mprs_pl, mlxsw_sp->parsing.parsing_depth,
+			    be16_to_cpu(udp_dport));
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl);
+	if (err)
+		goto out_unlock;
+
+	mlxsw_sp->parsing.vxlan_udp_dport = be16_to_cpu(udp_dport);
+
+out_unlock:
+	mutex_unlock(&mlxsw_sp->parsing.lock);
+	return err;
+}
+
 static void
 mlxsw_sp_port_lag_uppers_cleanup(struct mlxsw_sp_port *mlxsw_sp_port,
 				 struct net_device *lag_dev)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index f99db88ee884..3a43cba6d23c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -148,6 +148,13 @@ struct mlxsw_sp_port_mapping {
 	u8 lane;
 };
 
+struct mlxsw_sp_parsing {
+	refcount_t parsing_depth_ref;
+	u16 parsing_depth;
+	u16 vxlan_udp_dport;
+	struct mutex lock; /* Protects parsing configuration */
+};
+
 struct mlxsw_sp {
 	struct mlxsw_sp_port **ports;
 	struct mlxsw_core *core;
@@ -173,6 +180,7 @@ struct mlxsw_sp {
 	struct mlxsw_sp_counter_pool *counter_pool;
 	struct mlxsw_sp_span *span;
 	struct mlxsw_sp_trap *trap;
+	struct mlxsw_sp_parsing parsing;
 	const struct mlxsw_sp_switchdev_ops *switchdev_ops;
 	const struct mlxsw_sp_kvdl_ops *kvdl_ops;
 	const struct mlxsw_afa_ops *afa_ops;
@@ -652,6 +660,10 @@ struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev);
 struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev);
 void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port);
 struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev);
+int mlxsw_sp_parsing_depth_inc(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_parsing_depth_dec(struct mlxsw_sp *mlxsw_sp);
+int mlxsw_sp_parsing_vxlan_udp_dport_set(struct mlxsw_sp *mlxsw_sp,
+					 __be16 udp_dport);
 
 /* spectrum_dcb.c */
 #ifdef CONFIG_MLXSW_SPECTRUM_DCB
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
index d8104fc6c900..98d1fdc25eac 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
@@ -29,7 +29,6 @@ struct mlxsw_sp_nve {
 	unsigned int num_max_mc_entries[MLXSW_SP_L3_PROTO_MAX];
 	u32 tunnel_index;
 	u16 ul_rif_index;	/* Reserved for Spectrum */
-	unsigned int inc_parsing_depth_refs;
 };
 
 struct mlxsw_sp_nve_ops {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
index b84bb4b65098..d018d2da5949 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
@@ -10,14 +10,6 @@
 #include "spectrum.h"
 #include "spectrum_nve.h"
 
-/* Eth (18B) | IPv6 (40B) | UDP (8B) | VxLAN (8B) | Eth (14B) | IPv6 (40B)
- *
- * In the worst case - where we have a VLAN tag on the outer Ethernet
- * header and IPv6 in overlay and underlay - we need to parse 128 bytes
- */
-#define MLXSW_SP_NVE_VXLAN_PARSING_DEPTH 128
-#define MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH 96
-
 #define MLXSW_SP_NVE_VXLAN_SUPPORTED_FLAGS	(VXLAN_F_UDP_ZERO_CSUM_TX | \
 						 VXLAN_F_LEARN)
 
@@ -115,66 +107,6 @@ static void mlxsw_sp_nve_vxlan_config(const struct mlxsw_sp_nve *nve,
 	config->udp_dport = cfg->dst_port;
 }
 
-static int __mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp,
-				      unsigned int parsing_depth,
-				      __be16 udp_dport)
-{
-	char mprs_pl[MLXSW_REG_MPRS_LEN];
-
-	mlxsw_reg_mprs_pack(mprs_pl, parsing_depth, be16_to_cpu(udp_dport));
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl);
-}
-
-static int mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp,
-				    __be16 udp_dport)
-{
-	int parsing_depth = mlxsw_sp->nve->inc_parsing_depth_refs ?
-				MLXSW_SP_NVE_VXLAN_PARSING_DEPTH :
-				MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH;
-
-	return __mlxsw_sp_nve_parsing_set(mlxsw_sp, parsing_depth, udp_dport);
-}
-
-static int
-__mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp,
-				     __be16 udp_dport)
-{
-	int err;
-
-	mlxsw_sp->nve->inc_parsing_depth_refs++;
-
-	err = mlxsw_sp_nve_parsing_set(mlxsw_sp, udp_dport);
-	if (err)
-		goto err_nve_parsing_set;
-	return 0;
-
-err_nve_parsing_set:
-	mlxsw_sp->nve->inc_parsing_depth_refs--;
-	return err;
-}
-
-static void
-__mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp,
-				     __be16 udp_dport)
-{
-	mlxsw_sp->nve->inc_parsing_depth_refs--;
-	mlxsw_sp_nve_parsing_set(mlxsw_sp, udp_dport);
-}
-
-int mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp)
-{
-	__be16 udp_dport = mlxsw_sp->nve->config.udp_dport;
-
-	return __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, udp_dport);
-}
-
-void mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp)
-{
-	__be16 udp_dport = mlxsw_sp->nve->config.udp_dport;
-
-	__mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, udp_dport);
-}
-
 static void
 mlxsw_sp_nve_vxlan_config_prepare(char *tngcr_pl,
 				  const struct mlxsw_sp_nve_config *config)
@@ -238,10 +170,14 @@ static int mlxsw_sp1_nve_vxlan_init(struct mlxsw_sp_nve *nve,
 	struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp;
 	int err;
 
-	err = __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, config->udp_dport);
+	err = mlxsw_sp_parsing_vxlan_udp_dport_set(mlxsw_sp, config->udp_dport);
 	if (err)
 		return err;
 
+	err = mlxsw_sp_parsing_depth_inc(mlxsw_sp);
+	if (err)
+		goto err_parsing_depth_inc;
+
 	err = mlxsw_sp1_nve_vxlan_config_set(mlxsw_sp, config);
 	if (err)
 		goto err_config_set;
@@ -263,7 +199,9 @@ err_promote_decap:
 err_rtdp_set:
 	mlxsw_sp1_nve_vxlan_config_clear(mlxsw_sp);
 err_config_set:
-	__mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0);
+	mlxsw_sp_parsing_depth_dec(mlxsw_sp);
+err_parsing_depth_inc:
+	mlxsw_sp_parsing_vxlan_udp_dport_set(mlxsw_sp, 0);
 	return err;
 }
 
@@ -275,7 +213,8 @@ static void mlxsw_sp1_nve_vxlan_fini(struct mlxsw_sp_nve *nve)
 	mlxsw_sp_router_nve_demote_decap(mlxsw_sp, config->ul_tb_id,
 					 config->ul_proto, &config->ul_sip);
 	mlxsw_sp1_nve_vxlan_config_clear(mlxsw_sp);
-	__mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0);
+	mlxsw_sp_parsing_depth_dec(mlxsw_sp);
+	mlxsw_sp_parsing_vxlan_udp_dport_set(mlxsw_sp, 0);
 }
 
 static int
@@ -412,10 +351,14 @@ static int mlxsw_sp2_nve_vxlan_init(struct mlxsw_sp_nve *nve,
 	struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp;
 	int err;
 
-	err = __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, config->udp_dport);
+	err = mlxsw_sp_parsing_vxlan_udp_dport_set(mlxsw_sp, config->udp_dport);
 	if (err)
 		return err;
 
+	err = mlxsw_sp_parsing_depth_inc(mlxsw_sp);
+	if (err)
+		goto err_parsing_depth_inc;
+
 	err = mlxsw_sp2_nve_vxlan_config_set(mlxsw_sp, config);
 	if (err)
 		goto err_config_set;
@@ -438,7 +381,9 @@ err_promote_decap:
 err_rtdp_set:
 	mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp);
 err_config_set:
-	__mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0);
+	mlxsw_sp_parsing_depth_dec(mlxsw_sp);
+err_parsing_depth_inc:
+	mlxsw_sp_parsing_vxlan_udp_dport_set(mlxsw_sp, 0);
 	return err;
 }
 
@@ -450,7 +395,8 @@ static void mlxsw_sp2_nve_vxlan_fini(struct mlxsw_sp_nve *nve)
 	mlxsw_sp_router_nve_demote_decap(mlxsw_sp, config->ul_tb_id,
 					 config->ul_proto, &config->ul_sip);
 	mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp);
-	__mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0);
+	mlxsw_sp_parsing_depth_dec(mlxsw_sp);
+	mlxsw_sp_parsing_vxlan_udp_dport_set(mlxsw_sp, 0);
 }
 
 const struct mlxsw_sp_nve_ops mlxsw_sp2_nve_vxlan_ops = {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
index bfef65d1587c..1a180384e7e8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -975,14 +975,14 @@ static int mlxsw_sp1_ptp_mtpppc_update(struct mlxsw_sp_port *mlxsw_sp_port,
 	}
 
 	if ((ing_types || egr_types) && !(orig_ing_types || orig_egr_types)) {
-		err = mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp);
+		err = mlxsw_sp_parsing_depth_inc(mlxsw_sp);
 		if (err) {
 			netdev_err(mlxsw_sp_port->dev, "Failed to increase parsing depth");
 			return err;
 		}
 	}
 	if (!(ing_types || egr_types) && (orig_ing_types || orig_egr_types))
-		mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp);
+		mlxsw_sp_parsing_depth_dec(mlxsw_sp);
 
 	return mlxsw_sp1_ptp_mtpppc_set(mlxsw_sp_port->mlxsw_sp,
 				       ing_types, egr_types);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index f69cbb3852d5..19bb3ca0515e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -9484,6 +9484,7 @@ struct mlxsw_sp_mp_hash_config {
 	DECLARE_BITMAP(fields, __MLXSW_REG_RECR2_FIELD_CNT);
 	DECLARE_BITMAP(inner_headers, __MLXSW_REG_RECR2_HEADER_CNT);
 	DECLARE_BITMAP(inner_fields, __MLXSW_REG_RECR2_INNER_FIELD_CNT);
+	bool inc_parsing_depth;
 };
 
 #define MLXSW_SP_MP_HASH_HEADER_SET(_headers, _header) \
@@ -9654,6 +9655,7 @@ static void mlxsw_sp_mp6_hash_init(struct mlxsw_sp *mlxsw_sp,
 		MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_FLOW_LABEL);
 		/* Inner */
 		mlxsw_sp_mp_hash_inner_l3(config);
+		config->inc_parsing_depth = true;
 		break;
 	case 3:
 		/* Outer */
@@ -9678,22 +9680,53 @@ static void mlxsw_sp_mp6_hash_init(struct mlxsw_sp *mlxsw_sp,
 			MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_DPORT);
 		/* Inner */
 		mlxsw_sp_mp_hash_inner_custom(config, hash_fields);
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)
+			config->inc_parsing_depth = true;
 		break;
 	}
 }
 
+static int mlxsw_sp_mp_hash_parsing_depth_adjust(struct mlxsw_sp *mlxsw_sp,
+						 bool old_inc_parsing_depth,
+						 bool new_inc_parsing_depth)
+{
+	int err;
+
+	if (!old_inc_parsing_depth && new_inc_parsing_depth) {
+		err = mlxsw_sp_parsing_depth_inc(mlxsw_sp);
+		if (err)
+			return err;
+		mlxsw_sp->router->inc_parsing_depth = true;
+	} else if (old_inc_parsing_depth && !new_inc_parsing_depth) {
+		mlxsw_sp_parsing_depth_dec(mlxsw_sp);
+		mlxsw_sp->router->inc_parsing_depth = false;
+	}
+
+	return 0;
+}
+
 static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp)
 {
+	bool old_inc_parsing_depth, new_inc_parsing_depth;
 	struct mlxsw_sp_mp_hash_config config = {};
 	char recr2_pl[MLXSW_REG_RECR2_LEN];
 	unsigned long bit;
 	u32 seed;
+	int err;
 
 	seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac), 0);
 	mlxsw_reg_recr2_pack(recr2_pl, seed);
 	mlxsw_sp_mp4_hash_init(mlxsw_sp, &config);
 	mlxsw_sp_mp6_hash_init(mlxsw_sp, &config);
 
+	old_inc_parsing_depth = mlxsw_sp->router->inc_parsing_depth;
+	new_inc_parsing_depth = config.inc_parsing_depth;
+	err = mlxsw_sp_mp_hash_parsing_depth_adjust(mlxsw_sp,
+						    old_inc_parsing_depth,
+						    new_inc_parsing_depth);
+	if (err)
+		return err;
+
 	for_each_set_bit(bit, config.headers, __MLXSW_REG_RECR2_HEADER_CNT)
 		mlxsw_reg_recr2_outer_header_enables_set(recr2_pl, bit, 1);
 	for_each_set_bit(bit, config.fields, __MLXSW_REG_RECR2_FIELD_CNT)
@@ -9703,7 +9736,16 @@ static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp)
 	for_each_set_bit(bit, config.inner_fields, __MLXSW_REG_RECR2_INNER_FIELD_CNT)
 		mlxsw_reg_recr2_inner_header_fields_enable_set(recr2_pl, bit, 1);
 
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(recr2), recr2_pl);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(recr2), recr2_pl);
+	if (err)
+		goto err_reg_write;
+
+	return 0;
+
+err_reg_write:
+	mlxsw_sp_mp_hash_parsing_depth_adjust(mlxsw_sp, new_inc_parsing_depth,
+					      old_inc_parsing_depth);
+	return err;
 }
 #else
 static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index c5d7007f9173..25d3eae63501 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -81,6 +81,7 @@ struct mlxsw_sp_router {
 	size_t adj_grp_size_ranges_count;
 	struct delayed_work nh_grp_activity_dw;
 	struct list_head nh_res_grp_list;
+	bool inc_parsing_depth;
 };
 
 struct mlxsw_sp_fib_entry_priv {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 8f90cd323d5f..22fede5cb32c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -335,14 +335,16 @@ mlxsw_sp_bridge_port_find(struct mlxsw_sp_bridge *bridge,
 
 static struct mlxsw_sp_bridge_port *
 mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device,
-			    struct net_device *brport_dev)
+			    struct net_device *brport_dev,
+			    struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_bridge_port *bridge_port;
 	struct mlxsw_sp_port *mlxsw_sp_port;
+	int err;
 
 	bridge_port = kzalloc(sizeof(*bridge_port), GFP_KERNEL);
 	if (!bridge_port)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	mlxsw_sp_port = mlxsw_sp_port_dev_lower_find(brport_dev);
 	bridge_port->lagged = mlxsw_sp_port->lagged;
@@ -359,12 +361,23 @@ mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device,
 	list_add(&bridge_port->list, &bridge_device->ports_list);
 	bridge_port->ref_count = 1;
 
+	err = switchdev_bridge_port_offload(brport_dev, mlxsw_sp_port->dev,
+					    NULL, NULL, NULL, false, extack);
+	if (err)
+		goto err_switchdev_offload;
+
 	return bridge_port;
+
+err_switchdev_offload:
+	list_del(&bridge_port->list);
+	kfree(bridge_port);
+	return ERR_PTR(err);
 }
 
 static void
 mlxsw_sp_bridge_port_destroy(struct mlxsw_sp_bridge_port *bridge_port)
 {
+	switchdev_bridge_port_unoffload(bridge_port->dev, NULL, NULL, NULL);
 	list_del(&bridge_port->list);
 	WARN_ON(!list_empty(&bridge_port->vlans_list));
 	kfree(bridge_port);
@@ -390,9 +403,10 @@ mlxsw_sp_bridge_port_get(struct mlxsw_sp_bridge *bridge,
 	if (IS_ERR(bridge_device))
 		return ERR_CAST(bridge_device);
 
-	bridge_port = mlxsw_sp_bridge_port_create(bridge_device, brport_dev);
-	if (!bridge_port) {
-		err = -ENOMEM;
+	bridge_port = mlxsw_sp_bridge_port_create(bridge_device, brport_dev,
+						  extack);
+	if (IS_ERR(bridge_port)) {
+		err = PTR_ERR(bridge_port);
 		goto err_bridge_port_create;
 	}
 
@@ -1569,7 +1583,6 @@ mlxsw_sp_mc_write_mdb_entry(struct mlxsw_sp *mlxsw_sp,
 {
 	long *flood_bitmap;
 	int num_of_ports;
-	int alloc_size;
 	u16 mid_idx;
 	int err;
 
@@ -1579,18 +1592,17 @@ mlxsw_sp_mc_write_mdb_entry(struct mlxsw_sp *mlxsw_sp,
 		return false;
 
 	num_of_ports = mlxsw_core_max_ports(mlxsw_sp->core);
-	alloc_size = sizeof(long) * BITS_TO_LONGS(num_of_ports);
-	flood_bitmap = kzalloc(alloc_size, GFP_KERNEL);
+	flood_bitmap = bitmap_alloc(num_of_ports, GFP_KERNEL);
 	if (!flood_bitmap)
 		return false;
 
-	bitmap_copy(flood_bitmap,  mid->ports_in_mid, num_of_ports);
+	bitmap_copy(flood_bitmap, mid->ports_in_mid, num_of_ports);
 	mlxsw_sp_mc_get_mrouters_bitmap(flood_bitmap, bridge_device, mlxsw_sp);
 
 	mid->mid = mid_idx;
 	err = mlxsw_sp_port_smid_full_entry(mlxsw_sp, mid_idx, flood_bitmap,
 					    bridge_device->mrouter);
-	kfree(flood_bitmap);
+	bitmap_free(flood_bitmap);
 	if (err)
 		return false;
 
diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c
index 831518466de2..3f69bb59ba49 100644
--- a/drivers/net/ethernet/micrel/ks8851_common.c
+++ b/drivers/net/ethernet/micrel/ks8851_common.c
@@ -689,7 +689,7 @@ static int ks8851_net_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
 static const struct net_device_ops ks8851_netdev_ops = {
 	.ndo_open		= ks8851_net_open,
 	.ndo_stop		= ks8851_net_stop,
-	.ndo_do_ioctl		= ks8851_net_ioctl,
+	.ndo_eth_ioctl		= ks8851_net_ioctl,
 	.ndo_start_xmit		= ks8851_start_xmit,
 	.ndo_set_mac_address	= ks8851_set_mac_address,
 	.ndo_set_rx_mode	= ks8851_set_rx_mode,
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index 7945eb5e2fe8..a0ee155f9f51 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -6738,7 +6738,7 @@ static const struct net_device_ops netdev_ops = {
 	.ndo_set_features	= netdev_set_features,
 	.ndo_set_mac_address	= netdev_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= netdev_ioctl,
+	.ndo_eth_ioctl		= netdev_ioctl,
 	.ndo_set_rx_mode	= netdev_set_rx_mode,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= netdev_netpoll,
diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig
index d54aa164c4e9..735eea1dacf1 100644
--- a/drivers/net/ethernet/microchip/Kconfig
+++ b/drivers/net/ethernet/microchip/Kconfig
@@ -45,6 +45,7 @@ config ENCX24J600
 config LAN743X
 	tristate "LAN743x support"
 	depends on PCI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select PHYLIB
 	select CRC16
 	select CRC32
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index dae10328c6cf..9e8561cdc32a 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -2655,7 +2655,7 @@ static const struct net_device_ops lan743x_netdev_ops = {
 	.ndo_open		= lan743x_netdev_open,
 	.ndo_stop		= lan743x_netdev_close,
 	.ndo_start_xmit		= lan743x_netdev_xmit_frame,
-	.ndo_do_ioctl		= lan743x_netdev_ioctl,
+	.ndo_eth_ioctl		= lan743x_netdev_ioctl,
 	.ndo_set_rx_mode	= lan743x_netdev_set_multicast,
 	.ndo_change_mtu		= lan743x_netdev_change_mtu,
 	.ndo_get_stats64	= lan743x_netdev_get_stats64,
diff --git a/drivers/net/ethernet/microchip/sparx5/Makefile b/drivers/net/ethernet/microchip/sparx5/Makefile
index faa8f07a6b75..c271e86ee292 100644
--- a/drivers/net/ethernet/microchip/sparx5/Makefile
+++ b/drivers/net/ethernet/microchip/sparx5/Makefile
@@ -7,4 +7,4 @@ obj-$(CONFIG_SPARX5_SWITCH) += sparx5-switch.o
 
 sparx5-switch-objs  := sparx5_main.o sparx5_packet.o \
  sparx5_netdev.o sparx5_phylink.o sparx5_port.o sparx5_mactable.o sparx5_vlan.o \
- sparx5_switchdev.o sparx5_calendar.o sparx5_ethtool.o
+ sparx5_switchdev.o sparx5_calendar.o sparx5_ethtool.o sparx5_fdma.o
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
new file mode 100644
index 000000000000..7436f62fa152
--- /dev/null
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -0,0 +1,593 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Microchip Sparx5 Switch driver
+ *
+ * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries.
+ *
+ * The Sparx5 Chip Register Model can be browsed at this location:
+ * https://github.com/microchip-ung/sparx-5_reginfo
+ */
+
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/interrupt.h>
+#include <linux/ip.h>
+#include <linux/dma-mapping.h>
+
+#include "sparx5_main_regs.h"
+#include "sparx5_main.h"
+#include "sparx5_port.h"
+
+#define FDMA_XTR_CHANNEL		6
+#define FDMA_INJ_CHANNEL		0
+
+#define FDMA_DCB_INFO_DATAL(x)		((x) & GENMASK(15, 0))
+#define FDMA_DCB_INFO_TOKEN		BIT(17)
+#define FDMA_DCB_INFO_INTR		BIT(18)
+#define FDMA_DCB_INFO_SW(x)		(((x) << 24) & GENMASK(31, 24))
+
+#define FDMA_DCB_STATUS_BLOCKL(x)	((x) & GENMASK(15, 0))
+#define FDMA_DCB_STATUS_SOF		BIT(16)
+#define FDMA_DCB_STATUS_EOF		BIT(17)
+#define FDMA_DCB_STATUS_INTR		BIT(18)
+#define FDMA_DCB_STATUS_DONE		BIT(19)
+#define FDMA_DCB_STATUS_BLOCKO(x)	(((x) << 20) & GENMASK(31, 20))
+#define FDMA_DCB_INVALID_DATA		0x1
+
+#define FDMA_XTR_BUFFER_SIZE		2048
+#define FDMA_WEIGHT			4
+
+/* Frame DMA DCB format
+ *
+ * +---------------------------+
+ * |         Next Ptr          |
+ * +---------------------------+
+ * |   Reserved  |    Info     |
+ * +---------------------------+
+ * |         Data0 Ptr         |
+ * +---------------------------+
+ * |   Reserved  |    Status0  |
+ * +---------------------------+
+ * |         Data1 Ptr         |
+ * +---------------------------+
+ * |   Reserved  |    Status1  |
+ * +---------------------------+
+ * |         Data2 Ptr         |
+ * +---------------------------+
+ * |   Reserved  |    Status2  |
+ * |-------------|-------------|
+ * |                           |
+ * |                           |
+ * |                           |
+ * |                           |
+ * |                           |
+ * |---------------------------|
+ * |         Data14 Ptr        |
+ * +-------------|-------------+
+ * |   Reserved  |    Status14 |
+ * +-------------|-------------+
+ */
+
+/* For each hardware DB there is an entry in this list and when the HW DB
+ * entry is used, this SW DB entry is moved to the back of the list
+ */
+struct sparx5_db {
+	struct list_head list;
+	void *cpu_addr;
+};
+
+static void sparx5_fdma_rx_add_dcb(struct sparx5_rx *rx,
+				   struct sparx5_rx_dcb_hw *dcb,
+				   u64 nextptr)
+{
+	int idx = 0;
+
+	/* Reset the status of the DB */
+	for (idx = 0; idx < FDMA_RX_DCB_MAX_DBS; ++idx) {
+		struct sparx5_db_hw *db = &dcb->db[idx];
+
+		db->status = FDMA_DCB_STATUS_INTR;
+	}
+	dcb->nextptr = FDMA_DCB_INVALID_DATA;
+	dcb->info = FDMA_DCB_INFO_DATAL(FDMA_XTR_BUFFER_SIZE);
+	rx->last_entry->nextptr = nextptr;
+	rx->last_entry = dcb;
+}
+
+static void sparx5_fdma_tx_add_dcb(struct sparx5_tx *tx,
+				   struct sparx5_tx_dcb_hw *dcb,
+				   u64 nextptr)
+{
+	int idx = 0;
+
+	/* Reset the status of the DB */
+	for (idx = 0; idx < FDMA_TX_DCB_MAX_DBS; ++idx) {
+		struct sparx5_db_hw *db = &dcb->db[idx];
+
+		db->status = FDMA_DCB_STATUS_DONE;
+	}
+	dcb->nextptr = FDMA_DCB_INVALID_DATA;
+	dcb->info = FDMA_DCB_INFO_DATAL(FDMA_XTR_BUFFER_SIZE);
+}
+
+static void sparx5_fdma_rx_activate(struct sparx5 *sparx5, struct sparx5_rx *rx)
+{
+	/* Write the buffer address in the LLP and LLP1 regs */
+	spx5_wr(((u64)rx->dma) & GENMASK(31, 0), sparx5,
+		FDMA_DCB_LLP(rx->channel_id));
+	spx5_wr(((u64)rx->dma) >> 32, sparx5, FDMA_DCB_LLP1(rx->channel_id));
+
+	/* Set the number of RX DBs to be used, and DB end-of-frame interrupt */
+	spx5_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(FDMA_RX_DCB_MAX_DBS) |
+		FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY_SET(1) |
+		FDMA_CH_CFG_CH_INJ_PORT_SET(XTR_QUEUE),
+		sparx5, FDMA_CH_CFG(rx->channel_id));
+
+	/* Set the RX Watermark to max */
+	spx5_rmw(FDMA_XTR_CFG_XTR_FIFO_WM_SET(31), FDMA_XTR_CFG_XTR_FIFO_WM,
+		 sparx5,
+		 FDMA_XTR_CFG);
+
+	/* Start RX fdma */
+	spx5_rmw(FDMA_PORT_CTRL_XTR_STOP_SET(0), FDMA_PORT_CTRL_XTR_STOP,
+		 sparx5, FDMA_PORT_CTRL(0));
+
+	/* Enable RX channel DB interrupt */
+	spx5_rmw(BIT(rx->channel_id),
+		 BIT(rx->channel_id) & FDMA_INTR_DB_ENA_INTR_DB_ENA,
+		 sparx5, FDMA_INTR_DB_ENA);
+
+	/* Activate the RX channel */
+	spx5_wr(BIT(rx->channel_id), sparx5, FDMA_CH_ACTIVATE);
+}
+
+static void sparx5_fdma_rx_deactivate(struct sparx5 *sparx5, struct sparx5_rx *rx)
+{
+	/* Dectivate the RX channel */
+	spx5_rmw(0, BIT(rx->channel_id) & FDMA_CH_ACTIVATE_CH_ACTIVATE,
+		 sparx5, FDMA_CH_ACTIVATE);
+
+	/* Disable RX channel DB interrupt */
+	spx5_rmw(0, BIT(rx->channel_id) & FDMA_INTR_DB_ENA_INTR_DB_ENA,
+		 sparx5, FDMA_INTR_DB_ENA);
+
+	/* Stop RX fdma */
+	spx5_rmw(FDMA_PORT_CTRL_XTR_STOP_SET(1), FDMA_PORT_CTRL_XTR_STOP,
+		 sparx5, FDMA_PORT_CTRL(0));
+}
+
+static void sparx5_fdma_tx_activate(struct sparx5 *sparx5, struct sparx5_tx *tx)
+{
+	/* Write the buffer address in the LLP and LLP1 regs */
+	spx5_wr(((u64)tx->dma) & GENMASK(31, 0), sparx5,
+		FDMA_DCB_LLP(tx->channel_id));
+	spx5_wr(((u64)tx->dma) >> 32, sparx5, FDMA_DCB_LLP1(tx->channel_id));
+
+	/* Set the number of TX DBs to be used, and DB end-of-frame interrupt */
+	spx5_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(FDMA_TX_DCB_MAX_DBS) |
+		FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY_SET(1) |
+		FDMA_CH_CFG_CH_INJ_PORT_SET(INJ_QUEUE),
+		sparx5, FDMA_CH_CFG(tx->channel_id));
+
+	/* Start TX fdma */
+	spx5_rmw(FDMA_PORT_CTRL_INJ_STOP_SET(0), FDMA_PORT_CTRL_INJ_STOP,
+		 sparx5, FDMA_PORT_CTRL(0));
+
+	/* Activate the channel */
+	spx5_wr(BIT(tx->channel_id), sparx5, FDMA_CH_ACTIVATE);
+}
+
+static void sparx5_fdma_tx_deactivate(struct sparx5 *sparx5, struct sparx5_tx *tx)
+{
+	/* Disable the channel */
+	spx5_rmw(0, BIT(tx->channel_id) & FDMA_CH_ACTIVATE_CH_ACTIVATE,
+		 sparx5, FDMA_CH_ACTIVATE);
+}
+
+static void sparx5_fdma_rx_reload(struct sparx5 *sparx5, struct sparx5_rx *rx)
+{
+	/* Reload the RX channel */
+	spx5_wr(BIT(rx->channel_id), sparx5, FDMA_CH_RELOAD);
+}
+
+static void sparx5_fdma_tx_reload(struct sparx5 *sparx5, struct sparx5_tx *tx)
+{
+	/* Reload the TX channel */
+	spx5_wr(BIT(tx->channel_id), sparx5, FDMA_CH_RELOAD);
+}
+
+static struct sk_buff *sparx5_fdma_rx_alloc_skb(struct sparx5_rx *rx)
+{
+	return __netdev_alloc_skb(rx->ndev, FDMA_XTR_BUFFER_SIZE,
+				  GFP_ATOMIC);
+}
+
+static bool sparx5_fdma_rx_get_frame(struct sparx5 *sparx5, struct sparx5_rx *rx)
+{
+	struct sparx5_db_hw *db_hw;
+	unsigned int packet_size;
+	struct sparx5_port *port;
+	struct sk_buff *new_skb;
+	struct frame_info fi;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+
+	/* Check if the DCB is done */
+	db_hw = &rx->dcb_entries[rx->dcb_index].db[rx->db_index];
+	if (unlikely(!(db_hw->status & FDMA_DCB_STATUS_DONE)))
+		return false;
+	skb = rx->skb[rx->dcb_index][rx->db_index];
+	/* Replace the DB entry with a new SKB */
+	new_skb = sparx5_fdma_rx_alloc_skb(rx);
+	if (unlikely(!new_skb))
+		return false;
+	/* Map the new skb data and set the new skb */
+	dma_addr = virt_to_phys(new_skb->data);
+	rx->skb[rx->dcb_index][rx->db_index] = new_skb;
+	db_hw->dataptr = dma_addr;
+	packet_size = FDMA_DCB_STATUS_BLOCKL(db_hw->status);
+	skb_put(skb, packet_size);
+	/* Now do the normal processing of the skb */
+	sparx5_ifh_parse((u32 *)skb->data, &fi);
+	/* Map to port netdev */
+	port = fi.src_port < SPX5_PORTS ?  sparx5->ports[fi.src_port] : NULL;
+	if (!port || !port->ndev) {
+		dev_err(sparx5->dev, "Data on inactive port %d\n", fi.src_port);
+		sparx5_xtr_flush(sparx5, XTR_QUEUE);
+		return false;
+	}
+	skb->dev = port->ndev;
+	skb_pull(skb, IFH_LEN * sizeof(u32));
+	if (likely(!(skb->dev->features & NETIF_F_RXFCS)))
+		skb_trim(skb, skb->len - ETH_FCS_LEN);
+	skb->protocol = eth_type_trans(skb, skb->dev);
+	/* Everything we see on an interface that is in the HW bridge
+	 * has already been forwarded
+	 */
+	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++;
+	rx->packets++;
+	netif_receive_skb(skb);
+	return true;
+}
+
+static 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);
+	int counter = 0;
+
+	while (counter < weight && sparx5_fdma_rx_get_frame(sparx5, rx)) {
+		struct sparx5_rx_dcb_hw *old_dcb;
+
+		rx->db_index++;
+		counter++;
+		/* Check if the DCB can be reused */
+		if (rx->db_index != FDMA_RX_DCB_MAX_DBS)
+			continue;
+		/* As the DCB  can be reused, just advance the dcb_index
+		 * pointer and set the nextptr in the DCB
+		 */
+		rx->db_index = 0;
+		old_dcb = &rx->dcb_entries[rx->dcb_index];
+		rx->dcb_index++;
+		rx->dcb_index &= FDMA_DCB_MAX - 1;
+		sparx5_fdma_rx_add_dcb(rx, old_dcb,
+				       rx->dma +
+				       ((unsigned long)old_dcb -
+					(unsigned long)rx->dcb_entries));
+	}
+	if (counter < weight) {
+		napi_complete_done(&rx->napi, counter);
+		spx5_rmw(BIT(rx->channel_id),
+			 BIT(rx->channel_id) & FDMA_INTR_DB_ENA_INTR_DB_ENA,
+			 sparx5, FDMA_INTR_DB_ENA);
+	}
+	if (counter)
+		sparx5_fdma_rx_reload(sparx5, rx);
+	return counter;
+}
+
+static struct sparx5_tx_dcb_hw *sparx5_fdma_next_dcb(struct sparx5_tx *tx,
+						     struct sparx5_tx_dcb_hw *dcb)
+{
+	struct sparx5_tx_dcb_hw *next_dcb;
+
+	next_dcb = dcb;
+	next_dcb++;
+	/* Handle wrap-around */
+	if ((unsigned long)next_dcb >=
+	    ((unsigned long)tx->first_entry + FDMA_DCB_MAX * sizeof(*dcb)))
+		next_dcb = tx->first_entry;
+	return next_dcb;
+}
+
+int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb)
+{
+	struct sparx5_tx_dcb_hw *next_dcb_hw;
+	struct sparx5_tx *tx = &sparx5->tx;
+	static bool first_time = true;
+	struct sparx5_db_hw *db_hw;
+	struct sparx5_db *db;
+
+	next_dcb_hw = sparx5_fdma_next_dcb(tx, tx->curr_entry);
+	db_hw = &next_dcb_hw->db[0];
+	if (!(db_hw->status & FDMA_DCB_STATUS_DONE))
+		tx->dropped++;
+	db = list_first_entry(&tx->db_list, struct sparx5_db, list);
+	list_move_tail(&db->list, &tx->db_list);
+	next_dcb_hw->nextptr = FDMA_DCB_INVALID_DATA;
+	tx->curr_entry->nextptr = tx->dma +
+		((unsigned long)next_dcb_hw -
+		 (unsigned long)tx->first_entry);
+	tx->curr_entry = next_dcb_hw;
+	memset(db->cpu_addr, 0, FDMA_XTR_BUFFER_SIZE);
+	memcpy(db->cpu_addr, ifh, IFH_LEN * 4);
+	memcpy(db->cpu_addr + IFH_LEN * 4, skb->data, skb->len);
+	db_hw->status = FDMA_DCB_STATUS_SOF |
+			FDMA_DCB_STATUS_EOF |
+			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_tx_reload(sparx5, tx);
+	}
+	return NETDEV_TX_OK;
+}
+
+static int sparx5_fdma_rx_alloc(struct sparx5 *sparx5)
+{
+	struct sparx5_rx *rx = &sparx5->rx;
+	struct sparx5_rx_dcb_hw *dcb;
+	int idx, jdx;
+	int size;
+
+	size = sizeof(struct sparx5_rx_dcb_hw) * FDMA_DCB_MAX;
+	size = ALIGN(size, PAGE_SIZE);
+	rx->dcb_entries = devm_kzalloc(sparx5->dev, size, GFP_KERNEL);
+	if (!rx->dcb_entries)
+		return -ENOMEM;
+	rx->dma = virt_to_phys(rx->dcb_entries);
+	rx->last_entry = rx->dcb_entries;
+	rx->db_index = 0;
+	rx->dcb_index = 0;
+	/* Now for each dcb allocate the db */
+	for (idx = 0; idx < FDMA_DCB_MAX; ++idx) {
+		dcb = &rx->dcb_entries[idx];
+		dcb->info = 0;
+		/* For each db allocate an skb and map skb data pointer to the DB
+		 * dataptr. In this way when the frame is received the skb->data
+		 * will contain the frame, so no memcpy is needed
+		 */
+		for (jdx = 0; jdx < FDMA_RX_DCB_MAX_DBS; ++jdx) {
+			struct sparx5_db_hw *db_hw = &dcb->db[jdx];
+			dma_addr_t dma_addr;
+			struct sk_buff *skb;
+
+			skb = sparx5_fdma_rx_alloc_skb(rx);
+			if (!skb)
+				return -ENOMEM;
+
+			dma_addr = virt_to_phys(skb->data);
+			db_hw->dataptr = dma_addr;
+			db_hw->status = 0;
+			rx->skb[idx][jdx] = skb;
+		}
+		sparx5_fdma_rx_add_dcb(rx, dcb, rx->dma + sizeof(*dcb) * idx);
+	}
+	netif_napi_add(rx->ndev, &rx->napi, sparx5_fdma_napi_callback, FDMA_WEIGHT);
+	napi_enable(&rx->napi);
+	sparx5_fdma_rx_activate(sparx5, rx);
+	return 0;
+}
+
+static int sparx5_fdma_tx_alloc(struct sparx5 *sparx5)
+{
+	struct sparx5_tx *tx = &sparx5->tx;
+	struct sparx5_tx_dcb_hw *dcb;
+	int idx, jdx;
+	int size;
+
+	size = sizeof(struct sparx5_tx_dcb_hw) * FDMA_DCB_MAX;
+	size = ALIGN(size, PAGE_SIZE);
+	tx->curr_entry = devm_kzalloc(sparx5->dev, size, GFP_KERNEL);
+	if (!tx->curr_entry)
+		return -ENOMEM;
+	tx->dma = virt_to_phys(tx->curr_entry);
+	tx->first_entry = tx->curr_entry;
+	INIT_LIST_HEAD(&tx->db_list);
+	/* Now for each dcb allocate the db */
+	for (idx = 0; idx < FDMA_DCB_MAX; ++idx) {
+		dcb = &tx->curr_entry[idx];
+		dcb->info = 0;
+		/* TX databuffers must be 16byte aligned */
+		for (jdx = 0; jdx < FDMA_TX_DCB_MAX_DBS; ++jdx) {
+			struct sparx5_db_hw *db_hw = &dcb->db[jdx];
+			struct sparx5_db *db;
+			dma_addr_t phys;
+			void *cpu_addr;
+
+			cpu_addr = devm_kzalloc(sparx5->dev,
+						FDMA_XTR_BUFFER_SIZE,
+						GFP_KERNEL);
+			if (!cpu_addr)
+				return -ENOMEM;
+			phys = virt_to_phys(cpu_addr);
+			db_hw->dataptr = phys;
+			db_hw->status = 0;
+			db = devm_kzalloc(sparx5->dev, sizeof(*db), GFP_KERNEL);
+			db->cpu_addr = cpu_addr;
+			list_add_tail(&db->list, &tx->db_list);
+		}
+		sparx5_fdma_tx_add_dcb(tx, dcb, tx->dma + sizeof(*dcb) * idx);
+		/* Let the curr_entry to point to the last allocated entry */
+		if (idx == FDMA_DCB_MAX - 1)
+			tx->curr_entry = dcb;
+	}
+	return 0;
+}
+
+static void sparx5_fdma_rx_init(struct sparx5 *sparx5,
+				struct sparx5_rx *rx, int channel)
+{
+	int idx;
+
+	rx->channel_id = channel;
+	/* Fetch a netdev for SKB and NAPI use, any will do */
+	for (idx = 0; idx < SPX5_PORTS; ++idx) {
+		struct sparx5_port *port = sparx5->ports[idx];
+
+		if (port && port->ndev) {
+			rx->ndev = port->ndev;
+			break;
+		}
+	}
+}
+
+static void sparx5_fdma_tx_init(struct sparx5 *sparx5,
+				struct sparx5_tx *tx, int channel)
+{
+	tx->channel_id = channel;
+}
+
+irqreturn_t sparx5_fdma_handler(int irq, void *args)
+{
+	struct sparx5 *sparx5 = args;
+	u32 db = 0, err = 0;
+
+	db = spx5_rd(sparx5, FDMA_INTR_DB);
+	err = spx5_rd(sparx5, FDMA_INTR_ERR);
+	/* Clear interrupt */
+	if (db) {
+		spx5_wr(0, sparx5, FDMA_INTR_DB_ENA);
+		spx5_wr(db, sparx5, FDMA_INTR_DB);
+		napi_schedule(&sparx5->rx.napi);
+	}
+	if (err) {
+		u32 err_type = spx5_rd(sparx5, FDMA_ERRORS);
+
+		dev_err_ratelimited(sparx5->dev,
+				    "ERR: int: %#x, type: %#x\n",
+				    err, err_type);
+		spx5_wr(err, sparx5, FDMA_INTR_ERR);
+		spx5_wr(err_type, sparx5, FDMA_ERRORS);
+	}
+	return IRQ_HANDLED;
+}
+
+static void sparx5_fdma_injection_mode(struct sparx5 *sparx5)
+{
+	const int byte_swap = 1;
+	int portno;
+	int urgency;
+
+	/* Change mode to fdma extraction and injection */
+	spx5_wr(QS_XTR_GRP_CFG_MODE_SET(2) |
+		QS_XTR_GRP_CFG_STATUS_WORD_POS_SET(1) |
+		QS_XTR_GRP_CFG_BYTE_SWAP_SET(byte_swap),
+		sparx5, QS_XTR_GRP_CFG(XTR_QUEUE));
+	spx5_wr(QS_INJ_GRP_CFG_MODE_SET(2) |
+		QS_INJ_GRP_CFG_BYTE_SWAP_SET(byte_swap),
+		sparx5, QS_INJ_GRP_CFG(INJ_QUEUE));
+
+	/* CPU ports capture setup */
+	for (portno = SPX5_PORT_CPU_0; portno <= SPX5_PORT_CPU_1; portno++) {
+		/* ASM CPU port: No preamble, IFH, enable padding */
+		spx5_wr(ASM_PORT_CFG_PAD_ENA_SET(1) |
+			ASM_PORT_CFG_NO_PREAMBLE_ENA_SET(1) |
+			ASM_PORT_CFG_INJ_FORMAT_CFG_SET(1), /* 1 = IFH */
+			sparx5, ASM_PORT_CFG(portno));
+
+		/* Reset WM cnt to unclog queued frames */
+		spx5_rmw(DSM_DEV_TX_STOP_WM_CFG_DEV_TX_CNT_CLR_SET(1),
+			 DSM_DEV_TX_STOP_WM_CFG_DEV_TX_CNT_CLR,
+			 sparx5,
+			 DSM_DEV_TX_STOP_WM_CFG(portno));
+
+		/* Set Disassembler Stop Watermark level */
+		spx5_rmw(DSM_DEV_TX_STOP_WM_CFG_DEV_TX_STOP_WM_SET(100),
+			 DSM_DEV_TX_STOP_WM_CFG_DEV_TX_STOP_WM,
+			 sparx5,
+			 DSM_DEV_TX_STOP_WM_CFG(portno));
+
+		/* Enable port in queue system */
+		urgency = sparx5_port_fwd_urg(sparx5, SPEED_2500);
+		spx5_rmw(QFWD_SWITCH_PORT_MODE_PORT_ENA_SET(1) |
+			 QFWD_SWITCH_PORT_MODE_FWD_URGENCY_SET(urgency),
+			 QFWD_SWITCH_PORT_MODE_PORT_ENA |
+			 QFWD_SWITCH_PORT_MODE_FWD_URGENCY,
+			 sparx5,
+			 QFWD_SWITCH_PORT_MODE(portno));
+
+		/* Disable Disassembler buffer underrun watchdog
+		 * to avoid truncated packets in XTR
+		 */
+		spx5_rmw(DSM_BUF_CFG_UNDERFLOW_WATCHDOG_DIS_SET(1),
+			 DSM_BUF_CFG_UNDERFLOW_WATCHDOG_DIS,
+			 sparx5,
+			 DSM_BUF_CFG(portno));
+
+		/* Disabling frame aging */
+		spx5_rmw(HSCH_PORT_MODE_AGE_DIS_SET(1),
+			 HSCH_PORT_MODE_AGE_DIS,
+			 sparx5,
+			 HSCH_PORT_MODE(portno));
+	}
+}
+
+int sparx5_fdma_start(struct sparx5 *sparx5)
+{
+	int err;
+
+	/* Reset FDMA state */
+	spx5_wr(FDMA_CTRL_NRESET_SET(0), sparx5, FDMA_CTRL);
+	spx5_wr(FDMA_CTRL_NRESET_SET(1), sparx5, FDMA_CTRL);
+
+	/* Force ACP caching but disable read/write allocation */
+	spx5_rmw(CPU_PROC_CTRL_ACP_CACHE_FORCE_ENA_SET(1) |
+		 CPU_PROC_CTRL_ACP_AWCACHE_SET(0) |
+		 CPU_PROC_CTRL_ACP_ARCACHE_SET(0),
+		 CPU_PROC_CTRL_ACP_CACHE_FORCE_ENA |
+		 CPU_PROC_CTRL_ACP_AWCACHE |
+		 CPU_PROC_CTRL_ACP_ARCACHE,
+		 sparx5, CPU_PROC_CTRL);
+
+	sparx5_fdma_injection_mode(sparx5);
+	sparx5_fdma_rx_init(sparx5, &sparx5->rx, FDMA_XTR_CHANNEL);
+	sparx5_fdma_tx_init(sparx5, &sparx5->tx, FDMA_INJ_CHANNEL);
+	err = sparx5_fdma_rx_alloc(sparx5);
+	if (err) {
+		dev_err(sparx5->dev, "Could not allocate RX buffers: %d\n", err);
+		return err;
+	}
+	err = sparx5_fdma_tx_alloc(sparx5);
+	if (err) {
+		dev_err(sparx5->dev, "Could not allocate TX buffers: %d\n", err);
+		return err;
+	}
+	return err;
+}
+
+static u32 sparx5_fdma_port_ctrl(struct sparx5 *sparx5)
+{
+	return spx5_rd(sparx5, FDMA_PORT_CTRL(0));
+}
+
+int sparx5_fdma_stop(struct sparx5 *sparx5)
+{
+	u32 val;
+
+	napi_disable(&sparx5->rx.napi);
+	/* Stop the fdma and channel interrupts */
+	sparx5_fdma_rx_deactivate(sparx5, &sparx5->rx);
+	sparx5_fdma_tx_deactivate(sparx5, &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);
+	return 0;
+}
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
index f666133a15de..cbece6e9bff2 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
@@ -640,8 +640,23 @@ static int sparx5_start(struct sparx5 *sparx5)
 	sparx5_board_init(sparx5);
 	err = sparx5_register_notifier_blocks(sparx5);
 
-	/* Start register based INJ/XTR */
+	/* Start Frame DMA with fallback to register based INJ/XTR */
 	err = -ENXIO;
+	if (sparx5->fdma_irq >= 0) {
+		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 (err)
+			sparx5->fdma_irq = -ENXIO;
+	} else {
+		sparx5->fdma_irq = -ENXIO;
+	}
 	if (err && sparx5->xtr_irq >= 0) {
 		err = devm_request_irq(sparx5->dev, sparx5->xtr_irq,
 				       sparx5_xtr_handler, IRQF_SHARED,
@@ -766,6 +781,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev)
 		sparx5->base_mac[5] = 0;
 	}
 
+	sparx5->fdma_irq = platform_get_irq_byname(sparx5->pdev, "fdma");
 	sparx5->xtr_irq = platform_get_irq_byname(sparx5->pdev, "xtr");
 
 	/* Read chip ID to check CPU interface */
@@ -824,6 +840,11 @@ static int mchp_sparx5_remove(struct platform_device *pdev)
 		disable_irq(sparx5->xtr_irq);
 		sparx5->xtr_irq = -ENXIO;
 	}
+	if (sparx5->fdma_irq) {
+		disable_irq(sparx5->fdma_irq);
+		sparx5->fdma_irq = -ENXIO;
+	}
+	sparx5_fdma_stop(sparx5);
 	sparx5_cleanup_ports(sparx5);
 	/* Unregister netdevs */
 	sparx5_unregister_notifier_blocks(sparx5);
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
index 4d5f44c3a421..a1acc9b461f2 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
@@ -73,8 +73,61 @@ enum sparx5_vlan_port_type {
 #define XTR_QUEUE     0
 #define INJ_QUEUE     0
 
+#define FDMA_DCB_MAX			64
+#define FDMA_RX_DCB_MAX_DBS		15
+#define FDMA_TX_DCB_MAX_DBS		1
+
 struct sparx5;
 
+struct sparx5_db_hw {
+	u64 dataptr;
+	u64 status;
+};
+
+struct sparx5_rx_dcb_hw {
+	u64 nextptr;
+	u64 info;
+	struct sparx5_db_hw db[FDMA_RX_DCB_MAX_DBS];
+};
+
+struct sparx5_tx_dcb_hw {
+	u64 nextptr;
+	u64 info;
+	struct sparx5_db_hw db[FDMA_TX_DCB_MAX_DBS];
+};
+
+/* Frame DMA receive state:
+ * For each DB, there is a SKB, and the skb data pointer is mapped in
+ * the DB. Once a frame is received the skb is given to the upper layers
+ * and a new skb is added to the dcb.
+ * When the db_index reached FDMA_RX_DCB_MAX_DBS the DB is reused.
+ */
+struct sparx5_rx {
+	struct sparx5_rx_dcb_hw *dcb_entries;
+	struct sparx5_rx_dcb_hw *last_entry;
+	struct sk_buff *skb[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS];
+	int db_index;
+	int dcb_index;
+	dma_addr_t dma;
+	struct napi_struct napi;
+	u32 channel_id;
+	struct net_device *ndev;
+	u64 packets;
+};
+
+/* Frame DMA transmit state:
+ * DCBs are chained using the DCBs nextptr field.
+ */
+struct sparx5_tx {
+	struct sparx5_tx_dcb_hw *curr_entry;
+	struct sparx5_tx_dcb_hw *first_entry;
+	struct list_head db_list;
+	dma_addr_t dma;
+	u32 channel_id;
+	u64 packets;
+	u64 dropped;
+};
+
 struct sparx5_port_config {
 	phy_interface_t portmode;
 	u32 bandwidth;
@@ -167,6 +220,10 @@ struct sparx5 {
 	bool sd_sgpio_remapping;
 	/* Register based inj/xtr */
 	int xtr_irq;
+	/* Frame DMA */
+	int fdma_irq;
+	struct sparx5_rx rx;
+	struct sparx5_tx tx;
 };
 
 /* sparx5_switchdev.c */
@@ -174,11 +231,23 @@ int sparx5_register_notifier_blocks(struct sparx5 *sparx5);
 void sparx5_unregister_notifier_blocks(struct sparx5 *sparx5);
 
 /* sparx5_packet.c */
+struct frame_info {
+	int src_port;
+};
+
+void sparx5_xtr_flush(struct sparx5 *sparx5, u8 grp);
+void sparx5_ifh_parse(u32 *ifh, struct frame_info *info);
 irqreturn_t sparx5_xtr_handler(int irq, void *_priv);
 int sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev);
 int sparx5_manual_injection_mode(struct sparx5 *sparx5);
 void sparx5_port_inj_timer_setup(struct sparx5_port *port);
 
+/* sparx5_fdma.c */
+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);
+irqreturn_t sparx5_fdma_handler(int irq, void *args);
+
 /* sparx5_mactable.c */
 void sparx5_mact_pull_work(struct work_struct *work);
 int sparx5_mact_learn(struct sparx5 *sparx5, int port,
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
index 09ca7a3bafdc..dc7e5ea6ec15 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
@@ -20,11 +20,7 @@
 
 #define INJ_TIMEOUT_NS 50000
 
-struct frame_info {
-	int src_port;
-};
-
-static void sparx5_xtr_flush(struct sparx5 *sparx5, u8 grp)
+void sparx5_xtr_flush(struct sparx5 *sparx5, u8 grp)
 {
 	/* Start flush */
 	spx5_wr(QS_XTR_FLUSH_FLUSH_SET(BIT(grp)), sparx5, QS_XTR_FLUSH);
@@ -36,7 +32,7 @@ static void sparx5_xtr_flush(struct sparx5 *sparx5, u8 grp)
 	spx5_wr(0, sparx5, QS_XTR_FLUSH);
 }
 
-static void sparx5_ifh_parse(u32 *ifh, struct frame_info *info)
+void sparx5_ifh_parse(u32 *ifh, struct frame_info *info)
 {
 	u8 *xtr_hdr = (u8 *)ifh;
 
@@ -224,7 +220,10 @@ int sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev)
 	struct sparx5 *sparx5 = port->sparx5;
 	int ret;
 
-	ret = sparx5_inject(sparx5, port->ifh, skb, dev);
+	if (sparx5->fdma_irq > 0)
+		ret = sparx5_fdma_xmit(sparx5, port->ifh, skb);
+	else
+		ret = sparx5_inject(sparx5, port->ifh, skb, dev);
 
 	if (ret == NETDEV_TX_OK) {
 		stats->tx_bytes += skb->len;
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
index d2e3250928bf..189a6a0a2e08 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
@@ -596,7 +596,7 @@ static int sparx5_port_max_tags_set(struct sparx5 *sparx5,
 	return 0;
 }
 
-static int sparx5_port_fwd_urg(struct sparx5 *sparx5, u32 speed)
+int sparx5_port_fwd_urg(struct sparx5 *sparx5, u32 speed)
 {
 	u32 clk_period_ps = 1600; /* 625Mhz for now */
 	u32 urg = 672000;
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.h b/drivers/net/ethernet/microchip/sparx5/sparx5_port.h
index fd05ab6436d1..2f8043eac71b 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.h
@@ -89,5 +89,6 @@ int sparx5_get_port_status(struct sparx5 *sparx5,
 			   struct sparx5_port_status *status);
 
 void sparx5_port_enable(struct sparx5_port *port, bool enable);
+int sparx5_port_fwd_urg(struct sparx5 *sparx5, u32 speed);
 
 #endif	/* __SPARX5_PORT_H__ */
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c
index a72e3b3b596e..649ca609884a 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c
@@ -93,9 +93,12 @@ static int sparx5_port_attr_set(struct net_device *dev, const void *ctx,
 }
 
 static int sparx5_port_bridge_join(struct sparx5_port *port,
-				   struct net_device *bridge)
+				   struct net_device *bridge,
+				   struct netlink_ext_ack *extack)
 {
 	struct sparx5 *sparx5 = port->sparx5;
+	struct net_device *ndev = port->ndev;
+	int err;
 
 	if (bitmap_empty(sparx5->bridge_mask, SPX5_PORTS))
 		/* First bridged port */
@@ -109,12 +112,21 @@ static int sparx5_port_bridge_join(struct sparx5_port *port,
 
 	set_bit(port->portno, sparx5->bridge_mask);
 
+	err = switchdev_bridge_port_offload(ndev, ndev, NULL, NULL, NULL,
+					    false, extack);
+	if (err)
+		goto err_switchdev_offload;
+
 	/* Port enters in bridge mode therefor don't need to copy to CPU
 	 * frames for multicast in case the bridge is not requesting them
 	 */
-	__dev_mc_unsync(port->ndev, sparx5_mc_unsync);
+	__dev_mc_unsync(ndev, sparx5_mc_unsync);
 
 	return 0;
+
+err_switchdev_offload:
+	clear_bit(port->portno, sparx5->bridge_mask);
+	return err;
 }
 
 static void sparx5_port_bridge_leave(struct sparx5_port *port,
@@ -122,6 +134,8 @@ static void sparx5_port_bridge_leave(struct sparx5_port *port,
 {
 	struct sparx5 *sparx5 = port->sparx5;
 
+	switchdev_bridge_port_unoffload(port->ndev, NULL, NULL, NULL);
+
 	clear_bit(port->portno, sparx5->bridge_mask);
 	if (bitmap_empty(sparx5->bridge_mask, SPX5_PORTS))
 		sparx5->hw_bridge_dev = NULL;
@@ -139,11 +153,15 @@ static int sparx5_port_changeupper(struct net_device *dev,
 				   struct netdev_notifier_changeupper_info *info)
 {
 	struct sparx5_port *port = netdev_priv(dev);
+	struct netlink_ext_ack *extack;
 	int err = 0;
 
+	extack = netdev_notifier_info_to_extack(&info->info);
+
 	if (netif_is_bridge_master(info->upper_dev)) {
 		if (info->linking)
-			err = sparx5_port_bridge_join(port, info->upper_dev);
+			err = sparx5_port_bridge_join(port, info->upper_dev,
+						      extack);
 		else
 			sparx5_port_bridge_leave(port, info->upper_dev);
 
diff --git a/drivers/net/ethernet/microsoft/mana/gdma.h b/drivers/net/ethernet/microsoft/mana/gdma.h
index 33e53d32e891..41ecd156e95f 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma.h
+++ b/drivers/net/ethernet/microsoft/mana/gdma.h
@@ -239,10 +239,8 @@ struct gdma_event {
 
 struct gdma_queue;
 
-#define CQE_POLLING_BUFFER 512
 struct mana_eq {
 	struct gdma_queue *eq;
-	struct gdma_comp cqe_poll[CQE_POLLING_BUFFER];
 };
 
 typedef void gdma_eq_callback(void *context, struct gdma_queue *q,
@@ -291,11 +289,6 @@ struct gdma_queue {
 			unsigned int msix_index;
 
 			u32 log2_throttle_limit;
-
-			/* NAPI data */
-			struct napi_struct napi;
-			int work_done;
-			int budget;
 		} eq;
 
 		struct {
@@ -319,9 +312,6 @@ struct gdma_queue_spec {
 			void *context;
 
 			unsigned long log2_throttle_limit;
-
-			/* Only used by the MANA device. */
-			struct net_device *ndev;
 		} eq;
 
 		struct {
@@ -406,7 +396,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue);
 
 int mana_gd_poll_cq(struct gdma_queue *cq, struct gdma_comp *comp, int num_cqe);
 
-void mana_gd_arm_cq(struct gdma_queue *cq);
+void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit);
 
 struct gdma_wqe {
 	u32 reserved	:24;
@@ -496,16 +486,28 @@ enum {
 	GDMA_PROTOCOL_LAST	= GDMA_PROTOCOL_V1,
 };
 
+#define GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT BIT(0)
+
+#define GDMA_DRV_CAP_FLAGS1 GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT
+
+#define GDMA_DRV_CAP_FLAGS2 0
+
+#define GDMA_DRV_CAP_FLAGS3 0
+
+#define GDMA_DRV_CAP_FLAGS4 0
+
 struct gdma_verify_ver_req {
 	struct gdma_req_hdr hdr;
 
 	/* Mandatory fields required for protocol establishment */
 	u64 protocol_ver_min;
 	u64 protocol_ver_max;
-	u64 drv_cap_flags1;
-	u64 drv_cap_flags2;
-	u64 drv_cap_flags3;
-	u64 drv_cap_flags4;
+
+	/* Gdma Driver Capability Flags */
+	u64 gd_drv_cap_flags1;
+	u64 gd_drv_cap_flags2;
+	u64 gd_drv_cap_flags3;
+	u64 gd_drv_cap_flags4;
 
 	/* Advisory fields */
 	u64 drv_ver;
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 2f87bf90f8ec..cee75b561f59 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -67,6 +67,10 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
 	if (gc->max_num_queues > resp.max_rq)
 		gc->max_num_queues = resp.max_rq;
 
+	/* The Hardware Channel (HWC) used 1 MSI-X */
+	if (gc->max_num_queues > gc->num_msix_usable - 1)
+		gc->max_num_queues = gc->num_msix_usable - 1;
+
 	return 0;
 }
 
@@ -267,7 +271,7 @@ void mana_gd_wq_ring_doorbell(struct gdma_context *gc, struct gdma_queue *queue)
 			      queue->id, queue->head * GDMA_WQE_BU_SIZE, 1);
 }
 
-void mana_gd_arm_cq(struct gdma_queue *cq)
+void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit)
 {
 	struct gdma_context *gc = cq->gdma_dev->gdma_context;
 
@@ -276,7 +280,7 @@ void mana_gd_arm_cq(struct gdma_queue *cq)
 	u32 head = cq->head % (num_cqe << GDMA_CQE_OWNER_BITS);
 
 	mana_gd_ring_doorbell(gc, cq->gdma_dev->doorbell, cq->type, cq->id,
-			      head, SET_ARM_BIT);
+			      head, arm_bit);
 }
 
 static void mana_gd_process_eqe(struct gdma_queue *eq)
@@ -339,7 +343,6 @@ static void mana_gd_process_eq_events(void *arg)
 	struct gdma_queue *eq = arg;
 	struct gdma_context *gc;
 	struct gdma_eqe *eqe;
-	unsigned int arm_bit;
 	u32 head, num_eqe;
 	int i;
 
@@ -370,92 +373,54 @@ static void mana_gd_process_eq_events(void *arg)
 		eq->head++;
 	}
 
-	/* Always rearm the EQ for HWC. For MANA, rearm it when NAPI is done. */
-	if (mana_gd_is_hwc(eq->gdma_dev)) {
-		arm_bit = SET_ARM_BIT;
-	} else if (eq->eq.work_done < eq->eq.budget &&
-		   napi_complete_done(&eq->eq.napi, eq->eq.work_done)) {
-		arm_bit = SET_ARM_BIT;
-	} else {
-		arm_bit = 0;
-	}
-
 	head = eq->head % (num_eqe << GDMA_EQE_OWNER_BITS);
 
 	mana_gd_ring_doorbell(gc, eq->gdma_dev->doorbell, eq->type, eq->id,
-			      head, arm_bit);
-}
-
-static int mana_poll(struct napi_struct *napi, int budget)
-{
-	struct gdma_queue *eq = container_of(napi, struct gdma_queue, eq.napi);
-
-	eq->eq.work_done = 0;
-	eq->eq.budget = budget;
-
-	mana_gd_process_eq_events(eq);
-
-	return min(eq->eq.work_done, budget);
-}
-
-static void mana_gd_schedule_napi(void *arg)
-{
-	struct gdma_queue *eq = arg;
-	struct napi_struct *napi;
-
-	napi = &eq->eq.napi;
-	napi_schedule_irqoff(napi);
+			      head, SET_ARM_BIT);
 }
 
 static int mana_gd_register_irq(struct gdma_queue *queue,
 				const struct gdma_queue_spec *spec)
 {
 	struct gdma_dev *gd = queue->gdma_dev;
-	bool is_mana = mana_gd_is_mana(gd);
 	struct gdma_irq_context *gic;
 	struct gdma_context *gc;
 	struct gdma_resource *r;
 	unsigned int msi_index;
 	unsigned long flags;
-	int err;
+	struct device *dev;
+	int err = 0;
 
 	gc = gd->gdma_context;
 	r = &gc->msix_resource;
+	dev = gc->dev;
 
 	spin_lock_irqsave(&r->lock, flags);
 
 	msi_index = find_first_zero_bit(r->map, r->size);
-	if (msi_index >= r->size) {
+	if (msi_index >= r->size || msi_index >= gc->num_msix_usable) {
 		err = -ENOSPC;
 	} else {
 		bitmap_set(r->map, msi_index, 1);
 		queue->eq.msix_index = msi_index;
-		err = 0;
 	}
 
 	spin_unlock_irqrestore(&r->lock, flags);
 
-	if (err)
-		return err;
+	if (err) {
+		dev_err(dev, "Register IRQ err:%d, msi:%u rsize:%u, nMSI:%u",
+			err, msi_index, r->size, gc->num_msix_usable);
 
-	WARN_ON(msi_index >= gc->num_msix_usable);
+		return err;
+	}
 
 	gic = &gc->irq_contexts[msi_index];
 
-	if (is_mana) {
-		netif_napi_add(spec->eq.ndev, &queue->eq.napi, mana_poll,
-			       NAPI_POLL_WEIGHT);
-		napi_enable(&queue->eq.napi);
-	}
-
 	WARN_ON(gic->handler || gic->arg);
 
 	gic->arg = queue;
 
-	if (is_mana)
-		gic->handler = mana_gd_schedule_napi;
-	else
-		gic->handler = mana_gd_process_eq_events;
+	gic->handler = mana_gd_process_eq_events;
 
 	return 0;
 }
@@ -549,11 +514,6 @@ static void mana_gd_destroy_eq(struct gdma_context *gc, bool flush_evenets,
 
 	mana_gd_deregiser_irq(queue);
 
-	if (mana_gd_is_mana(queue->gdma_dev)) {
-		napi_disable(&queue->eq.napi);
-		netif_napi_del(&queue->eq.napi);
-	}
-
 	if (queue->eq.disable_needed)
 		mana_gd_disable_queue(queue);
 }
@@ -883,6 +843,11 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev)
 	req.protocol_ver_min = GDMA_PROTOCOL_FIRST;
 	req.protocol_ver_max = GDMA_PROTOCOL_LAST;
 
+	req.gd_drv_cap_flags1 = GDMA_DRV_CAP_FLAGS1;
+	req.gd_drv_cap_flags2 = GDMA_DRV_CAP_FLAGS2;
+	req.gd_drv_cap_flags3 = GDMA_DRV_CAP_FLAGS3;
+	req.gd_drv_cap_flags4 = GDMA_DRV_CAP_FLAGS4;
+
 	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
 	if (err || resp.hdr.status) {
 		dev_err(gc->dev, "VfVerifyVersionOutput: %d, status=0x%x\n",
@@ -1128,7 +1093,7 @@ static int mana_gd_read_cqe(struct gdma_queue *cq, struct gdma_comp *comp)
 
 	new_bits = (cq->head / num_cqe) & GDMA_CQE_OWNER_MASK;
 	/* Return -1 if overflow detected. */
-	if (owner_bits != new_bits)
+	if (WARN_ON_ONCE(owner_bits != new_bits))
 		return -1;
 
 	comp->wq_num = cqe->cqe_info.wq_num;
@@ -1201,10 +1166,8 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
 	if (max_queues_per_port > MANA_MAX_NUM_QUEUES)
 		max_queues_per_port = MANA_MAX_NUM_QUEUES;
 
-	max_irqs = max_queues_per_port * MAX_PORTS_IN_MANA_DEV;
-
 	/* Need 1 interrupt for the Hardware communication Channel (HWC) */
-	max_irqs++;
+	max_irqs = max_queues_per_port + 1;
 
 	nvec = pci_alloc_irq_vectors(pdev, 2, max_irqs, PCI_IRQ_MSIX);
 	if (nvec < 0)
@@ -1291,6 +1254,9 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	int bar = 0;
 	int err;
 
+	/* Each port has 2 CQs, each CQ has at most 1 EQE at a time */
+	BUILD_BUG_ON(2 * MAX_PORTS_IN_MANA_DEV * GDMA_EQE_SIZE > EQ_SIZE);
+
 	err = pci_enable_device(pdev);
 	if (err)
 		return -ENXIO;
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index 1a923fd99990..c1310ea1c216 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -304,7 +304,7 @@ static void mana_hwc_comp_event(void *ctx, struct gdma_queue *q_self)
 						&comp_data);
 	}
 
-	mana_gd_arm_cq(q_self);
+	mana_gd_ring_cq(q_self, SET_ARM_BIT);
 }
 
 static void mana_hwc_destroy_cq(struct gdma_context *gc, struct hwc_cq *hwc_cq)
diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/drivers/net/ethernet/microsoft/mana/mana.h
index a2c3f826f022..fc98a5ba5ed0 100644
--- a/drivers/net/ethernet/microsoft/mana/mana.h
+++ b/drivers/net/ethernet/microsoft/mana/mana.h
@@ -46,7 +46,7 @@ enum TRI_STATE {
 #define EQ_SIZE (8 * PAGE_SIZE)
 #define LOG2_EQ_THROTTLE 3
 
-#define MAX_PORTS_IN_MANA_DEV 16
+#define MAX_PORTS_IN_MANA_DEV 256
 
 struct mana_stats {
 	u64 packets;
@@ -225,6 +225,8 @@ struct mana_tx_comp_oob {
 
 struct mana_rxq;
 
+#define CQE_POLLING_BUFFER 512
+
 struct mana_cq {
 	struct gdma_queue *gdma_cq;
 
@@ -244,8 +246,13 @@ struct mana_cq {
 	 */
 	struct mana_txq *txq;
 
-	/* Pointer to a buffer which the CQ handler can copy the CQE's into. */
-	struct gdma_comp *gdma_comp_buf;
+	/* Buffer which the CQ handler can copy the CQE's into. */
+	struct gdma_comp gdma_comp_buf[CQE_POLLING_BUFFER];
+
+	/* NAPI data */
+	struct napi_struct napi;
+	int work_done;
+	int budget;
 };
 
 #define GDMA_MAX_RQE_SGES 15
@@ -315,6 +322,8 @@ struct mana_context {
 
 	u16 num_ports;
 
+	struct mana_eq *eqs;
+
 	struct net_device *ports[MAX_PORTS_IN_MANA_DEV];
 };
 
@@ -324,8 +333,6 @@ struct mana_port_context {
 
 	u8 mac_addr[ETH_ALEN];
 
-	struct mana_eq *eqs;
-
 	enum TRI_STATE rss_state;
 
 	mana_handle_t default_rxobj;
@@ -395,11 +402,11 @@ enum mana_command_code {
 struct mana_query_device_cfg_req {
 	struct gdma_req_hdr hdr;
 
-	/* Driver Capability flags */
-	u64 drv_cap_flags1;
-	u64 drv_cap_flags2;
-	u64 drv_cap_flags3;
-	u64 drv_cap_flags4;
+	/* MANA Nic Driver Capability flags */
+	u64 mn_drv_cap_flags1;
+	u64 mn_drv_cap_flags2;
+	u64 mn_drv_cap_flags3;
+	u64 mn_drv_cap_flags4;
 
 	u32 proto_major_ver;
 	u32 proto_minor_ver;
@@ -516,7 +523,7 @@ struct mana_cfg_rx_steer_resp {
 	struct gdma_resp_hdr hdr;
 }; /* HW DATA */
 
-#define MANA_MAX_NUM_QUEUES 16
+#define MANA_MAX_NUM_QUEUES 64
 
 #define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1)
 
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index fff78900fc8a..1b21030308e5 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -696,66 +696,56 @@ static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
 			   resp.hdr.status);
 }
 
-static void mana_init_cqe_poll_buf(struct gdma_comp *cqe_poll_buf)
-{
-	int i;
-
-	for (i = 0; i < CQE_POLLING_BUFFER; i++)
-		memset(&cqe_poll_buf[i], 0, sizeof(struct gdma_comp));
-}
-
-static void mana_destroy_eq(struct gdma_context *gc,
-			    struct mana_port_context *apc)
+static void mana_destroy_eq(struct mana_context *ac)
 {
+	struct gdma_context *gc = ac->gdma_dev->gdma_context;
 	struct gdma_queue *eq;
 	int i;
 
-	if (!apc->eqs)
+	if (!ac->eqs)
 		return;
 
-	for (i = 0; i < apc->num_queues; i++) {
-		eq = apc->eqs[i].eq;
+	for (i = 0; i < gc->max_num_queues; i++) {
+		eq = ac->eqs[i].eq;
 		if (!eq)
 			continue;
 
 		mana_gd_destroy_queue(gc, eq);
 	}
 
-	kfree(apc->eqs);
-	apc->eqs = NULL;
+	kfree(ac->eqs);
+	ac->eqs = NULL;
 }
 
-static int mana_create_eq(struct mana_port_context *apc)
+static int mana_create_eq(struct mana_context *ac)
 {
-	struct gdma_dev *gd = apc->ac->gdma_dev;
+	struct gdma_dev *gd = ac->gdma_dev;
+	struct gdma_context *gc = gd->gdma_context;
 	struct gdma_queue_spec spec = {};
 	int err;
 	int i;
 
-	apc->eqs = kcalloc(apc->num_queues, sizeof(struct mana_eq),
-			   GFP_KERNEL);
-	if (!apc->eqs)
+	ac->eqs = kcalloc(gc->max_num_queues, sizeof(struct mana_eq),
+			  GFP_KERNEL);
+	if (!ac->eqs)
 		return -ENOMEM;
 
 	spec.type = GDMA_EQ;
 	spec.monitor_avl_buf = false;
 	spec.queue_size = EQ_SIZE;
 	spec.eq.callback = NULL;
-	spec.eq.context = apc->eqs;
+	spec.eq.context = ac->eqs;
 	spec.eq.log2_throttle_limit = LOG2_EQ_THROTTLE;
-	spec.eq.ndev = apc->ndev;
-
-	for (i = 0; i < apc->num_queues; i++) {
-		mana_init_cqe_poll_buf(apc->eqs[i].cqe_poll);
 
-		err = mana_gd_create_mana_eq(gd, &spec, &apc->eqs[i].eq);
+	for (i = 0; i < gc->max_num_queues; i++) {
+		err = mana_gd_create_mana_eq(gd, &spec, &ac->eqs[i].eq);
 		if (err)
 			goto out;
 	}
 
 	return 0;
 out:
-	mana_destroy_eq(gd->gdma_context, apc);
+	mana_destroy_eq(ac);
 	return err;
 }
 
@@ -790,7 +780,6 @@ static void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc)
 
 static void mana_poll_tx_cq(struct mana_cq *cq)
 {
-	struct gdma_queue *gdma_eq = cq->gdma_cq->cq.parent;
 	struct gdma_comp *completions = cq->gdma_comp_buf;
 	struct gdma_posted_wqe_info *wqe_info;
 	unsigned int pkt_transmitted = 0;
@@ -812,6 +801,9 @@ static void mana_poll_tx_cq(struct mana_cq *cq)
 	comp_read = mana_gd_poll_cq(cq->gdma_cq, completions,
 				    CQE_POLLING_BUFFER);
 
+	if (comp_read < 1)
+		return;
+
 	for (i = 0; i < comp_read; i++) {
 		struct mana_tx_comp_oob *cqe_oob;
 
@@ -861,7 +853,7 @@ static void mana_poll_tx_cq(struct mana_cq *cq)
 
 		mana_unmap_skb(skb, apc);
 
-		napi_consume_skb(skb, gdma_eq->eq.budget);
+		napi_consume_skb(skb, cq->budget);
 
 		pkt_transmitted++;
 	}
@@ -890,6 +882,8 @@ static void mana_poll_tx_cq(struct mana_cq *cq)
 
 	if (atomic_sub_return(pkt_transmitted, &txq->pending_sends) < 0)
 		WARN_ON_ONCE(1);
+
+	cq->work_done = pkt_transmitted;
 }
 
 static void mana_post_pkt_rxq(struct mana_rxq *rxq)
@@ -918,17 +912,13 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe,
 	struct mana_stats *rx_stats = &rxq->stats;
 	struct net_device *ndev = rxq->ndev;
 	uint pkt_len = cqe->ppi[0].pkt_len;
-	struct mana_port_context *apc;
 	u16 rxq_idx = rxq->rxq_idx;
 	struct napi_struct *napi;
-	struct gdma_queue *eq;
 	struct sk_buff *skb;
 	u32 hash_value;
 
-	apc = netdev_priv(ndev);
-	eq = apc->eqs[rxq_idx].eq;
-	eq->eq.work_done++;
-	napi = &eq->eq.napi;
+	rxq->rx_cq.work_done++;
+	napi = &rxq->rx_cq.napi;
 
 	if (!buf_va) {
 		++ndev->stats.rx_dropped;
@@ -1081,6 +1071,7 @@ static void mana_poll_rx_cq(struct mana_cq *cq)
 static void mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
 {
 	struct mana_cq *cq = context;
+	u8 arm_bit;
 
 	WARN_ON_ONCE(cq->gdma_cq != gdma_queue);
 
@@ -1089,7 +1080,33 @@ static void mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
 	else
 		mana_poll_tx_cq(cq);
 
-	mana_gd_arm_cq(gdma_queue);
+	if (cq->work_done < cq->budget &&
+	    napi_complete_done(&cq->napi, cq->work_done)) {
+		arm_bit = SET_ARM_BIT;
+	} else {
+		arm_bit = 0;
+	}
+
+	mana_gd_ring_cq(gdma_queue, arm_bit);
+}
+
+static int mana_poll(struct napi_struct *napi, int budget)
+{
+	struct mana_cq *cq = container_of(napi, struct mana_cq, napi);
+
+	cq->work_done = 0;
+	cq->budget = budget;
+
+	mana_cq_handler(cq, cq->gdma_cq);
+
+	return min(cq->work_done, budget);
+}
+
+static void mana_schedule_napi(void *context, struct gdma_queue *gdma_queue)
+{
+	struct mana_cq *cq = context;
+
+	napi_schedule_irqoff(&cq->napi);
 }
 
 static void mana_deinit_cq(struct mana_port_context *apc, struct mana_cq *cq)
@@ -1114,12 +1131,18 @@ static void mana_deinit_txq(struct mana_port_context *apc, struct mana_txq *txq)
 
 static void mana_destroy_txq(struct mana_port_context *apc)
 {
+	struct napi_struct *napi;
 	int i;
 
 	if (!apc->tx_qp)
 		return;
 
 	for (i = 0; i < apc->num_queues; i++) {
+		napi = &apc->tx_qp[i].tx_cq.napi;
+		napi_synchronize(napi);
+		napi_disable(napi);
+		netif_napi_del(napi);
+
 		mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object);
 
 		mana_deinit_cq(apc, &apc->tx_qp[i].tx_cq);
@@ -1134,7 +1157,8 @@ static void mana_destroy_txq(struct mana_port_context *apc)
 static int mana_create_txq(struct mana_port_context *apc,
 			   struct net_device *net)
 {
-	struct gdma_dev *gd = apc->ac->gdma_dev;
+	struct mana_context *ac = apc->ac;
+	struct gdma_dev *gd = ac->gdma_dev;
 	struct mana_obj_spec wq_spec;
 	struct mana_obj_spec cq_spec;
 	struct gdma_queue_spec spec;
@@ -1186,7 +1210,6 @@ static int mana_create_txq(struct mana_port_context *apc,
 
 		/* Create SQ's CQ */
 		cq = &apc->tx_qp[i].tx_cq;
-		cq->gdma_comp_buf = apc->eqs[i].cqe_poll;
 		cq->type = MANA_CQ_TYPE_TX;
 
 		cq->txq = txq;
@@ -1195,8 +1218,8 @@ static int mana_create_txq(struct mana_port_context *apc,
 		spec.type = GDMA_CQ;
 		spec.monitor_avl_buf = false;
 		spec.queue_size = cq_size;
-		spec.cq.callback = mana_cq_handler;
-		spec.cq.parent_eq = apc->eqs[i].eq;
+		spec.cq.callback = mana_schedule_napi;
+		spec.cq.parent_eq = ac->eqs[i].eq;
 		spec.cq.context = cq;
 		err = mana_gd_create_mana_wq_cq(gd, &spec, &cq->gdma_cq);
 		if (err)
@@ -1237,7 +1260,10 @@ static int mana_create_txq(struct mana_port_context *apc,
 
 		gc->cq_table[cq->gdma_id] = cq->gdma_cq;
 
-		mana_gd_arm_cq(cq->gdma_cq);
+		netif_tx_napi_add(net, &cq->napi, mana_poll, NAPI_POLL_WEIGHT);
+		napi_enable(&cq->napi);
+
+		mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
 	}
 
 	return 0;
@@ -1246,21 +1272,6 @@ out:
 	return err;
 }
 
-static void mana_napi_sync_for_rx(struct mana_rxq *rxq)
-{
-	struct net_device *ndev = rxq->ndev;
-	struct mana_port_context *apc;
-	u16 rxq_idx = rxq->rxq_idx;
-	struct napi_struct *napi;
-	struct gdma_queue *eq;
-
-	apc = netdev_priv(ndev);
-	eq = apc->eqs[rxq_idx].eq;
-	napi = &eq->eq.napi;
-
-	napi_synchronize(napi);
-}
-
 static void mana_destroy_rxq(struct mana_port_context *apc,
 			     struct mana_rxq *rxq, bool validate_state)
 
@@ -1268,13 +1279,19 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
 	struct gdma_context *gc = apc->ac->gdma_dev->gdma_context;
 	struct mana_recv_buf_oob *rx_oob;
 	struct device *dev = gc->dev;
+	struct napi_struct *napi;
 	int i;
 
 	if (!rxq)
 		return;
 
+	napi = &rxq->rx_cq.napi;
+
 	if (validate_state)
-		mana_napi_sync_for_rx(rxq);
+		napi_synchronize(napi);
+
+	napi_disable(napi);
+	netif_napi_del(napi);
 
 	mana_destroy_wq_obj(apc, GDMA_RQ, rxq->rxobj);
 
@@ -1418,7 +1435,6 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 
 	/* Create RQ's CQ */
 	cq = &rxq->rx_cq;
-	cq->gdma_comp_buf = eq->cqe_poll;
 	cq->type = MANA_CQ_TYPE_RX;
 	cq->rxq = rxq;
 
@@ -1426,7 +1442,7 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 	spec.type = GDMA_CQ;
 	spec.monitor_avl_buf = false;
 	spec.queue_size = cq_size;
-	spec.cq.callback = mana_cq_handler;
+	spec.cq.callback = mana_schedule_napi;
 	spec.cq.parent_eq = eq->eq;
 	spec.cq.context = cq;
 	err = mana_gd_create_mana_wq_cq(gd, &spec, &cq->gdma_cq);
@@ -1466,7 +1482,10 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 
 	gc->cq_table[cq->gdma_id] = cq->gdma_cq;
 
-	mana_gd_arm_cq(cq->gdma_cq);
+	netif_napi_add(ndev, &cq->napi, mana_poll, 1);
+	napi_enable(&cq->napi);
+
+	mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
 out:
 	if (!err)
 		return rxq;
@@ -1484,12 +1503,13 @@ out:
 static int mana_add_rx_queues(struct mana_port_context *apc,
 			      struct net_device *ndev)
 {
+	struct mana_context *ac = apc->ac;
 	struct mana_rxq *rxq;
 	int err = 0;
 	int i;
 
 	for (i = 0; i < apc->num_queues; i++) {
-		rxq = mana_create_rxq(apc, i, &apc->eqs[i], ndev);
+		rxq = mana_create_rxq(apc, i, &ac->eqs[i], ndev);
 		if (!rxq) {
 			err = -ENOMEM;
 			goto out;
@@ -1601,16 +1621,11 @@ reset_apc:
 int mana_alloc_queues(struct net_device *ndev)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
-	struct gdma_dev *gd = apc->ac->gdma_dev;
 	int err;
 
-	err = mana_create_eq(apc);
-	if (err)
-		return err;
-
 	err = mana_create_vport(apc, ndev);
 	if (err)
-		goto destroy_eq;
+		return err;
 
 	err = netif_set_real_num_tx_queues(ndev, apc->num_queues);
 	if (err)
@@ -1636,8 +1651,6 @@ int mana_alloc_queues(struct net_device *ndev)
 
 destroy_vport:
 	mana_destroy_vport(apc);
-destroy_eq:
-	mana_destroy_eq(gd->gdma_context, apc);
 	return err;
 }
 
@@ -1714,8 +1727,6 @@ static int mana_dealloc_queues(struct net_device *ndev)
 
 	mana_destroy_vport(apc);
 
-	mana_destroy_eq(apc->ac->gdma_dev->gdma_context, apc);
-
 	return 0;
 }
 
@@ -1768,7 +1779,7 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	apc->ac = ac;
 	apc->ndev = ndev;
 	apc->max_queues = gc->max_num_queues;
-	apc->num_queues = min_t(uint, gc->max_num_queues, MANA_MAX_NUM_QUEUES);
+	apc->num_queues = gc->max_num_queues;
 	apc->port_handle = INVALID_MANA_HANDLE;
 	apc->port_idx = port_idx;
 
@@ -1839,6 +1850,10 @@ int mana_probe(struct gdma_dev *gd)
 	ac->num_ports = 1;
 	gd->driver_data = ac;
 
+	err = mana_create_eq(ac);
+	if (err)
+		goto out;
+
 	err = mana_query_device_cfg(ac, MANA_MAJOR_VERSION, MANA_MINOR_VERSION,
 				    MANA_MICRO_VERSION, &ac->num_ports);
 	if (err)
@@ -1888,6 +1903,9 @@ void mana_remove(struct gdma_dev *gd)
 
 		free_netdev(ndev);
 	}
+
+	mana_destroy_eq(ac);
+
 out:
 	mana_gd_deregister_device(gd);
 	gd->driver_data = NULL;
diff --git a/drivers/net/ethernet/mscc/Kconfig b/drivers/net/ethernet/mscc/Kconfig
index 2d3157e4d081..b6a73d151dec 100644
--- a/drivers/net/ethernet/mscc/Kconfig
+++ b/drivers/net/ethernet/mscc/Kconfig
@@ -16,7 +16,7 @@ config MSCC_OCELOT_SWITCH_LIB
 	select NET_DEVLINK
 	select REGMAP_MMIO
 	select PACKING
-	select PHYLIB
+	select PHYLINK
 	tristate
 	help
 	  This is a hardware support library for Ocelot network switches. It is
@@ -24,6 +24,7 @@ config MSCC_OCELOT_SWITCH_LIB
 
 config MSCC_OCELOT_SWITCH
 	tristate "Ocelot switch driver"
+	depends on PTP_1588_CLOCK_OPTIONAL
 	depends on BRIDGE || BRIDGE=n
 	depends on NET_SWITCHDEV
 	depends on HAS_IOMEM
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 2948d731a1c1..c581b955efb3 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -222,8 +222,35 @@ static void ocelot_port_set_pvid(struct ocelot *ocelot, int port,
 		       ANA_PORT_DROP_CFG, port);
 }
 
+static int ocelot_vlan_member_set(struct ocelot *ocelot, u32 vlan_mask, u16 vid)
+{
+	int err;
+
+	err = ocelot_vlant_set_mask(ocelot, vid, vlan_mask);
+	if (err)
+		return err;
+
+	ocelot->vlan_mask[vid] = vlan_mask;
+
+	return 0;
+}
+
+static int ocelot_vlan_member_add(struct ocelot *ocelot, int port, u16 vid)
+{
+	return ocelot_vlan_member_set(ocelot,
+				      ocelot->vlan_mask[vid] | BIT(port),
+				      vid);
+}
+
+static int ocelot_vlan_member_del(struct ocelot *ocelot, int port, u16 vid)
+{
+	return ocelot_vlan_member_set(ocelot,
+				      ocelot->vlan_mask[vid] & ~BIT(port),
+				      vid);
+}
+
 int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
-			       bool vlan_aware)
+			       bool vlan_aware, struct netlink_ext_ack *extack)
 {
 	struct ocelot_vcap_block *block = &ocelot->block[VCAP_IS1];
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
@@ -233,8 +260,8 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
 	list_for_each_entry(filter, &block->rules, list) {
 		if (filter->ingress_port_mask & BIT(port) &&
 		    filter->action.vid_replace_ena) {
-			dev_err(ocelot->dev,
-				"Cannot change VLAN state with vlan modify rules active\n");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Cannot change VLAN state with vlan modify rules active");
 			return -EBUSY;
 		}
 	}
@@ -259,16 +286,15 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
 EXPORT_SYMBOL(ocelot_port_vlan_filtering);
 
 int ocelot_vlan_prepare(struct ocelot *ocelot, int port, u16 vid, bool pvid,
-			bool untagged)
+			bool untagged, struct netlink_ext_ack *extack)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 
 	/* Deny changing the native VLAN, but always permit deleting it */
 	if (untagged && ocelot_port->native_vlan.vid != vid &&
 	    ocelot_port->native_vlan.valid) {
-		dev_err(ocelot->dev,
-			"Port already has a native VLAN: %d\n",
-			ocelot_port->native_vlan.vid);
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Port already has a native VLAN");
 		return -EBUSY;
 	}
 
@@ -279,13 +305,11 @@ EXPORT_SYMBOL(ocelot_vlan_prepare);
 int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 		    bool untagged)
 {
-	int ret;
+	int err;
 
-	/* Make the port a member of the VLAN */
-	ocelot->vlan_mask[vid] |= BIT(port);
-	ret = ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]);
-	if (ret)
-		return ret;
+	err = ocelot_vlan_member_add(ocelot, port, vid);
+	if (err)
+		return err;
 
 	/* Default ingress vlan classification */
 	if (pvid) {
@@ -312,13 +336,11 @@ EXPORT_SYMBOL(ocelot_vlan_add);
 int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	int ret;
+	int err;
 
-	/* Stop the port from being a member of the vlan */
-	ocelot->vlan_mask[vid] &= ~BIT(port);
-	ret = ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]);
-	if (ret)
-		return ret;
+	err = ocelot_vlan_member_del(ocelot, port, vid);
+	if (err)
+		return err;
 
 	/* Ingress */
 	if (ocelot_port->pvid_vlan.vid == vid) {
@@ -340,6 +362,7 @@ EXPORT_SYMBOL(ocelot_vlan_del);
 
 static void ocelot_vlan_init(struct ocelot *ocelot)
 {
+	unsigned long all_ports = GENMASK(ocelot->num_phys_ports - 1, 0);
 	u16 port, vid;
 
 	/* Clear VLAN table, by default all ports are members of all VLANs */
@@ -348,23 +371,19 @@ static void ocelot_vlan_init(struct ocelot *ocelot)
 	ocelot_vlant_wait_for_completion(ocelot);
 
 	/* Configure the port VLAN memberships */
-	for (vid = 1; vid < VLAN_N_VID; vid++) {
-		ocelot->vlan_mask[vid] = 0;
-		ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]);
-	}
+	for (vid = 1; vid < VLAN_N_VID; vid++)
+		ocelot_vlan_member_set(ocelot, 0, vid);
 
 	/* Because VLAN filtering is enabled, we need VID 0 to get untagged
 	 * traffic.  It is added automatically if 8021q module is loaded, but
 	 * we can't rely on it since module may be not loaded.
 	 */
-	ocelot->vlan_mask[0] = GENMASK(ocelot->num_phys_ports - 1, 0);
-	ocelot_vlant_set_mask(ocelot, 0, ocelot->vlan_mask[0]);
+	ocelot_vlan_member_set(ocelot, all_ports, 0);
 
 	/* Set vlan ingress filter mask to all ports but the CPU port by
 	 * default.
 	 */
-	ocelot_write(ocelot, GENMASK(ocelot->num_phys_ports - 1, 0),
-		     ANA_VLANMASK);
+	ocelot_write(ocelot, all_ports, ANA_VLANMASK);
 
 	for (port = 0; port < ocelot->num_phys_ports; port++) {
 		ocelot_write_gix(ocelot, 0, REW_PORT_VLAN_CFG, port);
@@ -377,7 +396,7 @@ static u32 ocelot_read_eq_avail(struct ocelot *ocelot, int port)
 	return ocelot_read_rix(ocelot, QSYS_SW_STATUS, port);
 }
 
-int ocelot_port_flush(struct ocelot *ocelot, int port)
+static int ocelot_port_flush(struct ocelot *ocelot, int port)
 {
 	unsigned int pause_ena;
 	int err, val;
@@ -429,63 +448,118 @@ int ocelot_port_flush(struct ocelot *ocelot, int port)
 
 	return err;
 }
-EXPORT_SYMBOL(ocelot_port_flush);
 
-void ocelot_adjust_link(struct ocelot *ocelot, int port,
-			struct phy_device *phydev)
+void ocelot_phylink_mac_link_down(struct ocelot *ocelot, int port,
+				  unsigned int link_an_mode,
+				  phy_interface_t interface,
+				  unsigned long quirks)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	int speed, mode = 0;
+	int err;
+
+	ocelot_port_rmwl(ocelot_port, 0, DEV_MAC_ENA_CFG_RX_ENA,
+			 DEV_MAC_ENA_CFG);
+
+	ocelot_fields_write(ocelot, port, QSYS_SWITCH_PORT_MODE_PORT_ENA, 0);
+
+	err = ocelot_port_flush(ocelot, port);
+	if (err)
+		dev_err(ocelot->dev, "failed to flush port %d: %d\n",
+			port, err);
+
+	/* Put the port in reset. */
+	if (interface != PHY_INTERFACE_MODE_QSGMII ||
+	    !(quirks & OCELOT_QUIRK_QSGMII_PORTS_MUST_BE_UP))
+		ocelot_port_rmwl(ocelot_port,
+				 DEV_CLOCK_CFG_MAC_TX_RST |
+				 DEV_CLOCK_CFG_MAC_TX_RST,
+				 DEV_CLOCK_CFG_MAC_TX_RST |
+				 DEV_CLOCK_CFG_MAC_TX_RST,
+				 DEV_CLOCK_CFG);
+}
+EXPORT_SYMBOL_GPL(ocelot_phylink_mac_link_down);
+
+void ocelot_phylink_mac_link_up(struct ocelot *ocelot, int port,
+				struct phy_device *phydev,
+				unsigned int link_an_mode,
+				phy_interface_t interface,
+				int speed, int duplex,
+				bool tx_pause, bool rx_pause,
+				unsigned long quirks)
+{
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	int mac_speed, mode = 0;
+	u32 mac_fc_cfg;
+
+	/* The MAC might be integrated in systems where the MAC speed is fixed
+	 * and it's the PCS who is performing the rate adaptation, so we have
+	 * to write "1000Mbps" into the LINK_SPEED field of DEV_CLOCK_CFG
+	 * (which is also its default value).
+	 */
+	if ((quirks & OCELOT_QUIRK_PCS_PERFORMS_RATE_ADAPTATION) ||
+	    speed == SPEED_1000) {
+		mac_speed = OCELOT_SPEED_1000;
+		mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA;
+	} else if (speed == SPEED_2500) {
+		mac_speed = OCELOT_SPEED_2500;
+		mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA;
+	} else if (speed == SPEED_100) {
+		mac_speed = OCELOT_SPEED_100;
+	} else {
+		mac_speed = OCELOT_SPEED_10;
+	}
 
-	switch (phydev->speed) {
+	if (duplex == DUPLEX_FULL)
+		mode |= DEV_MAC_MODE_CFG_FDX_ENA;
+
+	ocelot_port_writel(ocelot_port, mode, DEV_MAC_MODE_CFG);
+
+	/* Take port out of reset by clearing the MAC_TX_RST, MAC_RX_RST and
+	 * PORT_RST bits in DEV_CLOCK_CFG.
+	 */
+	ocelot_port_writel(ocelot_port, DEV_CLOCK_CFG_LINK_SPEED(mac_speed),
+			   DEV_CLOCK_CFG);
+
+	switch (speed) {
 	case SPEED_10:
-		speed = OCELOT_SPEED_10;
+		mac_fc_cfg = SYS_MAC_FC_CFG_FC_LINK_SPEED(OCELOT_SPEED_10);
 		break;
 	case SPEED_100:
-		speed = OCELOT_SPEED_100;
+		mac_fc_cfg = SYS_MAC_FC_CFG_FC_LINK_SPEED(OCELOT_SPEED_100);
 		break;
 	case SPEED_1000:
-		speed = OCELOT_SPEED_1000;
-		mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA;
-		break;
 	case SPEED_2500:
-		speed = OCELOT_SPEED_2500;
-		mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA;
+		mac_fc_cfg = SYS_MAC_FC_CFG_FC_LINK_SPEED(OCELOT_SPEED_1000);
 		break;
 	default:
-		dev_err(ocelot->dev, "Unsupported PHY speed on port %d: %d\n",
-			port, phydev->speed);
+		dev_err(ocelot->dev, "Unsupported speed on port %d: %d\n",
+			port, speed);
 		return;
 	}
 
-	phy_print_status(phydev);
-
-	if (!phydev->link)
-		return;
-
-	/* Only full duplex supported for now */
-	ocelot_port_writel(ocelot_port, DEV_MAC_MODE_CFG_FDX_ENA |
-			   mode, DEV_MAC_MODE_CFG);
-
-	/* Disable HDX fast control */
-	ocelot_port_writel(ocelot_port, DEV_PORT_MISC_HDX_FAST_DIS,
-			   DEV_PORT_MISC);
+	/* Handle RX pause in all cases, with 2500base-X this is used for rate
+	 * adaptation.
+	 */
+	mac_fc_cfg |= SYS_MAC_FC_CFG_RX_FC_ENA;
 
-	/* SGMII only for now */
-	ocelot_port_writel(ocelot_port, PCS1G_MODE_CFG_SGMII_MODE_ENA,
-			   PCS1G_MODE_CFG);
-	ocelot_port_writel(ocelot_port, PCS1G_SD_CFG_SD_SEL, PCS1G_SD_CFG);
+	if (tx_pause)
+		mac_fc_cfg |= SYS_MAC_FC_CFG_TX_FC_ENA |
+			      SYS_MAC_FC_CFG_PAUSE_VAL_CFG(0xffff) |
+			      SYS_MAC_FC_CFG_FC_LATENCY_CFG(0x7) |
+			      SYS_MAC_FC_CFG_ZERO_PAUSE_ENA;
 
-	/* Enable PCS */
-	ocelot_port_writel(ocelot_port, PCS1G_CFG_PCS_ENA, PCS1G_CFG);
+	/* Flow control. Link speed is only used here to evaluate the time
+	 * specification in incoming pause frames.
+	 */
+	ocelot_write_rix(ocelot, mac_fc_cfg, SYS_MAC_FC_CFG, port);
 
-	/* No aneg on SGMII */
-	ocelot_port_writel(ocelot_port, 0, PCS1G_ANEG_CFG);
+	ocelot_write_rix(ocelot, 0, ANA_POL_FLOWC, port);
 
-	/* No loopback */
-	ocelot_port_writel(ocelot_port, 0, PCS1G_LB_CFG);
+	ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, tx_pause);
 
-	/* Enable MAC module */
+	/* Undo the effects of ocelot_phylink_mac_link_down:
+	 * enable MAC module
+	 */
 	ocelot_port_writel(ocelot_port, DEV_MAC_ENA_CFG_RX_ENA |
 			   DEV_MAC_ENA_CFG_TX_ENA, DEV_MAC_ENA_CFG);
 
@@ -502,39 +576,8 @@ void ocelot_adjust_link(struct ocelot *ocelot, int port,
 	/* Core: Enable port for frame transfer */
 	ocelot_fields_write(ocelot, port,
 			    QSYS_SWITCH_PORT_MODE_PORT_ENA, 1);
-
-	/* Flow control */
-	ocelot_write_rix(ocelot, SYS_MAC_FC_CFG_PAUSE_VAL_CFG(0xffff) |
-			 SYS_MAC_FC_CFG_RX_FC_ENA | SYS_MAC_FC_CFG_TX_FC_ENA |
-			 SYS_MAC_FC_CFG_ZERO_PAUSE_ENA |
-			 SYS_MAC_FC_CFG_FC_LATENCY_CFG(0x7) |
-			 SYS_MAC_FC_CFG_FC_LINK_SPEED(speed),
-			 SYS_MAC_FC_CFG, port);
-	ocelot_write_rix(ocelot, 0, ANA_POL_FLOWC, port);
-}
-EXPORT_SYMBOL(ocelot_adjust_link);
-
-void ocelot_port_enable(struct ocelot *ocelot, int port,
-			struct phy_device *phy)
-{
-	/* Enable receiving frames on the port, and activate auto-learning of
-	 * MAC addresses.
-	 */
-	ocelot_write_gix(ocelot, ANA_PORT_PORT_CFG_LEARNAUTO |
-			 ANA_PORT_PORT_CFG_RECV_ENA |
-			 ANA_PORT_PORT_CFG_PORTID_VAL(port),
-			 ANA_PORT_PORT_CFG, port);
 }
-EXPORT_SYMBOL(ocelot_port_enable);
-
-void ocelot_port_disable(struct ocelot *ocelot, int port)
-{
-	struct ocelot_port *ocelot_port = ocelot->ports[port];
-
-	ocelot_port_writel(ocelot_port, 0, DEV_MAC_ENA_CFG);
-	ocelot_fields_write(ocelot, port, QSYS_SWITCH_PORT_MODE_PORT_ENA, 0);
-}
-EXPORT_SYMBOL(ocelot_port_disable);
+EXPORT_SYMBOL_GPL(ocelot_phylink_mac_link_up);
 
 static void ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port,
 					 struct sk_buff *clone)
@@ -1957,6 +2000,15 @@ void ocelot_init_port(struct ocelot *ocelot, int port)
 	/* Disable source address learning for standalone mode */
 	ocelot_port_set_learning(ocelot, port, false);
 
+	/* Set the port's initial logical port ID value, enable receiving
+	 * frames on it, and configure the MAC address learning type to
+	 * automatic.
+	 */
+	ocelot_write_gix(ocelot, ANA_PORT_PORT_CFG_LEARNAUTO |
+			 ANA_PORT_PORT_CFG_RECV_ENA |
+			 ANA_PORT_PORT_CFG_PORTID_VAL(port),
+			 ANA_PORT_PORT_CFG, port);
+
 	/* Enable vcap lookups */
 	ocelot_vcap_enable(ocelot, port);
 }
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index db6b1a4c3926..1952d6a1b98a 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -12,8 +12,7 @@
 #include <linux/etherdevice.h>
 #include <linux/if_vlan.h>
 #include <linux/net_tstamp.h>
-#include <linux/phy.h>
-#include <linux/phy/phy.h>
+#include <linux/phylink.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 
@@ -42,11 +41,9 @@ struct ocelot_port_tc {
 struct ocelot_port_private {
 	struct ocelot_port port;
 	struct net_device *dev;
-	struct phy_device *phy;
+	struct phylink *phylink;
+	struct phylink_config phylink_config;
 	u8 chip_port;
-
-	struct phy *serdes;
-
 	struct ocelot_port_tc tc;
 };
 
@@ -107,7 +104,7 @@ u32 ocelot_port_readl(struct ocelot_port *port, u32 reg);
 void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg);
 
 int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target,
-		      struct phy_device *phy);
+		      struct device_node *portnp);
 void ocelot_release_port(struct ocelot_port *ocelot_port);
 int ocelot_devlink_init(struct ocelot *ocelot);
 void ocelot_devlink_teardown(struct ocelot *ocelot);
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index e9d260d84bf3..c0c465a4a981 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -9,10 +9,14 @@
  */
 
 #include <linux/if_bridge.h>
+#include <linux/of_net.h>
+#include <linux/phy/phy.h>
 #include <net/pkt_cls.h>
 #include "ocelot.h"
 #include "ocelot_vcap.h"
 
+#define OCELOT_MAC_QUIRKS	OCELOT_QUIRK_QSGMII_PORTS_MUST_BE_UP
+
 static struct ocelot *devlink_port_to_ocelot(struct devlink_port *dlp)
 {
 	return devlink_priv(dlp->devlink);
@@ -160,6 +164,7 @@ int ocelot_port_devlink_init(struct ocelot *ocelot, int port,
 	struct devlink *dl = ocelot->devlink;
 	struct devlink_port_attrs attrs = {};
 
+	memset(dlp, 0, sizeof(*dlp));
 	memcpy(attrs.switch_id.id, &ocelot->base_mac, id_len);
 	attrs.switch_id.id_len = id_len;
 	attrs.phys.port_number = port;
@@ -381,26 +386,6 @@ static int ocelot_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	return 0;
 }
 
-static void ocelot_port_adjust_link(struct net_device *dev)
-{
-	struct ocelot_port_private *priv = netdev_priv(dev);
-	struct ocelot *ocelot = priv->port.ocelot;
-	int port = priv->chip_port;
-
-	ocelot_adjust_link(ocelot, port, dev->phydev);
-}
-
-static int ocelot_vlan_vid_prepare(struct net_device *dev, u16 vid, bool pvid,
-				   bool untagged)
-{
-	struct ocelot_port_private *priv = netdev_priv(dev);
-	struct ocelot_port *ocelot_port = &priv->port;
-	struct ocelot *ocelot = ocelot_port->ocelot;
-	int port = priv->chip_port;
-
-	return ocelot_vlan_prepare(ocelot, port, vid, pvid, untagged);
-}
-
 static int ocelot_vlan_vid_add(struct net_device *dev, u16 vid, bool pvid,
 			       bool untagged)
 {
@@ -448,33 +433,8 @@ static int ocelot_vlan_vid_del(struct net_device *dev, u16 vid)
 static int ocelot_port_open(struct net_device *dev)
 {
 	struct ocelot_port_private *priv = netdev_priv(dev);
-	struct ocelot_port *ocelot_port = &priv->port;
-	struct ocelot *ocelot = ocelot_port->ocelot;
-	int port = priv->chip_port;
-	int err;
 
-	if (priv->serdes) {
-		err = phy_set_mode_ext(priv->serdes, PHY_MODE_ETHERNET,
-				       ocelot_port->phy_mode);
-		if (err) {
-			netdev_err(dev, "Could not set mode of SerDes\n");
-			return err;
-		}
-	}
-
-	err = phy_connect_direct(dev, priv->phy, &ocelot_port_adjust_link,
-				 ocelot_port->phy_mode);
-	if (err) {
-		netdev_err(dev, "Could not attach to PHY\n");
-		return err;
-	}
-
-	dev->phydev = priv->phy;
-
-	phy_attached_info(priv->phy);
-	phy_start(priv->phy);
-
-	ocelot_port_enable(ocelot, port, priv->phy);
+	phylink_start(priv->phylink);
 
 	return 0;
 }
@@ -482,14 +442,8 @@ static int ocelot_port_open(struct net_device *dev)
 static int ocelot_port_stop(struct net_device *dev)
 {
 	struct ocelot_port_private *priv = netdev_priv(dev);
-	struct ocelot *ocelot = priv->port.ocelot;
-	int port = priv->chip_port;
-
-	phy_disconnect(priv->phy);
-
-	dev->phydev = NULL;
 
-	ocelot_port_disable(ocelot, port);
+	phylink_stop(priv->phylink);
 
 	return 0;
 }
@@ -823,7 +777,7 @@ static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_vlan_rx_kill_vid		= ocelot_vlan_rx_kill_vid,
 	.ndo_set_features		= ocelot_set_features,
 	.ndo_setup_tc			= ocelot_setup_tc,
-	.ndo_do_ioctl			= ocelot_ioctl,
+	.ndo_eth_ioctl			= ocelot_ioctl,
 	.ndo_get_devlink_port		= ocelot_get_devlink_port,
 };
 
@@ -959,7 +913,8 @@ static int ocelot_port_attr_set(struct net_device *dev, const void *ctx,
 		ocelot_port_attr_ageing_set(ocelot, port, attr->u.ageing_time);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
-		ocelot_port_vlan_filtering(ocelot, port, attr->u.vlan_filtering);
+		ocelot_port_vlan_filtering(ocelot, port, attr->u.vlan_filtering,
+					   extack);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED:
 		ocelot_port_attr_mc_set(ocelot, port, !attr->u.mc_disabled);
@@ -979,14 +934,26 @@ static int ocelot_port_attr_set(struct net_device *dev, const void *ctx,
 	return err;
 }
 
+static int ocelot_vlan_vid_prepare(struct net_device *dev, u16 vid, bool pvid,
+				   bool untagged, struct netlink_ext_ack *extack)
+{
+	struct ocelot_port_private *priv = netdev_priv(dev);
+	struct ocelot_port *ocelot_port = &priv->port;
+	struct ocelot *ocelot = ocelot_port->ocelot;
+	int port = priv->chip_port;
+
+	return ocelot_vlan_prepare(ocelot, port, vid, pvid, untagged, extack);
+}
+
 static int ocelot_port_obj_add_vlan(struct net_device *dev,
-				    const struct switchdev_obj_port_vlan *vlan)
+				    const struct switchdev_obj_port_vlan *vlan,
+				    struct netlink_ext_ack *extack)
 {
 	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
 	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
 	int ret;
 
-	ret = ocelot_vlan_vid_prepare(dev, vlan->vid, pvid, untagged);
+	ret = ocelot_vlan_vid_prepare(dev, vlan->vid, pvid, untagged, extack);
 	if (ret)
 		return ret;
 
@@ -1074,7 +1041,8 @@ static int ocelot_port_obj_add(struct net_device *dev, const void *ctx,
 	switch (obj->id) {
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
 		ret = ocelot_port_obj_add_vlan(dev,
-					       SWITCHDEV_OBJ_PORT_VLAN(obj));
+					       SWITCHDEV_OBJ_PORT_VLAN(obj),
+					       extack);
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_MDB:
 		ret = ocelot_port_obj_add_mdb(dev, SWITCHDEV_OBJ_PORT_MDB(obj));
@@ -1154,45 +1122,27 @@ static int ocelot_switchdev_sync(struct ocelot *ocelot, int port,
 				 struct net_device *bridge_dev,
 				 struct netlink_ext_ack *extack)
 {
-	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	struct ocelot_port_private *priv;
 	clock_t ageing_time;
 	u8 stp_state;
-	int err;
-
-	priv = container_of(ocelot_port, struct ocelot_port_private, port);
 
 	ocelot_inherit_brport_flags(ocelot, port, brport_dev);
 
 	stp_state = br_port_get_stp_state(brport_dev);
 	ocelot_bridge_stp_state_set(ocelot, port, stp_state);
 
-	err = ocelot_port_vlan_filtering(ocelot, port,
-					 br_vlan_enabled(bridge_dev));
-	if (err)
-		return err;
-
 	ageing_time = br_get_ageing_time(bridge_dev);
 	ocelot_port_attr_ageing_set(ocelot, port, ageing_time);
 
-	err = br_mdb_replay(bridge_dev, brport_dev, priv, true,
-			    &ocelot_switchdev_blocking_nb, extack);
-	if (err && err != -EOPNOTSUPP)
-		return err;
-
-	err = br_vlan_replay(bridge_dev, brport_dev, priv, true,
-			     &ocelot_switchdev_blocking_nb, extack);
-	if (err && err != -EOPNOTSUPP)
-		return err;
-
-	return 0;
+	return ocelot_port_vlan_filtering(ocelot, port,
+					  br_vlan_enabled(bridge_dev),
+					  extack);
 }
 
 static int ocelot_switchdev_unsync(struct ocelot *ocelot, int port)
 {
 	int err;
 
-	err = ocelot_port_vlan_filtering(ocelot, port, false);
+	err = ocelot_port_vlan_filtering(ocelot, port, false, NULL);
 	if (err)
 		return err;
 
@@ -1216,6 +1166,13 @@ static int ocelot_netdevice_bridge_join(struct net_device *dev,
 
 	ocelot_port_bridge_join(ocelot, port, bridge);
 
+	err = switchdev_bridge_port_offload(brport_dev, dev, priv,
+					    &ocelot_netdevice_nb,
+					    &ocelot_switchdev_blocking_nb,
+					    false, extack);
+	if (err)
+		goto err_switchdev_offload;
+
 	err = ocelot_switchdev_sync(ocelot, port, brport_dev, bridge, extack);
 	if (err)
 		goto err_switchdev_sync;
@@ -1223,10 +1180,24 @@ static int ocelot_netdevice_bridge_join(struct net_device *dev,
 	return 0;
 
 err_switchdev_sync:
+	switchdev_bridge_port_unoffload(brport_dev, priv,
+					&ocelot_netdevice_nb,
+					&ocelot_switchdev_blocking_nb);
+err_switchdev_offload:
 	ocelot_port_bridge_leave(ocelot, port, bridge);
 	return err;
 }
 
+static void ocelot_netdevice_pre_bridge_leave(struct net_device *dev,
+					      struct net_device *brport_dev)
+{
+	struct ocelot_port_private *priv = netdev_priv(dev);
+
+	switchdev_bridge_port_unoffload(brport_dev, priv,
+					&ocelot_netdevice_nb,
+					&ocelot_switchdev_blocking_nb);
+}
+
 static int ocelot_netdevice_bridge_leave(struct net_device *dev,
 					 struct net_device *brport_dev,
 					 struct net_device *bridge)
@@ -1279,6 +1250,18 @@ err_bridge_join:
 	return err;
 }
 
+static void ocelot_netdevice_pre_lag_leave(struct net_device *dev,
+					   struct net_device *bond)
+{
+	struct net_device *bridge_dev;
+
+	bridge_dev = netdev_master_upper_dev_get(bond);
+	if (!bridge_dev || !netif_is_bridge_master(bridge_dev))
+		return;
+
+	ocelot_netdevice_pre_bridge_leave(dev, bond);
+}
+
 static int ocelot_netdevice_lag_leave(struct net_device *dev,
 				      struct net_device *bond)
 {
@@ -1356,6 +1339,43 @@ ocelot_netdevice_lag_changeupper(struct net_device *dev,
 }
 
 static int
+ocelot_netdevice_prechangeupper(struct net_device *dev,
+				struct net_device *brport_dev,
+				struct netdev_notifier_changeupper_info *info)
+{
+	if (netif_is_bridge_master(info->upper_dev) && !info->linking)
+		ocelot_netdevice_pre_bridge_leave(dev, brport_dev);
+
+	if (netif_is_lag_master(info->upper_dev) && !info->linking)
+		ocelot_netdevice_pre_lag_leave(dev, info->upper_dev);
+
+	return NOTIFY_DONE;
+}
+
+static int
+ocelot_netdevice_lag_prechangeupper(struct net_device *dev,
+				    struct netdev_notifier_changeupper_info *info)
+{
+	struct net_device *lower;
+	struct list_head *iter;
+	int err = NOTIFY_DONE;
+
+	netdev_for_each_lower_dev(dev, lower, iter) {
+		struct ocelot_port_private *priv = netdev_priv(lower);
+		struct ocelot_port *ocelot_port = &priv->port;
+
+		if (ocelot_port->bond != dev)
+			return NOTIFY_OK;
+
+		err = ocelot_netdevice_prechangeupper(dev, lower, info);
+		if (err)
+			return err;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int
 ocelot_netdevice_changelowerstate(struct net_device *dev,
 				  struct netdev_lag_lower_state_info *info)
 {
@@ -1382,6 +1402,17 @@ static int ocelot_netdevice_event(struct notifier_block *unused,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
 	switch (event) {
+	case NETDEV_PRECHANGEUPPER: {
+		struct netdev_notifier_changeupper_info *info = ptr;
+
+		if (ocelot_netdevice_dev_check(dev))
+			return ocelot_netdevice_prechangeupper(dev, dev, info);
+
+		if (netif_is_lag_master(dev))
+			return ocelot_netdevice_lag_prechangeupper(dev, info);
+
+		break;
+	}
 	case NETDEV_CHANGEUPPER: {
 		struct netdev_notifier_changeupper_info *info = ptr;
 
@@ -1466,8 +1497,188 @@ struct notifier_block ocelot_switchdev_blocking_nb __read_mostly = {
 	.notifier_call = ocelot_switchdev_blocking_event,
 };
 
+static void vsc7514_phylink_validate(struct phylink_config *config,
+				     unsigned long *supported,
+				     struct phylink_link_state *state)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct ocelot_port_private *priv = netdev_priv(ndev);
+	struct ocelot_port *ocelot_port = &priv->port;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = {};
+
+	if (state->interface != PHY_INTERFACE_MODE_NA &&
+	    state->interface != ocelot_port->phy_mode) {
+		bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
+		return;
+	}
+
+	phylink_set_port_modes(mask);
+
+	phylink_set(mask, Pause);
+	phylink_set(mask, Autoneg);
+	phylink_set(mask, Asym_Pause);
+	phylink_set(mask, 10baseT_Half);
+	phylink_set(mask, 10baseT_Full);
+	phylink_set(mask, 100baseT_Half);
+	phylink_set(mask, 100baseT_Full);
+	phylink_set(mask, 1000baseT_Half);
+	phylink_set(mask, 1000baseT_Full);
+	phylink_set(mask, 1000baseX_Full);
+	phylink_set(mask, 2500baseT_Full);
+	phylink_set(mask, 2500baseX_Full);
+
+	bitmap_and(supported, supported, mask, __ETHTOOL_LINK_MODE_MASK_NBITS);
+	bitmap_and(state->advertising, state->advertising, mask,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
+static void vsc7514_phylink_mac_config(struct phylink_config *config,
+				       unsigned int link_an_mode,
+				       const struct phylink_link_state *state)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct ocelot_port_private *priv = netdev_priv(ndev);
+	struct ocelot_port *ocelot_port = &priv->port;
+
+	/* Disable HDX fast control */
+	ocelot_port_writel(ocelot_port, DEV_PORT_MISC_HDX_FAST_DIS,
+			   DEV_PORT_MISC);
+
+	/* SGMII only for now */
+	ocelot_port_writel(ocelot_port, PCS1G_MODE_CFG_SGMII_MODE_ENA,
+			   PCS1G_MODE_CFG);
+	ocelot_port_writel(ocelot_port, PCS1G_SD_CFG_SD_SEL, PCS1G_SD_CFG);
+
+	/* Enable PCS */
+	ocelot_port_writel(ocelot_port, PCS1G_CFG_PCS_ENA, PCS1G_CFG);
+
+	/* No aneg on SGMII */
+	ocelot_port_writel(ocelot_port, 0, PCS1G_ANEG_CFG);
+
+	/* No loopback */
+	ocelot_port_writel(ocelot_port, 0, PCS1G_LB_CFG);
+}
+
+static void vsc7514_phylink_mac_link_down(struct phylink_config *config,
+					  unsigned int link_an_mode,
+					  phy_interface_t interface)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct ocelot_port_private *priv = netdev_priv(ndev);
+	struct ocelot *ocelot = priv->port.ocelot;
+	int port = priv->chip_port;
+
+	ocelot_phylink_mac_link_down(ocelot, port, link_an_mode, interface,
+				     OCELOT_MAC_QUIRKS);
+}
+
+static void vsc7514_phylink_mac_link_up(struct phylink_config *config,
+					struct phy_device *phydev,
+					unsigned int link_an_mode,
+					phy_interface_t interface,
+					int speed, int duplex,
+					bool tx_pause, bool rx_pause)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct ocelot_port_private *priv = netdev_priv(ndev);
+	struct ocelot *ocelot = priv->port.ocelot;
+	int port = priv->chip_port;
+
+	ocelot_phylink_mac_link_up(ocelot, port, phydev, link_an_mode,
+				   interface, speed, duplex,
+				   tx_pause, rx_pause, OCELOT_MAC_QUIRKS);
+}
+
+static const struct phylink_mac_ops ocelot_phylink_ops = {
+	.validate		= vsc7514_phylink_validate,
+	.mac_config		= vsc7514_phylink_mac_config,
+	.mac_link_down		= vsc7514_phylink_mac_link_down,
+	.mac_link_up		= vsc7514_phylink_mac_link_up,
+};
+
+static int ocelot_port_phylink_create(struct ocelot *ocelot, int port,
+				      struct device_node *portnp)
+{
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	struct ocelot_port_private *priv;
+	struct device *dev = ocelot->dev;
+	phy_interface_t phy_mode;
+	struct phylink *phylink;
+	int err;
+
+	of_get_phy_mode(portnp, &phy_mode);
+	/* DT bindings of internal PHY ports are broken and don't
+	 * specify a phy-mode
+	 */
+	if (phy_mode == PHY_INTERFACE_MODE_NA)
+		phy_mode = PHY_INTERFACE_MODE_INTERNAL;
+
+	if (phy_mode != PHY_INTERFACE_MODE_SGMII &&
+	    phy_mode != PHY_INTERFACE_MODE_QSGMII &&
+	    phy_mode != PHY_INTERFACE_MODE_INTERNAL) {
+		dev_err(dev, "unsupported phy mode %s for port %d\n",
+			phy_modes(phy_mode), port);
+		return -EINVAL;
+	}
+
+	/* Ensure clock signals and speed are set on all QSGMII links */
+	if (phy_mode == PHY_INTERFACE_MODE_QSGMII)
+		ocelot_port_rmwl(ocelot_port, 0,
+				 DEV_CLOCK_CFG_MAC_TX_RST |
+				 DEV_CLOCK_CFG_MAC_TX_RST,
+				 DEV_CLOCK_CFG);
+
+	ocelot_port->phy_mode = phy_mode;
+
+	if (phy_mode != PHY_INTERFACE_MODE_INTERNAL) {
+		struct phy *serdes = of_phy_get(portnp, NULL);
+
+		if (IS_ERR(serdes)) {
+			err = PTR_ERR(serdes);
+			dev_err_probe(dev, err,
+				      "missing SerDes phys for port %d\n",
+				      port);
+			return err;
+		}
+
+		err = phy_set_mode_ext(serdes, PHY_MODE_ETHERNET, phy_mode);
+		of_phy_put(serdes);
+		if (err) {
+			dev_err(dev, "Could not SerDes mode on port %d: %pe\n",
+				port, ERR_PTR(err));
+			return err;
+		}
+	}
+
+	priv = container_of(ocelot_port, struct ocelot_port_private, port);
+
+	priv->phylink_config.dev = &priv->dev->dev;
+	priv->phylink_config.type = PHYLINK_NETDEV;
+
+	phylink = phylink_create(&priv->phylink_config,
+				 of_fwnode_handle(portnp),
+				 phy_mode, &ocelot_phylink_ops);
+	if (IS_ERR(phylink)) {
+		err = PTR_ERR(phylink);
+		dev_err(dev, "Could not create phylink (%pe)\n", phylink);
+		return err;
+	}
+
+	priv->phylink = phylink;
+
+	err = phylink_of_phy_connect(phylink, portnp, 0);
+	if (err) {
+		dev_err(dev, "Could not connect to PHY: %pe\n", ERR_PTR(err));
+		phylink_destroy(phylink);
+		priv->phylink = NULL;
+		return err;
+	}
+
+	return 0;
+}
+
 int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target,
-		      struct phy_device *phy)
+		      struct device_node *portnp)
 {
 	struct ocelot_port_private *priv;
 	struct ocelot_port *ocelot_port;
@@ -1480,7 +1691,6 @@ int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target,
 	SET_NETDEV_DEV(dev, ocelot->dev);
 	priv = netdev_priv(dev);
 	priv->dev = dev;
-	priv->phy = phy;
 	priv->chip_port = port;
 	ocelot_port = &priv->port;
 	ocelot_port->ocelot = ocelot;
@@ -1501,15 +1711,23 @@ int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target,
 
 	ocelot_init_port(ocelot, port);
 
+	err = ocelot_port_phylink_create(ocelot, port, portnp);
+	if (err)
+		goto out;
+
 	err = register_netdev(dev);
 	if (err) {
 		dev_err(ocelot->dev, "register_netdev failed\n");
-		free_netdev(dev);
-		ocelot->ports[port] = NULL;
-		return err;
+		goto out;
 	}
 
 	return 0;
+
+out:
+	ocelot->ports[port] = NULL;
+	free_netdev(dev);
+
+	return err;
 }
 
 void ocelot_release_port(struct ocelot_port *ocelot_port)
@@ -1519,5 +1737,14 @@ void ocelot_release_port(struct ocelot_port *ocelot_port)
 						port);
 
 	unregister_netdev(priv->dev);
+
+	if (priv->phylink) {
+		rtnl_lock();
+		phylink_disconnect_phy(priv->phylink);
+		rtnl_unlock();
+
+		phylink_destroy(priv->phylink);
+	}
+
 	free_netdev(priv->dev);
 }
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 4bd7e9d9ec61..291ae6817c26 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <linux/of_net.h>
 #include <linux/netdevice.h>
+#include <linux/phylink.h>
 #include <linux/of_mdio.h>
 #include <linux/of_platform.h>
 #include <linux/mfd/syscon.h>
@@ -945,13 +946,9 @@ static int mscc_ocelot_init_ports(struct platform_device *pdev,
 	for_each_available_child_of_node(ports, portnp) {
 		struct ocelot_port_private *priv;
 		struct ocelot_port *ocelot_port;
-		struct device_node *phy_node;
 		struct devlink_port *dlp;
-		phy_interface_t phy_mode;
-		struct phy_device *phy;
 		struct regmap *target;
 		struct resource *res;
-		struct phy *serdes;
 		char res_name[8];
 
 		if (of_property_read_u32(portnp, "reg", &reg))
@@ -975,77 +972,26 @@ static int mscc_ocelot_init_ports(struct platform_device *pdev,
 			goto out_teardown;
 		}
 
-		phy_node = of_parse_phandle(portnp, "phy-handle", 0);
-		if (!phy_node)
-			continue;
-
-		phy = of_phy_find_device(phy_node);
-		of_node_put(phy_node);
-		if (!phy)
-			continue;
-
 		err = ocelot_port_devlink_init(ocelot, port,
 					       DEVLINK_PORT_FLAVOUR_PHYSICAL);
 		if (err) {
 			of_node_put(portnp);
 			goto out_teardown;
 		}
-		devlink_ports_registered |= BIT(port);
 
-		err = ocelot_probe_port(ocelot, port, target, phy);
+		err = ocelot_probe_port(ocelot, port, target, portnp);
 		if (err) {
-			of_node_put(portnp);
-			goto out_teardown;
+			ocelot_port_devlink_teardown(ocelot, port);
+			continue;
 		}
 
+		devlink_ports_registered |= BIT(port);
+
 		ocelot_port = ocelot->ports[port];
 		priv = container_of(ocelot_port, struct ocelot_port_private,
 				    port);
 		dlp = &ocelot->devlink_ports[port];
 		devlink_port_type_eth_set(dlp, priv->dev);
-
-		of_get_phy_mode(portnp, &phy_mode);
-
-		ocelot_port->phy_mode = phy_mode;
-
-		switch (ocelot_port->phy_mode) {
-		case PHY_INTERFACE_MODE_NA:
-			continue;
-		case PHY_INTERFACE_MODE_SGMII:
-			break;
-		case PHY_INTERFACE_MODE_QSGMII:
-			/* Ensure clock signals and speed is set on all
-			 * QSGMII links
-			 */
-			ocelot_port_writel(ocelot_port,
-					   DEV_CLOCK_CFG_LINK_SPEED
-					   (OCELOT_SPEED_1000),
-					   DEV_CLOCK_CFG);
-			break;
-		default:
-			dev_err(ocelot->dev,
-				"invalid phy mode for port%d, (Q)SGMII only\n",
-				port);
-			of_node_put(portnp);
-			err = -EINVAL;
-			goto out_teardown;
-		}
-
-		serdes = devm_of_phy_get(ocelot->dev, portnp, NULL);
-		if (IS_ERR(serdes)) {
-			err = PTR_ERR(serdes);
-			if (err == -EPROBE_DEFER)
-				dev_dbg(ocelot->dev, "deferring probe\n");
-			else
-				dev_err(ocelot->dev,
-					"missing SerDes phys for port%d\n",
-					port);
-
-			of_node_put(portnp);
-			goto out_teardown;
-		}
-
-		priv->serdes = serdes;
 	}
 
 	/* Initialize unused devlink ports at the end */
@@ -1103,7 +1049,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 	if (!np && !pdev->dev.platform_data)
 		return -ENODEV;
 
-	devlink = devlink_alloc(&ocelot_devlink_ops, sizeof(*ocelot));
+	devlink =
+		devlink_alloc(&ocelot_devlink_ops, sizeof(*ocelot), &pdev->dev);
 	if (!devlink)
 		return -ENOMEM;
 
@@ -1187,7 +1134,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 	if (err)
 		goto out_put_ports;
 
-	err = devlink_register(devlink, ocelot->dev);
+	err = devlink_register(devlink);
 	if (err)
 		goto out_ocelot_deinit;
 
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index fc99ad8e4a38..c1a75b08ced7 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -850,9 +850,9 @@ static int myri10ge_dma_test(struct myri10ge_priv *mgp, int test_type)
 	dmatest_page = alloc_page(GFP_KERNEL);
 	if (!dmatest_page)
 		return -ENOMEM;
-	dmatest_bus = pci_map_page(mgp->pdev, dmatest_page, 0, PAGE_SIZE,
-				   DMA_BIDIRECTIONAL);
-	if (unlikely(pci_dma_mapping_error(mgp->pdev, dmatest_bus))) {
+	dmatest_bus = dma_map_page(&mgp->pdev->dev, dmatest_page, 0,
+				   PAGE_SIZE, DMA_BIDIRECTIONAL);
+	if (unlikely(dma_mapping_error(&mgp->pdev->dev, dmatest_bus))) {
 		__free_page(dmatest_page);
 		return -ENOMEM;
 	}
@@ -899,7 +899,8 @@ static int myri10ge_dma_test(struct myri10ge_priv *mgp, int test_type)
 	    (cmd.data0 & 0xffff);
 
 abort:
-	pci_unmap_page(mgp->pdev, dmatest_bus, PAGE_SIZE, DMA_BIDIRECTIONAL);
+	dma_unmap_page(&mgp->pdev->dev, dmatest_bus, PAGE_SIZE,
+		       DMA_BIDIRECTIONAL);
 	put_page(dmatest_page);
 
 	if (status != 0 && test_type != MXGEFW_CMD_UNALIGNED_TEST)
@@ -1205,10 +1206,10 @@ myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx,
 				return;
 			}
 
-			bus = pci_map_page(mgp->pdev, page, 0,
+			bus = dma_map_page(&mgp->pdev->dev, page, 0,
 					   MYRI10GE_ALLOC_SIZE,
-					   PCI_DMA_FROMDEVICE);
-			if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) {
+					   DMA_FROM_DEVICE);
+			if (unlikely(dma_mapping_error(&mgp->pdev->dev, bus))) {
 				__free_pages(page, MYRI10GE_ALLOC_ORDER);
 				if (rx->fill_cnt - rx->cnt < 16)
 					rx->watchdog_needed = 1;
@@ -1256,9 +1257,9 @@ myri10ge_unmap_rx_page(struct pci_dev *pdev,
 	/* unmap the recvd page if we're the only or last user of it */
 	if (bytes >= MYRI10GE_ALLOC_SIZE / 2 ||
 	    (info->page_offset + 2 * bytes) > MYRI10GE_ALLOC_SIZE) {
-		pci_unmap_page(pdev, (dma_unmap_addr(info, bus)
-				      & ~(MYRI10GE_ALLOC_SIZE - 1)),
-			       MYRI10GE_ALLOC_SIZE, PCI_DMA_FROMDEVICE);
+		dma_unmap_page(&pdev->dev, (dma_unmap_addr(info, bus)
+					    & ~(MYRI10GE_ALLOC_SIZE - 1)),
+			       MYRI10GE_ALLOC_SIZE, DMA_FROM_DEVICE);
 	}
 }
 
@@ -1398,16 +1399,16 @@ myri10ge_tx_done(struct myri10ge_slice_state *ss, int mcp_index)
 			ss->stats.tx_packets++;
 			dev_consume_skb_irq(skb);
 			if (len)
-				pci_unmap_single(pdev,
+				dma_unmap_single(&pdev->dev,
 						 dma_unmap_addr(&tx->info[idx],
 								bus), len,
-						 PCI_DMA_TODEVICE);
+						 DMA_TO_DEVICE);
 		} else {
 			if (len)
-				pci_unmap_page(pdev,
+				dma_unmap_page(&pdev->dev,
 					       dma_unmap_addr(&tx->info[idx],
 							      bus), len,
-					       PCI_DMA_TODEVICE);
+					       DMA_TO_DEVICE);
 		}
 	}
 
@@ -1651,8 +1652,10 @@ myri10ge_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info)
 	strlcpy(info->bus_info, pci_name(mgp->pdev), sizeof(info->bus_info));
 }
 
-static int
-myri10ge_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *coal)
+static int myri10ge_get_coalesce(struct net_device *netdev,
+				 struct ethtool_coalesce *coal,
+				 struct kernel_ethtool_coalesce *kernel_coal,
+				 struct netlink_ext_ack *extack)
 {
 	struct myri10ge_priv *mgp = netdev_priv(netdev);
 
@@ -1660,8 +1663,10 @@ myri10ge_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *coal)
 	return 0;
 }
 
-static int
-myri10ge_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *coal)
+static int myri10ge_set_coalesce(struct net_device *netdev,
+				 struct ethtool_coalesce *coal,
+				 struct kernel_ethtool_coalesce *kernel_coal,
+				 struct netlink_ext_ack *extack)
 {
 	struct myri10ge_priv *mgp = netdev_priv(netdev);
 
@@ -2110,16 +2115,16 @@ static void myri10ge_free_rings(struct myri10ge_slice_state *ss)
 			ss->stats.tx_dropped++;
 			dev_kfree_skb_any(skb);
 			if (len)
-				pci_unmap_single(mgp->pdev,
+				dma_unmap_single(&mgp->pdev->dev,
 						 dma_unmap_addr(&tx->info[idx],
 								bus), len,
-						 PCI_DMA_TODEVICE);
+						 DMA_TO_DEVICE);
 		} else {
 			if (len)
-				pci_unmap_page(mgp->pdev,
+				dma_unmap_page(&mgp->pdev->dev,
 					       dma_unmap_addr(&tx->info[idx],
 							      bus), len,
-					       PCI_DMA_TODEVICE);
+					       DMA_TO_DEVICE);
 		}
 	}
 	kfree(ss->rx_big.info);
@@ -2584,15 +2589,15 @@ static void myri10ge_unmap_tx_dma(struct myri10ge_priv *mgp,
 		len = dma_unmap_len(&tx->info[idx], len);
 		if (len) {
 			if (tx->info[idx].skb != NULL)
-				pci_unmap_single(mgp->pdev,
+				dma_unmap_single(&mgp->pdev->dev,
 						 dma_unmap_addr(&tx->info[idx],
 								bus), len,
-						 PCI_DMA_TODEVICE);
+						 DMA_TO_DEVICE);
 			else
-				pci_unmap_page(mgp->pdev,
+				dma_unmap_page(&mgp->pdev->dev,
 					       dma_unmap_addr(&tx->info[idx],
 							      bus), len,
-					       PCI_DMA_TODEVICE);
+					       DMA_TO_DEVICE);
 			dma_unmap_len_set(&tx->info[idx], len, 0);
 			tx->info[idx].skb = NULL;
 		}
@@ -2715,8 +2720,8 @@ again:
 
 	/* map the skb for DMA */
 	len = skb_headlen(skb);
-	bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE);
-	if (unlikely(pci_dma_mapping_error(mgp->pdev, bus)))
+	bus = dma_map_single(&mgp->pdev->dev, skb->data, len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(&mgp->pdev->dev, bus)))
 		goto drop;
 
 	idx = tx->req & tx->mask;
@@ -2824,7 +2829,7 @@ again:
 		len = skb_frag_size(frag);
 		bus = skb_frag_dma_map(&mgp->pdev->dev, frag, 0, len,
 				       DMA_TO_DEVICE);
-		if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) {
+		if (unlikely(dma_mapping_error(&mgp->pdev->dev, bus))) {
 			myri10ge_unmap_tx_dma(mgp, tx, idx);
 			goto drop;
 		}
@@ -3776,19 +3781,17 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	myri10ge_mask_surprise_down(pdev);
 	pci_set_master(pdev);
 	dac_enabled = 1;
-	status = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	status = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (status != 0) {
 		dac_enabled = 0;
 		dev_err(&pdev->dev,
-			"64-bit pci address mask was refused, "
-			"trying 32-bit\n");
-		status = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+			"64-bit pci address mask was refused, trying 32-bit\n");
+		status = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
 	}
 	if (status != 0) {
 		dev_err(&pdev->dev, "Error %d setting DMA mask\n", status);
 		goto abort_with_enabled;
 	}
-	(void)pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
 	mgp->cmd = dma_alloc_coherent(&pdev->dev, sizeof(*mgp->cmd),
 				      &mgp->cmd_bus, GFP_KERNEL);
 	if (!mgp->cmd) {
diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c
index ce3eca5d152b..d74a80f010c5 100644
--- a/drivers/net/ethernet/natsemi/jazzsonic.c
+++ b/drivers/net/ethernet/natsemi/jazzsonic.c
@@ -193,8 +193,6 @@ static int jazz_sonic_probe(struct platform_device *pdev)
 	SET_NETDEV_DEV(dev, &pdev->dev);
 	platform_set_drvdata(pdev, dev);
 
-	netdev_boot_setup_check(dev);
-
 	dev->base_addr = res->start;
 	dev->irq = platform_get_irq(pdev, 0);
 	err = sonic_probe1(dev);
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index 84f7dbe9edff..3f982033944b 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -790,7 +790,7 @@ static const struct net_device_ops natsemi_netdev_ops = {
 	.ndo_get_stats		= get_stats,
 	.ndo_set_rx_mode	= set_rx_mode,
 	.ndo_change_mtu		= natsemi_change_mtu,
-	.ndo_do_ioctl		= netdev_ioctl,
+	.ndo_eth_ioctl		= netdev_ioctl,
 	.ndo_tx_timeout 	= ns_tx_timeout,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c
index 28d9e98db81a..ca4686094701 100644
--- a/drivers/net/ethernet/natsemi/xtsonic.c
+++ b/drivers/net/ethernet/natsemi/xtsonic.c
@@ -215,7 +215,6 @@ int xtsonic_probe(struct platform_device *pdev)
 	lp->device = &pdev->dev;
 	platform_set_drvdata(pdev, dev);
 	SET_NETDEV_DEV(dev, &pdev->dev);
-	netdev_boot_setup_check(dev);
 
 	dev->base_addr = resmem->start;
 	dev->irq = resirq->start;
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 0b017d4f5c08..09c0e839cca5 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -7625,7 +7625,7 @@ static const struct net_device_ops s2io_netdev_ops = {
 	.ndo_start_xmit    	= s2io_xmit,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= s2io_ndo_set_multicast,
-	.ndo_do_ioctl	   	= s2io_ioctl,
+	.ndo_eth_ioctl		= s2io_ioctl,
 	.ndo_set_mac_address    = s2io_set_mac_addr,
 	.ndo_change_mtu	   	= s2io_change_mtu,
 	.ndo_set_features	= s2io_set_features,
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index 7abd13e69471..df4a3f3da83a 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -3339,7 +3339,7 @@ static const struct net_device_ops vxge_netdev_ops = {
 	.ndo_start_xmit         = vxge_xmit,
 	.ndo_validate_addr      = eth_validate_addr,
 	.ndo_set_rx_mode	= vxge_set_multicast,
-	.ndo_do_ioctl           = vxge_ioctl,
+	.ndo_eth_ioctl           = vxge_ioctl,
 	.ndo_set_mac_address    = vxge_set_mac_addr,
 	.ndo_change_mtu         = vxge_change_mtu,
 	.ndo_fix_features	= vxge_fix_features,
diff --git a/drivers/net/ethernet/netronome/Kconfig b/drivers/net/ethernet/netronome/Kconfig
index b82758d5beed..8844d1ac053a 100644
--- a/drivers/net/ethernet/netronome/Kconfig
+++ b/drivers/net/ethernet/netronome/Kconfig
@@ -23,6 +23,7 @@ config NFP
 	depends on TLS && TLS_DEVICE || TLS_DEVICE=n
 	select NET_DEVLINK
 	select CRC32
+	select DIMLIB
 	help
 	  This driver supports the Netronome(R) NFP4000/NFP6000 based
 	  cards working as a advanced Ethernet NIC.  It works with both
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 1cbe2c9f3959..2a432de11858 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -262,10 +262,10 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
 }
 
 static bool
-nfp_flower_tun_is_gre(struct flow_cls_offload *flow, int start_idx)
+nfp_flower_tun_is_gre(struct flow_rule *rule, int start_idx)
 {
-	struct flow_action_entry *act = flow->rule->action.entries;
-	int num_act = flow->rule->action.num_entries;
+	struct flow_action_entry *act = rule->action.entries;
+	int num_act = rule->action.num_entries;
 	int act_idx;
 
 	/* Preparse action list for next mirred or redirect action */
@@ -279,7 +279,7 @@ nfp_flower_tun_is_gre(struct flow_cls_offload *flow, int start_idx)
 
 static enum nfp_flower_tun_type
 nfp_fl_get_tun_from_act(struct nfp_app *app,
-			struct flow_cls_offload *flow,
+			struct flow_rule *rule,
 			const struct flow_action_entry *act, int act_idx)
 {
 	const struct ip_tunnel_info *tun = act->tunnel;
@@ -288,7 +288,7 @@ nfp_fl_get_tun_from_act(struct nfp_app *app,
 	/* Determine the tunnel type based on the egress netdev
 	 * in the mirred action for tunnels without l4.
 	 */
-	if (nfp_flower_tun_is_gre(flow, act_idx))
+	if (nfp_flower_tun_is_gre(rule, act_idx))
 		return NFP_FL_TUNNEL_GRE;
 
 	switch (tun->key.tp_dst) {
@@ -788,11 +788,10 @@ struct nfp_flower_pedit_acts {
 };
 
 static int
-nfp_fl_commit_mangle(struct flow_cls_offload *flow, char *nfp_action,
+nfp_fl_commit_mangle(struct flow_rule *rule, char *nfp_action,
 		     int *a_len, struct nfp_flower_pedit_acts *set_act,
 		     u32 *csum_updated)
 {
-	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	size_t act_size = 0;
 	u8 ip_proto = 0;
 
@@ -890,7 +889,7 @@ nfp_fl_commit_mangle(struct flow_cls_offload *flow, char *nfp_action,
 
 static int
 nfp_fl_pedit(const struct flow_action_entry *act,
-	     struct flow_cls_offload *flow, char *nfp_action, int *a_len,
+	     char *nfp_action, int *a_len,
 	     u32 *csum_updated, struct nfp_flower_pedit_acts *set_act,
 	     struct netlink_ext_ack *extack)
 {
@@ -977,7 +976,7 @@ nfp_flower_output_action(struct nfp_app *app,
 
 static int
 nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act,
-		       struct flow_cls_offload *flow,
+		       struct flow_rule *rule,
 		       struct nfp_fl_payload *nfp_fl, int *a_len,
 		       struct net_device *netdev,
 		       enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
@@ -1045,7 +1044,7 @@ nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act,
 	case FLOW_ACTION_TUNNEL_ENCAP: {
 		const struct ip_tunnel_info *ip_tun = act->tunnel;
 
-		*tun_type = nfp_fl_get_tun_from_act(app, flow, act, act_idx);
+		*tun_type = nfp_fl_get_tun_from_act(app, rule, act, act_idx);
 		if (*tun_type == NFP_FL_TUNNEL_NONE) {
 			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: unsupported tunnel type in action list");
 			return -EOPNOTSUPP;
@@ -1086,7 +1085,7 @@ nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act,
 		/* Tunnel decap is handled by default so accept action. */
 		return 0;
 	case FLOW_ACTION_MANGLE:
-		if (nfp_fl_pedit(act, flow, &nfp_fl->action_data[*a_len],
+		if (nfp_fl_pedit(act, &nfp_fl->action_data[*a_len],
 				 a_len, csum_updated, set_act, extack))
 			return -EOPNOTSUPP;
 		break;
@@ -1195,7 +1194,7 @@ static bool nfp_fl_check_mangle_end(struct flow_action *flow_act,
 }
 
 int nfp_flower_compile_action(struct nfp_app *app,
-			      struct flow_cls_offload *flow,
+			      struct flow_rule *rule,
 			      struct net_device *netdev,
 			      struct nfp_fl_payload *nfp_flow,
 			      struct netlink_ext_ack *extack)
@@ -1207,7 +1206,7 @@ int nfp_flower_compile_action(struct nfp_app *app,
 	bool pkt_host = false;
 	u32 csum_updated = 0;
 
-	if (!flow_action_hw_stats_check(&flow->rule->action, extack,
+	if (!flow_action_hw_stats_check(&rule->action, extack,
 					FLOW_ACTION_HW_STATS_DELAYED_BIT))
 		return -EOPNOTSUPP;
 
@@ -1219,18 +1218,18 @@ int nfp_flower_compile_action(struct nfp_app *app,
 	tun_out_cnt = 0;
 	out_cnt = 0;
 
-	flow_action_for_each(i, act, &flow->rule->action) {
-		if (nfp_fl_check_mangle_start(&flow->rule->action, i))
+	flow_action_for_each(i, act, &rule->action) {
+		if (nfp_fl_check_mangle_start(&rule->action, i))
 			memset(&set_act, 0, sizeof(set_act));
-		err = nfp_flower_loop_action(app, act, flow, nfp_flow, &act_len,
+		err = nfp_flower_loop_action(app, act, rule, nfp_flow, &act_len,
 					     netdev, &tun_type, &tun_out_cnt,
 					     &out_cnt, &csum_updated,
 					     &set_act, &pkt_host, extack, i);
 		if (err)
 			return err;
 		act_cnt++;
-		if (nfp_fl_check_mangle_end(&flow->rule->action, i))
-			nfp_fl_commit_mangle(flow,
+		if (nfp_fl_check_mangle_end(&rule->action, i))
+			nfp_fl_commit_mangle(rule,
 					     &nfp_flow->action_data[act_len],
 					     &act_len, &set_act, &csum_updated);
 	}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
index 062bb2db68bf..bfd7d1c35076 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2021 Corigine, Inc. */
 
 #include "conntrack.h"
+#include "../nfp_port.h"
 
 const struct rhashtable_params nfp_tc_ct_merge_params = {
 	.head_offset		= offsetof(struct nfp_fl_ct_tc_merge,
@@ -407,15 +408,491 @@ static int nfp_ct_check_meta(struct nfp_fl_ct_flow_entry *post_ct_entry,
 	return -EINVAL;
 }
 
+static int
+nfp_fl_calc_key_layers_sz(struct nfp_fl_key_ls in_key_ls, uint16_t *map)
+{
+	int key_size;
+
+	/* This field must always be present */
+	key_size = sizeof(struct nfp_flower_meta_tci);
+	map[FLOW_PAY_META_TCI] = 0;
+
+	if (in_key_ls.key_layer & NFP_FLOWER_LAYER_EXT_META) {
+		map[FLOW_PAY_EXT_META] = key_size;
+		key_size += sizeof(struct nfp_flower_ext_meta);
+	}
+	if (in_key_ls.key_layer & NFP_FLOWER_LAYER_PORT) {
+		map[FLOW_PAY_INPORT] = key_size;
+		key_size += sizeof(struct nfp_flower_in_port);
+	}
+	if (in_key_ls.key_layer & NFP_FLOWER_LAYER_MAC) {
+		map[FLOW_PAY_MAC_MPLS] = key_size;
+		key_size += sizeof(struct nfp_flower_mac_mpls);
+	}
+	if (in_key_ls.key_layer & NFP_FLOWER_LAYER_TP) {
+		map[FLOW_PAY_L4] = key_size;
+		key_size += sizeof(struct nfp_flower_tp_ports);
+	}
+	if (in_key_ls.key_layer & NFP_FLOWER_LAYER_IPV4) {
+		map[FLOW_PAY_IPV4] = key_size;
+		key_size += sizeof(struct nfp_flower_ipv4);
+	}
+	if (in_key_ls.key_layer & NFP_FLOWER_LAYER_IPV6) {
+		map[FLOW_PAY_IPV6] = key_size;
+		key_size += sizeof(struct nfp_flower_ipv6);
+	}
+
+	if (in_key_ls.key_layer_two & NFP_FLOWER_LAYER2_GRE) {
+		map[FLOW_PAY_GRE] = key_size;
+		if (in_key_ls.key_layer_two & NFP_FLOWER_LAYER2_TUN_IPV6)
+			key_size += sizeof(struct nfp_flower_ipv6_gre_tun);
+		else
+			key_size += sizeof(struct nfp_flower_ipv4_gre_tun);
+	}
+
+	if (in_key_ls.key_layer_two & NFP_FLOWER_LAYER2_QINQ) {
+		map[FLOW_PAY_QINQ] = key_size;
+		key_size += sizeof(struct nfp_flower_vlan);
+	}
+
+	if ((in_key_ls.key_layer & NFP_FLOWER_LAYER_VXLAN) ||
+	    (in_key_ls.key_layer_two & NFP_FLOWER_LAYER2_GENEVE)) {
+		map[FLOW_PAY_UDP_TUN] = key_size;
+		if (in_key_ls.key_layer_two & NFP_FLOWER_LAYER2_TUN_IPV6)
+			key_size += sizeof(struct nfp_flower_ipv6_udp_tun);
+		else
+			key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
+	}
+
+	if (in_key_ls.key_layer_two & NFP_FLOWER_LAYER2_GENEVE_OP) {
+		map[FLOW_PAY_GENEVE_OPT] = key_size;
+		key_size += sizeof(struct nfp_flower_geneve_options);
+	}
+
+	return key_size;
+}
+
+static int nfp_fl_merge_actions_offload(struct flow_rule **rules,
+					struct nfp_flower_priv *priv,
+					struct net_device *netdev,
+					struct nfp_fl_payload *flow_pay)
+{
+	struct flow_action_entry *a_in;
+	int i, j, num_actions, id;
+	struct flow_rule *a_rule;
+	int err = 0, offset = 0;
+
+	num_actions = rules[CT_TYPE_PRE_CT]->action.num_entries +
+		      rules[CT_TYPE_NFT]->action.num_entries +
+		      rules[CT_TYPE_POST_CT]->action.num_entries;
+
+	a_rule = flow_rule_alloc(num_actions);
+	if (!a_rule)
+		return -ENOMEM;
+
+	/* Actions need a BASIC dissector. */
+	a_rule->match = rules[CT_TYPE_PRE_CT]->match;
+
+	/* Copy actions */
+	for (j = 0; j < _CT_TYPE_MAX; j++) {
+		if (flow_rule_match_key(rules[j], FLOW_DISSECTOR_KEY_BASIC)) {
+			struct flow_match_basic match;
+
+			/* ip_proto is the only field that needed in later compile_action,
+			 * needed to set the correct checksum flags. It doesn't really matter
+			 * which input rule's ip_proto field we take as the earlier merge checks
+			 * would have made sure that they don't conflict. We do not know which
+			 * of the subflows would have the ip_proto filled in, so we need to iterate
+			 * through the subflows and assign the proper subflow to a_rule
+			 */
+			flow_rule_match_basic(rules[j], &match);
+			if (match.mask->ip_proto)
+				a_rule->match = rules[j]->match;
+		}
+
+		for (i = 0; i < rules[j]->action.num_entries; i++) {
+			a_in = &rules[j]->action.entries[i];
+			id = a_in->id;
+
+			/* Ignore CT related actions as these would already have
+			 * been taken care of by previous checks, and we do not send
+			 * any CT actions to the firmware.
+			 */
+			switch (id) {
+			case FLOW_ACTION_CT:
+			case FLOW_ACTION_GOTO:
+			case FLOW_ACTION_CT_METADATA:
+				continue;
+			default:
+				memcpy(&a_rule->action.entries[offset++],
+				       a_in, sizeof(struct flow_action_entry));
+				break;
+			}
+		}
+	}
+
+	/* Some actions would have been ignored, so update the num_entries field */
+	a_rule->action.num_entries = offset;
+	err = nfp_flower_compile_action(priv->app, a_rule, netdev, flow_pay, NULL);
+	kfree(a_rule);
+
+	return err;
+}
+
 static int nfp_fl_ct_add_offload(struct nfp_fl_nft_tc_merge *m_entry)
 {
-	return 0;
+	enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE;
+	struct nfp_fl_ct_zone_entry *zt = m_entry->zt;
+	struct nfp_fl_key_ls key_layer, tmp_layer;
+	struct nfp_flower_priv *priv = zt->priv;
+	u16 key_map[_FLOW_PAY_LAYERS_MAX];
+	struct nfp_fl_payload *flow_pay;
+
+	struct flow_rule *rules[_CT_TYPE_MAX];
+	u8 *key, *msk, *kdata, *mdata;
+	struct nfp_port *port = NULL;
+	struct net_device *netdev;
+	bool qinq_sup;
+	u32 port_id;
+	u16 offset;
+	int i, err;
+
+	netdev = m_entry->netdev;
+	qinq_sup = !!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_QINQ);
+
+	rules[CT_TYPE_PRE_CT] = m_entry->tc_m_parent->pre_ct_parent->rule;
+	rules[CT_TYPE_NFT] = m_entry->nft_parent->rule;
+	rules[CT_TYPE_POST_CT] = m_entry->tc_m_parent->post_ct_parent->rule;
+
+	memset(&key_layer, 0, sizeof(struct nfp_fl_key_ls));
+	memset(&key_map, 0, sizeof(key_map));
+
+	/* Calculate the resultant key layer and size for offload */
+	for (i = 0; i < _CT_TYPE_MAX; i++) {
+		err = nfp_flower_calculate_key_layers(priv->app,
+						      m_entry->netdev,
+						      &tmp_layer, rules[i],
+						      &tun_type, NULL);
+		if (err)
+			return err;
+
+		key_layer.key_layer |= tmp_layer.key_layer;
+		key_layer.key_layer_two |= tmp_layer.key_layer_two;
+	}
+	key_layer.key_size = nfp_fl_calc_key_layers_sz(key_layer, key_map);
+
+	flow_pay = nfp_flower_allocate_new(&key_layer);
+	if (!flow_pay)
+		return -ENOMEM;
+
+	memset(flow_pay->unmasked_data, 0, key_layer.key_size);
+	memset(flow_pay->mask_data, 0, key_layer.key_size);
+
+	kdata = flow_pay->unmasked_data;
+	mdata = flow_pay->mask_data;
+
+	offset = key_map[FLOW_PAY_META_TCI];
+	key = kdata + offset;
+	msk = mdata + offset;
+	nfp_flower_compile_meta((struct nfp_flower_meta_tci *)key,
+				(struct nfp_flower_meta_tci *)msk,
+				key_layer.key_layer);
+
+	if (NFP_FLOWER_LAYER_EXT_META & key_layer.key_layer) {
+		offset =  key_map[FLOW_PAY_EXT_META];
+		key = kdata + offset;
+		msk = mdata + offset;
+		nfp_flower_compile_ext_meta((struct nfp_flower_ext_meta *)key,
+					    key_layer.key_layer_two);
+		nfp_flower_compile_ext_meta((struct nfp_flower_ext_meta *)msk,
+					    key_layer.key_layer_two);
+	}
+
+	/* Using in_port from the -trk rule. The tc merge checks should already
+	 * be checking that the ingress netdevs are the same
+	 */
+	port_id = nfp_flower_get_port_id_from_netdev(priv->app, netdev);
+	offset = key_map[FLOW_PAY_INPORT];
+	key = kdata + offset;
+	msk = mdata + offset;
+	err = nfp_flower_compile_port((struct nfp_flower_in_port *)key,
+				      port_id, false, tun_type, NULL);
+	if (err)
+		goto ct_offload_err;
+	err = nfp_flower_compile_port((struct nfp_flower_in_port *)msk,
+				      port_id, true, tun_type, NULL);
+	if (err)
+		goto ct_offload_err;
+
+	/* This following part works on the assumption that previous checks has
+	 * already filtered out flows that has different values for the different
+	 * layers. Here we iterate through all three rules and merge their respective
+	 * masked value(cared bits), basic method is:
+	 * final_key = (r1_key & r1_mask) | (r2_key & r2_mask) | (r3_key & r3_mask)
+	 * final_mask = r1_mask | r2_mask | r3_mask
+	 * If none of the rules contains a match that is also fine, that simply means
+	 * that the layer is not present.
+	 */
+	if (!qinq_sup) {
+		for (i = 0; i < _CT_TYPE_MAX; i++) {
+			offset = key_map[FLOW_PAY_META_TCI];
+			key = kdata + offset;
+			msk = mdata + offset;
+			nfp_flower_compile_tci((struct nfp_flower_meta_tci *)key,
+					       (struct nfp_flower_meta_tci *)msk,
+					       rules[i]);
+		}
+	}
+
+	if (NFP_FLOWER_LAYER_MAC & key_layer.key_layer) {
+		offset = key_map[FLOW_PAY_MAC_MPLS];
+		key = kdata + offset;
+		msk = mdata + offset;
+		for (i = 0; i < _CT_TYPE_MAX; i++) {
+			nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)key,
+					       (struct nfp_flower_mac_mpls *)msk,
+					       rules[i]);
+			err = nfp_flower_compile_mpls((struct nfp_flower_mac_mpls *)key,
+						      (struct nfp_flower_mac_mpls *)msk,
+						      rules[i], NULL);
+			if (err)
+				goto ct_offload_err;
+		}
+	}
+
+	if (NFP_FLOWER_LAYER_IPV4 & key_layer.key_layer) {
+		offset = key_map[FLOW_PAY_IPV4];
+		key = kdata + offset;
+		msk = mdata + offset;
+		for (i = 0; i < _CT_TYPE_MAX; i++) {
+			nfp_flower_compile_ipv4((struct nfp_flower_ipv4 *)key,
+						(struct nfp_flower_ipv4 *)msk,
+						rules[i]);
+		}
+	}
+
+	if (NFP_FLOWER_LAYER_IPV6 & key_layer.key_layer) {
+		offset = key_map[FLOW_PAY_IPV6];
+		key = kdata + offset;
+		msk = mdata + offset;
+		for (i = 0; i < _CT_TYPE_MAX; i++) {
+			nfp_flower_compile_ipv6((struct nfp_flower_ipv6 *)key,
+						(struct nfp_flower_ipv6 *)msk,
+						rules[i]);
+		}
+	}
+
+	if (NFP_FLOWER_LAYER_TP & key_layer.key_layer) {
+		offset = key_map[FLOW_PAY_L4];
+		key = kdata + offset;
+		msk = mdata + offset;
+		for (i = 0; i < _CT_TYPE_MAX; i++) {
+			nfp_flower_compile_tport((struct nfp_flower_tp_ports *)key,
+						 (struct nfp_flower_tp_ports *)msk,
+						 rules[i]);
+		}
+	}
+
+	if (key_layer.key_layer_two & NFP_FLOWER_LAYER2_GRE) {
+		offset = key_map[FLOW_PAY_GRE];
+		key = kdata + offset;
+		msk = mdata + offset;
+		if (key_layer.key_layer_two & NFP_FLOWER_LAYER2_TUN_IPV6) {
+			struct nfp_flower_ipv6_gre_tun *gre_match;
+			struct nfp_ipv6_addr_entry *entry;
+			struct in6_addr *dst;
+
+			for (i = 0; i < _CT_TYPE_MAX; i++) {
+				nfp_flower_compile_ipv6_gre_tun((void *)key,
+								(void *)msk, rules[i]);
+			}
+			gre_match = (struct nfp_flower_ipv6_gre_tun *)key;
+			dst = &gre_match->ipv6.dst;
+
+			entry = nfp_tunnel_add_ipv6_off(priv->app, dst);
+			if (!entry) {
+				err = -ENOMEM;
+				goto ct_offload_err;
+			}
+
+			flow_pay->nfp_tun_ipv6 = entry;
+		} else {
+			__be32 dst;
+
+			for (i = 0; i < _CT_TYPE_MAX; i++) {
+				nfp_flower_compile_ipv4_gre_tun((void *)key,
+								(void *)msk, rules[i]);
+			}
+			dst = ((struct nfp_flower_ipv4_gre_tun *)key)->ipv4.dst;
+
+			/* Store the tunnel destination in the rule data.
+			 * This must be present and be an exact match.
+			 */
+			flow_pay->nfp_tun_ipv4_addr = dst;
+			nfp_tunnel_add_ipv4_off(priv->app, dst);
+		}
+	}
+
+	if (NFP_FLOWER_LAYER2_QINQ & key_layer.key_layer_two) {
+		offset = key_map[FLOW_PAY_QINQ];
+		key = kdata + offset;
+		msk = mdata + offset;
+		for (i = 0; i < _CT_TYPE_MAX; i++) {
+			nfp_flower_compile_vlan((struct nfp_flower_vlan *)key,
+						(struct nfp_flower_vlan *)msk,
+						rules[i]);
+		}
+	}
+
+	if (key_layer.key_layer & NFP_FLOWER_LAYER_VXLAN ||
+	    key_layer.key_layer_two & NFP_FLOWER_LAYER2_GENEVE) {
+		offset = key_map[FLOW_PAY_UDP_TUN];
+		key = kdata + offset;
+		msk = mdata + offset;
+		if (key_layer.key_layer_two & NFP_FLOWER_LAYER2_TUN_IPV6) {
+			struct nfp_flower_ipv6_udp_tun *udp_match;
+			struct nfp_ipv6_addr_entry *entry;
+			struct in6_addr *dst;
+
+			for (i = 0; i < _CT_TYPE_MAX; i++) {
+				nfp_flower_compile_ipv6_udp_tun((void *)key,
+								(void *)msk, rules[i]);
+			}
+			udp_match = (struct nfp_flower_ipv6_udp_tun *)key;
+			dst = &udp_match->ipv6.dst;
+
+			entry = nfp_tunnel_add_ipv6_off(priv->app, dst);
+			if (!entry) {
+				err = -ENOMEM;
+				goto ct_offload_err;
+			}
+
+			flow_pay->nfp_tun_ipv6 = entry;
+		} else {
+			__be32 dst;
+
+			for (i = 0; i < _CT_TYPE_MAX; i++) {
+				nfp_flower_compile_ipv4_udp_tun((void *)key,
+								(void *)msk, rules[i]);
+			}
+			dst = ((struct nfp_flower_ipv4_udp_tun *)key)->ipv4.dst;
+
+			/* Store the tunnel destination in the rule data.
+			 * This must be present and be an exact match.
+			 */
+			flow_pay->nfp_tun_ipv4_addr = dst;
+			nfp_tunnel_add_ipv4_off(priv->app, dst);
+		}
+
+		if (key_layer.key_layer_two & NFP_FLOWER_LAYER2_GENEVE_OP) {
+			offset = key_map[FLOW_PAY_GENEVE_OPT];
+			key = kdata + offset;
+			msk = mdata + offset;
+			for (i = 0; i < _CT_TYPE_MAX; i++)
+				nfp_flower_compile_geneve_opt(key, msk, rules[i]);
+		}
+	}
+
+	/* Merge actions into flow_pay */
+	err = nfp_fl_merge_actions_offload(rules, priv, netdev, flow_pay);
+	if (err)
+		goto ct_offload_err;
+
+	/* Use the pointer address as the cookie, but set the last bit to 1.
+	 * This is to avoid the 'is_merge_flow' check from detecting this as
+	 * an already merged flow. This works since address alignment means
+	 * that the last bit for pointer addresses will be 0.
+	 */
+	flow_pay->tc_flower_cookie = ((unsigned long)flow_pay) | 0x1;
+	err = nfp_compile_flow_metadata(priv->app, flow_pay->tc_flower_cookie,
+					flow_pay, netdev, NULL);
+	if (err)
+		goto ct_offload_err;
+
+	if (nfp_netdev_is_nfp_repr(netdev))
+		port = nfp_port_from_netdev(netdev);
+
+	err = rhashtable_insert_fast(&priv->flow_table, &flow_pay->fl_node,
+				     nfp_flower_table_params);
+	if (err)
+		goto ct_release_offload_meta_err;
+
+	err = nfp_flower_xmit_flow(priv->app, flow_pay,
+				   NFP_FLOWER_CMSG_TYPE_FLOW_ADD);
+	if (err)
+		goto ct_remove_rhash_err;
+
+	m_entry->tc_flower_cookie = flow_pay->tc_flower_cookie;
+	m_entry->flow_pay = flow_pay;
+
+	if (port)
+		port->tc_offload_cnt++;
+
+	return err;
+
+ct_remove_rhash_err:
+	WARN_ON_ONCE(rhashtable_remove_fast(&priv->flow_table,
+					    &flow_pay->fl_node,
+					    nfp_flower_table_params));
+ct_release_offload_meta_err:
+	nfp_modify_flow_metadata(priv->app, flow_pay);
+ct_offload_err:
+	if (flow_pay->nfp_tun_ipv4_addr)
+		nfp_tunnel_del_ipv4_off(priv->app, flow_pay->nfp_tun_ipv4_addr);
+	if (flow_pay->nfp_tun_ipv6)
+		nfp_tunnel_put_ipv6_off(priv->app, flow_pay->nfp_tun_ipv6);
+	kfree(flow_pay->action_data);
+	kfree(flow_pay->mask_data);
+	kfree(flow_pay->unmasked_data);
+	kfree(flow_pay);
+	return err;
 }
 
 static int nfp_fl_ct_del_offload(struct nfp_app *app, unsigned long cookie,
 				 struct net_device *netdev)
 {
-	return 0;
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_fl_payload *flow_pay;
+	struct nfp_port *port = NULL;
+	int err = 0;
+
+	if (nfp_netdev_is_nfp_repr(netdev))
+		port = nfp_port_from_netdev(netdev);
+
+	flow_pay = nfp_flower_search_fl_table(app, cookie, netdev);
+	if (!flow_pay)
+		return -ENOENT;
+
+	err = nfp_modify_flow_metadata(app, flow_pay);
+	if (err)
+		goto err_free_merge_flow;
+
+	if (flow_pay->nfp_tun_ipv4_addr)
+		nfp_tunnel_del_ipv4_off(app, flow_pay->nfp_tun_ipv4_addr);
+
+	if (flow_pay->nfp_tun_ipv6)
+		nfp_tunnel_put_ipv6_off(app, flow_pay->nfp_tun_ipv6);
+
+	if (!flow_pay->in_hw) {
+		err = 0;
+		goto err_free_merge_flow;
+	}
+
+	err = nfp_flower_xmit_flow(app, flow_pay,
+				   NFP_FLOWER_CMSG_TYPE_FLOW_DEL);
+
+err_free_merge_flow:
+	nfp_flower_del_linked_merge_flows(app, flow_pay);
+	if (port)
+		port->tc_offload_cnt--;
+	kfree(flow_pay->action_data);
+	kfree(flow_pay->mask_data);
+	kfree(flow_pay->unmasked_data);
+	WARN_ON_ONCE(rhashtable_remove_fast(&priv->flow_table,
+					    &flow_pay->fl_node,
+					    nfp_flower_table_params));
+	kfree_rcu(flow_pay, rcu);
+	return err;
 }
 
 static int nfp_ct_do_nft_merge(struct nfp_fl_ct_zone_entry *zt,
@@ -1048,6 +1525,139 @@ int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv,
 	return 0;
 }
 
+static void
+nfp_fl_ct_sub_stats(struct nfp_fl_nft_tc_merge *nft_merge,
+		    enum ct_entry_type type, u64 *m_pkts,
+		    u64 *m_bytes, u64 *m_used)
+{
+	struct nfp_flower_priv *priv = nft_merge->zt->priv;
+	struct nfp_fl_payload *nfp_flow;
+	u32 ctx_id;
+
+	nfp_flow = nft_merge->flow_pay;
+	if (!nfp_flow)
+		return;
+
+	ctx_id = be32_to_cpu(nfp_flow->meta.host_ctx_id);
+	*m_pkts += priv->stats[ctx_id].pkts;
+	*m_bytes += priv->stats[ctx_id].bytes;
+	*m_used = max_t(u64, *m_used, priv->stats[ctx_id].used);
+
+	/* If request is for a sub_flow which is part of a tunnel merged
+	 * flow then update stats from tunnel merged flows first.
+	 */
+	if (!list_empty(&nfp_flow->linked_flows))
+		nfp_flower_update_merge_stats(priv->app, nfp_flow);
+
+	if (type != CT_TYPE_NFT) {
+		/* Update nft cached stats */
+		flow_stats_update(&nft_merge->nft_parent->stats,
+				  priv->stats[ctx_id].bytes,
+				  priv->stats[ctx_id].pkts,
+				  0, priv->stats[ctx_id].used,
+				  FLOW_ACTION_HW_STATS_DELAYED);
+	} else {
+		/* Update pre_ct cached stats */
+		flow_stats_update(&nft_merge->tc_m_parent->pre_ct_parent->stats,
+				  priv->stats[ctx_id].bytes,
+				  priv->stats[ctx_id].pkts,
+				  0, priv->stats[ctx_id].used,
+				  FLOW_ACTION_HW_STATS_DELAYED);
+		/* Update post_ct cached stats */
+		flow_stats_update(&nft_merge->tc_m_parent->post_ct_parent->stats,
+				  priv->stats[ctx_id].bytes,
+				  priv->stats[ctx_id].pkts,
+				  0, priv->stats[ctx_id].used,
+				  FLOW_ACTION_HW_STATS_DELAYED);
+	}
+	/* Reset stats from the nfp */
+	priv->stats[ctx_id].pkts = 0;
+	priv->stats[ctx_id].bytes = 0;
+}
+
+int nfp_fl_ct_stats(struct flow_cls_offload *flow,
+		    struct nfp_fl_ct_map_entry *ct_map_ent)
+{
+	struct nfp_fl_ct_flow_entry *ct_entry = ct_map_ent->ct_entry;
+	struct nfp_fl_nft_tc_merge *nft_merge, *nft_m_tmp;
+	struct nfp_fl_ct_tc_merge *tc_merge, *tc_m_tmp;
+
+	u64 pkts = 0, bytes = 0, used = 0;
+	u64 m_pkts, m_bytes, m_used;
+
+	spin_lock_bh(&ct_entry->zt->priv->stats_lock);
+
+	if (ct_entry->type == CT_TYPE_PRE_CT) {
+		/* Iterate tc_merge entries associated with this flow */
+		list_for_each_entry_safe(tc_merge, tc_m_tmp, &ct_entry->children,
+					 pre_ct_list) {
+			m_pkts = 0;
+			m_bytes = 0;
+			m_used = 0;
+			/* Iterate nft_merge entries associated with this tc_merge flow */
+			list_for_each_entry_safe(nft_merge, nft_m_tmp, &tc_merge->children,
+						 tc_merge_list) {
+				nfp_fl_ct_sub_stats(nft_merge, CT_TYPE_PRE_CT,
+						    &m_pkts, &m_bytes, &m_used);
+			}
+			pkts += m_pkts;
+			bytes += m_bytes;
+			used = max_t(u64, used, m_used);
+			/* Update post_ct partner */
+			flow_stats_update(&tc_merge->post_ct_parent->stats,
+					  m_bytes, m_pkts, 0, m_used,
+					  FLOW_ACTION_HW_STATS_DELAYED);
+		}
+	} else if (ct_entry->type == CT_TYPE_POST_CT) {
+		/* Iterate tc_merge entries associated with this flow */
+		list_for_each_entry_safe(tc_merge, tc_m_tmp, &ct_entry->children,
+					 post_ct_list) {
+			m_pkts = 0;
+			m_bytes = 0;
+			m_used = 0;
+			/* Iterate nft_merge entries associated with this tc_merge flow */
+			list_for_each_entry_safe(nft_merge, nft_m_tmp, &tc_merge->children,
+						 tc_merge_list) {
+				nfp_fl_ct_sub_stats(nft_merge, CT_TYPE_POST_CT,
+						    &m_pkts, &m_bytes, &m_used);
+			}
+			pkts += m_pkts;
+			bytes += m_bytes;
+			used = max_t(u64, used, m_used);
+			/* Update pre_ct partner */
+			flow_stats_update(&tc_merge->pre_ct_parent->stats,
+					  m_bytes, m_pkts, 0, m_used,
+					  FLOW_ACTION_HW_STATS_DELAYED);
+		}
+	} else  {
+		/* Iterate nft_merge entries associated with this nft flow */
+		list_for_each_entry_safe(nft_merge, nft_m_tmp, &ct_entry->children,
+					 nft_flow_list) {
+			nfp_fl_ct_sub_stats(nft_merge, CT_TYPE_NFT,
+					    &pkts, &bytes, &used);
+		}
+	}
+
+	/* Add stats from this request to stats potentially cached by
+	 * previous requests.
+	 */
+	flow_stats_update(&ct_entry->stats, bytes, pkts, 0, used,
+			  FLOW_ACTION_HW_STATS_DELAYED);
+	/* Finally update the flow stats from the original stats request */
+	flow_stats_update(&flow->stats, ct_entry->stats.bytes,
+			  ct_entry->stats.pkts, 0,
+			  ct_entry->stats.lastused,
+			  FLOW_ACTION_HW_STATS_DELAYED);
+	/* Stats has been synced to original flow, can now clear
+	 * the cache.
+	 */
+	ct_entry->stats.pkts = 0;
+	ct_entry->stats.bytes = 0;
+	spin_unlock_bh(&ct_entry->zt->priv->stats_lock);
+
+	return 0;
+}
+
 static int
 nfp_fl_ct_offload_nft_flow(struct nfp_fl_ct_zone_entry *zt, struct flow_cls_offload *flow)
 {
@@ -1080,7 +1690,11 @@ nfp_fl_ct_offload_nft_flow(struct nfp_fl_ct_zone_entry *zt, struct flow_cls_offl
 						    nfp_ct_map_params);
 		return nfp_fl_ct_del_flow(ct_map_ent);
 	case FLOW_CLS_STATS:
-		return 0;
+		ct_map_ent = rhashtable_lookup_fast(&zt->priv->ct_map_table, &flow->cookie,
+						    nfp_ct_map_params);
+		if (ct_map_ent)
+			return nfp_fl_ct_stats(flow, ct_map_ent);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.h b/drivers/net/ethernet/netronome/nfp/flower/conntrack.h
index 170b6cdb8cd0..beb6cceff9d8 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.h
@@ -83,6 +83,24 @@ enum ct_entry_type {
 	CT_TYPE_PRE_CT,
 	CT_TYPE_NFT,
 	CT_TYPE_POST_CT,
+	_CT_TYPE_MAX,
+};
+
+enum nfp_nfp_layer_name {
+	FLOW_PAY_META_TCI =    0,
+	FLOW_PAY_INPORT,
+	FLOW_PAY_EXT_META,
+	FLOW_PAY_MAC_MPLS,
+	FLOW_PAY_L4,
+	FLOW_PAY_IPV4,
+	FLOW_PAY_IPV6,
+	FLOW_PAY_CT,
+	FLOW_PAY_GRE,
+	FLOW_PAY_QINQ,
+	FLOW_PAY_UDP_TUN,
+	FLOW_PAY_GENEVE_OPT,
+
+	_FLOW_PAY_LAYERS_MAX
 };
 
 /**
@@ -228,4 +246,12 @@ int nfp_fl_ct_del_flow(struct nfp_fl_ct_map_entry *ct_map_ent);
  */
 int nfp_fl_ct_handle_nft_flow(enum tc_setup_type type, void *type_data,
 			      void *cb_priv);
+
+/**
+ * nfp_fl_ct_stats() - Handle flower stats callbacks for ct flows
+ * @flow:	TC flower classifier offload structure.
+ * @ct_map_ent:	ct map entry for the flow that needs deleting
+ */
+int nfp_fl_ct_stats(struct flow_cls_offload *flow,
+		    struct nfp_fl_ct_map_entry *ct_map_ent);
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 0fbd682ccf72..917c450a7aad 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -413,20 +413,73 @@ int nfp_flower_setup_tc(struct nfp_app *app, struct net_device *netdev,
 int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
 				     struct nfp_fl_payload *sub_flow1,
 				     struct nfp_fl_payload *sub_flow2);
+void
+nfp_flower_compile_meta(struct nfp_flower_meta_tci *ext,
+			struct nfp_flower_meta_tci *msk, u8 key_type);
+void
+nfp_flower_compile_tci(struct nfp_flower_meta_tci *ext,
+		       struct nfp_flower_meta_tci *msk,
+		       struct flow_rule *rule);
+void
+nfp_flower_compile_ext_meta(struct nfp_flower_ext_meta *frame, u32 key_ext);
+int
+nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port,
+			bool mask_version, enum nfp_flower_tun_type tun_type,
+			struct netlink_ext_ack *extack);
+void
+nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext,
+		       struct nfp_flower_mac_mpls *msk,
+		       struct flow_rule *rule);
+int
+nfp_flower_compile_mpls(struct nfp_flower_mac_mpls *ext,
+			struct nfp_flower_mac_mpls *msk,
+			struct flow_rule *rule,
+			struct netlink_ext_ack *extack);
+void
+nfp_flower_compile_tport(struct nfp_flower_tp_ports *ext,
+			 struct nfp_flower_tp_ports *msk,
+			 struct flow_rule *rule);
+void
+nfp_flower_compile_vlan(struct nfp_flower_vlan *ext,
+			struct nfp_flower_vlan *msk,
+			struct flow_rule *rule);
+void
+nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *ext,
+			struct nfp_flower_ipv4 *msk, struct flow_rule *rule);
+void
+nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *ext,
+			struct nfp_flower_ipv6 *msk, struct flow_rule *rule);
+void
+nfp_flower_compile_geneve_opt(u8 *ext, u8 *msk, struct flow_rule *rule);
+void
+nfp_flower_compile_ipv4_gre_tun(struct nfp_flower_ipv4_gre_tun *ext,
+				struct nfp_flower_ipv4_gre_tun *msk,
+				struct flow_rule *rule);
+void
+nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *ext,
+				struct nfp_flower_ipv4_udp_tun *msk,
+				struct flow_rule *rule);
+void
+nfp_flower_compile_ipv6_udp_tun(struct nfp_flower_ipv6_udp_tun *ext,
+				struct nfp_flower_ipv6_udp_tun *msk,
+				struct flow_rule *rule);
+void
+nfp_flower_compile_ipv6_gre_tun(struct nfp_flower_ipv6_gre_tun *ext,
+				struct nfp_flower_ipv6_gre_tun *msk,
+				struct flow_rule *rule);
 int nfp_flower_compile_flow_match(struct nfp_app *app,
-				  struct flow_cls_offload *flow,
+				  struct flow_rule *rule,
 				  struct nfp_fl_key_ls *key_ls,
 				  struct net_device *netdev,
 				  struct nfp_fl_payload *nfp_flow,
 				  enum nfp_flower_tun_type tun_type,
 				  struct netlink_ext_ack *extack);
 int nfp_flower_compile_action(struct nfp_app *app,
-			      struct flow_cls_offload *flow,
+			      struct flow_rule *rule,
 			      struct net_device *netdev,
 			      struct nfp_fl_payload *nfp_flow,
 			      struct netlink_ext_ack *extack);
-int nfp_compile_flow_metadata(struct nfp_app *app,
-			      struct flow_cls_offload *flow,
+int nfp_compile_flow_metadata(struct nfp_app *app, u32 cookie,
 			      struct nfp_fl_payload *nfp_flow,
 			      struct net_device *netdev,
 			      struct netlink_ext_ack *extack);
@@ -498,4 +551,22 @@ int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app,
 				 struct nfp_fl_payload *flow);
 int nfp_flower_xmit_pre_tun_del_flow(struct nfp_app *app,
 				     struct nfp_fl_payload *flow);
+
+struct nfp_fl_payload *
+nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer);
+int nfp_flower_calculate_key_layers(struct nfp_app *app,
+				    struct net_device *netdev,
+				    struct nfp_fl_key_ls *ret_key_ls,
+				    struct flow_rule *flow,
+				    enum nfp_flower_tun_type *tun_type,
+				    struct netlink_ext_ack *extack);
+void
+nfp_flower_del_linked_merge_flows(struct nfp_app *app,
+				  struct nfp_fl_payload *sub_flow);
+int
+nfp_flower_xmit_flow(struct nfp_app *app, struct nfp_fl_payload *nfp_flow,
+		     u8 mtype);
+void
+nfp_flower_update_merge_stats(struct nfp_app *app,
+			      struct nfp_fl_payload *sub_flow);
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index 255a4dff6288..9d86eea4dc16 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -7,51 +7,68 @@
 #include "cmsg.h"
 #include "main.h"
 
-static void
-nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext,
-			    struct nfp_flower_meta_tci *msk,
-			    struct flow_rule *rule, u8 key_type, bool qinq_sup)
+void
+nfp_flower_compile_meta(struct nfp_flower_meta_tci *ext,
+			struct nfp_flower_meta_tci *msk, u8 key_type)
 {
-	u16 tmp_tci;
-
-	memset(ext, 0, sizeof(struct nfp_flower_meta_tci));
-	memset(msk, 0, sizeof(struct nfp_flower_meta_tci));
-
 	/* Populate the metadata frame. */
 	ext->nfp_flow_key_layer = key_type;
 	ext->mask_id = ~0;
 
 	msk->nfp_flow_key_layer = key_type;
 	msk->mask_id = ~0;
+}
 
-	if (!qinq_sup && flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+void
+nfp_flower_compile_tci(struct nfp_flower_meta_tci *ext,
+		       struct nfp_flower_meta_tci *msk,
+		       struct flow_rule *rule)
+{
+	u16 msk_tci, key_tci;
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
 		struct flow_match_vlan match;
 
 		flow_rule_match_vlan(rule, &match);
 		/* Populate the tci field. */
-		tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
-		tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+		key_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+		key_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
 				      match.key->vlan_priority) |
 			   FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
 				      match.key->vlan_id);
-		ext->tci = cpu_to_be16(tmp_tci);
 
-		tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
-		tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+		msk_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+		msk_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
 				      match.mask->vlan_priority) |
 			   FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
 				      match.mask->vlan_id);
-		msk->tci = cpu_to_be16(tmp_tci);
+
+		ext->tci |= cpu_to_be16((key_tci & msk_tci));
+		msk->tci |= cpu_to_be16(msk_tci);
 	}
 }
 
 static void
+nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext,
+			    struct nfp_flower_meta_tci *msk,
+			    struct flow_rule *rule, u8 key_type, bool qinq_sup)
+{
+	memset(ext, 0, sizeof(struct nfp_flower_meta_tci));
+	memset(msk, 0, sizeof(struct nfp_flower_meta_tci));
+
+	nfp_flower_compile_meta(ext, msk, key_type);
+
+	if (!qinq_sup)
+		nfp_flower_compile_tci(ext, msk, rule);
+}
+
+void
 nfp_flower_compile_ext_meta(struct nfp_flower_ext_meta *frame, u32 key_ext)
 {
 	frame->nfp_flow_key_layer2 = cpu_to_be32(key_ext);
 }
 
-static int
+int
 nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port,
 			bool mask_version, enum nfp_flower_tun_type tun_type,
 			struct netlink_ext_ack *extack)
@@ -74,28 +91,37 @@ nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port,
 	return 0;
 }
 
-static int
+void
 nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext,
-		       struct nfp_flower_mac_mpls *msk, struct flow_rule *rule,
-		       struct netlink_ext_ack *extack)
+		       struct nfp_flower_mac_mpls *msk,
+		       struct flow_rule *rule)
 {
-	memset(ext, 0, sizeof(struct nfp_flower_mac_mpls));
-	memset(msk, 0, sizeof(struct nfp_flower_mac_mpls));
-
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
 		struct flow_match_eth_addrs match;
+		int i;
 
 		flow_rule_match_eth_addrs(rule, &match);
 		/* Populate mac frame. */
-		ether_addr_copy(ext->mac_dst, &match.key->dst[0]);
-		ether_addr_copy(ext->mac_src, &match.key->src[0]);
-		ether_addr_copy(msk->mac_dst, &match.mask->dst[0]);
-		ether_addr_copy(msk->mac_src, &match.mask->src[0]);
+		for (i = 0; i < ETH_ALEN; i++) {
+			ext->mac_dst[i] |= match.key->dst[i] &
+					   match.mask->dst[i];
+			msk->mac_dst[i] |= match.mask->dst[i];
+			ext->mac_src[i] |= match.key->src[i] &
+					   match.mask->src[i];
+			msk->mac_src[i] |= match.mask->src[i];
+		}
 	}
+}
 
+int
+nfp_flower_compile_mpls(struct nfp_flower_mac_mpls *ext,
+			struct nfp_flower_mac_mpls *msk,
+			struct flow_rule *rule,
+			struct netlink_ext_ack *extack)
+{
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) {
 		struct flow_match_mpls match;
-		u32 t_mpls;
+		u32 key_mpls, msk_mpls;
 
 		flow_rule_match_mpls(rule, &match);
 
@@ -106,22 +132,24 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext,
 			return -EOPNOTSUPP;
 		}
 
-		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB,
-				    match.key->ls[0].mpls_label) |
-			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC,
-				    match.key->ls[0].mpls_tc) |
-			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS,
-				    match.key->ls[0].mpls_bos) |
-			 NFP_FLOWER_MASK_MPLS_Q;
-		ext->mpls_lse = cpu_to_be32(t_mpls);
-		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB,
-				    match.mask->ls[0].mpls_label) |
-			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC,
-				    match.mask->ls[0].mpls_tc) |
-			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS,
-				    match.mask->ls[0].mpls_bos) |
-			 NFP_FLOWER_MASK_MPLS_Q;
-		msk->mpls_lse = cpu_to_be32(t_mpls);
+		key_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB,
+				      match.key->ls[0].mpls_label) |
+			   FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC,
+				      match.key->ls[0].mpls_tc) |
+			   FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS,
+				      match.key->ls[0].mpls_bos) |
+			   NFP_FLOWER_MASK_MPLS_Q;
+
+		msk_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB,
+				      match.mask->ls[0].mpls_label) |
+			   FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC,
+				      match.mask->ls[0].mpls_tc) |
+			   FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS,
+				      match.mask->ls[0].mpls_bos) |
+			   NFP_FLOWER_MASK_MPLS_Q;
+
+		ext->mpls_lse |= cpu_to_be32((key_mpls & msk_mpls));
+		msk->mpls_lse |= cpu_to_be32(msk_mpls);
 	} else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
 		/* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q
 		 * bit, which indicates an mpls ether type but without any
@@ -132,30 +160,41 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext,
 		flow_rule_match_basic(rule, &match);
 		if (match.key->n_proto == cpu_to_be16(ETH_P_MPLS_UC) ||
 		    match.key->n_proto == cpu_to_be16(ETH_P_MPLS_MC)) {
-			ext->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
-			msk->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
+			ext->mpls_lse |= cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
+			msk->mpls_lse |= cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
 		}
 	}
 
 	return 0;
 }
 
-static void
+static int
+nfp_flower_compile_mac_mpls(struct nfp_flower_mac_mpls *ext,
+			    struct nfp_flower_mac_mpls *msk,
+			    struct flow_rule *rule,
+			    struct netlink_ext_ack *extack)
+{
+	memset(ext, 0, sizeof(struct nfp_flower_mac_mpls));
+	memset(msk, 0, sizeof(struct nfp_flower_mac_mpls));
+
+	nfp_flower_compile_mac(ext, msk, rule);
+
+	return nfp_flower_compile_mpls(ext, msk, rule, extack);
+}
+
+void
 nfp_flower_compile_tport(struct nfp_flower_tp_ports *ext,
 			 struct nfp_flower_tp_ports *msk,
 			 struct flow_rule *rule)
 {
-	memset(ext, 0, sizeof(struct nfp_flower_tp_ports));
-	memset(msk, 0, sizeof(struct nfp_flower_tp_ports));
-
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
 		struct flow_match_ports match;
 
 		flow_rule_match_ports(rule, &match);
-		ext->port_src = match.key->src;
-		ext->port_dst = match.key->dst;
-		msk->port_src = match.mask->src;
-		msk->port_dst = match.mask->dst;
+		ext->port_src |= match.key->src & match.mask->src;
+		ext->port_dst |= match.key->dst & match.mask->dst;
+		msk->port_src |= match.mask->src;
+		msk->port_dst |= match.mask->dst;
 	}
 }
 
@@ -167,18 +206,18 @@ nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *ext,
 		struct flow_match_basic match;
 
 		flow_rule_match_basic(rule, &match);
-		ext->proto = match.key->ip_proto;
-		msk->proto = match.mask->ip_proto;
+		ext->proto |= match.key->ip_proto & match.mask->ip_proto;
+		msk->proto |= match.mask->ip_proto;
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
 		struct flow_match_ip match;
 
 		flow_rule_match_ip(rule, &match);
-		ext->tos = match.key->tos;
-		ext->ttl = match.key->ttl;
-		msk->tos = match.mask->tos;
-		msk->ttl = match.mask->ttl;
+		ext->tos |= match.key->tos & match.mask->tos;
+		ext->ttl |= match.key->ttl & match.mask->ttl;
+		msk->tos |= match.mask->tos;
+		msk->ttl |= match.mask->ttl;
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) {
@@ -231,99 +270,108 @@ nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *ext,
 }
 
 static void
-nfp_flower_fill_vlan(struct flow_dissector_key_vlan *key,
-		     struct nfp_flower_vlan *frame,
-		     bool outer_vlan)
+nfp_flower_fill_vlan(struct flow_match_vlan *match,
+		     struct nfp_flower_vlan *ext,
+		     struct nfp_flower_vlan *msk, bool outer_vlan)
 {
-	u16 tci;
-
-	tci = NFP_FLOWER_MASK_VLAN_PRESENT;
-	tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
-			  key->vlan_priority) |
-	       FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
-			  key->vlan_id);
+	struct flow_dissector_key_vlan *mask = match->mask;
+	struct flow_dissector_key_vlan *key = match->key;
+	u16 msk_tci, key_tci;
+
+	key_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+	key_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+			      key->vlan_priority) |
+		   FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
+			      key->vlan_id);
+	msk_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+	msk_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+			      mask->vlan_priority) |
+		   FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
+			      mask->vlan_id);
 
 	if (outer_vlan) {
-		frame->outer_tci = cpu_to_be16(tci);
-		frame->outer_tpid = key->vlan_tpid;
+		ext->outer_tci |= cpu_to_be16((key_tci & msk_tci));
+		ext->outer_tpid |= key->vlan_tpid & mask->vlan_tpid;
+		msk->outer_tci |= cpu_to_be16(msk_tci);
+		msk->outer_tpid |= mask->vlan_tpid;
 	} else {
-		frame->inner_tci = cpu_to_be16(tci);
-		frame->inner_tpid = key->vlan_tpid;
+		ext->inner_tci |= cpu_to_be16((key_tci & msk_tci));
+		ext->inner_tpid |= key->vlan_tpid & mask->vlan_tpid;
+		msk->inner_tci |= cpu_to_be16(msk_tci);
+		msk->inner_tpid |= mask->vlan_tpid;
 	}
 }
 
-static void
+void
 nfp_flower_compile_vlan(struct nfp_flower_vlan *ext,
 			struct nfp_flower_vlan *msk,
 			struct flow_rule *rule)
 {
 	struct flow_match_vlan match;
 
-	memset(ext, 0, sizeof(struct nfp_flower_vlan));
-	memset(msk, 0, sizeof(struct nfp_flower_vlan));
-
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
 		flow_rule_match_vlan(rule, &match);
-		nfp_flower_fill_vlan(match.key, ext, true);
-		nfp_flower_fill_vlan(match.mask, msk, true);
+		nfp_flower_fill_vlan(&match, ext, msk, true);
 	}
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) {
 		flow_rule_match_cvlan(rule, &match);
-		nfp_flower_fill_vlan(match.key, ext, false);
-		nfp_flower_fill_vlan(match.mask, msk, false);
+		nfp_flower_fill_vlan(&match, ext, msk, false);
 	}
 }
 
-static void
+void
 nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *ext,
 			struct nfp_flower_ipv4 *msk, struct flow_rule *rule)
 {
-	struct flow_match_ipv4_addrs match;
-
-	memset(ext, 0, sizeof(struct nfp_flower_ipv4));
-	memset(msk, 0, sizeof(struct nfp_flower_ipv4));
-
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs match;
+
 		flow_rule_match_ipv4_addrs(rule, &match);
-		ext->ipv4_src = match.key->src;
-		ext->ipv4_dst = match.key->dst;
-		msk->ipv4_src = match.mask->src;
-		msk->ipv4_dst = match.mask->dst;
+		ext->ipv4_src |= match.key->src & match.mask->src;
+		ext->ipv4_dst |= match.key->dst & match.mask->dst;
+		msk->ipv4_src |= match.mask->src;
+		msk->ipv4_dst |= match.mask->dst;
 	}
 
 	nfp_flower_compile_ip_ext(&ext->ip_ext, &msk->ip_ext, rule);
 }
 
-static void
+void
 nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *ext,
 			struct nfp_flower_ipv6 *msk, struct flow_rule *rule)
 {
-	memset(ext, 0, sizeof(struct nfp_flower_ipv6));
-	memset(msk, 0, sizeof(struct nfp_flower_ipv6));
-
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
 		struct flow_match_ipv6_addrs match;
+		int i;
 
 		flow_rule_match_ipv6_addrs(rule, &match);
-		ext->ipv6_src = match.key->src;
-		ext->ipv6_dst = match.key->dst;
-		msk->ipv6_src = match.mask->src;
-		msk->ipv6_dst = match.mask->dst;
+		for (i = 0; i < sizeof(ext->ipv6_src); i++) {
+			ext->ipv6_src.s6_addr[i] |= match.key->src.s6_addr[i] &
+						    match.mask->src.s6_addr[i];
+			ext->ipv6_dst.s6_addr[i] |= match.key->dst.s6_addr[i] &
+						    match.mask->dst.s6_addr[i];
+			msk->ipv6_src.s6_addr[i] |= match.mask->src.s6_addr[i];
+			msk->ipv6_dst.s6_addr[i] |= match.mask->dst.s6_addr[i];
+		}
 	}
 
 	nfp_flower_compile_ip_ext(&ext->ip_ext, &msk->ip_ext, rule);
 }
 
-static int
-nfp_flower_compile_geneve_opt(void *ext, void *msk, struct flow_rule *rule)
+void
+nfp_flower_compile_geneve_opt(u8 *ext, u8 *msk, struct flow_rule *rule)
 {
 	struct flow_match_enc_opts match;
+	int i;
 
-	flow_rule_match_enc_opts(rule, &match);
-	memcpy(ext, match.key->data, match.key->len);
-	memcpy(msk, match.mask->data, match.mask->len);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS)) {
+		flow_rule_match_enc_opts(rule, &match);
 
-	return 0;
+		for (i = 0; i < match.mask->len; i++) {
+			ext[i] |= match.key->data[i] & match.mask->data[i];
+			msk[i] |= match.mask->data[i];
+		}
+	}
 }
 
 static void
@@ -335,10 +383,10 @@ nfp_flower_compile_tun_ipv4_addrs(struct nfp_flower_tun_ipv4 *ext,
 		struct flow_match_ipv4_addrs match;
 
 		flow_rule_match_enc_ipv4_addrs(rule, &match);
-		ext->src = match.key->src;
-		ext->dst = match.key->dst;
-		msk->src = match.mask->src;
-		msk->dst = match.mask->dst;
+		ext->src |= match.key->src & match.mask->src;
+		ext->dst |= match.key->dst & match.mask->dst;
+		msk->src |= match.mask->src;
+		msk->dst |= match.mask->dst;
 	}
 }
 
@@ -349,12 +397,17 @@ nfp_flower_compile_tun_ipv6_addrs(struct nfp_flower_tun_ipv6 *ext,
 {
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
 		struct flow_match_ipv6_addrs match;
+		int i;
 
 		flow_rule_match_enc_ipv6_addrs(rule, &match);
-		ext->src = match.key->src;
-		ext->dst = match.key->dst;
-		msk->src = match.mask->src;
-		msk->dst = match.mask->dst;
+		for (i = 0; i < sizeof(ext->src); i++) {
+			ext->src.s6_addr[i] |= match.key->src.s6_addr[i] &
+					       match.mask->src.s6_addr[i];
+			ext->dst.s6_addr[i] |= match.key->dst.s6_addr[i] &
+					       match.mask->dst.s6_addr[i];
+			msk->src.s6_addr[i] |= match.mask->src.s6_addr[i];
+			msk->dst.s6_addr[i] |= match.mask->dst.s6_addr[i];
+		}
 	}
 }
 
@@ -367,10 +420,10 @@ nfp_flower_compile_tun_ip_ext(struct nfp_flower_tun_ip_ext *ext,
 		struct flow_match_ip match;
 
 		flow_rule_match_enc_ip(rule, &match);
-		ext->tos = match.key->tos;
-		ext->ttl = match.key->ttl;
-		msk->tos = match.mask->tos;
-		msk->ttl = match.mask->ttl;
+		ext->tos |= match.key->tos & match.mask->tos;
+		ext->ttl |= match.key->ttl & match.mask->ttl;
+		msk->tos |= match.mask->tos;
+		msk->ttl |= match.mask->ttl;
 	}
 }
 
@@ -383,10 +436,11 @@ nfp_flower_compile_tun_udp_key(__be32 *key, __be32 *key_msk,
 		u32 vni;
 
 		flow_rule_match_enc_keyid(rule, &match);
-		vni = be32_to_cpu(match.key->keyid) << NFP_FL_TUN_VNI_OFFSET;
-		*key = cpu_to_be32(vni);
+		vni = be32_to_cpu((match.key->keyid & match.mask->keyid)) <<
+		      NFP_FL_TUN_VNI_OFFSET;
+		*key |= cpu_to_be32(vni);
 		vni = be32_to_cpu(match.mask->keyid) << NFP_FL_TUN_VNI_OFFSET;
-		*key_msk = cpu_to_be32(vni);
+		*key_msk |= cpu_to_be32(vni);
 	}
 }
 
@@ -398,22 +452,19 @@ nfp_flower_compile_tun_gre_key(__be32 *key, __be32 *key_msk, __be16 *flags,
 		struct flow_match_enc_keyid match;
 
 		flow_rule_match_enc_keyid(rule, &match);
-		*key = match.key->keyid;
-		*key_msk = match.mask->keyid;
+		*key |= match.key->keyid & match.mask->keyid;
+		*key_msk |= match.mask->keyid;
 
 		*flags = cpu_to_be16(NFP_FL_GRE_FLAG_KEY);
 		*flags_msk = cpu_to_be16(NFP_FL_GRE_FLAG_KEY);
 	}
 }
 
-static void
+void
 nfp_flower_compile_ipv4_gre_tun(struct nfp_flower_ipv4_gre_tun *ext,
 				struct nfp_flower_ipv4_gre_tun *msk,
 				struct flow_rule *rule)
 {
-	memset(ext, 0, sizeof(struct nfp_flower_ipv4_gre_tun));
-	memset(msk, 0, sizeof(struct nfp_flower_ipv4_gre_tun));
-
 	/* NVGRE is the only supported GRE tunnel type */
 	ext->ethertype = cpu_to_be16(ETH_P_TEB);
 	msk->ethertype = cpu_to_be16(~0);
@@ -424,40 +475,31 @@ nfp_flower_compile_ipv4_gre_tun(struct nfp_flower_ipv4_gre_tun *ext,
 				       &ext->tun_flags, &msk->tun_flags, rule);
 }
 
-static void
+void
 nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *ext,
 				struct nfp_flower_ipv4_udp_tun *msk,
 				struct flow_rule *rule)
 {
-	memset(ext, 0, sizeof(struct nfp_flower_ipv4_udp_tun));
-	memset(msk, 0, sizeof(struct nfp_flower_ipv4_udp_tun));
-
 	nfp_flower_compile_tun_ipv4_addrs(&ext->ipv4, &msk->ipv4, rule);
 	nfp_flower_compile_tun_ip_ext(&ext->ip_ext, &msk->ip_ext, rule);
 	nfp_flower_compile_tun_udp_key(&ext->tun_id, &msk->tun_id, rule);
 }
 
-static void
+void
 nfp_flower_compile_ipv6_udp_tun(struct nfp_flower_ipv6_udp_tun *ext,
 				struct nfp_flower_ipv6_udp_tun *msk,
 				struct flow_rule *rule)
 {
-	memset(ext, 0, sizeof(struct nfp_flower_ipv6_udp_tun));
-	memset(msk, 0, sizeof(struct nfp_flower_ipv6_udp_tun));
-
 	nfp_flower_compile_tun_ipv6_addrs(&ext->ipv6, &msk->ipv6, rule);
 	nfp_flower_compile_tun_ip_ext(&ext->ip_ext, &msk->ip_ext, rule);
 	nfp_flower_compile_tun_udp_key(&ext->tun_id, &msk->tun_id, rule);
 }
 
-static void
+void
 nfp_flower_compile_ipv6_gre_tun(struct nfp_flower_ipv6_gre_tun *ext,
 				struct nfp_flower_ipv6_gre_tun *msk,
 				struct flow_rule *rule)
 {
-	memset(ext, 0, sizeof(struct nfp_flower_ipv6_gre_tun));
-	memset(msk, 0, sizeof(struct nfp_flower_ipv6_gre_tun));
-
 	/* NVGRE is the only supported GRE tunnel type */
 	ext->ethertype = cpu_to_be16(ETH_P_TEB);
 	msk->ethertype = cpu_to_be16(~0);
@@ -469,14 +511,13 @@ nfp_flower_compile_ipv6_gre_tun(struct nfp_flower_ipv6_gre_tun *ext,
 }
 
 int nfp_flower_compile_flow_match(struct nfp_app *app,
-				  struct flow_cls_offload *flow,
+				  struct flow_rule *rule,
 				  struct nfp_fl_key_ls *key_ls,
 				  struct net_device *netdev,
 				  struct nfp_fl_payload *nfp_flow,
 				  enum nfp_flower_tun_type tun_type,
 				  struct netlink_ext_ack *extack)
 {
-	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	struct nfp_flower_priv *priv = app->priv;
 	bool qinq_sup;
 	u32 port_id;
@@ -527,9 +568,9 @@ int nfp_flower_compile_flow_match(struct nfp_app *app,
 	msk += sizeof(struct nfp_flower_in_port);
 
 	if (NFP_FLOWER_LAYER_MAC & key_ls->key_layer) {
-		err = nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)ext,
-					     (struct nfp_flower_mac_mpls *)msk,
-					     rule, extack);
+		err = nfp_flower_compile_mac_mpls((struct nfp_flower_mac_mpls *)ext,
+						  (struct nfp_flower_mac_mpls *)msk,
+						  rule, extack);
 		if (err)
 			return err;
 
@@ -640,9 +681,7 @@ int nfp_flower_compile_flow_match(struct nfp_app *app,
 		}
 
 		if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE_OP) {
-			err = nfp_flower_compile_geneve_opt(ext, msk, rule);
-			if (err)
-				return err;
+			nfp_flower_compile_geneve_opt(ext, msk, rule);
 		}
 	}
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index 621113650a9b..2af9faee96c5 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -290,8 +290,7 @@ nfp_check_mask_remove(struct nfp_app *app, char *mask_data, u32 mask_len,
 	return true;
 }
 
-int nfp_compile_flow_metadata(struct nfp_app *app,
-			      struct flow_cls_offload *flow,
+int nfp_compile_flow_metadata(struct nfp_app *app, u32 cookie,
 			      struct nfp_fl_payload *nfp_flow,
 			      struct net_device *netdev,
 			      struct netlink_ext_ack *extack)
@@ -310,7 +309,7 @@ int nfp_compile_flow_metadata(struct nfp_app *app,
 	}
 
 	nfp_flow->meta.host_ctx_id = cpu_to_be32(stats_cxt);
-	nfp_flow->meta.host_cookie = cpu_to_be64(flow->cookie);
+	nfp_flow->meta.host_cookie = cpu_to_be64(cookie);
 	nfp_flow->ingress_dev = netdev;
 
 	ctx_entry = kzalloc(sizeof(*ctx_entry), GFP_KERNEL);
@@ -357,7 +356,7 @@ int nfp_compile_flow_metadata(struct nfp_app *app,
 	priv->stats[stats_cxt].bytes = 0;
 	priv->stats[stats_cxt].used = jiffies;
 
-	check_entry = nfp_flower_search_fl_table(app, flow->cookie, netdev);
+	check_entry = nfp_flower_search_fl_table(app, cookie, netdev);
 	if (check_entry) {
 		NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot offload duplicate flow entry");
 		if (nfp_release_stats_entry(app, stats_cxt)) {
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 2406d33356ad..556c3495211d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -41,6 +41,8 @@
 	 BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_IP) | \
 	 BIT(FLOW_DISSECTOR_KEY_MPLS) | \
+	 BIT(FLOW_DISSECTOR_KEY_CT) | \
+	 BIT(FLOW_DISSECTOR_KEY_META) | \
 	 BIT(FLOW_DISSECTOR_KEY_IP))
 
 #define NFP_FLOWER_WHITELIST_TUN_DISSECTOR \
@@ -89,7 +91,7 @@ struct nfp_flower_merge_check {
 	};
 };
 
-static int
+int
 nfp_flower_xmit_flow(struct nfp_app *app, struct nfp_fl_payload *nfp_flow,
 		     u8 mtype)
 {
@@ -134,20 +136,16 @@ nfp_flower_xmit_flow(struct nfp_app *app, struct nfp_fl_payload *nfp_flow,
 	return 0;
 }
 
-static bool nfp_flower_check_higher_than_mac(struct flow_cls_offload *f)
+static bool nfp_flower_check_higher_than_mac(struct flow_rule *rule)
 {
-	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
-
 	return flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS) ||
 	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS) ||
 	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS) ||
 	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP);
 }
 
-static bool nfp_flower_check_higher_than_l3(struct flow_cls_offload *f)
+static bool nfp_flower_check_higher_than_l3(struct flow_rule *rule)
 {
-	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
-
 	return flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS) ||
 	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP);
 }
@@ -236,15 +234,14 @@ nfp_flower_calc_udp_tun_layer(struct flow_dissector_key_ports *enc_ports,
 	return 0;
 }
 
-static int
+int
 nfp_flower_calculate_key_layers(struct nfp_app *app,
 				struct net_device *netdev,
 				struct nfp_fl_key_ls *ret_key_ls,
-				struct flow_cls_offload *flow,
+				struct flow_rule *rule,
 				enum nfp_flower_tun_type *tun_type,
 				struct netlink_ext_ack *extack)
 {
-	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	struct flow_dissector *dissector = rule->match.dissector;
 	struct flow_match_basic basic = { NULL, NULL};
 	struct nfp_flower_priv *priv = app->priv;
@@ -452,7 +449,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: match on given EtherType is not supported");
 			return -EOPNOTSUPP;
 		}
-	} else if (nfp_flower_check_higher_than_mac(flow)) {
+	} else if (nfp_flower_check_higher_than_mac(rule)) {
 		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: cannot match above L2 without specified EtherType");
 		return -EOPNOTSUPP;
 	}
@@ -471,7 +468,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 	}
 
 	if (!(key_layer & NFP_FLOWER_LAYER_TP) &&
-	    nfp_flower_check_higher_than_l3(flow)) {
+	    nfp_flower_check_higher_than_l3(rule)) {
 		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: cannot match on L4 information without specified IP protocol type");
 		return -EOPNOTSUPP;
 	}
@@ -543,7 +540,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 	return 0;
 }
 
-static struct nfp_fl_payload *
+struct nfp_fl_payload *
 nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer)
 {
 	struct nfp_fl_payload *flow_pay;
@@ -1005,9 +1002,7 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
 				     struct nfp_fl_payload *sub_flow1,
 				     struct nfp_fl_payload *sub_flow2)
 {
-	struct flow_cls_offload merge_tc_off;
 	struct nfp_flower_priv *priv = app->priv;
-	struct netlink_ext_ack *extack = NULL;
 	struct nfp_fl_payload *merge_flow;
 	struct nfp_fl_key_ls merge_key_ls;
 	struct nfp_merge_info *merge_info;
@@ -1016,7 +1011,6 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
 
 	ASSERT_RTNL();
 
-	extack = merge_tc_off.common.extack;
 	if (sub_flow1 == sub_flow2 ||
 	    nfp_flower_is_merge_flow(sub_flow1) ||
 	    nfp_flower_is_merge_flow(sub_flow2))
@@ -1061,9 +1055,8 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
 	if (err)
 		goto err_unlink_sub_flow1;
 
-	merge_tc_off.cookie = merge_flow->tc_flower_cookie;
-	err = nfp_compile_flow_metadata(app, &merge_tc_off, merge_flow,
-					merge_flow->ingress_dev, extack);
+	err = nfp_compile_flow_metadata(app, merge_flow->tc_flower_cookie, merge_flow,
+					merge_flow->ingress_dev, NULL);
 	if (err)
 		goto err_unlink_sub_flow2;
 
@@ -1305,6 +1298,7 @@ static int
 nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 		       struct flow_cls_offload *flow)
 {
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE;
 	struct nfp_flower_priv *priv = app->priv;
 	struct netlink_ext_ack *extack = NULL;
@@ -1330,7 +1324,7 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 	if (!key_layer)
 		return -ENOMEM;
 
-	err = nfp_flower_calculate_key_layers(app, netdev, key_layer, flow,
+	err = nfp_flower_calculate_key_layers(app, netdev, key_layer, rule,
 					      &tun_type, extack);
 	if (err)
 		goto err_free_key_ls;
@@ -1341,12 +1335,12 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 		goto err_free_key_ls;
 	}
 
-	err = nfp_flower_compile_flow_match(app, flow, key_layer, netdev,
+	err = nfp_flower_compile_flow_match(app, rule, key_layer, netdev,
 					    flow_pay, tun_type, extack);
 	if (err)
 		goto err_destroy_flow;
 
-	err = nfp_flower_compile_action(app, flow, netdev, flow_pay, extack);
+	err = nfp_flower_compile_action(app, rule, netdev, flow_pay, extack);
 	if (err)
 		goto err_destroy_flow;
 
@@ -1356,7 +1350,7 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 			goto err_destroy_flow;
 	}
 
-	err = nfp_compile_flow_metadata(app, flow, flow_pay, netdev, extack);
+	err = nfp_compile_flow_metadata(app, flow->cookie, flow_pay, netdev, extack);
 	if (err)
 		goto err_destroy_flow;
 
@@ -1476,7 +1470,7 @@ err_free_links:
 	kfree_rcu(merge_flow, rcu);
 }
 
-static void
+void
 nfp_flower_del_linked_merge_flows(struct nfp_app *app,
 				  struct nfp_fl_payload *sub_flow)
 {
@@ -1601,7 +1595,7 @@ __nfp_flower_update_merge_stats(struct nfp_app *app,
 	}
 }
 
-static void
+void
 nfp_flower_update_merge_stats(struct nfp_app *app,
 			      struct nfp_fl_payload *sub_flow)
 {
@@ -1628,10 +1622,17 @@ nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev,
 		     struct flow_cls_offload *flow)
 {
 	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_fl_ct_map_entry *ct_map_ent;
 	struct netlink_ext_ack *extack = NULL;
 	struct nfp_fl_payload *nfp_flow;
 	u32 ctx_id;
 
+	/* Check ct_map table first */
+	ct_map_ent = rhashtable_lookup_fast(&priv->ct_map_table, &flow->cookie,
+					    nfp_ct_map_params);
+	if (ct_map_ent)
+		return nfp_fl_ct_stats(flow, ct_map_ent);
+
 	extack = flow->common.extack;
 	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev);
 	if (!nfp_flow) {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index 742a420152b3..bb3b8a7f6c5d 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -692,7 +692,7 @@ static int nfp_pci_probe(struct pci_dev *pdev,
 		goto err_pci_disable;
 	}
 
-	devlink = devlink_alloc(&nfp_devlink_ops, sizeof(*pf));
+	devlink = devlink_alloc(&nfp_devlink_ops, sizeof(*pf), &pdev->dev);
 	if (!devlink) {
 		err = -ENOMEM;
 		goto err_rel_regions;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index df5b748be068..df203738511b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -17,6 +17,7 @@
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
+#include <linux/dim.h>
 #include <linux/io-64-nonatomic-hi-lo.h>
 #include <linux/semaphore.h>
 #include <linux/workqueue.h>
@@ -360,6 +361,9 @@ struct nfp_net_rx_ring {
  * @rx_ring:        Pointer to RX ring
  * @xdp_ring:	    Pointer to an extra TX ring for XDP
  * @irq_entry:      MSI-X table entry (use for talking to the device)
+ * @event_ctr:	    Number of interrupt
+ * @rx_dim:	    Dynamic interrupt moderation structure for RX
+ * @tx_dim:	    Dynamic interrupt moderation structure for TX
  * @rx_sync:	    Seqlock for atomic updates of RX stats
  * @rx_pkts:        Number of received packets
  * @rx_bytes:	    Number of received bytes
@@ -410,6 +414,10 @@ struct nfp_net_r_vector {
 
 	u16 irq_entry;
 
+	u16 event_ctr;
+	struct dim rx_dim;
+	struct dim tx_dim;
+
 	struct u64_stats_sync rx_sync;
 	u64 rx_pkts;
 	u64 rx_bytes;
@@ -571,6 +579,8 @@ struct nfp_net_dp {
  *			mailbox area, crypto TLV
  * @link_up:            Is the link up?
  * @link_status_lock:	Protects @link_* and ensures atomicity with BAR reading
+ * @rx_coalesce_adapt_on:   Is RX interrupt moderation adaptive?
+ * @tx_coalesce_adapt_on:   Is TX interrupt moderation adaptive?
  * @rx_coalesce_usecs:      RX interrupt moderation usecs delay parameter
  * @rx_coalesce_max_frames: RX interrupt moderation frame count parameter
  * @tx_coalesce_usecs:      TX interrupt moderation usecs delay parameter
@@ -654,6 +664,8 @@ struct nfp_net {
 
 	struct semaphore bar_lock;
 
+	bool rx_coalesce_adapt_on;
+	bool tx_coalesce_adapt_on;
 	u32 rx_coalesce_usecs;
 	u32 rx_coalesce_max_frames;
 	u32 tx_coalesce_usecs;
@@ -919,6 +931,14 @@ static inline bool nfp_netdev_is_nfp_net(struct net_device *netdev)
 	return netdev->netdev_ops == &nfp_net_netdev_ops;
 }
 
+static inline int nfp_net_coalesce_para_check(u32 usecs, u32 pkts)
+{
+	if ((usecs >= ((1 << 16) - 1)) || (pkts >= ((1 << 16) - 1)))
+		return -EINVAL;
+
+	return 0;
+}
+
 /* Prototypes */
 void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver,
 			    void __iomem *ctrl_bar);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 5dfa4799c34f..5bfa22accf2c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -474,6 +474,12 @@ static irqreturn_t nfp_net_irq_rxtx(int irq, void *data)
 {
 	struct nfp_net_r_vector *r_vec = data;
 
+	/* Currently we cannot tell if it's a rx or tx interrupt,
+	 * since dim does not need accurate event_ctr to calculate,
+	 * we just use this counter for both rx and tx dim.
+	 */
+	r_vec->event_ctr++;
+
 	napi_schedule_irqoff(&r_vec->napi);
 
 	/* The FW auto-masks any interrupt, either via the MASK bit in
@@ -1697,7 +1703,7 @@ nfp_net_parse_meta(struct net_device *netdev, struct nfp_meta_parsed *meta,
 		case NFP_NET_META_RESYNC_INFO:
 			if (nfp_net_tls_rx_resync_req(netdev, data, pkt,
 						      pkt_len))
-				return NULL;
+				return false;
 			data += sizeof(struct nfp_net_tls_resync_req);
 			break;
 		default:
@@ -2061,6 +2067,36 @@ static int nfp_net_poll(struct napi_struct *napi, int budget)
 		if (napi_complete_done(napi, pkts_polled))
 			nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
 
+	if (r_vec->nfp_net->rx_coalesce_adapt_on) {
+		struct dim_sample dim_sample = {};
+		unsigned int start;
+		u64 pkts, bytes;
+
+		do {
+			start = u64_stats_fetch_begin(&r_vec->rx_sync);
+			pkts = r_vec->rx_pkts;
+			bytes = r_vec->rx_bytes;
+		} while (u64_stats_fetch_retry(&r_vec->rx_sync, start));
+
+		dim_update_sample(r_vec->event_ctr, pkts, bytes, &dim_sample);
+		net_dim(&r_vec->rx_dim, dim_sample);
+	}
+
+	if (r_vec->nfp_net->tx_coalesce_adapt_on) {
+		struct dim_sample dim_sample = {};
+		unsigned int start;
+		u64 pkts, bytes;
+
+		do {
+			start = u64_stats_fetch_begin(&r_vec->tx_sync);
+			pkts = r_vec->tx_pkts;
+			bytes = r_vec->tx_bytes;
+		} while (u64_stats_fetch_retry(&r_vec->tx_sync, start));
+
+		dim_update_sample(r_vec->event_ctr, pkts, bytes, &dim_sample);
+		net_dim(&r_vec->tx_dim, dim_sample);
+	}
+
 	return pkts_polled;
 }
 
@@ -2873,6 +2909,7 @@ static int nfp_net_set_config_and_enable(struct nfp_net *nn)
  */
 static void nfp_net_close_stack(struct nfp_net *nn)
 {
+	struct nfp_net_r_vector *r_vec;
 	unsigned int r;
 
 	disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
@@ -2880,8 +2917,16 @@ static void nfp_net_close_stack(struct nfp_net *nn)
 	nn->link_up = false;
 
 	for (r = 0; r < nn->dp.num_r_vecs; r++) {
-		disable_irq(nn->r_vecs[r].irq_vector);
-		napi_disable(&nn->r_vecs[r].napi);
+		r_vec = &nn->r_vecs[r];
+
+		disable_irq(r_vec->irq_vector);
+		napi_disable(&r_vec->napi);
+
+		if (r_vec->rx_ring)
+			cancel_work_sync(&r_vec->rx_dim.work);
+
+		if (r_vec->tx_ring)
+			cancel_work_sync(&r_vec->tx_dim.work);
 	}
 
 	netif_tx_disable(nn->dp.netdev);
@@ -2948,17 +2993,92 @@ void nfp_ctrl_close(struct nfp_net *nn)
 	rtnl_unlock();
 }
 
+static void nfp_net_rx_dim_work(struct work_struct *work)
+{
+	struct nfp_net_r_vector *r_vec;
+	unsigned int factor, value;
+	struct dim_cq_moder moder;
+	struct nfp_net *nn;
+	struct dim *dim;
+
+	dim = container_of(work, struct dim, work);
+	moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
+	r_vec = container_of(dim, struct nfp_net_r_vector, rx_dim);
+	nn = r_vec->nfp_net;
+
+	/* Compute factor used to convert coalesce '_usecs' parameters to
+	 * ME timestamp ticks.  There are 16 ME clock cycles for each timestamp
+	 * count.
+	 */
+	factor = nn->tlv_caps.me_freq_mhz / 16;
+	if (nfp_net_coalesce_para_check(factor * moder.usec, moder.pkts))
+		return;
+
+	/* copy RX interrupt coalesce parameters */
+	value = (moder.pkts << 16) | (factor * moder.usec);
+	rtnl_lock();
+	nn_writel(nn, NFP_NET_CFG_RXR_IRQ_MOD(r_vec->rx_ring->idx), value);
+	(void)nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_IRQMOD);
+	rtnl_unlock();
+
+	dim->state = DIM_START_MEASURE;
+}
+
+static void nfp_net_tx_dim_work(struct work_struct *work)
+{
+	struct nfp_net_r_vector *r_vec;
+	unsigned int factor, value;
+	struct dim_cq_moder moder;
+	struct nfp_net *nn;
+	struct dim *dim;
+
+	dim = container_of(work, struct dim, work);
+	moder = net_dim_get_tx_moderation(dim->mode, dim->profile_ix);
+	r_vec = container_of(dim, struct nfp_net_r_vector, tx_dim);
+	nn = r_vec->nfp_net;
+
+	/* Compute factor used to convert coalesce '_usecs' parameters to
+	 * ME timestamp ticks.  There are 16 ME clock cycles for each timestamp
+	 * count.
+	 */
+	factor = nn->tlv_caps.me_freq_mhz / 16;
+	if (nfp_net_coalesce_para_check(factor * moder.usec, moder.pkts))
+		return;
+
+	/* copy TX interrupt coalesce parameters */
+	value = (moder.pkts << 16) | (factor * moder.usec);
+	rtnl_lock();
+	nn_writel(nn, NFP_NET_CFG_TXR_IRQ_MOD(r_vec->tx_ring->idx), value);
+	(void)nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_IRQMOD);
+	rtnl_unlock();
+
+	dim->state = DIM_START_MEASURE;
+}
+
 /**
  * nfp_net_open_stack() - Start the device from stack's perspective
  * @nn:      NFP Net device to reconfigure
  */
 static void nfp_net_open_stack(struct nfp_net *nn)
 {
+	struct nfp_net_r_vector *r_vec;
 	unsigned int r;
 
 	for (r = 0; r < nn->dp.num_r_vecs; r++) {
-		napi_enable(&nn->r_vecs[r].napi);
-		enable_irq(nn->r_vecs[r].irq_vector);
+		r_vec = &nn->r_vecs[r];
+
+		if (r_vec->rx_ring) {
+			INIT_WORK(&r_vec->rx_dim.work, nfp_net_rx_dim_work);
+			r_vec->rx_dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+		}
+
+		if (r_vec->tx_ring) {
+			INIT_WORK(&r_vec->tx_dim.work, nfp_net_tx_dim_work);
+			r_vec->tx_dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+		}
+
+		napi_enable(&r_vec->napi);
+		enable_irq(r_vec->irq_vector);
 	}
 
 	netif_tx_wake_all_queues(nn->dp.netdev);
@@ -3161,17 +3281,12 @@ static int nfp_net_dp_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp)
 	for (r = 0; r <	nn->max_r_vecs; r++)
 		nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r);
 
-	err = netif_set_real_num_rx_queues(nn->dp.netdev, nn->dp.num_rx_rings);
+	err = netif_set_real_num_queues(nn->dp.netdev,
+					nn->dp.num_stack_tx_rings,
+					nn->dp.num_rx_rings);
 	if (err)
 		return err;
 
-	if (nn->dp.netdev->real_num_tx_queues != nn->dp.num_stack_tx_rings) {
-		err = netif_set_real_num_tx_queues(nn->dp.netdev,
-						   nn->dp.num_stack_tx_rings);
-		if (err)
-			return err;
-	}
-
 	return nfp_net_set_config_and_enable(nn);
 }
 
@@ -3893,6 +4008,9 @@ static void nfp_net_irqmod_init(struct nfp_net *nn)
 	nn->rx_coalesce_max_frames = 64;
 	nn->tx_coalesce_usecs      = 50;
 	nn->tx_coalesce_max_frames = 64;
+
+	nn->rx_coalesce_adapt_on   = true;
+	nn->tx_coalesce_adapt_on   = true;
 }
 
 static void nfp_net_netdev_init(struct nfp_net *nn)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 8803faadd302..0685ece1f155 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -1078,13 +1078,18 @@ static void nfp_net_get_regs(struct net_device *netdev,
 }
 
 static int nfp_net_get_coalesce(struct net_device *netdev,
-				struct ethtool_coalesce *ec)
+				struct ethtool_coalesce *ec,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 
 	if (!(nn->cap & NFP_NET_CFG_CTRL_IRQMOD))
 		return -EINVAL;
 
+	ec->use_adaptive_rx_coalesce = nn->rx_coalesce_adapt_on;
+	ec->use_adaptive_tx_coalesce = nn->tx_coalesce_adapt_on;
+
 	ec->rx_coalesce_usecs       = nn->rx_coalesce_usecs;
 	ec->rx_max_coalesced_frames = nn->rx_coalesce_max_frames;
 	ec->tx_coalesce_usecs       = nn->tx_coalesce_usecs;
@@ -1327,7 +1332,9 @@ exit_close_nsp:
 }
 
 static int nfp_net_set_coalesce(struct net_device *netdev,
-				struct ethtool_coalesce *ec)
+				struct ethtool_coalesce *ec,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	unsigned int factor;
@@ -1361,19 +1368,18 @@ static int nfp_net_set_coalesce(struct net_device *netdev,
 	if (!ec->tx_coalesce_usecs && !ec->tx_max_coalesced_frames)
 		return -EINVAL;
 
-	if (ec->rx_coalesce_usecs * factor >= ((1 << 16) - 1))
-		return -EINVAL;
-
-	if (ec->tx_coalesce_usecs * factor >= ((1 << 16) - 1))
+	if (nfp_net_coalesce_para_check(ec->rx_coalesce_usecs * factor,
+					ec->rx_max_coalesced_frames))
 		return -EINVAL;
 
-	if (ec->rx_max_coalesced_frames >= ((1 << 16) - 1))
-		return -EINVAL;
-
-	if (ec->tx_max_coalesced_frames >= ((1 << 16) - 1))
+	if (nfp_net_coalesce_para_check(ec->tx_coalesce_usecs * factor,
+					ec->tx_max_coalesced_frames))
 		return -EINVAL;
 
 	/* configuration is valid */
+	nn->rx_coalesce_adapt_on = !!ec->use_adaptive_rx_coalesce;
+	nn->tx_coalesce_adapt_on = !!ec->use_adaptive_tx_coalesce;
+
 	nn->rx_coalesce_usecs      = ec->rx_coalesce_usecs;
 	nn->rx_coalesce_max_frames = ec->rx_max_coalesced_frames;
 	nn->tx_coalesce_usecs      = ec->tx_coalesce_usecs;
@@ -1445,7 +1451,8 @@ static int nfp_net_set_channels(struct net_device *netdev,
 
 static const struct ethtool_ops nfp_net_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
-				     ETHTOOL_COALESCE_MAX_FRAMES,
+				     ETHTOOL_COALESCE_MAX_FRAMES |
+				     ETHTOOL_COALESCE_USE_ADAPTIVE,
 	.get_drvinfo		= nfp_net_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_ringparam		= nfp_net_get_ringparam,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
index 921db40047d7..d10a93801344 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
@@ -701,7 +701,7 @@ int nfp_net_pci_probe(struct nfp_pf *pf)
 	if (err)
 		goto err_unmap;
 
-	err = devlink_register(devlink, &pf->pdev->dev);
+	err = devlink_register(devlink);
 	if (err)
 		goto err_app_clean;
 
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index 2d097dcb7bda..346145d3180e 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -993,8 +993,11 @@ static void nixge_ethtools_get_drvinfo(struct net_device *ndev,
 	strlcpy(ed->bus_info, "platform", sizeof(ed->bus_info));
 }
 
-static int nixge_ethtools_get_coalesce(struct net_device *ndev,
-				       struct ethtool_coalesce *ecoalesce)
+static int
+nixge_ethtools_get_coalesce(struct net_device *ndev,
+			    struct ethtool_coalesce *ecoalesce,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct nixge_priv *priv = netdev_priv(ndev);
 	u32 regval = 0;
@@ -1008,8 +1011,11 @@ static int nixge_ethtools_get_coalesce(struct net_device *ndev,
 	return 0;
 }
 
-static int nixge_ethtools_set_coalesce(struct net_device *ndev,
-				       struct ethtool_coalesce *ecoalesce)
+static int
+nixge_ethtools_set_coalesce(struct net_device *ndev,
+			    struct ethtool_coalesce *ecoalesce,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct nixge_priv *priv = netdev_priv(ndev);
 
@@ -1223,7 +1229,6 @@ static int nixge_of_get_resources(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id;
 	enum nixge_version version;
-	struct resource *ctrlres;
 	struct net_device *ndev;
 	struct nixge_priv *priv;
 
@@ -1242,13 +1247,10 @@ static int nixge_of_get_resources(struct platform_device *pdev)
 		netdev_err(ndev, "failed to map dma regs\n");
 		return PTR_ERR(priv->dma_regs);
 	}
-	if (version <= NIXGE_V2) {
+	if (version <= NIXGE_V2)
 		priv->ctrl_regs = priv->dma_regs + NIXGE_REG_CTRL_OFFSET;
-	} else {
-		ctrlres = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-						       "ctrl");
-		priv->ctrl_regs = devm_ioremap_resource(&pdev->dev, ctrlres);
-	}
+	else
+		priv->ctrl_regs = devm_platform_ioremap_resource_byname(pdev, "ctrl");
 	if (IS_ERR(priv->ctrl_regs)) {
 		netdev_err(ndev, "failed to map ctrl regs\n");
 		return PTR_ERR(priv->ctrl_regs);
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 8724d6a9ed02..ef3fb4cc90af 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -5782,15 +5782,11 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 		np->desc_ver = DESC_VER_3;
 		np->txrxctl_bits = NVREG_TXRXCTL_DESC_3;
 		if (dma_64bit) {
-			if (pci_set_dma_mask(pci_dev, DMA_BIT_MASK(39)))
+			if (dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(39)))
 				dev_info(&pci_dev->dev,
 					 "64-bit DMA failed, using 32-bit addressing\n");
 			else
 				dev->features |= NETIF_F_HIGHDMA;
-			if (pci_set_consistent_dma_mask(pci_dev, DMA_BIT_MASK(39))) {
-				dev_info(&pci_dev->dev,
-					 "64-bit DMA (consistent) failed, using 32-bit ring buffers\n");
-			}
 		}
 	} else if (id->driver_data & DEV_HAS_LARGEDESC) {
 		/* packet format 2: supports jumbo frames */
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index 64c6842bd452..d29fe562b3de 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1219,7 +1219,7 @@ static const struct net_device_ops lpc_netdev_ops = {
 	.ndo_stop		= lpc_eth_close,
 	.ndo_start_xmit		= lpc_eth_hard_start_xmit,
 	.ndo_set_rx_mode	= lpc_eth_set_multicast_list,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_set_mac_address	= lpc_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 };
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig b/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig
index af84f72bf08e..4e18b64dceb9 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig
@@ -6,6 +6,7 @@
 config PCH_GBE
 	tristate "OKI SEMICONDUCTOR IOH(ML7223/ML7831) GbE"
 	depends on PCI && (X86_32 || COMPILE_TEST)
+	depends on PTP_1588_CLOCK
 	select MII
 	select PTP_1588_CLOCK_PCH
 	select NET_PTP_CLASSIFY
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 e351f3d1608f..ec3e558f890e 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
@@ -1031,13 +1031,7 @@ static void pch_gbe_watchdog(struct timer_list *t)
 		struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET };
 		netdev->tx_queue_len = adapter->tx_queue_len;
 		/* mii library handles link maintenance tasks */
-		if (mii_ethtool_gset(&adapter->mii, &cmd)) {
-			netdev_err(netdev, "ethtool get setting Error\n");
-			mod_timer(&adapter->watchdog_timer,
-				  round_jiffies(jiffies +
-						PCH_GBE_WATCHDOG_PERIOD));
-			return;
-		}
+		mii_ethtool_gset(&adapter->mii, &cmd);
 		hw->mac.link_speed = ethtool_cmd_speed(&cmd);
 		hw->mac.link_duplex = cmd.duplex;
 		/* Set the RGMII control. */
@@ -2333,7 +2327,7 @@ static const struct net_device_ops pch_gbe_netdev_ops = {
 	.ndo_tx_timeout = pch_gbe_tx_timeout,
 	.ndo_change_mtu = pch_gbe_change_mtu,
 	.ndo_set_features = pch_gbe_set_features,
-	.ndo_do_ioctl = pch_gbe_ioctl,
+	.ndo_eth_ioctl = pch_gbe_ioctl,
 	.ndo_set_rx_mode = pch_gbe_set_multi,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = pch_gbe_netpoll,
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c
index ed832046216a..3426f6fa2b57 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c
@@ -301,9 +301,7 @@ void pch_gbe_phy_init_setting(struct pch_gbe_hw *hw)
 	int ret;
 	u16 mii_reg;
 
-	ret = mii_ethtool_gset(&adapter->mii, &cmd);
-	if (ret)
-		netdev_err(adapter->netdev, "Error: mii_ethtool_gset\n");
+	mii_ethtool_gset(&adapter->mii, &cmd);
 
 	ethtool_cmd_speed_set(&cmd, hw->mac.link_speed);
 	cmd.duplex = hw->mac.link_duplex;
diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c
index d058a63602a9..1a6336a56d3d 100644
--- a/drivers/net/ethernet/packetengines/hamachi.c
+++ b/drivers/net/ethernet/packetengines/hamachi.c
@@ -546,7 +546,9 @@ static int read_eeprom(void __iomem *ioaddr, int location);
 static int mdio_read(struct net_device *dev, int phy_id, int location);
 static void mdio_write(struct net_device *dev, int phy_id, int location, int value);
 static int hamachi_open(struct net_device *dev);
-static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
+static int hamachi_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
+static int hamachi_siocdevprivate(struct net_device *dev, struct ifreq *rq,
+				  void __user *data, int cmd);
 static void hamachi_timer(struct timer_list *t);
 static void hamachi_tx_timeout(struct net_device *dev, unsigned int txqueue);
 static void hamachi_init_ring(struct net_device *dev);
@@ -571,7 +573,8 @@ static const struct net_device_ops hamachi_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_tx_timeout		= hamachi_tx_timeout,
-	.ndo_do_ioctl		= netdev_ioctl,
+	.ndo_eth_ioctl		= hamachi_ioctl,
+	.ndo_siocdevprivate	= hamachi_siocdevprivate,
 };
 
 
@@ -1867,7 +1870,36 @@ static const struct ethtool_ops ethtool_ops_no_mii = {
 	.get_drvinfo = hamachi_get_drvinfo,
 };
 
-static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+/* private ioctl: set rx,tx intr params */
+static int hamachi_siocdevprivate(struct net_device *dev, struct ifreq *rq,
+				  void __user *data, int cmd)
+{
+	struct hamachi_private *np = netdev_priv(dev);
+	u32 *d = (u32 *)&rq->ifr_ifru;
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	if (cmd != SIOCDEVPRIVATE + 3)
+		return -EOPNOTSUPP;
+
+	/* Should add this check here or an ordinary user can do nasty
+	 * things. -KDU
+	 *
+	 * TODO: Shut down the Rx and Tx engines while doing this.
+	 */
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+	writel(d[0], np->base + TxIntrCtrl);
+	writel(d[1], np->base + RxIntrCtrl);
+	printk(KERN_NOTICE "%s: tx %08x, rx %08x intr\n", dev->name,
+	       (u32)readl(np->base + TxIntrCtrl),
+	       (u32)readl(np->base + RxIntrCtrl));
+
+	return 0;
+}
+
+static int hamachi_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
 	struct hamachi_private *np = netdev_priv(dev);
 	struct mii_ioctl_data *data = if_mii(rq);
@@ -1876,28 +1908,9 @@ static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	if (!netif_running(dev))
 		return -EINVAL;
 
-	if (cmd == (SIOCDEVPRIVATE+3)) { /* set rx,tx intr params */
-		u32 *d = (u32 *)&rq->ifr_ifru;
-		/* Should add this check here or an ordinary user can do nasty
-		 * things. -KDU
-		 *
-		 * TODO: Shut down the Rx and Tx engines while doing this.
-		 */
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		writel(d[0], np->base + TxIntrCtrl);
-		writel(d[1], np->base + RxIntrCtrl);
-		printk(KERN_NOTICE "%s: tx %08x, rx %08x intr\n", dev->name,
-		  (u32) readl(np->base + TxIntrCtrl),
-		  (u32) readl(np->base + RxIntrCtrl));
-		rc = 0;
-	}
-
-	else {
-		spin_lock_irq(&np->lock);
-		rc = generic_mii_ioctl(&np->mii_if, data, cmd, NULL);
-		spin_unlock_irq(&np->lock);
-	}
+	spin_lock_irq(&np->lock);
+	rc = generic_mii_ioctl(&np->mii_if, data, cmd, NULL);
+	spin_unlock_irq(&np->lock);
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c
index d1dd9bc1bc7f..f5cd8f51be7c 100644
--- a/drivers/net/ethernet/packetengines/yellowfin.c
+++ b/drivers/net/ethernet/packetengines/yellowfin.c
@@ -362,7 +362,7 @@ static const struct net_device_ops netdev_ops = {
 	.ndo_set_rx_mode	= set_rx_mode,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address 	= eth_mac_addr,
-	.ndo_do_ioctl 		= netdev_ioctl,
+	.ndo_eth_ioctl		= netdev_ioctl,
 	.ndo_tx_timeout 	= yellowfin_tx_timeout,
 };
 
diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c
index 040a15a828b4..7e096b2888b9 100644
--- a/drivers/net/ethernet/pasemi/pasemi_mac.c
+++ b/drivers/net/ethernet/pasemi/pasemi_mac.c
@@ -247,12 +247,13 @@ static int pasemi_mac_unmap_tx_skb(struct pasemi_mac *mac,
 	int f;
 	struct pci_dev *pdev = mac->dma_pdev;
 
-	pci_unmap_single(pdev, dmas[0], skb_headlen(skb), PCI_DMA_TODEVICE);
+	dma_unmap_single(&pdev->dev, dmas[0], skb_headlen(skb), DMA_TO_DEVICE);
 
 	for (f = 0; f < nfrags; f++) {
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
 
-		pci_unmap_page(pdev, dmas[f+1], skb_frag_size(frag), PCI_DMA_TODEVICE);
+		dma_unmap_page(&pdev->dev, dmas[f + 1], skb_frag_size(frag),
+			       DMA_TO_DEVICE);
 	}
 	dev_kfree_skb_irq(skb);
 
@@ -548,10 +549,8 @@ static void pasemi_mac_free_rx_buffers(struct pasemi_mac *mac)
 	for (i = 0; i < RX_RING_SIZE; i++) {
 		info = &RX_DESC_INFO(rx, i);
 		if (info->skb && info->dma) {
-			pci_unmap_single(mac->dma_pdev,
-					 info->dma,
-					 info->skb->len,
-					 PCI_DMA_FROMDEVICE);
+			dma_unmap_single(&mac->dma_pdev->dev, info->dma,
+					 info->skb->len, DMA_FROM_DEVICE);
 			dev_kfree_skb_any(info->skb);
 		}
 		info->dma = 0;
@@ -600,11 +599,11 @@ static void pasemi_mac_replenish_rx_ring(struct net_device *dev,
 		if (unlikely(!skb))
 			break;
 
-		dma = pci_map_single(mac->dma_pdev, skb->data,
+		dma = dma_map_single(&mac->dma_pdev->dev, skb->data,
 				     mac->bufsz - LOCAL_SKB_ALIGN,
-				     PCI_DMA_FROMDEVICE);
+				     DMA_FROM_DEVICE);
 
-		if (unlikely(pci_dma_mapping_error(mac->dma_pdev, dma))) {
+		if (dma_mapping_error(&mac->dma_pdev->dev, dma)) {
 			dev_kfree_skb_irq(info->skb);
 			break;
 		}
@@ -741,8 +740,9 @@ static int pasemi_mac_clean_rx(struct pasemi_mac_rxring *rx,
 
 		len = (macrx & XCT_MACRX_LLEN_M) >> XCT_MACRX_LLEN_S;
 
-		pci_unmap_single(pdev, dma, mac->bufsz - LOCAL_SKB_ALIGN,
-				 PCI_DMA_FROMDEVICE);
+		dma_unmap_single(&pdev->dev, dma,
+				 mac->bufsz - LOCAL_SKB_ALIGN,
+				 DMA_FROM_DEVICE);
 
 		if (macrx & XCT_MACRX_CRC) {
 			/* CRC error flagged */
@@ -1444,10 +1444,10 @@ static int pasemi_mac_start_tx(struct sk_buff *skb, struct net_device *dev)
 
 	nfrags = skb_shinfo(skb)->nr_frags;
 
-	map[0] = pci_map_single(mac->dma_pdev, skb->data, skb_headlen(skb),
-				PCI_DMA_TODEVICE);
+	map[0] = dma_map_single(&mac->dma_pdev->dev, skb->data,
+				skb_headlen(skb), DMA_TO_DEVICE);
 	map_size[0] = skb_headlen(skb);
-	if (pci_dma_mapping_error(mac->dma_pdev, map[0]))
+	if (dma_mapping_error(&mac->dma_pdev->dev, map[0]))
 		goto out_err_nolock;
 
 	for (i = 0; i < nfrags; i++) {
@@ -1534,8 +1534,8 @@ out_err:
 	spin_unlock_irqrestore(&txring->lock, flags);
 out_err_nolock:
 	while (nfrags--)
-		pci_unmap_single(mac->dma_pdev, map[nfrags], map_size[nfrags],
-				 PCI_DMA_TODEVICE);
+		dma_unmap_single(&mac->dma_pdev->dev, map[nfrags],
+				 map_size[nfrags], DMA_TO_DEVICE);
 
 	return NETDEV_TX_BUSY;
 }
diff --git a/drivers/net/ethernet/pensando/Kconfig b/drivers/net/ethernet/pensando/Kconfig
index 202973a82712..3f7519e435b8 100644
--- a/drivers/net/ethernet/pensando/Kconfig
+++ b/drivers/net/ethernet/pensando/Kconfig
@@ -20,7 +20,7 @@ if NET_VENDOR_PENSANDO
 config IONIC
 	tristate "Pensando Ethernet IONIC Support"
 	depends on 64BIT && PCI
-	depends on PTP_1588_CLOCK || !PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select NET_DEVLINK
 	select DIMLIB
 	help
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
index e4a5416adc80..7e296fa71b36 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
@@ -165,10 +165,10 @@ static int ionic_vf_alloc(struct ionic *ionic, int num_vfs)
 			goto out;
 		}
 
+		ionic->num_vfs++;
 		/* ignore failures from older FW, we just won't get stats */
 		(void)ionic_set_vf_config(ionic, i, IONIC_VF_ATTR_STATSADDR,
 					  (u8 *)&v->stats_pa);
-		ionic->num_vfs++;
 	}
 
 out:
@@ -373,9 +373,6 @@ static void ionic_remove(struct pci_dev *pdev)
 {
 	struct ionic *ionic = pci_get_drvdata(pdev);
 
-	if (!ionic)
-		return;
-
 	del_timer_sync(&ionic->watchdog_timer);
 
 	if (ionic->lif) {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index 1dfe962e22e0..0d6858ab511c 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -15,6 +15,7 @@ static void ionic_watchdog_cb(struct timer_list *t)
 {
 	struct ionic *ionic = from_timer(ionic, t, watchdog_timer);
 	struct ionic_lif *lif = ionic->lif;
+	struct ionic_deferred_work *work;
 	int hb;
 
 	mod_timer(&ionic->watchdog_timer,
@@ -31,6 +32,18 @@ static void ionic_watchdog_cb(struct timer_list *t)
 	if (hb >= 0 &&
 	    !test_bit(IONIC_LIF_F_FW_RESET, lif->state))
 		ionic_link_status_check_request(lif, CAN_NOT_SLEEP);
+
+	if (test_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state)) {
+		work = kzalloc(sizeof(*work), GFP_ATOMIC);
+		if (!work) {
+			netdev_err(lif->netdev, "rxmode change dropped\n");
+			return;
+		}
+
+		work->type = IONIC_DW_TYPE_RX_MODE;
+		netdev_dbg(lif->netdev, "deferred: rx_mode\n");
+		ionic_lif_deferred_enqueue(&lif->deferred, work);
+	}
 }
 
 void ionic_init_devinfo(struct ionic *ionic)
@@ -106,6 +119,8 @@ int ionic_dev_setup(struct ionic *ionic)
 	idev->last_fw_hb = 0;
 	idev->fw_hb_ready = true;
 	idev->fw_status_ready = true;
+	idev->fw_generation = IONIC_FW_STS_F_GENERATION &
+			      ioread8(&idev->dev_info_regs->fw_status);
 
 	mod_timer(&ionic->watchdog_timer,
 		  round_jiffies(jiffies + ionic->watchdog_period));
@@ -121,7 +136,9 @@ int ionic_heartbeat_check(struct ionic *ionic)
 {
 	struct ionic_dev *idev = &ionic->idev;
 	unsigned long check_time, last_check_time;
-	bool fw_status_ready, fw_hb_ready;
+	bool fw_status_ready = true;
+	bool fw_hb_ready;
+	u8 fw_generation;
 	u8 fw_status;
 	u32 fw_hb;
 
@@ -140,9 +157,29 @@ do_check_time:
 
 	/* firmware is useful only if the running bit is set and
 	 * fw_status != 0xff (bad PCI read)
+	 * If fw_status is not ready don't bother with the generation.
 	 */
 	fw_status = ioread8(&idev->dev_info_regs->fw_status);
-	fw_status_ready = (fw_status != 0xff) && (fw_status & IONIC_FW_STS_F_RUNNING);
+
+	if (fw_status == 0xff || !(fw_status & IONIC_FW_STS_F_RUNNING)) {
+		fw_status_ready = false;
+	} else {
+		fw_generation = fw_status & IONIC_FW_STS_F_GENERATION;
+		if (idev->fw_generation != fw_generation) {
+			dev_info(ionic->dev, "FW generation 0x%02x -> 0x%02x\n",
+				 idev->fw_generation, fw_generation);
+
+			idev->fw_generation = fw_generation;
+
+			/* If the generation changed, the fw status is not
+			 * ready so we need to trigger a fw-down cycle.  After
+			 * the down, the next watchdog will see the fw is up
+			 * and the generation value stable, so will trigger
+			 * the fw-up activity.
+			 */
+			fw_status_ready = false;
+		}
+	}
 
 	/* is this a transition? */
 	if (fw_status_ready != idev->fw_status_ready) {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index c25cf9b744c5..8311086fb1f4 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -143,6 +143,7 @@ struct ionic_dev {
 	u32 last_fw_hb;
 	bool fw_hb_ready;
 	bool fw_status_ready;
+	u8 fw_generation;
 
 	u64 __iomem *db_pages;
 	dma_addr_t phy_db_pages;
@@ -160,8 +161,6 @@ struct ionic_dev {
 struct ionic_cq_info {
 	union {
 		void *cq_desc;
-		struct ionic_txq_comp *txcq;
-		struct ionic_rxq_comp *rxcq;
 		struct ionic_admin_comp *admincq;
 		struct ionic_notifyq_event *notifyq;
 	};
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
index b41301a5b0df..c7d0e195d176 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
@@ -64,7 +64,7 @@ struct ionic *ionic_devlink_alloc(struct device *dev)
 {
 	struct devlink *dl;
 
-	dl = devlink_alloc(&ionic_dl_ops, sizeof(struct ionic));
+	dl = devlink_alloc(&ionic_dl_ops, sizeof(struct ionic), dev);
 
 	return devlink_priv(dl);
 }
@@ -82,7 +82,7 @@ int ionic_devlink_register(struct ionic *ionic)
 	struct devlink_port_attrs attrs = {};
 	int err;
 
-	err = devlink_register(dl, ionic->dev);
+	err = devlink_register(dl);
 	if (err) {
 		dev_warn(ionic->dev, "devlink_register failed: %d\n", err);
 		return err;
@@ -91,20 +91,20 @@ int ionic_devlink_register(struct ionic *ionic)
 	attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
 	devlink_port_attrs_set(&ionic->dl_port, &attrs);
 	err = devlink_port_register(dl, &ionic->dl_port, 0);
-	if (err)
+	if (err) {
 		dev_err(ionic->dev, "devlink_port_register failed: %d\n", err);
-	else
-		devlink_port_type_eth_set(&ionic->dl_port,
-					  ionic->lif->netdev);
+		devlink_unregister(dl);
+		return err;
+	}
 
-	return err;
+	devlink_port_type_eth_set(&ionic->dl_port, ionic->lif->netdev);
+	return 0;
 }
 
 void ionic_devlink_unregister(struct ionic *ionic)
 {
 	struct devlink *dl = priv_to_devlink(ionic);
 
-	if (ionic->dl_port.registered)
-		devlink_port_unregister(&ionic->dl_port);
+	devlink_port_unregister(&ionic->dl_port);
 	devlink_unregister(dl);
 }
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index 6583be570e45..e91b4874a57f 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -32,6 +32,9 @@ static void ionic_get_stats(struct net_device *netdev,
 	struct ionic_lif *lif = netdev_priv(netdev);
 	u32 i;
 
+	if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+		return;
+
 	memset(buf, 0, stats->n_stats * sizeof(*buf));
 	for (i = 0; i < ionic_num_stats_grps; i++)
 		ionic_stats_groups[i].get_values(lif, &buf);
@@ -274,6 +277,9 @@ static int ionic_set_link_ksettings(struct net_device *netdev,
 	struct ionic *ionic = lif->ionic;
 	int err = 0;
 
+	if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+		return -EBUSY;
+
 	/* set autoneg */
 	if (ks->base.autoneg != idev->port_info->config.an_enable) {
 		mutex_lock(&ionic->dev_cmd_lock);
@@ -320,6 +326,9 @@ static int ionic_set_pauseparam(struct net_device *netdev,
 	u32 requested_pause;
 	int err;
 
+	if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+		return -EBUSY;
+
 	if (pause->autoneg)
 		return -EOPNOTSUPP;
 
@@ -372,6 +381,9 @@ static int ionic_set_fecparam(struct net_device *netdev,
 	u8 fec_type;
 	int ret = 0;
 
+	if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+		return -EBUSY;
+
 	if (lif->ionic->idev.port_info->config.an_enable) {
 		netdev_err(netdev, "FEC request not allowed while autoneg is enabled\n");
 		return -EINVAL;
@@ -408,7 +420,9 @@ static int ionic_set_fecparam(struct net_device *netdev,
 }
 
 static int ionic_get_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *coalesce)
+			      struct ethtool_coalesce *coalesce,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 
@@ -426,7 +440,9 @@ static int ionic_get_coalesce(struct net_device *netdev,
 }
 
 static int ionic_set_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *coalesce)
+			      struct ethtool_coalesce *coalesce,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 	struct ionic_identity *ident;
@@ -528,6 +544,9 @@ static int ionic_set_ringparam(struct net_device *netdev,
 	struct ionic_queue_params qparam;
 	int err;
 
+	if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+		return -EBUSY;
+
 	ionic_init_queue_params(lif, &qparam);
 
 	if (ring->rx_mini_pending || ring->rx_jumbo_pending) {
@@ -597,6 +616,9 @@ static int ionic_set_channels(struct net_device *netdev,
 	int max_cnt;
 	int err;
 
+	if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+		return -EBUSY;
+
 	ionic_init_queue_params(lif, &qparam);
 
 	if (ch->rx_count != ch->tx_count) {
@@ -947,6 +969,9 @@ static int ionic_nway_reset(struct net_device *netdev)
 	struct ionic *ionic = lif->ionic;
 	int err = 0;
 
+	if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+		return -EBUSY;
+
 	/* flap the link to force auto-negotiation */
 
 	mutex_lock(&ionic->dev_cmd_lock);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index 0478b48d9895..278610ed7227 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -2936,6 +2936,8 @@ struct ionic_hwstamp_regs {
  * @asic_type:       Asic type
  * @asic_rev:        Asic revision
  * @fw_status:       Firmware status
+ *			bit 0   - 1 = fw running
+ *			bit 4-7 - 4 bit generation number, changes on fw restart
  * @fw_heartbeat:    Firmware heartbeat counter
  * @serial_num:      Serial number
  * @fw_version:      Firmware version
@@ -2949,7 +2951,8 @@ union ionic_dev_info_regs {
 		u8     version;
 		u8     asic_type;
 		u8     asic_rev;
-#define IONIC_FW_STS_F_RUNNING	0x1
+#define IONIC_FW_STS_F_RUNNING		0x01
+#define IONIC_FW_STS_F_GENERATION	0xF0
 		u8     fw_status;
 		u32    fw_heartbeat;
 		char   fw_version[IONIC_DEVINFO_FWVERS_BUFLEN];
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index e795fa63ca12..23c9e196a784 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -11,6 +11,7 @@
 #include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <linux/cpumask.h>
+#include <linux/crash_dump.h>
 
 #include "ionic.h"
 #include "ionic_bus.h"
@@ -29,9 +30,6 @@ static const u8 ionic_qtype_versions[IONIC_QTYPE_MAX] = {
 				      */
 };
 
-static void ionic_lif_rx_mode(struct ionic_lif *lif);
-static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr);
-static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr);
 static void ionic_link_status_check(struct ionic_lif *lif);
 static void ionic_lif_handle_fw_down(struct ionic_lif *lif);
 static void ionic_lif_handle_fw_up(struct ionic_lif *lif);
@@ -91,20 +89,21 @@ static void ionic_lif_deferred_work(struct work_struct *work)
 		case IONIC_DW_TYPE_RX_MODE:
 			ionic_lif_rx_mode(lif);
 			break;
-		case IONIC_DW_TYPE_RX_ADDR_ADD:
-			ionic_lif_addr_add(lif, w->addr);
-			break;
-		case IONIC_DW_TYPE_RX_ADDR_DEL:
-			ionic_lif_addr_del(lif, w->addr);
-			break;
 		case IONIC_DW_TYPE_LINK_STATUS:
 			ionic_link_status_check(lif);
 			break;
 		case IONIC_DW_TYPE_LIF_RESET:
-			if (w->fw_status)
+			if (w->fw_status) {
 				ionic_lif_handle_fw_up(lif);
-			else
+			} else {
 				ionic_lif_handle_fw_down(lif);
+
+				/* Fire off another watchdog to see
+				 * if the FW is already back rather than
+				 * waiting another whole cycle
+				 */
+				mod_timer(&lif->ionic->watchdog_timer, jiffies + 1);
+			}
 			break;
 		default:
 			break;
@@ -850,10 +849,8 @@ int ionic_lif_create_hwstamp_txq(struct ionic_lif *lif)
 	u64 features;
 	int err;
 
-	mutex_lock(&lif->queue_lock);
-
 	if (lif->hwstamp_txq)
-		goto out;
+		return 0;
 
 	features = IONIC_Q_F_2X_CQ_DESC | IONIC_TXQ_F_HWSTAMP;
 
@@ -895,9 +892,6 @@ int ionic_lif_create_hwstamp_txq(struct ionic_lif *lif)
 		}
 	}
 
-out:
-	mutex_unlock(&lif->queue_lock);
-
 	return 0;
 
 err_qcq_enable:
@@ -908,7 +902,6 @@ err_qcq_init:
 	ionic_qcq_free(lif, txq);
 	devm_kfree(lif->ionic->dev, txq);
 err_qcq_alloc:
-	mutex_unlock(&lif->queue_lock);
 	return err;
 }
 
@@ -920,10 +913,8 @@ int ionic_lif_create_hwstamp_rxq(struct ionic_lif *lif)
 	u64 features;
 	int err;
 
-	mutex_lock(&lif->queue_lock);
-
 	if (lif->hwstamp_rxq)
-		goto out;
+		return 0;
 
 	features = IONIC_Q_F_2X_CQ_DESC | IONIC_RXQ_F_HWSTAMP;
 
@@ -961,9 +952,6 @@ int ionic_lif_create_hwstamp_rxq(struct ionic_lif *lif)
 		}
 	}
 
-out:
-	mutex_unlock(&lif->queue_lock);
-
 	return 0;
 
 err_qcq_enable:
@@ -974,7 +962,6 @@ err_qcq_init:
 	ionic_qcq_free(lif, rxq);
 	devm_kfree(lif->ionic->dev, rxq);
 err_qcq_alloc:
-	mutex_unlock(&lif->queue_lock);
 	return err;
 }
 
@@ -1077,7 +1064,11 @@ static int ionic_lif_add_hwstamp_rxfilt(struct ionic_lif *lif, u64 pkt_class)
 	if (err && err != -EEXIST)
 		return err;
 
-	return ionic_rx_filter_save(lif, 0, qid, 0, &ctx);
+	spin_lock_bh(&lif->rx_filters.lock);
+	err = ionic_rx_filter_save(lif, 0, qid, 0, &ctx, IONIC_FILTER_STATE_SYNCED);
+	spin_unlock_bh(&lif->rx_filters.lock);
+
+	return err;
 }
 
 int ionic_lif_set_hwstamp_rxfilt(struct ionic_lif *lif, u64 pkt_class)
@@ -1250,7 +1241,7 @@ void ionic_get_stats64(struct net_device *netdev,
 	ns->tx_errors = ns->tx_aborted_errors;
 }
 
-static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr)
+int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr)
 {
 	struct ionic_admin_ctx ctx = {
 		.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
@@ -1260,27 +1251,83 @@ static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr)
 			.match = cpu_to_le16(IONIC_RX_FILTER_MATCH_MAC),
 		},
 	};
+	int nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters);
+	bool mc = is_multicast_ether_addr(addr);
 	struct ionic_rx_filter *f;
-	int err;
+	int err = 0;
+
+	memcpy(ctx.cmd.rx_filter_add.mac.addr, addr, ETH_ALEN);
 
-	/* don't bother if we already have it */
 	spin_lock_bh(&lif->rx_filters.lock);
 	f = ionic_rx_filter_by_addr(lif, addr);
+	if (f) {
+		/* don't bother if we already have it and it is sync'd */
+		if (f->state == IONIC_FILTER_STATE_SYNCED) {
+			spin_unlock_bh(&lif->rx_filters.lock);
+			return 0;
+		}
+
+		/* mark preemptively as sync'd to block any parallel attempts */
+		f->state = IONIC_FILTER_STATE_SYNCED;
+	} else {
+		/* save as SYNCED to catch any DEL requests while processing */
+		err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx,
+					   IONIC_FILTER_STATE_SYNCED);
+	}
 	spin_unlock_bh(&lif->rx_filters.lock);
-	if (f)
-		return 0;
+	if (err)
+		return err;
 
 	netdev_dbg(lif->netdev, "rx_filter add ADDR %pM\n", addr);
 
-	memcpy(ctx.cmd.rx_filter_add.mac.addr, addr, ETH_ALEN);
-	err = ionic_adminq_post_wait(lif, &ctx);
-	if (err && err != -EEXIST)
-		return err;
+	/* Don't bother with the write to FW if we know there's no room,
+	 * we can try again on the next sync attempt.
+	 */
+	if ((lif->nucast + lif->nmcast) >= nfilters)
+		err = -ENOSPC;
+	else
+		err = ionic_adminq_post_wait(lif, &ctx);
+
+	spin_lock_bh(&lif->rx_filters.lock);
+	if (err && err != -EEXIST) {
+		/* set the state back to NEW so we can try again later */
+		f = ionic_rx_filter_by_addr(lif, addr);
+		if (f && f->state == IONIC_FILTER_STATE_SYNCED)
+			f->state = IONIC_FILTER_STATE_NEW;
+
+		spin_unlock_bh(&lif->rx_filters.lock);
+
+		if (err == -ENOSPC)
+			return 0;
+		else
+			return err;
+	}
 
-	return ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx);
+	if (mc)
+		lif->nmcast++;
+	else
+		lif->nucast++;
+
+	f = ionic_rx_filter_by_addr(lif, addr);
+	if (f && f->state == IONIC_FILTER_STATE_OLD) {
+		/* Someone requested a delete while we were adding
+		 * so update the filter info with the results from the add
+		 * and the data will be there for the delete on the next
+		 * sync cycle.
+		 */
+		err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx,
+					   IONIC_FILTER_STATE_OLD);
+	} else {
+		err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx,
+					   IONIC_FILTER_STATE_SYNCED);
+	}
+
+	spin_unlock_bh(&lif->rx_filters.lock);
+
+	return err;
 }
 
-static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr)
+int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr)
 {
 	struct ionic_admin_ctx ctx = {
 		.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
@@ -1290,6 +1337,7 @@ static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr)
 		},
 	};
 	struct ionic_rx_filter *f;
+	int state;
 	int err;
 
 	spin_lock_bh(&lif->rx_filters.lock);
@@ -1302,65 +1350,37 @@ static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr)
 	netdev_dbg(lif->netdev, "rx_filter del ADDR %pM (id %d)\n",
 		   addr, f->filter_id);
 
+	state = f->state;
 	ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id);
 	ionic_rx_filter_free(lif, f);
-	spin_unlock_bh(&lif->rx_filters.lock);
-
-	err = ionic_adminq_post_wait(lif, &ctx);
-	if (err && err != -EEXIST)
-		return err;
 
-	return 0;
-}
+	if (is_multicast_ether_addr(addr) && lif->nmcast)
+		lif->nmcast--;
+	else if (!is_multicast_ether_addr(addr) && lif->nucast)
+		lif->nucast--;
 
-static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add)
-{
-	unsigned int nmfilters;
-	unsigned int nufilters;
+	spin_unlock_bh(&lif->rx_filters.lock);
 
-	if (add) {
-		/* Do we have space for this filter?  We test the counters
-		 * here before checking the need for deferral so that we
-		 * can return an overflow error to the stack.
-		 */
-		nmfilters = le32_to_cpu(lif->identity->eth.max_mcast_filters);
-		nufilters = le32_to_cpu(lif->identity->eth.max_ucast_filters);
-
-		if ((is_multicast_ether_addr(addr) && lif->nmcast < nmfilters))
-			lif->nmcast++;
-		else if (!is_multicast_ether_addr(addr) &&
-			 lif->nucast < nufilters)
-			lif->nucast++;
-		else
-			return -ENOSPC;
-	} else {
-		if (is_multicast_ether_addr(addr) && lif->nmcast)
-			lif->nmcast--;
-		else if (!is_multicast_ether_addr(addr) && lif->nucast)
-			lif->nucast--;
+	if (state != IONIC_FILTER_STATE_NEW) {
+		err = ionic_adminq_post_wait(lif, &ctx);
+		if (err && err != -EEXIST)
+			return err;
 	}
 
-	netdev_dbg(lif->netdev, "rx_filter %s %pM\n",
-		   add ? "add" : "del", addr);
-	if (add)
-		return ionic_lif_addr_add(lif, addr);
-	else
-		return ionic_lif_addr_del(lif, addr);
-
 	return 0;
 }
 
 static int ionic_addr_add(struct net_device *netdev, const u8 *addr)
 {
-	return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR);
+	return ionic_lif_list_addr(netdev_priv(netdev), addr, ADD_ADDR);
 }
 
 static int ionic_addr_del(struct net_device *netdev, const u8 *addr)
 {
-	return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR);
+	return ionic_lif_list_addr(netdev_priv(netdev), addr, DEL_ADDR);
 }
 
-static void ionic_lif_rx_mode(struct ionic_lif *lif)
+void ionic_lif_rx_mode(struct ionic_lif *lif)
 {
 	struct net_device *netdev = lif->netdev;
 	unsigned int nfilters;
@@ -1381,32 +1401,26 @@ static void ionic_lif_rx_mode(struct ionic_lif *lif)
 	rx_mode |= (nd_flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0;
 	rx_mode |= (nd_flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0;
 
-	/* sync unicast addresses
-	 * next check to see if we're in an overflow state
+	/* sync the mac filters */
+	ionic_rx_filter_sync(lif);
+
+	/* check for overflow state
 	 *    if so, we track that we overflowed and enable NIC PROMISC
 	 *    else if the overflow is set and not needed
 	 *       we remove our overflow flag and check the netdev flags
 	 *       to see if we can disable NIC PROMISC
 	 */
-	__dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del);
 	nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters);
-	if (netdev_uc_count(netdev) + 1 > nfilters) {
+	if ((lif->nucast + lif->nmcast) >= nfilters) {
 		rx_mode |= IONIC_RX_MODE_F_PROMISC;
+		rx_mode |= IONIC_RX_MODE_F_ALLMULTI;
 		lif->uc_overflow = true;
+		lif->mc_overflow = true;
 	} else if (lif->uc_overflow) {
 		lif->uc_overflow = false;
+		lif->mc_overflow = false;
 		if (!(nd_flags & IFF_PROMISC))
 			rx_mode &= ~IONIC_RX_MODE_F_PROMISC;
-	}
-
-	/* same for multicast */
-	__dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del);
-	nfilters = le32_to_cpu(lif->identity->eth.max_mcast_filters);
-	if (netdev_mc_count(netdev) > nfilters) {
-		rx_mode |= IONIC_RX_MODE_F_ALLMULTI;
-		lif->mc_overflow = true;
-	} else if (lif->mc_overflow) {
-		lif->mc_overflow = false;
 		if (!(nd_flags & IFF_ALLMULTI))
 			rx_mode &= ~IONIC_RX_MODE_F_ALLMULTI;
 	}
@@ -1449,28 +1463,26 @@ static void ionic_lif_rx_mode(struct ionic_lif *lif)
 	mutex_unlock(&lif->config_lock);
 }
 
-static void ionic_set_rx_mode(struct net_device *netdev, bool can_sleep)
+static void ionic_ndo_set_rx_mode(struct net_device *netdev)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 	struct ionic_deferred_work *work;
 
-	if (!can_sleep) {
-		work = kzalloc(sizeof(*work), GFP_ATOMIC);
-		if (!work) {
-			netdev_err(lif->netdev, "rxmode change dropped\n");
-			return;
-		}
-		work->type = IONIC_DW_TYPE_RX_MODE;
-		netdev_dbg(lif->netdev, "deferred: rx_mode\n");
-		ionic_lif_deferred_enqueue(&lif->deferred, work);
-	} else {
-		ionic_lif_rx_mode(lif);
-	}
-}
+	/* Sync the kernel filter list with the driver filter list */
+	__dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del);
+	__dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del);
 
-static void ionic_ndo_set_rx_mode(struct net_device *netdev)
-{
-	ionic_set_rx_mode(netdev, CAN_NOT_SLEEP);
+	/* Shove off the rest of the rxmode work to the work task
+	 * which will include syncing the filters to the firmware.
+	 */
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work) {
+		netdev_err(lif->netdev, "rxmode change dropped\n");
+		return;
+	}
+	work->type = IONIC_DW_TYPE_RX_MODE;
+	netdev_dbg(lif->netdev, "deferred: rx_mode\n");
+	ionic_lif_deferred_enqueue(&lif->deferred, work);
 }
 
 static __le64 ionic_netdev_features_to_nic(netdev_features_t features)
@@ -1599,7 +1611,6 @@ static int ionic_init_nic_features(struct ionic_lif *lif)
 	features = NETIF_F_HW_VLAN_CTAG_TX |
 		   NETIF_F_HW_VLAN_CTAG_RX |
 		   NETIF_F_HW_VLAN_CTAG_FILTER |
-		   NETIF_F_RXHASH |
 		   NETIF_F_SG |
 		   NETIF_F_HW_CSUM |
 		   NETIF_F_RXCSUM |
@@ -1607,6 +1618,9 @@ static int ionic_init_nic_features(struct ionic_lif *lif)
 		   NETIF_F_TSO6 |
 		   NETIF_F_TSO_ECN;
 
+	if (lif->nxqs > 1)
+		features |= NETIF_F_RXHASH;
+
 	err = ionic_set_nic_features(lif, features);
 	if (err)
 		return err;
@@ -1689,13 +1703,13 @@ static int ionic_set_mac_address(struct net_device *netdev, void *sa)
 	if (!is_zero_ether_addr(netdev->dev_addr)) {
 		netdev_info(netdev, "deleting mac addr %pM\n",
 			    netdev->dev_addr);
-		ionic_addr_del(netdev, netdev->dev_addr);
+		ionic_lif_addr_del(netdev_priv(netdev), netdev->dev_addr);
 	}
 
 	eth_commit_mac_addr_change(netdev, addr);
 	netdev_info(netdev, "updating mac addr %pM\n", mac);
 
-	return ionic_addr_add(netdev, mac);
+	return ionic_lif_addr_add(netdev_priv(netdev), mac);
 }
 
 static void ionic_stop_queues_reconfig(struct ionic_lif *lif)
@@ -1801,7 +1815,12 @@ static int ionic_vlan_rx_add_vid(struct net_device *netdev, __be16 proto,
 	if (err)
 		return err;
 
-	return ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx);
+	spin_lock_bh(&lif->rx_filters.lock);
+	err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx,
+				   IONIC_FILTER_STATE_SYNCED);
+	spin_unlock_bh(&lif->rx_filters.lock);
+
+	return err;
 }
 
 static int ionic_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto,
@@ -2104,7 +2123,7 @@ static int ionic_txrx_init(struct ionic_lif *lif)
 	if (lif->netdev->features & NETIF_F_RXHASH)
 		ionic_lif_rss_init(lif);
 
-	ionic_set_rx_mode(lif->netdev, CAN_SLEEP);
+	ionic_lif_rx_mode(lif);
 
 	return 0;
 
@@ -2202,9 +2221,11 @@ static int ionic_open(struct net_device *netdev)
 	if (test_and_clear_bit(IONIC_LIF_F_BROKEN, lif->state))
 		netdev_info(netdev, "clearing broken state\n");
 
+	mutex_lock(&lif->queue_lock);
+
 	err = ionic_txrx_alloc(lif);
 	if (err)
-		return err;
+		goto err_unlock;
 
 	err = ionic_txrx_init(lif);
 	if (err)
@@ -2225,12 +2246,21 @@ static int ionic_open(struct net_device *netdev)
 			goto err_txrx_deinit;
 	}
 
+	/* If hardware timestamping is enabled, but the queues were freed by
+	 * ionic_stop, those need to be reallocated and initialized, too.
+	 */
+	ionic_lif_hwstamp_recreate_queues(lif);
+
+	mutex_unlock(&lif->queue_lock);
+
 	return 0;
 
 err_txrx_deinit:
 	ionic_txrx_deinit(lif);
 err_txrx_free:
 	ionic_txrx_free(lif);
+err_unlock:
+	mutex_unlock(&lif->queue_lock);
 	return err;
 }
 
@@ -2250,14 +2280,16 @@ static int ionic_stop(struct net_device *netdev)
 	if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
 		return 0;
 
+	mutex_lock(&lif->queue_lock);
 	ionic_stop_queues(lif);
 	ionic_txrx_deinit(lif);
 	ionic_txrx_free(lif);
+	mutex_unlock(&lif->queue_lock);
 
 	return 0;
 }
 
-static int ionic_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+static int ionic_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 
@@ -2519,7 +2551,7 @@ static int ionic_set_vf_link_state(struct net_device *netdev, int vf, int set)
 static const struct net_device_ops ionic_netdev_ops = {
 	.ndo_open               = ionic_open,
 	.ndo_stop               = ionic_stop,
-	.ndo_do_ioctl		= ionic_do_ioctl,
+	.ndo_eth_ioctl		= ionic_eth_ioctl,
 	.ndo_start_xmit		= ionic_start_xmit,
 	.ndo_get_stats64	= ionic_get_stats64,
 	.ndo_set_rx_mode	= ionic_ndo_set_rx_mode,
@@ -2580,22 +2612,26 @@ int ionic_reconfigure_queues(struct ionic_lif *lif,
 	struct ionic_qcq **tx_qcqs = NULL;
 	struct ionic_qcq **rx_qcqs = NULL;
 	unsigned int flags, i;
-	int err = -ENOMEM;
+	int err = 0;
 
 	/* allocate temporary qcq arrays to hold new queue structs */
 	if (qparam->nxqs != lif->nxqs || qparam->ntxq_descs != lif->ntxq_descs) {
 		tx_qcqs = devm_kcalloc(lif->ionic->dev, lif->ionic->ntxqs_per_lif,
 				       sizeof(struct ionic_qcq *), GFP_KERNEL);
-		if (!tx_qcqs)
+		if (!tx_qcqs) {
+			err = -ENOMEM;
 			goto err_out;
+		}
 	}
 	if (qparam->nxqs != lif->nxqs ||
 	    qparam->nrxq_descs != lif->nrxq_descs ||
 	    qparam->rxq_features != lif->rxq_features) {
 		rx_qcqs = devm_kcalloc(lif->ionic->dev, lif->ionic->nrxqs_per_lif,
 				       sizeof(struct ionic_qcq *), GFP_KERNEL);
-		if (!rx_qcqs)
+		if (!rx_qcqs) {
+			err = -ENOMEM;
 			goto err_out;
+		}
 	}
 
 	/* allocate new desc_info and rings, but leave the interrupt setup
@@ -2774,6 +2810,9 @@ err_out:
 		ionic_qcq_free(lif, lif->rxqcqs[i]);
 	}
 
+	if (err)
+		netdev_info(lif->netdev, "%s: failed %d\n", __func__, err);
+
 	return err;
 }
 
@@ -2827,8 +2866,14 @@ int ionic_lif_alloc(struct ionic *ionic)
 
 	lif->ionic = ionic;
 	lif->index = 0;
-	lif->ntxq_descs = IONIC_DEF_TXRX_DESC;
-	lif->nrxq_descs = IONIC_DEF_TXRX_DESC;
+
+	if (is_kdump_kernel()) {
+		lif->ntxq_descs = IONIC_MIN_TXRX_DESC;
+		lif->nrxq_descs = IONIC_MIN_TXRX_DESC;
+	} else {
+		lif->ntxq_descs = IONIC_DEF_TXRX_DESC;
+		lif->nrxq_descs = IONIC_DEF_TXRX_DESC;
+	}
 
 	/* Convert the default coalesce value to actual hw resolution */
 	lif->rx_coalesce_usecs = IONIC_ITR_COAL_USEC_DEFAULT;
@@ -3179,7 +3224,7 @@ static int ionic_station_set(struct ionic_lif *lif)
 		 */
 		if (!ether_addr_equal(ctx.comp.lif_getattr.mac,
 				      netdev->dev_addr))
-			ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR);
+			ionic_lif_addr_add(lif, netdev->dev_addr);
 	} else {
 		/* Update the netdev mac with the device's mac */
 		memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len);
@@ -3196,7 +3241,7 @@ static int ionic_station_set(struct ionic_lif *lif)
 
 	netdev_dbg(lif->netdev, "adding station MAC addr %pM\n",
 		   netdev->dev_addr);
-	ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR);
+	ionic_lif_addr_add(lif, netdev->dev_addr);
 
 	return 0;
 }
@@ -3514,6 +3559,7 @@ int ionic_lif_size(struct ionic *ionic)
 	unsigned int min_intrs;
 	int err;
 
+	/* retrieve basic values from FW */
 	lc = &ident->lif.eth.config;
 	dev_nintrs = le32_to_cpu(ident->dev.nintrs);
 	neqs_per_lif = le32_to_cpu(ident->lif.rdma.eq_qtype.qid_count);
@@ -3521,6 +3567,15 @@ int ionic_lif_size(struct ionic *ionic)
 	ntxqs_per_lif = le32_to_cpu(lc->queue_count[IONIC_QTYPE_TXQ]);
 	nrxqs_per_lif = le32_to_cpu(lc->queue_count[IONIC_QTYPE_RXQ]);
 
+	/* limit values to play nice with kdump */
+	if (is_kdump_kernel()) {
+		dev_nintrs = 2;
+		neqs_per_lif = 0;
+		nnqs_per_lif = 0;
+		ntxqs_per_lif = 1;
+		nrxqs_per_lif = 1;
+	}
+
 	/* reserve last queue id for hardware timestamping */
 	if (lc->features & cpu_to_le64(IONIC_ETH_HW_TIMESTAMP)) {
 		if (ntxqs_per_lif <= 1 || nrxqs_per_lif <= 1) {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
index 69ab59fedb6c..4915184f3efb 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
@@ -98,8 +98,6 @@ struct ionic_qcq {
 
 enum ionic_deferred_work_type {
 	IONIC_DW_TYPE_RX_MODE,
-	IONIC_DW_TYPE_RX_ADDR_ADD,
-	IONIC_DW_TYPE_RX_ADDR_DEL,
 	IONIC_DW_TYPE_LINK_STATUS,
 	IONIC_DW_TYPE_LIF_RESET,
 };
@@ -147,6 +145,7 @@ enum ionic_lif_state_flags {
 	IONIC_LIF_F_SW_DEBUG_STATS,
 	IONIC_LIF_F_UP,
 	IONIC_LIF_F_LINK_CHECK_REQUESTED,
+	IONIC_LIF_F_FILTER_SYNC_NEEDED,
 	IONIC_LIF_F_FW_RESET,
 	IONIC_LIF_F_SPLIT_INTR,
 	IONIC_LIF_F_BROKEN,
@@ -295,6 +294,10 @@ int ionic_lif_alloc(struct ionic *ionic);
 int ionic_lif_init(struct ionic_lif *lif);
 void ionic_lif_free(struct ionic_lif *lif);
 void ionic_lif_deinit(struct ionic_lif *lif);
+
+int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr);
+int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr);
+
 int ionic_lif_register(struct ionic_lif *lif);
 void ionic_lif_unregister(struct ionic_lif *lif);
 int ionic_lif_identify(struct ionic *ionic, u8 lif_type,
@@ -303,6 +306,7 @@ int ionic_lif_size(struct ionic *ionic);
 
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 void ionic_lif_hwstamp_replay(struct ionic_lif *lif);
+void ionic_lif_hwstamp_recreate_queues(struct ionic_lif *lif);
 int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr);
 int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr);
 ktime_t ionic_lif_phc_ktime(struct ionic_lif *lif, u64 counter);
@@ -312,6 +316,7 @@ void ionic_lif_alloc_phc(struct ionic_lif *lif);
 void ionic_lif_free_phc(struct ionic_lif *lif);
 #else
 static inline void ionic_lif_hwstamp_replay(struct ionic_lif *lif) {}
+static inline void ionic_lif_hwstamp_recreate_queues(struct ionic_lif *lif) {}
 
 static inline int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr)
 {
@@ -342,6 +347,7 @@ int ionic_lif_set_hwstamp_rxfilt(struct ionic_lif *lif, u64 pkt_class);
 
 int ionic_lif_rss_config(struct ionic_lif *lif, u16 types,
 			 const u8 *key, const u32 *indir);
+void ionic_lif_rx_mode(struct ionic_lif *lif);
 int ionic_reconfigure_queues(struct ionic_lif *lif,
 			     struct ionic_queue_params *qparam);
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 61cfe2120817..6f07bf509efe 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -375,8 +375,8 @@ try_again:
 		 * heartbeat check but is still alive and will process this
 		 * request, so don't clean the dev_cmd in this case.
 		 */
-		dev_warn(ionic->dev, "DEVCMD %s (%d) failed - FW halted\n",
-			 ionic_opcode_to_str(opcode), opcode);
+		dev_dbg(ionic->dev, "DEVCMD %s (%d) failed - FW halted\n",
+			ionic_opcode_to_str(opcode), opcode);
 		return -ENXIO;
 	}
 
@@ -450,6 +450,8 @@ int ionic_identify(struct ionic *ionic)
 	}
 	mutex_unlock(&ionic->dev_cmd_lock);
 
+	dev_info(ionic->dev, "FW: %s\n", idev->dev_info.fw_version);
+
 	if (err) {
 		dev_err(ionic->dev, "Cannot identify ionic: %dn", err);
 		goto err_out;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_phc.c b/drivers/net/ethernet/pensando/ionic/ionic_phc.c
index 6e2403c71608..eed2db69d708 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_phc.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_phc.c
@@ -119,8 +119,8 @@ static int ionic_lif_hwstamp_set_ts_config(struct ionic_lif *lif,
 		config->rx_filter = HWTSTAMP_FILTER_ALL;
 	}
 
-	dev_dbg(ionic->dev, "config_rx_filter %d rx_filt %#llx rx_all %d\n",
-		config->rx_filter, rx_filt, rx_all);
+	dev_dbg(ionic->dev, "%s: config_rx_filter %d rx_filt %#llx rx_all %d\n",
+		__func__, config->rx_filter, rx_filt, rx_all);
 
 	if (tx_mode) {
 		err = ionic_lif_create_hwstamp_txq(lif);
@@ -194,7 +194,9 @@ int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr)
 	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
 		return -EFAULT;
 
+	mutex_lock(&lif->queue_lock);
 	err = ionic_lif_hwstamp_set_ts_config(lif, &config);
+	mutex_unlock(&lif->queue_lock);
 	if (err) {
 		netdev_info(lif->netdev, "hwstamp set failed: %d\n", err);
 		return err;
@@ -213,11 +215,37 @@ void ionic_lif_hwstamp_replay(struct ionic_lif *lif)
 	if (!lif->phc || !lif->phc->ptp)
 		return;
 
+	mutex_lock(&lif->queue_lock);
 	err = ionic_lif_hwstamp_set_ts_config(lif, NULL);
+	mutex_unlock(&lif->queue_lock);
 	if (err)
 		netdev_info(lif->netdev, "hwstamp replay failed: %d\n", err);
 }
 
+void ionic_lif_hwstamp_recreate_queues(struct ionic_lif *lif)
+{
+	int err;
+
+	if (!lif->phc || !lif->phc->ptp)
+		return;
+
+	mutex_lock(&lif->phc->config_lock);
+
+	if (lif->phc->ts_config_tx_mode) {
+		err = ionic_lif_create_hwstamp_txq(lif);
+		if (err)
+			netdev_info(lif->netdev, "hwstamp recreate txq failed: %d\n", err);
+	}
+
+	if (lif->phc->ts_config_rx_filt) {
+		err = ionic_lif_create_hwstamp_rxq(lif);
+		if (err)
+			netdev_info(lif->netdev, "hwstamp recreate rxq failed: %d\n", err);
+	}
+
+	mutex_unlock(&lif->phc->config_lock);
+}
+
 int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr)
 {
 	struct hwtstamp_config config;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c
index d71316d9ded2..7e3a5634c161 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c
@@ -4,6 +4,7 @@
 #include <linux/netdevice.h>
 #include <linux/dynamic_debug.h>
 #include <linux/etherdevice.h>
+#include <linux/list.h>
 
 #include "ionic.h"
 #include "ionic_lif.h"
@@ -120,11 +121,12 @@ void ionic_rx_filters_deinit(struct ionic_lif *lif)
 }
 
 int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index,
-			 u32 hash, struct ionic_admin_ctx *ctx)
+			 u32 hash, struct ionic_admin_ctx *ctx,
+			 enum ionic_filter_state state)
 {
 	struct device *dev = lif->ionic->dev;
 	struct ionic_rx_filter_add_cmd *ac;
-	struct ionic_rx_filter *f;
+	struct ionic_rx_filter *f = NULL;
 	struct hlist_head *head;
 	unsigned int key;
 
@@ -133,9 +135,11 @@ int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index,
 	switch (le16_to_cpu(ac->match)) {
 	case IONIC_RX_FILTER_MATCH_VLAN:
 		key = le16_to_cpu(ac->vlan.vlan);
+		f = ionic_rx_filter_by_vlan(lif, le16_to_cpu(ac->vlan.vlan));
 		break;
 	case IONIC_RX_FILTER_MATCH_MAC:
 		key = *(u32 *)ac->mac.addr;
+		f = ionic_rx_filter_by_addr(lif, ac->mac.addr);
 		break;
 	case IONIC_RX_FILTER_MATCH_MAC_VLAN:
 		key = le16_to_cpu(ac->mac_vlan.vlan);
@@ -147,12 +151,19 @@ int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index,
 		return -EINVAL;
 	}
 
-	f = devm_kzalloc(dev, sizeof(*f), GFP_KERNEL);
-	if (!f)
-		return -ENOMEM;
+	if (f) {
+		/* remove from current linking so we can refresh it */
+		hlist_del(&f->by_id);
+		hlist_del(&f->by_hash);
+	} else {
+		f = devm_kzalloc(dev, sizeof(*f), GFP_ATOMIC);
+		if (!f)
+			return -ENOMEM;
+	}
 
 	f->flow_id = flow_id;
 	f->filter_id = le32_to_cpu(ctx->comp.rx_filter_add.filter_id);
+	f->state = state;
 	f->rxq_index = rxq_index;
 	memcpy(&f->cmd, ac, sizeof(f->cmd));
 	netdev_dbg(lif->netdev, "rx_filter add filter_id %d\n", f->filter_id);
@@ -160,8 +171,6 @@ int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index,
 	INIT_HLIST_NODE(&f->by_hash);
 	INIT_HLIST_NODE(&f->by_id);
 
-	spin_lock_bh(&lif->rx_filters.lock);
-
 	key = hash_32(key, IONIC_RX_FILTER_HASH_BITS);
 	head = &lif->rx_filters.by_hash[key];
 	hlist_add_head(&f->by_hash, head);
@@ -170,8 +179,6 @@ int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index,
 	head = &lif->rx_filters.by_id[key];
 	hlist_add_head(&f->by_id, head);
 
-	spin_unlock_bh(&lif->rx_filters.lock);
-
 	return 0;
 }
 
@@ -231,3 +238,121 @@ struct ionic_rx_filter *ionic_rx_filter_rxsteer(struct ionic_lif *lif)
 
 	return NULL;
 }
+
+int ionic_lif_list_addr(struct ionic_lif *lif, const u8 *addr, bool mode)
+{
+	struct ionic_rx_filter *f;
+	int err;
+
+	spin_lock_bh(&lif->rx_filters.lock);
+
+	f = ionic_rx_filter_by_addr(lif, addr);
+	if (mode == ADD_ADDR && !f) {
+		struct ionic_admin_ctx ctx = {
+			.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
+			.cmd.rx_filter_add = {
+				.opcode = IONIC_CMD_RX_FILTER_ADD,
+				.lif_index = cpu_to_le16(lif->index),
+				.match = cpu_to_le16(IONIC_RX_FILTER_MATCH_MAC),
+			},
+		};
+
+		memcpy(ctx.cmd.rx_filter_add.mac.addr, addr, ETH_ALEN);
+		err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx,
+					   IONIC_FILTER_STATE_NEW);
+		if (err) {
+			spin_unlock_bh(&lif->rx_filters.lock);
+			return err;
+		}
+
+	} else if (mode == ADD_ADDR && f) {
+		if (f->state == IONIC_FILTER_STATE_OLD)
+			f->state = IONIC_FILTER_STATE_SYNCED;
+
+	} else if (mode == DEL_ADDR && f) {
+		if (f->state == IONIC_FILTER_STATE_NEW)
+			ionic_rx_filter_free(lif, f);
+		else if (f->state == IONIC_FILTER_STATE_SYNCED)
+			f->state = IONIC_FILTER_STATE_OLD;
+	} else if (mode == DEL_ADDR && !f) {
+		spin_unlock_bh(&lif->rx_filters.lock);
+		return -ENOENT;
+	}
+
+	spin_unlock_bh(&lif->rx_filters.lock);
+
+	set_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state);
+
+	return 0;
+}
+
+struct sync_item {
+	struct list_head list;
+	struct ionic_rx_filter f;
+};
+
+void ionic_rx_filter_sync(struct ionic_lif *lif)
+{
+	struct device *dev = lif->ionic->dev;
+	struct list_head sync_add_list;
+	struct list_head sync_del_list;
+	struct sync_item *sync_item;
+	struct ionic_rx_filter *f;
+	struct hlist_head *head;
+	struct hlist_node *tmp;
+	struct sync_item *spos;
+	unsigned int i;
+
+	INIT_LIST_HEAD(&sync_add_list);
+	INIT_LIST_HEAD(&sync_del_list);
+
+	clear_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state);
+
+	/* Copy the filters to be added and deleted
+	 * into a separate local list that needs no locking.
+	 */
+	spin_lock_bh(&lif->rx_filters.lock);
+	for (i = 0; i < IONIC_RX_FILTER_HLISTS; i++) {
+		head = &lif->rx_filters.by_id[i];
+		hlist_for_each_entry_safe(f, tmp, head, by_id) {
+			if (f->state == IONIC_FILTER_STATE_NEW ||
+			    f->state == IONIC_FILTER_STATE_OLD) {
+				sync_item = devm_kzalloc(dev, sizeof(*sync_item),
+							 GFP_KERNEL);
+				if (!sync_item)
+					goto loop_out;
+
+				sync_item->f = *f;
+
+				if (f->state == IONIC_FILTER_STATE_NEW)
+					list_add(&sync_item->list, &sync_add_list);
+				else
+					list_add(&sync_item->list, &sync_del_list);
+			}
+		}
+	}
+loop_out:
+	spin_unlock_bh(&lif->rx_filters.lock);
+
+	/* If the add or delete fails, it won't get marked as sync'd
+	 * and will be tried again in the next sync action.
+	 * Do the deletes first in case we're in an overflow state and
+	 * they can clear room for some new filters
+	 */
+	list_for_each_entry_safe(sync_item, spos, &sync_del_list, list) {
+		(void)ionic_lif_addr_del(lif, sync_item->f.cmd.mac.addr);
+
+		list_del(&sync_item->list);
+		devm_kfree(dev, sync_item);
+	}
+
+	list_for_each_entry_safe(sync_item, spos, &sync_add_list, list) {
+		(void)ionic_lif_addr_add(lif, sync_item->f.cmd.mac.addr);
+
+		if (sync_item->f.state != IONIC_FILTER_STATE_SYNCED)
+			set_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state);
+
+		list_del(&sync_item->list);
+		devm_kfree(dev, sync_item);
+	}
+}
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h
index 1ead48be3c83..a66e35f0833b 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h
@@ -5,10 +5,18 @@
 #define _IONIC_RX_FILTER_H_
 
 #define IONIC_RXQ_INDEX_ANY		(0xFFFF)
+
+enum ionic_filter_state {
+	IONIC_FILTER_STATE_SYNCED,
+	IONIC_FILTER_STATE_NEW,
+	IONIC_FILTER_STATE_OLD,
+};
+
 struct ionic_rx_filter {
 	u32 flow_id;
 	u32 filter_id;
 	u16 rxq_index;
+	enum ionic_filter_state state;
 	struct ionic_rx_filter_add_cmd cmd;
 	struct hlist_node by_hash;
 	struct hlist_node by_id;
@@ -28,9 +36,13 @@ void ionic_rx_filter_replay(struct ionic_lif *lif);
 int ionic_rx_filters_init(struct ionic_lif *lif);
 void ionic_rx_filters_deinit(struct ionic_lif *lif);
 int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index,
-			 u32 hash, struct ionic_admin_ctx *ctx);
+			 u32 hash, struct ionic_admin_ctx *ctx,
+			 enum ionic_filter_state state);
 struct ionic_rx_filter *ionic_rx_filter_by_vlan(struct ionic_lif *lif, u16 vid);
 struct ionic_rx_filter *ionic_rx_filter_by_addr(struct ionic_lif *lif, const u8 *addr);
 struct ionic_rx_filter *ionic_rx_filter_rxsteer(struct ionic_lif *lif);
+void ionic_rx_filter_sync(struct ionic_lif *lif);
+int ionic_lif_list_addr(struct ionic_lif *lif, const u8 *addr, bool mode);
+int ionic_rx_filters_need_sync(struct ionic_lif *lif);
 
 #endif /* _IONIC_RX_FILTER_H_ */
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 08870190e4d2..37c39581b659 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -32,19 +32,13 @@ static inline struct netdev_queue *q_to_ndq(struct ionic_queue *q)
 	return netdev_get_tx_queue(q->lif->netdev, q->index);
 }
 
-static void ionic_rx_buf_reset(struct ionic_buf_info *buf_info)
-{
-	buf_info->page = NULL;
-	buf_info->page_offset = 0;
-	buf_info->dma_addr = 0;
-}
-
 static int ionic_rx_page_alloc(struct ionic_queue *q,
 			       struct ionic_buf_info *buf_info)
 {
 	struct net_device *netdev = q->lif->netdev;
 	struct ionic_rx_stats *stats;
 	struct device *dev;
+	struct page *page;
 
 	dev = q->dev;
 	stats = q_to_rx_stats(q);
@@ -55,26 +49,27 @@ static int ionic_rx_page_alloc(struct ionic_queue *q,
 		return -EINVAL;
 	}
 
-	buf_info->page = alloc_pages(IONIC_PAGE_GFP_MASK, 0);
-	if (unlikely(!buf_info->page)) {
+	page = alloc_pages(IONIC_PAGE_GFP_MASK, 0);
+	if (unlikely(!page)) {
 		net_err_ratelimited("%s: %s page alloc failed\n",
 				    netdev->name, q->name);
 		stats->alloc_err++;
 		return -ENOMEM;
 	}
-	buf_info->page_offset = 0;
 
-	buf_info->dma_addr = dma_map_page(dev, buf_info->page, buf_info->page_offset,
+	buf_info->dma_addr = dma_map_page(dev, page, 0,
 					  IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(dev, buf_info->dma_addr))) {
-		__free_pages(buf_info->page, 0);
-		ionic_rx_buf_reset(buf_info);
+		__free_pages(page, 0);
 		net_err_ratelimited("%s: %s dma map failed\n",
 				    netdev->name, q->name);
 		stats->dma_map_err++;
 		return -EIO;
 	}
 
+	buf_info->page = page;
+	buf_info->page_offset = 0;
+
 	return 0;
 }
 
@@ -95,7 +90,7 @@ static void ionic_rx_page_free(struct ionic_queue *q,
 
 	dma_unmap_page(dev, buf_info->dma_addr, IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
 	__free_pages(buf_info->page, 0);
-	ionic_rx_buf_reset(buf_info);
+	buf_info->page = NULL;
 }
 
 static bool ionic_rx_buf_recycle(struct ionic_queue *q,
@@ -139,7 +134,7 @@ static struct sk_buff *ionic_rx_frags(struct ionic_queue *q,
 	buf_info = &desc_info->bufs[0];
 	len = le16_to_cpu(comp->len);
 
-	prefetch(buf_info->page);
+	prefetchw(buf_info->page);
 
 	skb = napi_get_frags(&q_to_qcq(q)->napi);
 	if (unlikely(!skb)) {
@@ -170,7 +165,7 @@ static struct sk_buff *ionic_rx_frags(struct ionic_queue *q,
 		if (!ionic_rx_buf_recycle(q, buf_info, frag_len)) {
 			dma_unmap_page(dev, buf_info->dma_addr,
 				       IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
-			ionic_rx_buf_reset(buf_info);
+			buf_info->page = NULL;
 		}
 
 		buf_info++;
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index 98f430905ffa..1203353238e5 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -99,7 +99,7 @@ config QED_SRIOV
 config QEDE
 	tristate "QLogic QED 25/40/100Gb Ethernet NIC"
 	depends on QED
-	imply PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  This enables the support for Marvell FastLinQ adapters family,
 	  ethernet driver.
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic.h b/drivers/net/ethernet/qlogic/netxen/netxen_nic.h
index e5c51256243a..f13fa7396aef 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic.h
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic.h
@@ -1863,7 +1863,6 @@ static inline u32 netxen_tx_avail(struct nx_host_tx_ring *tx_ring)
 int netxen_get_flash_mac_addr(struct netxen_adapter *adapter, u64 *mac);
 int netxen_p3_get_mac_addr(struct netxen_adapter *adapter, u64 *mac);
 void netxen_change_ringparam(struct netxen_adapter *adapter);
-int netxen_rom_fast_read(struct netxen_adapter *adapter, int addr, int *valp);
 
 extern const struct ethtool_ops netxen_nic_ethtool_ops;
 
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
index dd22cb056d03..a075643f5826 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
@@ -731,7 +731,9 @@ netxen_nic_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
  * firmware coalescing to default.
  */
 static int netxen_set_intr_coalesce(struct net_device *netdev,
-			struct ethtool_coalesce *ethcoal)
+				    struct ethtool_coalesce *ethcoal,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct netxen_adapter *adapter = netdev_priv(netdev);
 
@@ -775,7 +777,9 @@ static int netxen_set_intr_coalesce(struct net_device *netdev,
 }
 
 static int netxen_get_intr_coalesce(struct net_device *netdev,
-			struct ethtool_coalesce *ethcoal)
+				    struct ethtool_coalesce *ethcoal,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct netxen_adapter *adapter = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index b590c70539b5..d58e021614cd 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -26,15 +26,6 @@
 
 extern const struct qed_common_ops qed_common_ops_pass;
 
-#define QED_MAJOR_VERSION		8
-#define QED_MINOR_VERSION		37
-#define QED_REVISION_VERSION		0
-#define QED_ENGINEERING_VERSION		20
-
-#define QED_VERSION						 \
-	((QED_MAJOR_VERSION << 24) | (QED_MINOR_VERSION << 16) | \
-	 (QED_REVISION_VERSION << 8) | QED_ENGINEERING_VERSION)
-
 #define STORM_FW_VERSION				       \
 	((FW_MAJOR_VERSION << 24) | (FW_MINOR_VERSION << 16) | \
 	 (FW_REVISION_VERSION << 8) | FW_ENGINEERING_VERSION)
@@ -517,12 +508,6 @@ enum qed_hsi_def_type {
 	QED_NUM_HSI_DEFS
 };
 
-#define DRV_MODULE_VERSION		      \
-	__stringify(QED_MAJOR_VERSION) "."    \
-	__stringify(QED_MINOR_VERSION) "."    \
-	__stringify(QED_REVISION_VERSION) "." \
-	__stringify(QED_ENGINEERING_VERSION)
-
 struct qed_simd_fp_handler {
 	void	*token;
 	void	(*func)(void *);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index e81dd34a3cac..dc93ddea8906 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -741,7 +741,6 @@ static int
 qed_dcbx_read_local_lldp_mib(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct qed_dcbx_mib_meta_data data;
-	int rc = 0;
 
 	memset(&data, 0, sizeof(data));
 	data.addr = p_hwfn->mcp_info->port_addr + offsetof(struct public_port,
@@ -750,7 +749,7 @@ qed_dcbx_read_local_lldp_mib(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	data.size = sizeof(struct lldp_config_params_s);
 	qed_memcpy_from(p_hwfn, p_ptt, data.lldp_local, data.addr, data.size);
 
-	return rc;
+	return 0;
 }
 
 static int
@@ -810,7 +809,6 @@ static int
 qed_dcbx_read_local_mib(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct qed_dcbx_mib_meta_data data;
-	int rc = 0;
 
 	memset(&data, 0, sizeof(data));
 	data.addr = p_hwfn->mcp_info->port_addr +
@@ -819,7 +817,7 @@ qed_dcbx_read_local_mib(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	data.size = sizeof(struct dcbx_local_params);
 	qed_memcpy_from(p_hwfn, p_ptt, data.local_admin, data.addr, data.size);
 
-	return rc;
+	return 0;
 }
 
 static int qed_dcbx_read_mib(struct qed_hwfn *p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c
index cf7f4da68e69..78070682f2df 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_devlink.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c
@@ -93,7 +93,7 @@ static const struct devlink_health_reporter_ops qed_fw_fatal_reporter_ops = {
 		.dump = qed_fw_fatal_reporter_dump,
 };
 
-#define QED_REPORTER_FW_GRACEFUL_PERIOD 1200000
+#define QED_REPORTER_FW_GRACEFUL_PERIOD 0
 
 void qed_fw_reporters_create(struct devlink *devlink)
 {
@@ -207,14 +207,15 @@ struct devlink *qed_devlink_register(struct qed_dev *cdev)
 	struct devlink *dl;
 	int rc;
 
-	dl = devlink_alloc(&qed_dl_ops, sizeof(struct qed_devlink));
+	dl = devlink_alloc(&qed_dl_ops, sizeof(struct qed_devlink),
+			   &cdev->pdev->dev);
 	if (!dl)
 		return ERR_PTR(-ENOMEM);
 
 	qdevlink = devlink_priv(dl);
 	qdevlink->cdev = cdev;
 
-	rc = devlink_register(dl, &cdev->pdev->dev);
+	rc = devlink_register(dl);
 	if (rc)
 		goto err_free;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 578935f643b8..f78e6055f654 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -351,6 +351,9 @@ static int qed_fw_assertion(struct qed_hwfn *p_hwfn)
 	qed_hw_err_notify(p_hwfn, p_hwfn->p_dpc_ptt, QED_HW_ERR_FW_ASSERT,
 			  "FW assertion!\n");
 
+	/* Clear assert indications */
+	qed_wr(p_hwfn, p_hwfn->p_dpc_ptt, MISC_REG_AEU_GENERAL_ATTN_32, 0);
+
 	return -EINVAL;
 }
 
@@ -464,12 +467,19 @@ static int qed_dorq_attn_int_sts(struct qed_hwfn *p_hwfn)
 	u32 int_sts, first_drop_reason, details, address, all_drops_reason;
 	struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
 
+	int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
+	if (int_sts == 0xdeadbeaf) {
+		DP_NOTICE(p_hwfn->cdev,
+			  "DORQ is being reset, skipping int_sts handler\n");
+
+		return 0;
+	}
+
 	/* int_sts may be zero since all PFs were interrupted for doorbell
 	 * overflow but another one already handled it. Can abort here. If
 	 * This PF also requires overflow recovery we will be interrupted again.
 	 * The masked almost full indication may also be set. Ignoring.
 	 */
-	int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
 	if (!(int_sts & ~DORQ_REG_INT_STS_DORQ_FIFO_AFULL))
 		return 0;
 
@@ -528,6 +538,9 @@ static int qed_dorq_attn_int_sts(struct qed_hwfn *p_hwfn)
 
 static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
 {
+	if (p_hwfn->cdev->recov_in_prog)
+		return 0;
+
 	p_hwfn->db_recovery_info.dorq_attn = true;
 	qed_dorq_attn_overflow(p_hwfn);
 
@@ -943,6 +956,13 @@ qed_int_deassertion_aeu_bit(struct qed_hwfn *p_hwfn,
 	DP_INFO(p_hwfn, "`%s' - Disabled future attentions\n",
 		p_bit_name);
 
+	/* Re-enable FW aassertion (Gen 32) interrupts */
+	val = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		     MISC_REG_AEU_ENABLE4_IGU_OUT_0);
+	val |= MISC_REG_AEU_ENABLE4_IGU_OUT_0_GENERAL_ATTN32;
+	qed_wr(p_hwfn, p_hwfn->p_dpc_ptt,
+	       MISC_REG_AEU_ENABLE4_IGU_OUT_0, val);
+
 out:
 	return rc;
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index a99861124630..fc8b3e64f153 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -1624,8 +1624,6 @@ qed_iwarp_get_listener(struct qed_hwfn *p_hwfn,
 	static const u32 ip_zero[4] = { 0, 0, 0, 0 };
 	bool found = false;
 
-	qed_iwarp_print_cm_info(p_hwfn, cm_info);
-
 	list_for_each_entry(listener,
 			    &p_hwfn->p_rdma_info->iwarp.listen_list,
 			    list_entry) {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 6bb9ec98a12b..15ef59aa34ff 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -49,11 +49,10 @@
 #define QED_NVM_CFG_MAX_ATTRS		50
 
 static char version[] =
-	"QLogic FastLinQ 4xxxx Core Module qed " DRV_MODULE_VERSION "\n";
+	"QLogic FastLinQ 4xxxx Core Module qed\n";
 
 MODULE_DESCRIPTION("QLogic FastLinQ 4xxxx Core Module");
 MODULE_LICENSE("GPL");
-MODULE_VERSION(DRV_MODULE_VERSION);
 
 #define FW_FILE_VERSION				\
 	__stringify(FW_MAJOR_VERSION) "."	\
@@ -1221,6 +1220,10 @@ static void qed_slowpath_task(struct work_struct *work)
 
 	if (test_and_clear_bit(QED_SLOWPATH_PERIODIC_DB_REC,
 			       &hwfn->slowpath_task_flags)) {
+		/* skip qed_db_rec_handler during recovery/unload */
+		if (hwfn->cdev->recov_in_prog || !hwfn->slowpath_wq_active)
+			goto out;
+
 		qed_db_rec_handler(hwfn, ptt);
 		if (hwfn->periodic_db_rec_count--)
 			qed_slowpath_delayed_work(hwfn,
@@ -1228,6 +1231,7 @@ static void qed_slowpath_task(struct work_struct *work)
 						  QED_PERIODIC_DB_REC_INTERVAL);
 	}
 
+out:
 	qed_ptt_release(hwfn, ptt);
 }
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 4387292c37e2..6e5a6cc97d0e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -944,7 +944,6 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
 
 	memset(&in_params, 0, sizeof(in_params));
 	in_params.hsi_ver = QED_LOAD_REQ_HSI_VER_DEFAULT;
-	in_params.drv_ver_0 = QED_VERSION;
 	in_params.drv_ver_1 = qed_get_config_bitmap();
 	in_params.fw_ver = STORM_FW_VERSION;
 	rc = eocre_get_mfw_drv_role(p_hwfn, p_params->drv_role, &mfw_drv_role);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c
index c1dd71d19f3f..3b84d00cf987 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c
@@ -4,7 +4,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/mm.h>
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
index 9db22be42476..da1b7fdcbda7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
@@ -504,6 +504,8 @@
 	0x180824UL
 #define  MISC_REG_AEU_GENERAL_ATTN_0 \
 	0x008400UL
+#define MISC_REG_AEU_GENERAL_ATTN_32 \
+	0x008480UL
 #define MISC_REG_AEU_GENERAL_ATTN_35 \
 	0x00848cUL
 #define  CAU_REG_SB_ADDR_MEMORY \
@@ -518,6 +520,12 @@
 	0x180804UL
 #define  MISC_REG_AEU_ENABLE1_IGU_OUT_0 \
 	0x00849cUL
+#define MISC_REG_AEU_ENABLE4_IGU_OUT_0 \
+	0x0084a8UL
+#define MISC_REG_AEU_ENABLE4_IGU_OUT_0_GENERAL_ATTN32      \
+	(0x1UL << 0)
+#define MISC_REG_AEU_ENABLE4_IGU_OUT_0_GENERAL_ATTN32_SHIFT \
+	0
 #define MISC_REG_AEU_AFTER_INVERT_1_IGU	\
 	0x0087b4UL
 #define  MISC_REG_AEU_MASK_ATTN_IGU \
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 5630008f38b7..f90dcfe9ee68 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -30,15 +30,6 @@
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
 
-#define QEDE_MAJOR_VERSION		8
-#define QEDE_MINOR_VERSION		37
-#define QEDE_REVISION_VERSION		0
-#define QEDE_ENGINEERING_VERSION	20
-#define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "."	\
-		__stringify(QEDE_MINOR_VERSION) "."		\
-		__stringify(QEDE_REVISION_VERSION) "."		\
-		__stringify(QEDE_ENGINEERING_VERSION)
-
 #define DRV_MODULE_SYM		qede
 
 struct qede_stats_common {
@@ -589,7 +580,9 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
 			    struct flow_cls_offload *f);
 
 void qede_forced_speed_maps_init(void);
-int qede_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal);
+int qede_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal,
+		      struct kernel_ethtool_coalesce *kernel_coal,
+		      struct netlink_ext_ack *extack);
 int qede_set_per_coalesce(struct net_device *dev, u32 queue,
 			  struct ethtool_coalesce *coal);
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 1560ad3d9290..8284c4c1528f 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -625,13 +625,13 @@ static void qede_get_drvinfo(struct net_device *ndev,
 		 (edev->dev_info.common.mfw_rev >> 8) & 0xFF,
 		 edev->dev_info.common.mfw_rev & 0xFF);
 
-	if ((strlen(storm) + strlen(DRV_MODULE_VERSION) + strlen("[storm]  ")) <
+	if ((strlen(storm) + strlen("[storm]")) <
 	    sizeof(info->version))
 		snprintf(info->version, sizeof(info->version),
-			 "%s [storm %s]", DRV_MODULE_VERSION, storm);
+			 "[storm %s]", storm);
 	else
 		snprintf(info->version, sizeof(info->version),
-			 "%s %s", DRV_MODULE_VERSION, storm);
+			 "%s", storm);
 
 	if (edev->dev_info.common.mbi_version) {
 		snprintf(mbi, ETHTOOL_FWVERS_LEN, "%d.%d.%d",
@@ -760,7 +760,9 @@ static int qede_flash_device(struct net_device *dev,
 }
 
 static int qede_get_coalesce(struct net_device *dev,
-			     struct ethtool_coalesce *coal)
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	void *rx_handle = NULL, *tx_handle = NULL;
 	struct qede_dev *edev = netdev_priv(dev);
@@ -819,7 +821,9 @@ out:
 	return rc;
 }
 
-int qede_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal)
+int qede_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal,
+		      struct kernel_ethtool_coalesce *kernel_coal,
+		      struct netlink_ext_ack *extack)
 {
 	struct qede_dev *edev = netdev_priv(dev);
 	struct qede_fastpath *fp;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 1c7f9ed6f1c1..9837bdb89cd4 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -39,12 +39,8 @@
 #include "qede.h"
 #include "qede_ptp.h"
 
-static char version[] =
-	"QLogic FastLinQ 4xxxx Ethernet Driver qede " DRV_MODULE_VERSION "\n";
-
 MODULE_DESCRIPTION("QLogic FastLinQ 4xxxx Ethernet Driver");
 MODULE_LICENSE("GPL");
-MODULE_VERSION(DRV_MODULE_VERSION);
 
 static uint debug;
 module_param(debug, uint, 0);
@@ -258,7 +254,7 @@ int __init qede_init(void)
 {
 	int ret;
 
-	pr_info("qede_init: %s\n", version);
+	pr_info("qede init: QLogic FastLinQ 4xxxx Ethernet Driver qede\n");
 
 	qede_forced_speed_maps_init();
 
@@ -644,7 +640,7 @@ static const struct net_device_ops qede_netdev_ops = {
 	.ndo_set_mac_address	= qede_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= qede_change_mtu,
-	.ndo_do_ioctl		= qede_ioctl,
+	.ndo_eth_ioctl		= qede_ioctl,
 	.ndo_tx_timeout		= qede_tx_timeout,
 #ifdef CONFIG_QED_SRIOV
 	.ndo_set_vf_mac		= qede_set_vf_mac,
@@ -1157,10 +1153,6 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 	/* Start the Slowpath-process */
 	memset(&sp_params, 0, sizeof(sp_params));
 	sp_params.int_mode = QED_INT_MODE_MSIX;
-	sp_params.drv_major = QEDE_MAJOR_VERSION;
-	sp_params.drv_minor = QEDE_MINOR_VERSION;
-	sp_params.drv_rev = QEDE_REVISION_VERSION;
-	sp_params.drv_eng = QEDE_ENGINEERING_VERSION;
 	strlcpy(sp_params.name, "qede LAN", QED_DRV_VER_STR_SIZE);
 	rc = qed_ops->common->slowpath_start(cdev, &sp_params);
 	if (rc) {
@@ -1907,6 +1899,12 @@ static int qede_req_msix_irqs(struct qede_dev *edev)
 				 &edev->fp_array[i]);
 		if (rc) {
 			DP_ERR(edev, "Request fp %d irq failed\n", i);
+#ifdef CONFIG_RFS_ACCEL
+			if (edev->ndev->rx_cpu_rmap)
+				free_irq_cpu_rmap(edev->ndev->rx_cpu_rmap);
+
+			edev->ndev->rx_cpu_rmap = NULL;
+#endif
 			qede_sync_free_irqs(edev);
 			return rc;
 		}
@@ -2299,6 +2297,15 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
 
 		rc = qede_stop_queues(edev);
 		if (rc) {
+#ifdef CONFIG_RFS_ACCEL
+			if (edev->dev_info.common.b_arfs_capable) {
+				qede_poll_for_freeing_arfs_filters(edev);
+				if (edev->ndev->rx_cpu_rmap)
+					free_irq_cpu_rmap(edev->ndev->rx_cpu_rmap);
+
+				edev->ndev->rx_cpu_rmap = NULL;
+			}
+#endif
 			qede_sync_free_irqs(edev);
 			goto out;
 		}
@@ -2628,8 +2635,10 @@ static void qede_generic_hw_err_handler(struct qede_dev *edev)
 		  "Generic sleepable HW error handling started - err_flags 0x%lx\n",
 		  edev->err_flags);
 
-	if (edev->devlink)
+	if (edev->devlink) {
+		DP_NOTICE(edev, "Reporting fatal error to devlink\n");
 		edev->ops->common->report_fatal_error(edev->devlink, edev->last_err_type);
+	}
 
 	clear_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags);
 
@@ -2651,6 +2660,8 @@ static void qede_set_hw_err_flags(struct qede_dev *edev,
 	case QED_HW_ERR_FW_ASSERT:
 		set_bit(QEDE_ERR_ATTN_CLR_EN, &err_flags);
 		set_bit(QEDE_ERR_GET_DBG_INFO, &err_flags);
+		/* make this error as recoverable and start recovery*/
+		set_bit(QEDE_ERR_IS_RECOVERABLE, &err_flags);
 		break;
 
 	default:
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index d8f0863b3934..fc364b4ab6eb 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -1021,7 +1021,7 @@ clear_diag_irq:
 
 static void qlcnic_create_loopback_buff(unsigned char *data, u8 mac[])
 {
-	unsigned char random_data[] = {0xa8, 0x06, 0x45, 0x00};
+	static const unsigned char random_data[] = {0xa8, 0x06, 0x45, 0x00};
 
 	memset(data, 0x4e, QLCNIC_ILB_PKT_SIZE);
 
@@ -1527,7 +1527,9 @@ qlcnic_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
  * firmware coalescing to default.
  */
 static int qlcnic_set_intr_coalesce(struct net_device *netdev,
-			struct ethtool_coalesce *ethcoal)
+				    struct ethtool_coalesce *ethcoal,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	int err;
@@ -1551,7 +1553,9 @@ static int qlcnic_set_intr_coalesce(struct net_device *netdev,
 }
 
 static int qlcnic_get_intr_coalesce(struct net_device *netdev,
-			struct ethtool_coalesce *ethcoal)
+				    struct ethtool_coalesce *ethcoal,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c
index e6784023bce4..3d61a767a8a3 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c
@@ -94,10 +94,8 @@ void qlcnic_release_rx_buffers(struct qlcnic_adapter *adapter)
 			if (rx_buf->skb == NULL)
 				continue;
 
-			pci_unmap_single(adapter->pdev,
-					rx_buf->dma,
-					rds_ring->dma_size,
-					PCI_DMA_FROMDEVICE);
+			dma_unmap_single(&adapter->pdev->dev, rx_buf->dma,
+					 rds_ring->dma_size, DMA_FROM_DEVICE);
 
 			dev_kfree_skb_any(rx_buf->skb);
 		}
@@ -139,16 +137,16 @@ void qlcnic_release_tx_buffers(struct qlcnic_adapter *adapter,
 	for (i = 0; i < tx_ring->num_desc; i++) {
 		buffrag = cmd_buf->frag_array;
 		if (buffrag->dma) {
-			pci_unmap_single(adapter->pdev, buffrag->dma,
-					 buffrag->length, PCI_DMA_TODEVICE);
+			dma_unmap_single(&adapter->pdev->dev, buffrag->dma,
+					 buffrag->length, DMA_TO_DEVICE);
 			buffrag->dma = 0ULL;
 		}
 		for (j = 1; j < cmd_buf->frag_count; j++) {
 			buffrag++;
 			if (buffrag->dma) {
-				pci_unmap_page(adapter->pdev, buffrag->dma,
-					       buffrag->length,
-					       PCI_DMA_TODEVICE);
+				dma_unmap_page(&adapter->pdev->dev,
+					       buffrag->dma, buffrag->length,
+					       DMA_TO_DEVICE);
 				buffrag->dma = 0ULL;
 			}
 		}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index af4c516a9e7c..29cdcb2285b1 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -587,9 +587,9 @@ static int qlcnic_map_tx_skb(struct pci_dev *pdev, struct sk_buff *skb,
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	nf = &pbuf->frag_array[0];
 
-	map = pci_map_single(pdev, skb->data, skb_headlen(skb),
-			     PCI_DMA_TODEVICE);
-	if (pci_dma_mapping_error(pdev, map))
+	map = dma_map_single(&pdev->dev, skb->data, skb_headlen(skb),
+			     DMA_TO_DEVICE);
+	if (dma_mapping_error(&pdev->dev, map))
 		goto out_err;
 
 	nf->dma = map;
@@ -612,11 +612,11 @@ static int qlcnic_map_tx_skb(struct pci_dev *pdev, struct sk_buff *skb,
 unwind:
 	while (--i >= 0) {
 		nf = &pbuf->frag_array[i+1];
-		pci_unmap_page(pdev, nf->dma, nf->length, PCI_DMA_TODEVICE);
+		dma_unmap_page(&pdev->dev, nf->dma, nf->length, DMA_TO_DEVICE);
 	}
 
 	nf = &pbuf->frag_array[0];
-	pci_unmap_single(pdev, nf->dma, skb_headlen(skb), PCI_DMA_TODEVICE);
+	dma_unmap_single(&pdev->dev, nf->dma, skb_headlen(skb), DMA_TO_DEVICE);
 
 out_err:
 	return -ENOMEM;
@@ -630,11 +630,11 @@ static void qlcnic_unmap_buffers(struct pci_dev *pdev, struct sk_buff *skb,
 
 	for (i = 0; i < nr_frags; i++) {
 		nf = &pbuf->frag_array[i+1];
-		pci_unmap_page(pdev, nf->dma, nf->length, PCI_DMA_TODEVICE);
+		dma_unmap_page(&pdev->dev, nf->dma, nf->length, DMA_TO_DEVICE);
 	}
 
 	nf = &pbuf->frag_array[0];
-	pci_unmap_single(pdev, nf->dma, skb_headlen(skb), PCI_DMA_TODEVICE);
+	dma_unmap_single(&pdev->dev, nf->dma, skb_headlen(skb), DMA_TO_DEVICE);
 	pbuf->skb = NULL;
 }
 
@@ -825,10 +825,10 @@ static int qlcnic_alloc_rx_skb(struct qlcnic_adapter *adapter,
 	}
 
 	skb_reserve(skb, NET_IP_ALIGN);
-	dma = pci_map_single(pdev, skb->data,
-			     rds_ring->dma_size, PCI_DMA_FROMDEVICE);
+	dma = dma_map_single(&pdev->dev, skb->data, rds_ring->dma_size,
+			     DMA_FROM_DEVICE);
 
-	if (pci_dma_mapping_error(pdev, dma)) {
+	if (dma_mapping_error(&pdev->dev, dma)) {
 		adapter->stats.rx_dma_map_error++;
 		dev_kfree_skb_any(skb);
 		return -ENOMEM;
@@ -903,13 +903,13 @@ static int qlcnic_process_cmd_ring(struct qlcnic_adapter *adapter,
 		buffer = &tx_ring->cmd_buf_arr[sw_consumer];
 		if (buffer->skb) {
 			frag = &buffer->frag_array[0];
-			pci_unmap_single(pdev, frag->dma, frag->length,
-					 PCI_DMA_TODEVICE);
+			dma_unmap_single(&pdev->dev, frag->dma, frag->length,
+					 DMA_TO_DEVICE);
 			frag->dma = 0ULL;
 			for (i = 1; i < buffer->frag_count; i++) {
 				frag++;
-				pci_unmap_page(pdev, frag->dma, frag->length,
-					       PCI_DMA_TODEVICE);
+				dma_unmap_page(&pdev->dev, frag->dma,
+					       frag->length, DMA_TO_DEVICE);
 				frag->dma = 0ULL;
 			}
 			tx_ring->tx_stats.xmit_finished++;
@@ -1147,8 +1147,8 @@ static struct sk_buff *qlcnic_process_rxbuf(struct qlcnic_adapter *adapter,
 		return NULL;
 	}
 
-	pci_unmap_single(adapter->pdev, buffer->dma, ring->dma_size,
-			 PCI_DMA_FROMDEVICE);
+	dma_unmap_single(&adapter->pdev->dev, buffer->dma, ring->dma_size,
+			 DMA_FROM_DEVICE);
 
 	skb = buffer->skb;
 	if (likely((adapter->netdev->features & NETIF_F_RXCSUM) &&
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index a4fa507903ee..75960a29f80e 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -2343,11 +2343,9 @@ qlcnic_setup_netdev(struct qlcnic_adapter *adapter, struct net_device *netdev,
 
 static int qlcnic_set_dma_mask(struct pci_dev *pdev, int *pci_using_dac)
 {
-	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) &&
-			!pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)))
+	if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)))
 		*pci_using_dac = 1;
-	else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) &&
-			!pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)))
+	else if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)))
 		*pci_using_dac = 0;
 	else {
 		dev_err(&pdev->dev, "Unable to set DMA mask, aborting\n");
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index ad655f0a4965..9015a38eaced 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -377,7 +377,7 @@ static const struct net_device_ops emac_netdev_ops = {
 	.ndo_start_xmit		= emac_start_xmit,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_change_mtu		= emac_change_mtu,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_tx_timeout		= emac_tx_timeout,
 	.ndo_get_stats64	= emac_get_stats64,
 	.ndo_set_features       = emac_set_features,
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index b64c254e00ba..8427fe1b8fd1 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -434,7 +434,7 @@ qcaspi_receive(struct qcaspi *qca)
 				skb_put(qca->rx_skb, retcode);
 				qca->rx_skb->protocol = eth_type_trans(
 					qca->rx_skb, qca->rx_skb->dev);
-				qca->rx_skb->ip_summed = CHECKSUM_UNNECESSARY;
+				skb_checksum_none_assert(qca->rx_skb);
 				netif_rx_ni(qca->rx_skb);
 				qca->rx_skb = netdev_alloc_skb_ip_align(net_dev,
 					net_dev->mtu + VLAN_ETH_HLEN);
diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c
index bcdeca7b3366..ce3f7ce31adc 100644
--- a/drivers/net/ethernet/qualcomm/qca_uart.c
+++ b/drivers/net/ethernet/qualcomm/qca_uart.c
@@ -107,7 +107,7 @@ qca_tty_receive(struct serdev_device *serdev, const unsigned char *data,
 			skb_put(qca->rx_skb, retcode);
 			qca->rx_skb->protocol = eth_type_trans(
 						qca->rx_skb, qca->rx_skb->dev);
-			qca->rx_skb->ip_summed = CHECKSUM_UNNECESSARY;
+			skb_checksum_none_assert(qca->rx_skb);
 			netif_rx_ni(qca->rx_skb);
 			qca->rx_skb = netdev_alloc_skb_ip_align(netdev,
 								netdev->mtu +
diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c
index 47e9998b62f0..4b2eca5e08e2 100644
--- a/drivers/net/ethernet/rdc/r6040.c
+++ b/drivers/net/ethernet/rdc/r6040.c
@@ -954,7 +954,7 @@ static const struct net_device_ops r6040_netdev_ops = {
 	.ndo_set_rx_mode	= r6040_multicast_list,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
-	.ndo_do_ioctl		= phy_do_ioctl,
+	.ndo_eth_ioctl		= phy_do_ioctl,
 	.ndo_tx_timeout		= r6040_tx_timeout,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= r6040_poll_controller,
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index 9677e257e9a1..2b84b4565e64 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -514,7 +514,7 @@ static int cp_rx_poll(struct napi_struct *napi, int budget)
 		}
 
 		new_mapping = dma_map_single(&cp->pdev->dev, new_skb->data, buflen,
-					 PCI_DMA_FROMDEVICE);
+					 DMA_FROM_DEVICE);
 		if (dma_mapping_error(&cp->pdev->dev, new_mapping)) {
 			dev->stats.rx_dropped++;
 			kfree_skb(new_skb);
@@ -522,7 +522,7 @@ static int cp_rx_poll(struct napi_struct *napi, int budget)
 		}
 
 		dma_unmap_single(&cp->pdev->dev, mapping,
-				 buflen, PCI_DMA_FROMDEVICE);
+				 buflen, DMA_FROM_DEVICE);
 
 		/* Handle checksum offloading for incoming packets. */
 		if (cp_rx_csum_ok(status))
@@ -666,7 +666,7 @@ static void cp_tx (struct cp_private *cp)
 
 		dma_unmap_single(&cp->pdev->dev, le64_to_cpu(txd->addr),
 				 cp->tx_opts[tx_tail] & 0xffff,
-				 PCI_DMA_TODEVICE);
+				 DMA_TO_DEVICE);
 
 		if (status & LastFrag) {
 			if (status & (TxError | TxFIFOUnder)) {
@@ -724,7 +724,7 @@ static void unwind_tx_frag_mapping(struct cp_private *cp, struct sk_buff *skb,
 		txd = &cp->tx_ring[index];
 		this_frag = &skb_shinfo(skb)->frags[frag];
 		dma_unmap_single(&cp->pdev->dev, le64_to_cpu(txd->addr),
-				 skb_frag_size(this_frag), PCI_DMA_TODEVICE);
+				 skb_frag_size(this_frag), DMA_TO_DEVICE);
 	}
 }
 
@@ -781,7 +781,7 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 		dma_addr_t mapping;
 
 		len = skb->len;
-		mapping = dma_map_single(&cp->pdev->dev, skb->data, len, PCI_DMA_TODEVICE);
+		mapping = dma_map_single(&cp->pdev->dev, skb->data, len, DMA_TO_DEVICE);
 		if (dma_mapping_error(&cp->pdev->dev, mapping))
 			goto out_dma_error;
 
@@ -810,7 +810,7 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 		first_eor = eor;
 		first_len = skb_headlen(skb);
 		first_mapping = dma_map_single(&cp->pdev->dev, skb->data,
-					       first_len, PCI_DMA_TODEVICE);
+					       first_len, DMA_TO_DEVICE);
 		if (dma_mapping_error(&cp->pdev->dev, first_mapping))
 			goto out_dma_error;
 
@@ -826,7 +826,7 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 			len = skb_frag_size(this_frag);
 			mapping = dma_map_single(&cp->pdev->dev,
 						 skb_frag_address(this_frag),
-						 len, PCI_DMA_TODEVICE);
+						 len, DMA_TO_DEVICE);
 			if (dma_mapping_error(&cp->pdev->dev, mapping)) {
 				unwind_tx_frag_mapping(cp, skb, first_entry, entry);
 				goto out_dma_error;
@@ -1069,7 +1069,7 @@ static int cp_refill_rx(struct cp_private *cp)
 			goto err_out;
 
 		mapping = dma_map_single(&cp->pdev->dev, skb->data,
-					 cp->rx_buf_sz, PCI_DMA_FROMDEVICE);
+					 cp->rx_buf_sz, DMA_FROM_DEVICE);
 		if (dma_mapping_error(&cp->pdev->dev, mapping)) {
 			kfree_skb(skb);
 			goto err_out;
@@ -1139,7 +1139,7 @@ static void cp_clean_rings (struct cp_private *cp)
 		if (cp->rx_skb[i]) {
 			desc = cp->rx_ring + i;
 			dma_unmap_single(&cp->pdev->dev,le64_to_cpu(desc->addr),
-					 cp->rx_buf_sz, PCI_DMA_FROMDEVICE);
+					 cp->rx_buf_sz, DMA_FROM_DEVICE);
 			dev_kfree_skb_any(cp->rx_skb[i]);
 		}
 	}
@@ -1151,7 +1151,7 @@ static void cp_clean_rings (struct cp_private *cp)
 			desc = cp->tx_ring + i;
 			dma_unmap_single(&cp->pdev->dev,le64_to_cpu(desc->addr),
 					 le32_to_cpu(desc->opts1) & 0xffff,
-					 PCI_DMA_TODEVICE);
+					 DMA_TO_DEVICE);
 			if (le32_to_cpu(desc->opts1) & LastFrag)
 				dev_kfree_skb_any(skb);
 			cp->dev->stats.tx_dropped++;
@@ -1869,7 +1869,7 @@ static const struct net_device_ops cp_netdev_ops = {
 	.ndo_set_mac_address 	= cp_set_mac_address,
 	.ndo_set_rx_mode	= cp_set_rx_mode,
 	.ndo_get_stats		= cp_get_stats,
-	.ndo_do_ioctl		= cp_ioctl,
+	.ndo_eth_ioctl		= cp_ioctl,
 	.ndo_start_xmit		= cp_start_xmit,
 	.ndo_tx_timeout		= cp_tx_timeout,
 	.ndo_set_features	= cp_set_features,
@@ -1945,24 +1945,17 @@ static int cp_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* Configure DMA attributes. */
 	if ((sizeof(dma_addr_t) > 4) &&
-	    !pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) &&
-	    !pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+	    !dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
 		pci_using_dac = 1;
 	} else {
 		pci_using_dac = 0;
 
-		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 		if (rc) {
 			dev_err(&pdev->dev,
 				"No usable DMA configuration, aborting\n");
 			goto err_out_res;
 		}
-		rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (rc) {
-			dev_err(&pdev->dev,
-				"No usable consistent DMA configuration, aborting\n");
-			goto err_out_res;
-		}
 	}
 
 	cp->cpcmd = (pci_using_dac ? PCIDAC : 0) |
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index f0608f050050..2e6923cc653e 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -932,7 +932,7 @@ static const struct net_device_ops rtl8139_netdev_ops = {
 	.ndo_set_mac_address 	= rtl8139_set_mac_address,
 	.ndo_start_xmit		= rtl8139_start_xmit,
 	.ndo_set_rx_mode	= rtl8139_set_rx_mode,
-	.ndo_do_ioctl		= netdev_ioctl,
+	.ndo_eth_ioctl		= netdev_ioctl,
 	.ndo_tx_timeout		= rtl8139_tx_timeout,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= rtl8139_poll_controller,
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 4d8e337f5085..46a6ff9a782d 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1749,7 +1749,10 @@ rtl_coalesce_info(struct rtl8169_private *tp)
 	return ERR_PTR(-ELNRNG);
 }
 
-static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
+static int rtl_get_coalesce(struct net_device *dev,
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	const struct rtl_coalesce_info *ci;
@@ -1807,7 +1810,10 @@ static int rtl_coalesce_choose_scale(struct rtl8169_private *tp, u32 usec,
 	return -ERANGE;
 }
 
-static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
+static int rtl_set_coalesce(struct net_device *dev,
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	u32 tx_fr = ec->tx_max_coalesced_frames;
@@ -2598,7 +2604,7 @@ static u32 rtl_csi_read(struct rtl8169_private *tp, int addr)
 		RTL_R32(tp, CSIDR) : ~0;
 }
 
-static void rtl_csi_access_enable(struct rtl8169_private *tp, u8 val)
+static void rtl_set_aspm_entry_latency(struct rtl8169_private *tp, u8 val)
 {
 	struct pci_dev *pdev = tp->pci_dev;
 	u32 csi;
@@ -2606,6 +2612,8 @@ static void rtl_csi_access_enable(struct rtl8169_private *tp, u8 val)
 	/* According to Realtek the value at config space address 0x070f
 	 * controls the L0s/L1 entrance latency. We try standard ECAM access
 	 * first and if it fails fall back to CSI.
+	 * bit 0..2: L0: 0 = 1us, 1 = 2us .. 6 = 7us, 7 = 7us (no typo)
+	 * bit 3..5: L1: 0 = 1us, 1 = 2us .. 6 = 64us, 7 = 64us
 	 */
 	if (pdev->cfg_size > 0x070f &&
 	    pci_write_config_byte(pdev, 0x070f, val) == PCIBIOS_SUCCESSFUL)
@@ -2619,7 +2627,8 @@ static void rtl_csi_access_enable(struct rtl8169_private *tp, u8 val)
 
 static void rtl_set_def_aspm_entry_latency(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable(tp, 0x27);
+	/* L0 7us, L1 16us */
+	rtl_set_aspm_entry_latency(tp, 0x27);
 }
 
 struct ephy_info {
@@ -2660,6 +2669,34 @@ static void rtl_pcie_state_l2l3_disable(struct rtl8169_private *tp)
 	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Rdy_to_L23);
 }
 
+static void rtl_enable_exit_l1(struct rtl8169_private *tp)
+{
+	/* Bits control which events trigger ASPM L1 exit:
+	 * Bit 12: rxdv
+	 * Bit 11: ltr_msg
+	 * Bit 10: txdma_poll
+	 * Bit  9: xadm
+	 * Bit  8: pktavi
+	 * Bit  7: txpla
+	 */
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_36:
+		rtl_eri_set_bits(tp, 0xd4, 0x1f00);
+		break;
+	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_53:
+		rtl_eri_set_bits(tp, 0xd4, 0x1f80);
+		break;
+	case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_63:
+		r8168_mac_ocp_modify(tp, 0xc0ac, 0, 0x1f80);
+		break;
+	default:
+		break;
+	}
+}
+
 static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 {
 	/* Don't enable ASPM in the chip if OS can't control ASPM */
@@ -2848,7 +2885,6 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
 	rtl_eri_write(tp, 0xb8, ERIAR_MASK_1111, 0x0000);
 	rtl_set_fifo_size(tp, 0x10, 0x10, 0x02, 0x06);
-	rtl_eri_set_bits(tp, 0x0d4, 0x1f00);
 	rtl_eri_set_bits(tp, 0x1d0, BIT(1));
 	rtl_reset_packet_filter(tp);
 	rtl_eri_set_bits(tp, 0x1b0, BIT(4));
@@ -2905,8 +2941,6 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
 	rtl_hw_start_8168f(tp);
 
 	rtl_ephy_init(tp, e_info_8168f_1);
-
-	rtl_eri_set_bits(tp, 0x0d4, 0x1f00);
 }
 
 static void rtl_hw_start_8411(struct rtl8169_private *tp)
@@ -2923,8 +2957,6 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp)
 	rtl_pcie_state_l2l3_disable(tp);
 
 	rtl_ephy_init(tp, e_info_8168f_1);
-
-	rtl_eri_set_bits(tp, 0x0d4, 0x0c00);
 }
 
 static void rtl_hw_start_8168g(struct rtl8169_private *tp)
@@ -2941,7 +2973,6 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp)
 
 	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
 	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
-	rtl_eri_set_bits(tp, 0x0d4, 0x1f80);
 
 	rtl8168_config_eee_mac(tp);
 
@@ -3172,7 +3203,6 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 
 	rtl_reset_packet_filter(tp);
 
-	rtl_eri_set_bits(tp, 0xd4, 0x1f00);
 	rtl_eri_set_bits(tp, 0xdc, 0x001c);
 
 	rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87);
@@ -3226,8 +3256,6 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp)
 
 	rtl_reset_packet_filter(tp);
 
-	rtl_eri_set_bits(tp, 0xd4, 0x1f80);
-
 	rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87);
 
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) & ~RXDV_GATED_EN);
@@ -3329,7 +3357,7 @@ static void rtl_hw_start_8117(struct rtl8169_private *tp)
 
 	rtl_reset_packet_filter(tp);
 
-	rtl_eri_set_bits(tp, 0xd4, 0x1f90);
+	rtl_eri_set_bits(tp, 0xd4, 0x0010);
 
 	rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87);
 
@@ -3502,8 +3530,8 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp)
 	RTL_W8(tp, MCU, RTL_R8(tp, MCU) | EN_NDP | EN_OOB_RESET);
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN);
 
-	/* The default value is 0x13. Change it to 0x2f */
-	rtl_csi_access_enable(tp, 0x2f);
+	/* L0 7us, L1 32us - needed to avoid issues with link-up detection */
+	rtl_set_aspm_entry_latency(tp, 0x2f);
 
 	rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000);
 
@@ -3560,7 +3588,6 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp)
 	r8168_mac_ocp_modify(tp, 0xea1c, 0x0003, 0x0001);
 	r8168_mac_ocp_modify(tp, 0xe0c0, 0x4f0f, 0x4403);
 	r8168_mac_ocp_modify(tp, 0xe052, 0x0080, 0x0068);
-	r8168_mac_ocp_modify(tp, 0xc0ac, 0x0080, 0x1f00);
 	r8168_mac_ocp_modify(tp, 0xd430, 0x0fff, 0x047f);
 
 	r8168_mac_ocp_modify(tp, 0xea1c, 0x0004, 0x0000);
@@ -3783,6 +3810,7 @@ static void rtl_hw_start(struct  rtl8169_private *tp)
 	else
 		rtl_hw_start_8168(tp);
 
+	rtl_enable_exit_l1(tp);
 	rtl_set_rx_max_size(tp);
 	rtl_set_rx_tx_desc_registers(tp);
 	rtl_lock_config_regs(tp);
@@ -4983,7 +5011,7 @@ static const struct net_device_ops rtl_netdev_ops = {
 	.ndo_fix_features	= rtl8169_fix_features,
 	.ndo_set_features	= rtl8169_set_features,
 	.ndo_set_mac_address	= rtl_set_mac_address,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_set_rx_mode	= rtl_set_rx_mode,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= rtl8169_netpoll,
@@ -5278,11 +5306,10 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		return rc;
 
-	/* Disable ASPM completely as that cause random device stop working
+	/* Disable ASPM L1 as that cause random device stop working
 	 * problems as well as full system hangs for some PCIe devices users.
 	 */
-	rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S |
-					  PCIE_LINK_STATE_L1);
+	rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1);
 	tp->aspm_manageable = !rc;
 
 	/* enable device (incl. PCI PM wakeup and hotplug setup) */
diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig
index 5a2a4af31812..8008b2f45934 100644
--- a/drivers/net/ethernet/renesas/Kconfig
+++ b/drivers/net/ethernet/renesas/Kconfig
@@ -32,11 +32,11 @@ config SH_ETH
 config RAVB
 	tristate "Renesas Ethernet AVB support"
 	depends on ARCH_RENESAS || COMPILE_TEST
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select CRC32
 	select MII
 	select MDIO_BITBANG
 	select PHYLIB
-	imply PTP_1588_CLOCK
 	help
 	  Renesas Ethernet AVB device driver.
 	  This driver supports the following SoCs:
diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h
index 80e62ca2e3d3..47c5377e4f42 100644
--- a/drivers/net/ethernet/renesas/ravb.h
+++ b/drivers/net/ethernet/renesas/ravb.h
@@ -956,10 +956,6 @@ enum RAVB_QUEUE {
 
 #define RX_BUF_SZ	(2048 - ETH_FCS_LEN + sizeof(__sum16))
 
-/* TX descriptors per packet */
-#define NUM_TX_DESC_GEN2	2
-#define NUM_TX_DESC_GEN3	1
-
 struct ravb_tstamp_skb {
 	struct list_head list;
 	struct sk_buff *skb;
@@ -983,9 +979,29 @@ struct ravb_ptp {
 	struct ravb_ptp_perout perout[N_PER_OUT];
 };
 
-enum ravb_chip_id {
-	RCAR_GEN2,
-	RCAR_GEN3,
+struct ravb_hw_info {
+	void (*rx_ring_free)(struct net_device *ndev, int q);
+	void (*rx_ring_format)(struct net_device *ndev, int q);
+	void *(*alloc_rx_desc)(struct net_device *ndev, int q);
+	bool (*receive)(struct net_device *ndev, int *quota, int q);
+	void (*set_rate)(struct net_device *ndev);
+	int (*set_rx_csum_feature)(struct net_device *ndev, netdev_features_t features);
+	void (*dmac_init)(struct net_device *ndev);
+	void (*emac_init)(struct net_device *ndev);
+	const char (*gstrings_stats)[ETH_GSTRING_LEN];
+	size_t gstrings_size;
+	netdev_features_t net_hw_features;
+	netdev_features_t net_features;
+	int stats_len;
+	size_t max_rx_len;
+	unsigned aligned_tx: 1;
+
+	/* hardware features */
+	unsigned internal_delay:1;	/* AVB-DMAC has internal delays */
+	unsigned tx_counters:1;		/* E-MAC has TX counters */
+	unsigned multi_irqs:1;		/* AVB-DMAC and E-MAC has multiple irqs */
+	unsigned no_ptp_cfg_active:1;	/* AVB-DMAC does not support gPTP active in config mode */
+	unsigned ptp_cfg_active:1;	/* AVB-DMAC has gPTP support active in config mode */
 };
 
 struct ravb_private {
@@ -1029,7 +1045,6 @@ struct ravb_private {
 	int msg_enable;
 	int speed;
 	int emac_irq;
-	enum ravb_chip_id chip_id;
 	int rx_irqs[NUM_RX_QUEUE];
 	int tx_irqs[NUM_TX_QUEUE];
 
@@ -1039,7 +1054,10 @@ struct ravb_private {
 	unsigned rxcidm:1;		/* RX Clock Internal Delay Mode */
 	unsigned txcidm:1;		/* TX Clock Internal Delay Mode */
 	unsigned rgmii_override:1;	/* Deprecated rgmii-*id behavior */
-	int num_tx_desc;		/* TX descriptors per packet */
+	unsigned int num_tx_desc;	/* TX descriptors per packet */
+
+	const struct ravb_hw_info *info;
+	struct reset_control *rstc;
 };
 
 static inline u32 ravb_read(struct net_device *ndev, enum ravb_reg reg)
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 805397088850..0f85f2d97b18 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/sys_soc.h>
+#include <linux/reset.h>
 
 #include <asm/div64.h>
 
@@ -177,10 +178,10 @@ static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 	struct net_device_stats *stats = &priv->stats[q];
-	int num_tx_desc = priv->num_tx_desc;
+	unsigned int num_tx_desc = priv->num_tx_desc;
 	struct ravb_tx_desc *desc;
+	unsigned int entry;
 	int free_num = 0;
-	int entry;
 	u32 size;
 
 	for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) {
@@ -216,31 +217,42 @@ static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only)
 	return free_num;
 }
 
-/* Free skb's and DMA buffers for Ethernet AVB */
-static void ravb_ring_free(struct net_device *ndev, int q)
+static void ravb_rx_ring_free(struct net_device *ndev, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
-	int num_tx_desc = priv->num_tx_desc;
-	int ring_size;
-	int i;
+	unsigned int ring_size;
+	unsigned int i;
+
+	if (!priv->rx_ring[q])
+		return;
 
-	if (priv->rx_ring[q]) {
-		for (i = 0; i < priv->num_rx_ring[q]; i++) {
-			struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i];
+	for (i = 0; i < priv->num_rx_ring[q]; i++) {
+		struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i];
 
-			if (!dma_mapping_error(ndev->dev.parent,
-					       le32_to_cpu(desc->dptr)))
-				dma_unmap_single(ndev->dev.parent,
-						 le32_to_cpu(desc->dptr),
-						 RX_BUF_SZ,
-						 DMA_FROM_DEVICE);
-		}
-		ring_size = sizeof(struct ravb_ex_rx_desc) *
-			    (priv->num_rx_ring[q] + 1);
-		dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q],
-				  priv->rx_desc_dma[q]);
-		priv->rx_ring[q] = NULL;
+		if (!dma_mapping_error(ndev->dev.parent,
+				       le32_to_cpu(desc->dptr)))
+			dma_unmap_single(ndev->dev.parent,
+					 le32_to_cpu(desc->dptr),
+					 RX_BUF_SZ,
+					 DMA_FROM_DEVICE);
 	}
+	ring_size = sizeof(struct ravb_ex_rx_desc) *
+		    (priv->num_rx_ring[q] + 1);
+	dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q],
+			  priv->rx_desc_dma[q]);
+	priv->rx_ring[q] = NULL;
+}
+
+/* Free skb's and DMA buffers for Ethernet AVB */
+static void ravb_ring_free(struct net_device *ndev, int q)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
+	unsigned int num_tx_desc = priv->num_tx_desc;
+	unsigned int ring_size;
+	unsigned int i;
+
+	info->rx_ring_free(ndev, q);
 
 	if (priv->tx_ring[q]) {
 		ravb_tx_free(ndev, q, false);
@@ -271,24 +283,13 @@ static void ravb_ring_free(struct net_device *ndev, int q)
 	priv->tx_skb[q] = NULL;
 }
 
-/* Format skb and descriptor buffer for Ethernet AVB */
-static void ravb_ring_format(struct net_device *ndev, int q)
+static void ravb_rx_ring_format(struct net_device *ndev, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
-	int num_tx_desc = priv->num_tx_desc;
 	struct ravb_ex_rx_desc *rx_desc;
-	struct ravb_tx_desc *tx_desc;
-	struct ravb_desc *desc;
-	int rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q];
-	int tx_ring_size = sizeof(*tx_desc) * priv->num_tx_ring[q] *
-			   num_tx_desc;
+	unsigned int rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q];
 	dma_addr_t dma_addr;
-	int i;
-
-	priv->cur_rx[q] = 0;
-	priv->cur_tx[q] = 0;
-	priv->dirty_rx[q] = 0;
-	priv->dirty_tx[q] = 0;
+	unsigned int i;
 
 	memset(priv->rx_ring[q], 0, rx_ring_size);
 	/* Build RX ring buffer */
@@ -310,6 +311,26 @@ static void ravb_ring_format(struct net_device *ndev, int q)
 	rx_desc = &priv->rx_ring[q][i];
 	rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]);
 	rx_desc->die_dt = DT_LINKFIX; /* type */
+}
+
+/* Format skb and descriptor buffer for Ethernet AVB */
+static void ravb_ring_format(struct net_device *ndev, int q)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
+	unsigned int num_tx_desc = priv->num_tx_desc;
+	struct ravb_tx_desc *tx_desc;
+	struct ravb_desc *desc;
+	unsigned int tx_ring_size = sizeof(*tx_desc) * priv->num_tx_ring[q] *
+				    num_tx_desc;
+	unsigned int i;
+
+	priv->cur_rx[q] = 0;
+	priv->cur_tx[q] = 0;
+	priv->dirty_rx[q] = 0;
+	priv->dirty_tx[q] = 0;
+
+	info->rx_ring_format(ndev, q);
 
 	memset(priv->tx_ring[q], 0, tx_ring_size);
 	/* Build TX ring buffer */
@@ -335,14 +356,28 @@ static void ravb_ring_format(struct net_device *ndev, int q)
 	desc->dptr = cpu_to_le32((u32)priv->tx_desc_dma[q]);
 }
 
+static void *ravb_alloc_rx_desc(struct net_device *ndev, int q)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	unsigned int ring_size;
+
+	ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1);
+
+	priv->rx_ring[q] = dma_alloc_coherent(ndev->dev.parent, ring_size,
+					      &priv->rx_desc_dma[q],
+					      GFP_KERNEL);
+	return priv->rx_ring[q];
+}
+
 /* Init skb and descriptor buffer for Ethernet AVB */
 static int ravb_ring_init(struct net_device *ndev, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
-	int num_tx_desc = priv->num_tx_desc;
+	const struct ravb_hw_info *info = priv->info;
+	unsigned int num_tx_desc = priv->num_tx_desc;
+	unsigned int ring_size;
 	struct sk_buff *skb;
-	int ring_size;
-	int i;
+	unsigned int i;
 
 	/* Allocate RX and TX skb rings */
 	priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q],
@@ -353,7 +388,7 @@ static int ravb_ring_init(struct net_device *ndev, int q)
 		goto error;
 
 	for (i = 0; i < priv->num_rx_ring[q]; i++) {
-		skb = netdev_alloc_skb(ndev, RX_BUF_SZ + RAVB_ALIGN - 1);
+		skb = netdev_alloc_skb(ndev, info->max_rx_len);
 		if (!skb)
 			goto error;
 		ravb_set_buffer_align(skb);
@@ -369,11 +404,7 @@ static int ravb_ring_init(struct net_device *ndev, int q)
 	}
 
 	/* Allocate all RX descriptors. */
-	ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1);
-	priv->rx_ring[q] = dma_alloc_coherent(ndev->dev.parent, ring_size,
-					      &priv->rx_desc_dma[q],
-					      GFP_KERNEL);
-	if (!priv->rx_ring[q])
+	if (!info->alloc_rx_desc(ndev, q))
 		goto error;
 
 	priv->dirty_rx[q] = 0;
@@ -395,8 +426,7 @@ error:
 	return -ENOMEM;
 }
 
-/* E-MAC init function */
-static void ravb_emac_init(struct net_device *ndev)
+static void ravb_rcar_emac_init(struct net_device *ndev)
 {
 	/* Receive frame limit set register */
 	ravb_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN, RFLR);
@@ -422,29 +452,19 @@ static void ravb_emac_init(struct net_device *ndev)
 	ravb_write(ndev, ECSIPR_ICDIP | ECSIPR_MPDIP | ECSIPR_LCHNGIP, ECSIPR);
 }
 
-/* Device init function for Ethernet AVB */
-static int ravb_dmac_init(struct net_device *ndev)
+/* E-MAC init function */
+static void ravb_emac_init(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
-	int error;
+	const struct ravb_hw_info *info = priv->info;
 
-	/* Set CONFIG mode */
-	error = ravb_config(ndev);
-	if (error)
-		return error;
-
-	error = ravb_ring_init(ndev, RAVB_BE);
-	if (error)
-		return error;
-	error = ravb_ring_init(ndev, RAVB_NC);
-	if (error) {
-		ravb_ring_free(ndev, RAVB_BE);
-		return error;
-	}
+	info->emac_init(ndev);
+}
 
-	/* Descriptor format */
-	ravb_ring_format(ndev, RAVB_BE);
-	ravb_ring_format(ndev, RAVB_NC);
+static void ravb_rcar_dmac_init(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 
 	/* Set AVB RX */
 	ravb_write(ndev,
@@ -457,7 +477,7 @@ static int ravb_dmac_init(struct net_device *ndev)
 	ravb_write(ndev, TCCR_TFEN, TCCR);
 
 	/* Interrupt init: */
-	if (priv->chip_id == RCAR_GEN3) {
+	if (info->multi_irqs) {
 		/* Clear DIL.DPLx */
 		ravb_write(ndev, 0, DIL);
 		/* Set queue specific interrupt */
@@ -471,6 +491,34 @@ static int ravb_dmac_init(struct net_device *ndev)
 	ravb_write(ndev, RIC2_QFE0 | RIC2_QFE1 | RIC2_RFFE, RIC2);
 	/* Frame transmitted, timestamp FIFO updated */
 	ravb_write(ndev, TIC_FTE0 | TIC_FTE1 | TIC_TFUE, TIC);
+}
+
+/* Device init function for Ethernet AVB */
+static int ravb_dmac_init(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
+	int error;
+
+	/* Set CONFIG mode */
+	error = ravb_config(ndev);
+	if (error)
+		return error;
+
+	error = ravb_ring_init(ndev, RAVB_BE);
+	if (error)
+		return error;
+	error = ravb_ring_init(ndev, RAVB_NC);
+	if (error) {
+		ravb_ring_free(ndev, RAVB_BE);
+		return error;
+	}
+
+	/* Descriptor format */
+	ravb_ring_format(ndev, RAVB_BE);
+	ravb_ring_format(ndev, RAVB_NC);
+
+	info->dmac_init(ndev);
 
 	/* Setting the control will start the AVB-DMAC process. */
 	ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_OPERATION);
@@ -531,10 +579,10 @@ static void ravb_rx_csum(struct sk_buff *skb)
 	skb_trim(skb, skb->len - sizeof(__sum16));
 }
 
-/* Packet receive function for Ethernet AVB */
-static bool ravb_rx(struct net_device *ndev, int *quota, int q)
+static bool ravb_rcar_rx(struct net_device *ndev, int *quota, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 	int entry = priv->cur_rx[q] % priv->num_rx_ring[q];
 	int boguscnt = (priv->dirty_rx[q] + priv->num_rx_ring[q]) -
 			priv->cur_rx[q];
@@ -619,9 +667,7 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q)
 		desc->ds_cc = cpu_to_le16(RX_BUF_SZ);
 
 		if (!priv->rx_skb[q][entry]) {
-			skb = netdev_alloc_skb(ndev,
-					       RX_BUF_SZ +
-					       RAVB_ALIGN - 1);
+			skb = netdev_alloc_skb(ndev, info->max_rx_len);
 			if (!skb)
 				break;	/* Better luck next round. */
 			ravb_set_buffer_align(skb);
@@ -647,6 +693,15 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q)
 	return boguscnt <= 0;
 }
 
+/* Packet receive function for Ethernet AVB */
+static bool ravb_rx(struct net_device *ndev, int *quota, int q)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
+
+	return info->receive(ndev, quota, q);
+}
+
 static void ravb_rcv_snd_disable(struct net_device *ndev)
 {
 	/* Disable TX and RX */
@@ -758,6 +813,7 @@ static void ravb_error_interrupt(struct net_device *ndev)
 static bool ravb_queue_interrupt(struct net_device *ndev, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 	u32 ris0 = ravb_read(ndev, RIS0);
 	u32 ric0 = ravb_read(ndev, RIC0);
 	u32 tis  = ravb_read(ndev, TIS);
@@ -766,7 +822,7 @@ static bool ravb_queue_interrupt(struct net_device *ndev, int q)
 	if (((ris0 & ric0) & BIT(q)) || ((tis  & tic)  & BIT(q))) {
 		if (napi_schedule_prep(&priv->napi[q])) {
 			/* Mask RX and TX interrupts */
-			if (priv->chip_id == RCAR_GEN2) {
+			if (!info->multi_irqs) {
 				ravb_write(ndev, ric0 & ~BIT(q), RIC0);
 				ravb_write(ndev, tic & ~BIT(q), TIC);
 			} else {
@@ -909,6 +965,7 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 {
 	struct net_device *ndev = napi->dev;
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 	unsigned long flags;
 	int q = napi - priv->napi;
 	int mask = BIT(q);
@@ -932,7 +989,7 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 
 	/* Re-enable RX/TX interrupts */
 	spin_lock_irqsave(&priv->lock, flags);
-	if (priv->chip_id == RCAR_GEN2) {
+	if (!info->multi_irqs) {
 		ravb_modify(ndev, RIC0, mask, mask);
 		ravb_modify(ndev, TIC,  mask, mask);
 	} else {
@@ -956,6 +1013,7 @@ out:
 static void ravb_adjust_link(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 	struct phy_device *phydev = ndev->phydev;
 	bool new_state = false;
 	unsigned long flags;
@@ -970,7 +1028,7 @@ static void ravb_adjust_link(struct net_device *ndev)
 		if (phydev->speed != priv->speed) {
 			new_state = true;
 			priv->speed = phydev->speed;
-			ravb_set_rate(ndev);
+			info->set_rate(ndev);
 		}
 		if (!priv->link) {
 			ravb_modify(ndev, ECMR, ECMR_TXF, 0);
@@ -1133,13 +1191,14 @@ static const char ravb_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"rx_queue_1_over_errors",
 };
 
-#define RAVB_STATS_LEN	ARRAY_SIZE(ravb_gstrings_stats)
-
 static int ravb_get_sset_count(struct net_device *netdev, int sset)
 {
+	struct ravb_private *priv = netdev_priv(netdev);
+	const struct ravb_hw_info *info = priv->info;
+
 	switch (sset) {
 	case ETH_SS_STATS:
-		return RAVB_STATS_LEN;
+		return info->stats_len;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1176,9 +1235,12 @@ static void ravb_get_ethtool_stats(struct net_device *ndev,
 
 static void ravb_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 {
+	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
+
 	switch (stringset) {
 	case ETH_SS_STATS:
-		memcpy(data, ravb_gstrings_stats, sizeof(ravb_gstrings_stats));
+		memcpy(data, info->gstrings_stats, info->gstrings_size);
 		break;
 	}
 }
@@ -1198,6 +1260,7 @@ static int ravb_set_ringparam(struct net_device *ndev,
 			      struct ethtool_ringparam *ring)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 	int error;
 
 	if (ring->tx_pending > BE_TX_RING_MAX ||
@@ -1211,7 +1274,7 @@ static int ravb_set_ringparam(struct net_device *ndev,
 	if (netif_running(ndev)) {
 		netif_device_detach(ndev);
 		/* Stop PTP Clock driver */
-		if (priv->chip_id == RCAR_GEN2)
+		if (info->no_ptp_cfg_active)
 			ravb_ptp_stop(ndev);
 		/* Wait for DMA stopping */
 		error = ravb_stop_dma(ndev);
@@ -1243,7 +1306,7 @@ static int ravb_set_ringparam(struct net_device *ndev,
 		ravb_emac_init(ndev);
 
 		/* Initialise PTP Clock driver */
-		if (priv->chip_id == RCAR_GEN2)
+		if (info->no_ptp_cfg_active)
 			ravb_ptp_init(ndev, priv->pdev);
 
 		netif_device_attach(ndev);
@@ -1334,6 +1397,7 @@ static inline int ravb_hook_irq(unsigned int irq, irq_handler_t handler,
 static int ravb_open(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 	struct platform_device *pdev = priv->pdev;
 	struct device *dev = &pdev->dev;
 	int error;
@@ -1341,7 +1405,7 @@ static int ravb_open(struct net_device *ndev)
 	napi_enable(&priv->napi[RAVB_BE]);
 	napi_enable(&priv->napi[RAVB_NC]);
 
-	if (priv->chip_id == RCAR_GEN2) {
+	if (!info->multi_irqs) {
 		error = request_irq(ndev->irq, ravb_interrupt, IRQF_SHARED,
 				    ndev->name, ndev);
 		if (error) {
@@ -1382,7 +1446,7 @@ static int ravb_open(struct net_device *ndev)
 	ravb_emac_init(ndev);
 
 	/* Initialise PTP Clock driver */
-	if (priv->chip_id == RCAR_GEN2)
+	if (info->no_ptp_cfg_active)
 		ravb_ptp_init(ndev, priv->pdev);
 
 	netif_tx_start_all_queues(ndev);
@@ -1396,10 +1460,10 @@ static int ravb_open(struct net_device *ndev)
 
 out_ptp_stop:
 	/* Stop PTP Clock driver */
-	if (priv->chip_id == RCAR_GEN2)
+	if (info->no_ptp_cfg_active)
 		ravb_ptp_stop(ndev);
 out_free_irq_nc_tx:
-	if (priv->chip_id == RCAR_GEN2)
+	if (!info->multi_irqs)
 		goto out_free_irq;
 	free_irq(priv->tx_irqs[RAVB_NC], ndev);
 out_free_irq_nc_rx:
@@ -1437,13 +1501,14 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 {
 	struct ravb_private *priv = container_of(work, struct ravb_private,
 						 work);
+	const struct ravb_hw_info *info = priv->info;
 	struct net_device *ndev = priv->ndev;
 	int error;
 
 	netif_tx_stop_all_queues(ndev);
 
 	/* Stop PTP Clock driver */
-	if (priv->chip_id == RCAR_GEN2)
+	if (info->no_ptp_cfg_active)
 		ravb_ptp_stop(ndev);
 
 	/* Wait for DMA stopping */
@@ -1478,7 +1543,7 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 
 out:
 	/* Initialise PTP Clock driver */
-	if (priv->chip_id == RCAR_GEN2)
+	if (info->no_ptp_cfg_active)
 		ravb_ptp_init(ndev, priv->pdev);
 
 	netif_tx_start_all_queues(ndev);
@@ -1488,7 +1553,7 @@ out:
 static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
-	int num_tx_desc = priv->num_tx_desc;
+	unsigned int num_tx_desc = priv->num_tx_desc;
 	u16 q = skb_get_queue_mapping(skb);
 	struct ravb_tstamp_skb *ts_skb;
 	struct ravb_tx_desc *desc;
@@ -1628,13 +1693,14 @@ static u16 ravb_select_queue(struct net_device *ndev, struct sk_buff *skb,
 static struct net_device_stats *ravb_get_stats(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 	struct net_device_stats *nstats, *stats0, *stats1;
 
 	nstats = &ndev->stats;
 	stats0 = &priv->stats[RAVB_BE];
 	stats1 = &priv->stats[RAVB_NC];
 
-	if (priv->chip_id == RCAR_GEN3) {
+	if (info->tx_counters) {
 		nstats->tx_dropped += ravb_read(ndev, TROCR);
 		ravb_write(ndev, 0, TROCR);	/* (write clear) */
 	}
@@ -1675,6 +1741,7 @@ static int ravb_close(struct net_device *ndev)
 {
 	struct device_node *np = ndev->dev.parent->of_node;
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 	struct ravb_tstamp_skb *ts_skb, *ts_skb2;
 
 	netif_tx_stop_all_queues(ndev);
@@ -1685,7 +1752,7 @@ static int ravb_close(struct net_device *ndev)
 	ravb_write(ndev, 0, TIC);
 
 	/* Stop PTP Clock driver */
-	if (priv->chip_id == RCAR_GEN2)
+	if (info->no_ptp_cfg_active)
 		ravb_ptp_stop(ndev);
 
 	/* Set the config mode to stop the AVB-DMAC's processes */
@@ -1708,7 +1775,7 @@ static int ravb_close(struct net_device *ndev)
 			of_phy_deregister_fixed_link(np);
 	}
 
-	if (priv->chip_id != RCAR_GEN2) {
+	if (info->multi_irqs) {
 		free_irq(priv->tx_irqs[RAVB_NC], ndev);
 		free_irq(priv->rx_irqs[RAVB_NC], ndev);
 		free_irq(priv->tx_irqs[RAVB_BE], ndev);
@@ -1851,8 +1918,8 @@ static void ravb_set_rx_csum(struct net_device *ndev, bool enable)
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
-static int ravb_set_features(struct net_device *ndev,
-			     netdev_features_t features)
+static int ravb_set_features_rx_csum(struct net_device *ndev,
+				     netdev_features_t features)
 {
 	netdev_features_t changed = ndev->features ^ features;
 
@@ -1864,6 +1931,15 @@ static int ravb_set_features(struct net_device *ndev,
 	return 0;
 }
 
+static int ravb_set_features(struct net_device *ndev,
+			     netdev_features_t features)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
+
+	return info->set_rx_csum_feature(ndev, features);
+}
+
 static const struct net_device_ops ravb_netdev_ops = {
 	.ndo_open		= ravb_open,
 	.ndo_stop		= ravb_close,
@@ -1872,7 +1948,7 @@ static const struct net_device_ops ravb_netdev_ops = {
 	.ndo_get_stats		= ravb_get_stats,
 	.ndo_set_rx_mode	= ravb_set_rx_mode,
 	.ndo_tx_timeout		= ravb_tx_timeout,
-	.ndo_do_ioctl		= ravb_do_ioctl,
+	.ndo_eth_ioctl		= ravb_do_ioctl,
 	.ndo_change_mtu		= ravb_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
@@ -1924,12 +2000,52 @@ static int ravb_mdio_release(struct ravb_private *priv)
 	return 0;
 }
 
+static const struct ravb_hw_info ravb_gen3_hw_info = {
+	.rx_ring_free = ravb_rx_ring_free,
+	.rx_ring_format = ravb_rx_ring_format,
+	.alloc_rx_desc = ravb_alloc_rx_desc,
+	.receive = ravb_rcar_rx,
+	.set_rate = ravb_set_rate,
+	.set_rx_csum_feature = ravb_set_features_rx_csum,
+	.dmac_init = ravb_rcar_dmac_init,
+	.emac_init = ravb_rcar_emac_init,
+	.gstrings_stats = ravb_gstrings_stats,
+	.gstrings_size = sizeof(ravb_gstrings_stats),
+	.net_hw_features = NETIF_F_RXCSUM,
+	.net_features = NETIF_F_RXCSUM,
+	.stats_len = ARRAY_SIZE(ravb_gstrings_stats),
+	.max_rx_len = RX_BUF_SZ + RAVB_ALIGN - 1,
+	.internal_delay = 1,
+	.tx_counters = 1,
+	.multi_irqs = 1,
+	.ptp_cfg_active = 1,
+};
+
+static const struct ravb_hw_info ravb_gen2_hw_info = {
+	.rx_ring_free = ravb_rx_ring_free,
+	.rx_ring_format = ravb_rx_ring_format,
+	.alloc_rx_desc = ravb_alloc_rx_desc,
+	.receive = ravb_rcar_rx,
+	.set_rate = ravb_set_rate,
+	.set_rx_csum_feature = ravb_set_features_rx_csum,
+	.dmac_init = ravb_rcar_dmac_init,
+	.emac_init = ravb_rcar_emac_init,
+	.gstrings_stats = ravb_gstrings_stats,
+	.gstrings_size = sizeof(ravb_gstrings_stats),
+	.net_hw_features = NETIF_F_RXCSUM,
+	.net_features = NETIF_F_RXCSUM,
+	.stats_len = ARRAY_SIZE(ravb_gstrings_stats),
+	.max_rx_len = RX_BUF_SZ + RAVB_ALIGN - 1,
+	.aligned_tx = 1,
+	.no_ptp_cfg_active = 1,
+};
+
 static const struct of_device_id ravb_match_table[] = {
-	{ .compatible = "renesas,etheravb-r8a7790", .data = (void *)RCAR_GEN2 },
-	{ .compatible = "renesas,etheravb-r8a7794", .data = (void *)RCAR_GEN2 },
-	{ .compatible = "renesas,etheravb-rcar-gen2", .data = (void *)RCAR_GEN2 },
-	{ .compatible = "renesas,etheravb-r8a7795", .data = (void *)RCAR_GEN3 },
-	{ .compatible = "renesas,etheravb-rcar-gen3", .data = (void *)RCAR_GEN3 },
+	{ .compatible = "renesas,etheravb-r8a7790", .data = &ravb_gen2_hw_info },
+	{ .compatible = "renesas,etheravb-r8a7794", .data = &ravb_gen2_hw_info },
+	{ .compatible = "renesas,etheravb-rcar-gen2", .data = &ravb_gen2_hw_info },
+	{ .compatible = "renesas,etheravb-r8a7795", .data = &ravb_gen3_hw_info },
+	{ .compatible = "renesas,etheravb-rcar-gen3", .data = &ravb_gen3_hw_info },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, ravb_match_table);
@@ -1962,8 +2078,9 @@ static int ravb_set_gti(struct net_device *ndev)
 static void ravb_set_config_mode(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 
-	if (priv->chip_id == RCAR_GEN2) {
+	if (info->no_ptp_cfg_active) {
 		ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG);
 		/* Set CSEL value */
 		ravb_modify(ndev, CCC, CCC_CSEL, CCC_CSEL_HPB);
@@ -1973,13 +2090,6 @@ static void ravb_set_config_mode(struct net_device *ndev)
 	}
 }
 
-static const struct soc_device_attribute ravb_delay_mode_quirk_match[] = {
-	{ .soc_id = "r8a774c0" },
-	{ .soc_id = "r8a77990" },
-	{ .soc_id = "r8a77995" },
-	{ /* sentinel */ }
-};
-
 /* Set tx and rx clock internal delay modes */
 static void ravb_parse_delay_mode(struct device_node *np, struct net_device *ndev)
 {
@@ -2010,12 +2120,8 @@ static void ravb_parse_delay_mode(struct device_node *np, struct net_device *nde
 
 	if (priv->phy_interface == PHY_INTERFACE_MODE_RGMII_ID ||
 	    priv->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID) {
-		if (!WARN(soc_device_match(ravb_delay_mode_quirk_match),
-			  "phy-mode %s requires TX clock internal delay mode which is not supported by this hardware revision. Please update device tree",
-			  phy_modes(priv->phy_interface))) {
-			priv->txcidm = 1;
-			priv->rgmii_override = 1;
-		}
+		priv->txcidm = 1;
+		priv->rgmii_override = 1;
 	}
 }
 
@@ -2034,8 +2140,9 @@ static void ravb_set_delay_mode(struct net_device *ndev)
 static int ravb_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
+	const struct ravb_hw_info *info;
+	struct reset_control *rstc;
 	struct ravb_private *priv;
-	enum ravb_chip_id chip_id;
 	struct net_device *ndev;
 	int error, irq, q;
 	struct resource *res;
@@ -2047,20 +2154,26 @@ static int ravb_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	rstc = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL);
+	if (IS_ERR(rstc))
+		return dev_err_probe(&pdev->dev, PTR_ERR(rstc),
+				     "failed to get cpg reset\n");
+
 	ndev = alloc_etherdev_mqs(sizeof(struct ravb_private),
 				  NUM_TX_QUEUE, NUM_RX_QUEUE);
 	if (!ndev)
 		return -ENOMEM;
 
-	ndev->features = NETIF_F_RXCSUM;
-	ndev->hw_features = NETIF_F_RXCSUM;
+	info = of_device_get_match_data(&pdev->dev);
 
+	ndev->features = info->net_features;
+	ndev->hw_features = info->net_hw_features;
+
+	reset_control_deassert(rstc);
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_get_sync(&pdev->dev);
 
-	chip_id = (enum ravb_chip_id)of_device_get_match_data(&pdev->dev);
-
-	if (chip_id == RCAR_GEN3)
+	if (info->multi_irqs)
 		irq = platform_get_irq_byname(pdev, "ch22");
 	else
 		irq = platform_get_irq(pdev, 0);
@@ -2073,6 +2186,8 @@ static int ravb_probe(struct platform_device *pdev)
 	SET_NETDEV_DEV(ndev, &pdev->dev);
 
 	priv = netdev_priv(ndev);
+	priv->info = info;
+	priv->rstc = rstc;
 	priv->ndev = ndev;
 	priv->pdev = pdev;
 	priv->num_tx_ring[RAVB_BE] = BE_TX_RING_SIZE;
@@ -2099,7 +2214,7 @@ static int ravb_probe(struct platform_device *pdev)
 	priv->avb_link_active_low =
 		of_property_read_bool(np, "renesas,ether-link-active-low");
 
-	if (chip_id == RCAR_GEN3) {
+	if (info->multi_irqs) {
 		irq = platform_get_irq_byname(pdev, "ch24");
 		if (irq < 0) {
 			error = irq;
@@ -2124,8 +2239,6 @@ static int ravb_probe(struct platform_device *pdev)
 		}
 	}
 
-	priv->chip_id = chip_id;
-
 	priv->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(priv->clk)) {
 		error = PTR_ERR(priv->clk);
@@ -2142,8 +2255,12 @@ static int ravb_probe(struct platform_device *pdev)
 	ndev->max_mtu = 2048 - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN);
 	ndev->min_mtu = ETH_MIN_MTU;
 
-	priv->num_tx_desc = chip_id == RCAR_GEN2 ?
-		NUM_TX_DESC_GEN2 : NUM_TX_DESC_GEN3;
+	/* FIXME: R-Car Gen2 has 4byte alignment restriction for tx buffer
+	 * Use two descriptor to handle such situation. First descriptor to
+	 * handle aligned data buffer and second descriptor to handle the
+	 * overflow data because of alignment.
+	 */
+	priv->num_tx_desc = info->aligned_tx ? 2 : 1;
 
 	/* Set function */
 	ndev->netdev_ops = &ravb_netdev_ops;
@@ -2160,7 +2277,7 @@ static int ravb_probe(struct platform_device *pdev)
 	/* Request GTI loading */
 	ravb_modify(ndev, GCCR, GCCR_LTI, GCCR_LTI);
 
-	if (priv->chip_id != RCAR_GEN2) {
+	if (info->internal_delay) {
 		ravb_parse_delay_mode(np, ndev);
 		ravb_set_delay_mode(ndev);
 	}
@@ -2184,7 +2301,7 @@ static int ravb_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&priv->ts_skb_list);
 
 	/* Initialise PTP Clock driver */
-	if (chip_id != RCAR_GEN2)
+	if (info->ptp_cfg_active)
 		ravb_ptp_init(ndev, pdev);
 
 	/* Debug message level */
@@ -2232,7 +2349,7 @@ out_dma_free:
 			  priv->desc_bat_dma);
 
 	/* Stop PTP Clock driver */
-	if (chip_id != RCAR_GEN2)
+	if (info->ptp_cfg_active)
 		ravb_ptp_stop(ndev);
 out_disable_refclk:
 	clk_disable_unprepare(priv->refclk);
@@ -2241,6 +2358,7 @@ out_release:
 
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+	reset_control_assert(rstc);
 	return error;
 }
 
@@ -2248,9 +2366,10 @@ static int ravb_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 
 	/* Stop PTP Clock driver */
-	if (priv->chip_id != RCAR_GEN2)
+	if (info->ptp_cfg_active)
 		ravb_ptp_stop(ndev);
 
 	clk_disable_unprepare(priv->refclk);
@@ -2265,6 +2384,7 @@ static int ravb_remove(struct platform_device *pdev)
 	netif_napi_del(&priv->napi[RAVB_BE]);
 	ravb_mdio_release(priv);
 	pm_runtime_disable(&pdev->dev);
+	reset_control_assert(priv->rstc);
 	free_netdev(ndev);
 	platform_set_drvdata(pdev, NULL);
 
@@ -2333,6 +2453,7 @@ static int __maybe_unused ravb_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct ravb_private *priv = netdev_priv(ndev);
+	const struct ravb_hw_info *info = priv->info;
 	int ret = 0;
 
 	/* If WoL is enabled set reset mode to rearm the WoL logic */
@@ -2355,7 +2476,7 @@ static int __maybe_unused ravb_resume(struct device *dev)
 	/* Request GTI loading */
 	ravb_modify(ndev, GCCR, GCCR_LTI, GCCR_LTI);
 
-	if (priv->chip_id != RCAR_GEN2)
+	if (info->internal_delay)
 		ravb_set_delay_mode(ndev);
 
 	/* Restore descriptor base address table */
diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c
index 6984bd5b7da9..c099656dd75b 100644
--- a/drivers/net/ethernet/renesas/ravb_ptp.c
+++ b/drivers/net/ethernet/renesas/ravb_ptp.c
@@ -179,6 +179,7 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp,
 {
 	struct ravb_private *priv = container_of(ptp, struct ravb_private,
 						 ptp.info);
+	const struct ravb_hw_info *info = priv->info;
 	struct net_device *ndev = priv->ndev;
 	unsigned long flags;
 
@@ -197,7 +198,7 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp,
 	priv->ptp.extts[req->index] = on;
 
 	spin_lock_irqsave(&priv->lock, flags);
-	if (priv->chip_id == RCAR_GEN2)
+	if (!info->multi_irqs)
 		ravb_modify(ndev, GIC, GIC_PTCE, on ? GIC_PTCE : 0);
 	else if (on)
 		ravb_write(ndev, GIE_PTCS, GIE);
@@ -213,6 +214,7 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp,
 {
 	struct ravb_private *priv = container_of(ptp, struct ravb_private,
 						 ptp.info);
+	const struct ravb_hw_info *info = priv->info;
 	struct net_device *ndev = priv->ndev;
 	struct ravb_ptp_perout *perout;
 	unsigned long flags;
@@ -252,7 +254,7 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp,
 		error = ravb_ptp_update_compare(priv, (u32)start_ns);
 		if (!error) {
 			/* Unmask interrupt */
-			if (priv->chip_id == RCAR_GEN2)
+			if (!info->multi_irqs)
 				ravb_modify(ndev, GIC, GIC_PTME, GIC_PTME);
 			else
 				ravb_write(ndev, GIE_PTMS0, GIE);
@@ -264,7 +266,7 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp,
 		perout->period = 0;
 
 		/* Mask interrupt */
-		if (priv->chip_id == RCAR_GEN2)
+		if (!info->multi_irqs)
 			ravb_modify(ndev, GIC, GIC_PTME, 0);
 		else
 			ravb_write(ndev, GID_PTMD0, GID);
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 840478692a37..6c8ba916d1a6 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -3141,7 +3141,7 @@ static const struct net_device_ops sh_eth_netdev_ops = {
 	.ndo_get_stats		= sh_eth_get_stats,
 	.ndo_set_rx_mode	= sh_eth_set_rx_mode,
 	.ndo_tx_timeout		= sh_eth_tx_timeout,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_change_mtu		= sh_eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
@@ -3157,7 +3157,7 @@ static const struct net_device_ops sh_eth_netdev_ops_tsu = {
 	.ndo_vlan_rx_add_vid	= sh_eth_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= sh_eth_vlan_rx_kill_vid,
 	.ndo_tx_timeout		= sh_eth_tx_timeout,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_change_mtu		= sh_eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
diff --git a/drivers/net/ethernet/rocker/rocker.h b/drivers/net/ethernet/rocker/rocker.h
index 315a6e5c0f59..e75814a4654f 100644
--- a/drivers/net/ethernet/rocker/rocker.h
+++ b/drivers/net/ethernet/rocker/rocker.h
@@ -119,7 +119,8 @@ struct rocker_world_ops {
 	int (*port_obj_fdb_del)(struct rocker_port *rocker_port,
 				u16 vid, const unsigned char *addr);
 	int (*port_master_linked)(struct rocker_port *rocker_port,
-				  struct net_device *master);
+				  struct net_device *master,
+				  struct netlink_ext_ack *extack);
 	int (*port_master_unlinked)(struct rocker_port *rocker_port,
 				    struct net_device *master);
 	int (*port_neigh_update)(struct rocker_port *rocker_port,
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 1f06b92ee5bb..3364b6a56bd1 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -1670,13 +1670,14 @@ rocker_world_port_fdb_del(struct rocker_port *rocker_port,
 }
 
 static int rocker_world_port_master_linked(struct rocker_port *rocker_port,
-					   struct net_device *master)
+					   struct net_device *master,
+					   struct netlink_ext_ack *extack)
 {
 	struct rocker_world_ops *wops = rocker_port->rocker->wops;
 
 	if (!wops->port_master_linked)
 		return -EOPNOTSUPP;
-	return wops->port_master_linked(rocker_port, master);
+	return wops->port_master_linked(rocker_port, master, extack);
 }
 
 static int rocker_world_port_master_unlinked(struct rocker_port *rocker_port,
@@ -3107,6 +3108,7 @@ struct rocker_port *rocker_port_dev_lower_find(struct net_device *dev,
 static int rocker_netdevice_event(struct notifier_block *unused,
 				  unsigned long event, void *ptr)
 {
+	struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr);
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct netdev_notifier_changeupper_info *info;
 	struct rocker_port *rocker_port;
@@ -3123,7 +3125,8 @@ static int rocker_netdevice_event(struct notifier_block *unused,
 		rocker_port = netdev_priv(dev);
 		if (info->linking) {
 			err = rocker_world_port_master_linked(rocker_port,
-							      info->upper_dev);
+							      info->upper_dev,
+							      extack);
 			if (err)
 				netdev_warn(dev, "failed to reflect master linked (err %d)\n",
 					    err);
diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index e33a9d283a4e..3e1ca7a8d029 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -2571,8 +2571,10 @@ static int ofdpa_port_obj_fdb_del(struct rocker_port *rocker_port,
 }
 
 static int ofdpa_port_bridge_join(struct ofdpa_port *ofdpa_port,
-				  struct net_device *bridge)
+				  struct net_device *bridge,
+				  struct netlink_ext_ack *extack)
 {
+	struct net_device *dev = ofdpa_port->dev;
 	int err;
 
 	/* Port is joining bridge, so the internal VLAN for the
@@ -2592,13 +2594,21 @@ static int ofdpa_port_bridge_join(struct ofdpa_port *ofdpa_port,
 
 	ofdpa_port->bridge_dev = bridge;
 
-	return ofdpa_port_vlan_add(ofdpa_port, OFDPA_UNTAGGED_VID, 0);
+	err = ofdpa_port_vlan_add(ofdpa_port, OFDPA_UNTAGGED_VID, 0);
+	if (err)
+		return err;
+
+	return switchdev_bridge_port_offload(dev, dev, NULL, NULL, NULL,
+					     false, extack);
 }
 
 static int ofdpa_port_bridge_leave(struct ofdpa_port *ofdpa_port)
 {
+	struct net_device *dev = ofdpa_port->dev;
 	int err;
 
+	switchdev_bridge_port_unoffload(dev, NULL, NULL, NULL);
+
 	err = ofdpa_port_vlan_del(ofdpa_port, OFDPA_UNTAGGED_VID, 0);
 	if (err)
 		return err;
@@ -2637,13 +2647,14 @@ static int ofdpa_port_ovs_changed(struct ofdpa_port *ofdpa_port,
 }
 
 static int ofdpa_port_master_linked(struct rocker_port *rocker_port,
-				    struct net_device *master)
+				    struct net_device *master,
+				    struct netlink_ext_ack *extack)
 {
 	struct ofdpa_port *ofdpa_port = rocker_port->wpriv;
 	int err = 0;
 
 	if (netif_is_bridge_master(master))
-		err = ofdpa_port_bridge_join(ofdpa_port, master);
+		err = ofdpa_port_bridge_join(ofdpa_port, master, extack);
 	else if (netif_is_ovs_master(master))
 		err = ofdpa_port_ovs_changed(ofdpa_port, master);
 	return err;
diff --git a/drivers/net/ethernet/samsung/Kconfig b/drivers/net/ethernet/samsung/Kconfig
index 0582e110b1c0..2a6c2658d284 100644
--- a/drivers/net/ethernet/samsung/Kconfig
+++ b/drivers/net/ethernet/samsung/Kconfig
@@ -20,9 +20,9 @@ if NET_VENDOR_SAMSUNG
 config SXGBE_ETH
 	tristate "Samsung 10G/2.5G/1G SXGBE Ethernet driver"
 	depends on HAS_IOMEM && HAS_DMA
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select PHYLIB
 	select CRC32
-	imply PTP_1588_CLOCK
 	help
 	  This is the driver for the SXGBE 10G Ethernet IP block found on
 	  Samsung platforms.
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
index 7f8b10c49660..98edb01024f0 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
@@ -274,7 +274,9 @@ static u32 sxgbe_usec2riwt(u32 usec, struct sxgbe_priv_data *priv)
 }
 
 static int sxgbe_get_coalesce(struct net_device *dev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct sxgbe_priv_data *priv = netdev_priv(dev);
 
@@ -285,7 +287,9 @@ static int sxgbe_get_coalesce(struct net_device *dev,
 }
 
 static int sxgbe_set_coalesce(struct net_device *dev,
-			      struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct sxgbe_priv_data *priv = netdev_priv(dev);
 	unsigned int rx_riwt;
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index 090bcd2fb758..6781aa636d58 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -1964,7 +1964,7 @@ static const struct net_device_ops sxgbe_netdev_ops = {
 	.ndo_set_features	= sxgbe_set_features,
 	.ndo_set_rx_mode	= sxgbe_set_rx_mode,
 	.ndo_tx_timeout		= sxgbe_tx_timeout,
-	.ndo_do_ioctl		= sxgbe_ioctl,
+	.ndo_eth_ioctl		= sxgbe_ioctl,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= sxgbe_poll_controller,
 #endif
diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index 5e37c8313725..97ce64079855 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -19,9 +19,9 @@ if NET_VENDOR_SOLARFLARE
 config SFC
 	tristate "Solarflare SFC9000/SFC9100/EF100-family support"
 	depends on PCI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select MDIO
 	select CRC32
-	imply PTP_1588_CLOCK
 	help
 	  This driver supports 10/40-gigabit Ethernet cards based on
 	  the Solarflare SFC9000-family and SFC9100-family controllers.
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 37fcf2eb0741..a295e2621cf3 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -591,7 +591,7 @@ 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_do_ioctl		= efx_ioctl,
+	.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,
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 058d9fe41d99..e002ce21788d 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -97,7 +97,9 @@ static void efx_ethtool_get_regs(struct net_device *net_dev,
  */
 
 static int efx_ethtool_get_coalesce(struct net_device *net_dev,
-				    struct ethtool_coalesce *coalesce)
+				    struct ethtool_coalesce *coalesce,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	unsigned int tx_usecs, rx_usecs;
@@ -115,7 +117,9 @@ static int efx_ethtool_get_coalesce(struct net_device *net_dev,
 }
 
 static int efx_ethtool_set_coalesce(struct net_device *net_dev,
-				    struct ethtool_coalesce *coalesce)
+				    struct ethtool_coalesce *coalesce,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct efx_channel *channel;
diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c
index 9ec752a43c75..c177ea0f301e 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.c
+++ b/drivers/net/ethernet/sfc/falcon/efx.c
@@ -2219,7 +2219,7 @@ static const struct net_device_ops ef4_netdev_ops = {
 	.ndo_tx_timeout		= ef4_watchdog,
 	.ndo_start_xmit		= ef4_hard_start_xmit,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= ef4_ioctl,
+	.ndo_eth_ioctl		= ef4_ioctl,
 	.ndo_change_mtu		= ef4_change_mtu,
 	.ndo_set_mac_address	= ef4_set_mac_address,
 	.ndo_set_rx_mode	= ef4_set_rx_mode,
diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c
index a6bae6a234ba..137e8a7aeaa1 100644
--- a/drivers/net/ethernet/sfc/falcon/ethtool.c
+++ b/drivers/net/ethernet/sfc/falcon/ethtool.c
@@ -577,7 +577,9 @@ static int ef4_ethtool_nway_reset(struct net_device *net_dev)
  */
 
 static int ef4_ethtool_get_coalesce(struct net_device *net_dev,
-				    struct ethtool_coalesce *coalesce)
+				    struct ethtool_coalesce *coalesce,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct ef4_nic *efx = netdev_priv(net_dev);
 	unsigned int tx_usecs, rx_usecs;
@@ -595,7 +597,9 @@ static int ef4_ethtool_get_coalesce(struct net_device *net_dev,
 }
 
 static int ef4_ethtool_set_coalesce(struct net_device *net_dev,
-				    struct ethtool_coalesce *coalesce)
+				    struct ethtool_coalesce *coalesce,
+				    struct kernel_ethtool_coalesce *kernel_coal,
+				    struct netlink_ext_ack *extack)
 {
 	struct ef4_nic *efx = netdev_priv(net_dev);
 	struct ef4_channel *channel;
diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 2b29fd4cbdf4..062f7844c496 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -820,7 +820,7 @@ static const struct net_device_ops ioc3_netdev_ops = {
 	.ndo_tx_timeout		= ioc3_timeout,
 	.ndo_get_stats		= ioc3_get_stats,
 	.ndo_set_rx_mode	= ioc3_set_multicast_list,
-	.ndo_do_ioctl		= ioc3_ioctl,
+	.ndo_eth_ioctl		= ioc3_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= ioc3_set_mac_address,
 };
diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c
index 0c396ecd3389..efce834d8ee6 100644
--- a/drivers/net/ethernet/sgi/meth.c
+++ b/drivers/net/ethernet/sgi/meth.c
@@ -812,7 +812,7 @@ static const struct net_device_ops meth_netdev_ops = {
 	.ndo_open		= meth_open,
 	.ndo_stop		= meth_release,
 	.ndo_start_xmit		= meth_tx,
-	.ndo_do_ioctl		= meth_ioctl,
+	.ndo_eth_ioctl		= meth_ioctl,
 	.ndo_tx_timeout		= meth_tx_timeout,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c
index 676b193833c0..3d1a18a01ce5 100644
--- a/drivers/net/ethernet/sis/sis190.c
+++ b/drivers/net/ethernet/sis/sis190.c
@@ -1841,7 +1841,7 @@ static int sis190_mac_addr(struct net_device  *dev, void *p)
 static const struct net_device_ops sis190_netdev_ops = {
 	.ndo_open		= sis190_open,
 	.ndo_stop		= sis190_close,
-	.ndo_do_ioctl		= sis190_ioctl,
+	.ndo_eth_ioctl		= sis190_ioctl,
 	.ndo_start_xmit		= sis190_start_xmit,
 	.ndo_tx_timeout		= sis190_tx_timeout,
 	.ndo_set_rx_mode	= sis190_set_rx_mode,
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index cff87de9178a..60a0c0e9ded2 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -404,7 +404,7 @@ static const struct net_device_ops sis900_netdev_ops = {
 	.ndo_set_rx_mode	= set_rx_mode,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address 	= eth_mac_addr,
-	.ndo_do_ioctl		= mii_ioctl,
+	.ndo_eth_ioctl		= mii_ioctl,
 	.ndo_tx_timeout		= sis900_tx_timeout,
 #ifdef CONFIG_NET_POLL_CONTROLLER
         .ndo_poll_controller	= sis900_poll,
diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig
index c52a38df0e0d..72e42a868346 100644
--- a/drivers/net/ethernet/smsc/Kconfig
+++ b/drivers/net/ethernet/smsc/Kconfig
@@ -23,6 +23,7 @@ config SMC9194
 	tristate "SMC 9194 support"
 	depends on ISA
 	select CRC32
+	select NETDEV_LEGACY_INIT
 	help
 	  This is support for the SMC9xxx based Ethernet cards. Choose this
 	  option if you have a DELL laptop with the docking station, or
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 51cd7dca91cd..44daf79a8f97 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -312,7 +312,7 @@ static const struct net_device_ops epic_netdev_ops = {
 	.ndo_tx_timeout 	= epic_tx_timeout,
 	.ndo_get_stats		= epic_get_stats,
 	.ndo_set_rx_mode	= set_rx_mode,
-	.ndo_do_ioctl 		= netdev_ioctl,
+	.ndo_eth_ioctl		= netdev_ioctl,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
diff --git a/drivers/net/ethernet/smsc/smc9194.c b/drivers/net/ethernet/smsc/smc9194.c
index bf7c8c8b1350..0ce403fa5f1a 100644
--- a/drivers/net/ethernet/smsc/smc9194.c
+++ b/drivers/net/ethernet/smsc/smc9194.c
@@ -1508,7 +1508,7 @@ MODULE_PARM_DESC(io, "SMC 99194 I/O base address");
 MODULE_PARM_DESC(irq, "SMC 99194 IRQ number");
 MODULE_PARM_DESC(ifport, "SMC 99194 interface port (0-default, 1-TP, 2-AUI)");
 
-int __init init_module(void)
+static int __init smc_init_module(void)
 {
 	if (io == 0)
 		printk(KERN_WARNING
@@ -1518,13 +1518,15 @@ int __init init_module(void)
 	devSMC9194 = smc_init(-1);
 	return PTR_ERR_OR_ZERO(devSMC9194);
 }
+module_init(smc_init_module);
 
-void __exit cleanup_module(void)
+static void __exit smc_cleanup_module(void)
 {
 	unregister_netdev(devSMC9194);
 	free_irq(devSMC9194->irq, devSMC9194);
 	release_region(devSMC9194->base_addr, SMC_IO_EXTENT);
 	free_netdev(devSMC9194);
 }
+module_exit(smc_cleanup_module);
 
 #endif /* MODULE */
diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c
index f2a50eb3c1e0..42fc37c7887a 100644
--- a/drivers/net/ethernet/smsc/smc91c92_cs.c
+++ b/drivers/net/ethernet/smsc/smc91c92_cs.c
@@ -294,7 +294,7 @@ static const struct net_device_ops smc_netdev_ops = {
 	.ndo_tx_timeout 	= smc_tx_timeout,
 	.ndo_set_config 	= s9k_config,
 	.ndo_set_rx_mode	= set_rx_mode,
-	.ndo_do_ioctl		= smc_ioctl,
+	.ndo_eth_ioctl		= smc_ioctl,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 556a9790cdcf..199a97339280 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -2148,7 +2148,7 @@ static const struct net_device_ops smsc911x_netdev_ops = {
 	.ndo_start_xmit		= smsc911x_hard_start_xmit,
 	.ndo_get_stats		= smsc911x_get_stats,
 	.ndo_set_rx_mode	= smsc911x_set_multicast_list,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address 	= smsc911x_set_mac_address,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c
index c1dab009415d..fdbd2a43e267 100644
--- a/drivers/net/ethernet/smsc/smsc9420.c
+++ b/drivers/net/ethernet/smsc/smsc9420.c
@@ -1482,7 +1482,7 @@ static const struct net_device_ops smsc9420_netdev_ops = {
 	.ndo_start_xmit		= smsc9420_hard_start_xmit,
 	.ndo_get_stats		= smsc9420_get_stats,
 	.ndo_set_rx_mode	= smsc9420_set_multicast_list,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address 	= eth_mac_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 20d148c019d8..1f46af136aa8 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -532,7 +532,9 @@ static void netsec_et_get_drvinfo(struct net_device *net_device,
 }
 
 static int netsec_et_get_coalesce(struct net_device *net_device,
-				  struct ethtool_coalesce *et_coalesce)
+				  struct ethtool_coalesce *et_coalesce,
+				  struct kernel_ethtool_coalesce *kernel_coal,
+				  struct netlink_ext_ack *extack)
 {
 	struct netsec_priv *priv = netdev_priv(net_device);
 
@@ -542,7 +544,9 @@ static int netsec_et_get_coalesce(struct net_device *net_device,
 }
 
 static int netsec_et_set_coalesce(struct net_device *net_device,
-				  struct ethtool_coalesce *et_coalesce)
+				  struct ethtool_coalesce *et_coalesce,
+				  struct kernel_ethtool_coalesce *kernel_coal,
+				  struct netlink_ext_ack *extack)
 {
 	struct netsec_priv *priv = netdev_priv(net_device);
 
@@ -1544,7 +1548,7 @@ static int netsec_start_gmac(struct netsec_priv *priv)
 	netsec_write(priv, NETSEC_REG_NRM_RX_INTEN_CLR, ~0);
 	netsec_write(priv, NETSEC_REG_NRM_TX_INTEN_CLR, ~0);
 
-	netsec_et_set_coalesce(priv->ndev, &priv->et_coalesce);
+	netsec_et_set_coalesce(priv->ndev, &priv->et_coalesce, NULL, NULL);
 
 	if (netsec_mac_write(priv, GMAC_REG_OMR, value))
 		return -ETIMEDOUT;
@@ -1831,7 +1835,7 @@ static const struct net_device_ops netsec_netdev_ops = {
 	.ndo_set_features	= netsec_netdev_set_features,
 	.ndo_set_mac_address    = eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= phy_do_ioctl,
+	.ndo_eth_ioctl		= phy_do_ioctl,
 	.ndo_xdp_xmit		= netsec_xdp_xmit,
 	.ndo_bpf		= netsec_xdp,
 };
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index 5eb6bb4f7b6c..ae31ed93aaf0 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -1543,7 +1543,7 @@ static const struct net_device_ops ave_netdev_ops = {
 	.ndo_open		= ave_open,
 	.ndo_stop		= ave_stop,
 	.ndo_start_xmit		= ave_start_xmit,
-	.ndo_do_ioctl		= ave_ioctl,
+	.ndo_eth_ioctl		= ave_ioctl,
 	.ndo_set_rx_mode	= ave_set_rx_mode,
 	.ndo_get_stats64	= ave_get_stats64,
 	.ndo_set_mac_address	= ave_set_mac_address,
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index ac3c248d4f9b..929cfc22cd0c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -2,12 +2,12 @@
 config STMMAC_ETH
 	tristate "STMicroelectronics Multi-Gigabit Ethernet driver"
 	depends on HAS_IOMEM && HAS_DMA
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select MII
 	select PCS_XPCS
 	select PAGE_POOL
 	select PHYLINK
 	select CRC32
-	imply PTP_1588_CLOCK
 	select RESET_CONTROLLER
 	help
 	  This is the driver for the Ethernet IPs built around a
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 5fecc83f175b..b6d945ea903d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -58,6 +58,16 @@
 #undef FRAME_FILTER_DEBUG
 /* #define FRAME_FILTER_DEBUG */
 
+struct stmmac_txq_stats {
+	unsigned long tx_pkt_n;
+	unsigned long tx_normal_irq_n;
+};
+
+struct stmmac_rxq_stats {
+	unsigned long rx_pkt_n;
+	unsigned long rx_normal_irq_n;
+};
+
 /* Extra statistic and debug information exposed by ethtool */
 struct stmmac_extra_stats {
 	/* Transmit errors */
@@ -189,6 +199,9 @@ struct stmmac_extra_stats {
 	unsigned long mtl_est_hlbf;
 	unsigned long mtl_est_btre;
 	unsigned long mtl_est_btrlm;
+	/* per queue statistics */
+	struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES];
+	struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES];
 };
 
 /* Safety Feature statistics exposed by ethtool */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 28dd0ed85a82..f7dc8458cde8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -289,10 +289,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 		val &= ~NSS_COMMON_GMAC_CTL_PHY_IFACE_SEL;
 		break;
 	default:
-		dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n",
-			phy_modes(gmac->phy_mode));
-		err = -EINVAL;
-		goto err_remove_config_dt;
+		goto err_unsupported_phy;
 	}
 	regmap_write(gmac->nss_common, NSS_COMMON_GMAC_CTL(gmac->id), val);
 
@@ -309,10 +306,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 			NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id);
 		break;
 	default:
-		dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n",
-			phy_modes(gmac->phy_mode));
-		err = -EINVAL;
-		goto err_remove_config_dt;
+		goto err_unsupported_phy;
 	}
 	regmap_write(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, val);
 
@@ -329,8 +323,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 				NSS_COMMON_CLK_GATE_GMII_TX_EN(gmac->id);
 		break;
 	default:
-		/* We don't get here; the switch above will have errored out */
-		unreachable();
+		goto err_unsupported_phy;
 	}
 	regmap_write(gmac->nss_common, NSS_COMMON_CLK_GATE, val);
 
@@ -361,6 +354,11 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_unsupported_phy:
+	dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n",
+		phy_modes(gmac->phy_mode));
+	err = -EINVAL;
+
 err_remove_config_dt:
 	stmmac_remove_config_dt(pdev, plat_dat);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index e63270267578..9292a1fab7d3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -170,13 +170,16 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr,
 		x->normal_irq_n++;
 	if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
 		x->rx_normal_irq_n++;
+		x->rxq_stats[chan].rx_normal_irq_n++;
 		ret |= handle_rx;
 	}
-	if (likely(intr_status & (DMA_CHAN_STATUS_TI |
-		DMA_CHAN_STATUS_TBU))) {
+	if (likely(intr_status & DMA_CHAN_STATUS_TI)) {
 		x->tx_normal_irq_n++;
+		x->txq_stats[chan].tx_normal_irq_n++;
 		ret |= handle_tx;
 	}
+	if (unlikely(intr_status & DMA_CHAN_STATUS_TBU))
+		ret |= handle_tx;
 	if (unlikely(intr_status & DMA_CHAN_STATUS_ERI))
 		x->rx_early_irq++;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index d0ce608b81c3..d89455803bed 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -261,6 +261,18 @@ static const struct stmmac_stats stmmac_mmc[] = {
 };
 #define STMMAC_MMC_STATS_LEN ARRAY_SIZE(stmmac_mmc)
 
+static const char stmmac_qstats_tx_string[][ETH_GSTRING_LEN] = {
+	"tx_pkt_n",
+	"tx_irq_n",
+#define STMMAC_TXQ_STATS ARRAY_SIZE(stmmac_qstats_tx_string)
+};
+
+static const char stmmac_qstats_rx_string[][ETH_GSTRING_LEN] = {
+	"rx_pkt_n",
+	"rx_irq_n",
+#define STMMAC_RXQ_STATS ARRAY_SIZE(stmmac_qstats_rx_string)
+};
+
 static void stmmac_ethtool_getdrvinfo(struct net_device *dev,
 				      struct ethtool_drvinfo *info)
 {
@@ -510,6 +522,31 @@ stmmac_set_pauseparam(struct net_device *netdev,
 	}
 }
 
+static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
+{
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	int q, stat;
+	char *p;
+
+	for (q = 0; q < tx_cnt; q++) {
+		p = (char *)priv + offsetof(struct stmmac_priv,
+					    xstats.txq_stats[q].tx_pkt_n);
+		for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
+			*data++ = (*(u64 *)p);
+			p += sizeof(u64 *);
+		}
+	}
+	for (q = 0; q < rx_cnt; q++) {
+		p = (char *)priv + offsetof(struct stmmac_priv,
+					    xstats.rxq_stats[q].rx_pkt_n);
+		for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
+			*data++ = (*(u64 *)p);
+			p += sizeof(u64 *);
+		}
+	}
+}
+
 static void stmmac_get_ethtool_stats(struct net_device *dev,
 				 struct ethtool_stats *dummy, u64 *data)
 {
@@ -560,16 +597,21 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 		data[j++] = (stmmac_gstrings_stats[i].sizeof_stat ==
 			     sizeof(u64)) ? (*(u64 *)p) : (*(u32 *)p);
 	}
+	stmmac_get_per_qstats(priv, &data[j]);
 }
 
 static int stmmac_get_sset_count(struct net_device *netdev, int sset)
 {
 	struct stmmac_priv *priv = netdev_priv(netdev);
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
 	int i, len, safety_len = 0;
 
 	switch (sset) {
 	case ETH_SS_STATS:
-		len = STMMAC_STATS_LEN;
+		len = STMMAC_STATS_LEN +
+		      STMMAC_TXQ_STATS * tx_cnt +
+		      STMMAC_RXQ_STATS * rx_cnt;
 
 		if (priv->dma_cap.rmon)
 			len += STMMAC_MMC_STATS_LEN;
@@ -592,6 +634,28 @@ static int stmmac_get_sset_count(struct net_device *netdev, int sset)
 	}
 }
 
+static void stmmac_get_qstats_string(struct stmmac_priv *priv, u8 *data)
+{
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	int q, stat;
+
+	for (q = 0; q < tx_cnt; q++) {
+		for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
+			snprintf(data, ETH_GSTRING_LEN, "q%d_%s", q,
+				 stmmac_qstats_tx_string[stat]);
+			data += ETH_GSTRING_LEN;
+		}
+	}
+	for (q = 0; q < rx_cnt; q++) {
+		for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
+			snprintf(data, ETH_GSTRING_LEN, "q%d_%s", q,
+				 stmmac_qstats_rx_string[stat]);
+			data += ETH_GSTRING_LEN;
+		}
+	}
+}
+
 static void stmmac_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 {
 	int i;
@@ -622,6 +686,7 @@ static void stmmac_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 				ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
+		stmmac_get_qstats_string(priv, p);
 		break;
 	case ETH_SS_TEST:
 		stmmac_selftest_get_strings(priv, p);
@@ -809,7 +874,9 @@ static int __stmmac_get_coalesce(struct net_device *dev,
 }
 
 static int stmmac_get_coalesce(struct net_device *dev,
-			       struct ethtool_coalesce *ec)
+			       struct ethtool_coalesce *ec,
+			       struct kernel_ethtool_coalesce *kernel_coal,
+			       struct netlink_ext_ack *extack)
 {
 	return __stmmac_get_coalesce(dev, ec, -1);
 }
@@ -893,7 +960,9 @@ static int __stmmac_set_coalesce(struct net_device *dev,
 }
 
 static int stmmac_set_coalesce(struct net_device *dev,
-			       struct ethtool_coalesce *ec)
+			       struct ethtool_coalesce *ec,
+			       struct kernel_ethtool_coalesce *kernel_coal,
+			       struct netlink_ext_ack *extack)
 {
 	return __stmmac_set_coalesce(dev, ec, -1);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index fa90bcdf4e45..ed0cd3920171 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2500,6 +2500,7 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
 			} else {
 				priv->dev->stats.tx_packets++;
 				priv->xstats.tx_pkt_n++;
+				priv->xstats.txq_stats[queue].tx_pkt_n++;
 			}
 			if (skb)
 				stmmac_get_tx_hwtstamp(priv, p, skb);
@@ -5000,6 +5001,9 @@ read_again:
 
 	stmmac_finalize_xdp_rx(priv, xdp_status);
 
+	priv->xstats.rx_pkt_n += count;
+	priv->xstats.rxq_stats[queue].rx_pkt_n += count;
+
 	if (xsk_uses_need_wakeup(rx_q->xsk_pool)) {
 		if (failure || stmmac_rx_dirty(priv, queue) > 0)
 			xsk_set_rx_need_wakeup(rx_q->xsk_pool);
@@ -5287,6 +5291,7 @@ drain_data:
 	stmmac_rx_refill(priv, queue);
 
 	priv->xstats.rx_pkt_n += count;
+	priv->xstats.rxq_stats[queue].rx_pkt_n += count;
 
 	return count;
 }
@@ -6451,7 +6456,7 @@ static const struct net_device_ops stmmac_netdev_ops = {
 	.ndo_set_features = stmmac_set_features,
 	.ndo_set_rx_mode = stmmac_set_rx_mode,
 	.ndo_tx_timeout = stmmac_tx_timeout,
-	.ndo_do_ioctl = stmmac_ioctl,
+	.ndo_eth_ioctl = stmmac_ioctl,
 	.ndo_setup_tc = stmmac_setup_tc,
 	.ndo_select_queue = stmmac_select_queue,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 981685c88308..287ae4c538aa 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -4876,7 +4876,7 @@ static const struct net_device_ops cas_netdev_ops = {
 	.ndo_start_xmit		= cas_start_xmit,
 	.ndo_get_stats 		= cas_get_stats,
 	.ndo_set_rx_mode	= cas_set_multicast,
-	.ndo_do_ioctl		= cas_ioctl,
+	.ndo_eth_ioctl		= cas_ioctl,
 	.ndo_tx_timeout		= cas_tx_timeout,
 	.ndo_change_mtu		= cas_change_mtu,
 	.ndo_set_mac_address	= eth_mac_addr,
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 860644d182ab..a68a01d1b2b1 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -9208,7 +9208,7 @@ static int niu_get_of_props(struct niu *np)
 	else
 		dp = pci_device_to_OF_node(np->pdev);
 
-	phy_type = of_get_property(dp, "phy-type", &prop_len);
+	phy_type = of_get_property(dp, "phy-type", NULL);
 	if (!phy_type) {
 		netdev_err(dev, "%pOF: OF node lacks phy-type property\n", dp);
 		return -EINVAL;
@@ -9242,12 +9242,12 @@ static int niu_get_of_props(struct niu *np)
 		return -EINVAL;
 	}
 
-	model = of_get_property(dp, "model", &prop_len);
+	model = of_get_property(dp, "model", NULL);
 
 	if (model)
 		strcpy(np->vpd.model, model);
 
-	if (of_find_property(dp, "hot-swappable-phy", &prop_len)) {
+	if (of_find_property(dp, "hot-swappable-phy", NULL)) {
 		np->flags |= (NIU_FLAGS_10G | NIU_FLAGS_FIBER |
 			NIU_FLAGS_HOTPLUG_PHY);
 	}
@@ -9668,7 +9668,7 @@ static const struct net_device_ops niu_netdev_ops = {
 	.ndo_set_rx_mode	= niu_set_rx_mode,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= niu_set_mac_addr,
-	.ndo_do_ioctl		= niu_ioctl,
+	.ndo_eth_ioctl		= niu_ioctl,
 	.ndo_tx_timeout		= niu_tx_timeout,
 	.ndo_change_mtu		= niu_change_mtu,
 };
@@ -9722,7 +9722,6 @@ static int niu_pci_init_one(struct pci_dev *pdev,
 	struct net_device *dev;
 	struct niu *np;
 	int err;
-	u64 dma_mask;
 
 	niu_driver_version();
 
@@ -9777,18 +9776,11 @@ static int niu_pci_init_one(struct pci_dev *pdev,
 		PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE |
 		PCI_EXP_DEVCTL_RELAX_EN);
 
-	dma_mask = DMA_BIT_MASK(44);
-	err = pci_set_dma_mask(pdev, dma_mask);
-	if (!err) {
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(44));
+	if (!err)
 		dev->features |= NETIF_F_HIGHDMA;
-		err = pci_set_consistent_dma_mask(pdev, dma_mask);
-		if (err) {
-			dev_err(&pdev->dev, "Unable to obtain 44 bit DMA for consistent allocations, aborting\n");
-			goto err_out_release_parent;
-		}
-	}
 	if (err) {
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
 			dev_err(&pdev->dev, "No usable DMA configuration, aborting\n");
 			goto err_out_release_parent;
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index cfb9e21b18b7..d72018a60c0f 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -2831,7 +2831,7 @@ static const struct net_device_ops gem_netdev_ops = {
 	.ndo_start_xmit		= gem_start_xmit,
 	.ndo_get_stats		= gem_get_stats,
 	.ndo_set_rx_mode	= gem_set_multicast,
-	.ndo_do_ioctl		= gem_ioctl,
+	.ndo_eth_ioctl		= gem_ioctl,
 	.ndo_tx_timeout		= gem_tx_timeout,
 	.ndo_change_mtu		= gem_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index a2c1a404c52d..62f81b0d14ed 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -251,14 +251,6 @@ static u32 pci_hme_read_desc32(hme32 *p)
 	((__hp)->write_txd((__txd), (__flags), (__addr)))
 #define hme_read_desc32(__hp, __p) \
 	((__hp)->read_desc32(__p))
-#define hme_dma_map(__hp, __ptr, __size, __dir) \
-	((__hp)->dma_map((__hp)->dma_dev, (__ptr), (__size), (__dir)))
-#define hme_dma_unmap(__hp, __addr, __size, __dir) \
-	((__hp)->dma_unmap((__hp)->dma_dev, (__addr), (__size), (__dir)))
-#define hme_dma_sync_for_cpu(__hp, __addr, __size, __dir) \
-	((__hp)->dma_sync_for_cpu((__hp)->dma_dev, (__addr), (__size), (__dir)))
-#define hme_dma_sync_for_device(__hp, __addr, __size, __dir) \
-	((__hp)->dma_sync_for_device((__hp)->dma_dev, (__addr), (__size), (__dir)))
 #else
 #ifdef CONFIG_SBUS
 /* SBUS only compilation */
@@ -277,14 +269,6 @@ do {	(__txd)->tx_addr = (__force hme32)(u32)(__addr); \
 	(__txd)->tx_flags = (__force hme32)(u32)(__flags); \
 } while(0)
 #define hme_read_desc32(__hp, __p)	((__force u32)(hme32)*(__p))
-#define hme_dma_map(__hp, __ptr, __size, __dir) \
-	dma_map_single((__hp)->dma_dev, (__ptr), (__size), (__dir))
-#define hme_dma_unmap(__hp, __addr, __size, __dir) \
-	dma_unmap_single((__hp)->dma_dev, (__addr), (__size), (__dir))
-#define hme_dma_sync_for_cpu(__hp, __addr, __size, __dir) \
-	dma_dma_sync_single_for_cpu((__hp)->dma_dev, (__addr), (__size), (__dir))
-#define hme_dma_sync_for_device(__hp, __addr, __size, __dir) \
-	dma_dma_sync_single_for_device((__hp)->dma_dev, (__addr), (__size), (__dir))
 #else
 /* PCI only compilation */
 #define hme_write32(__hp, __reg, __val) \
@@ -305,14 +289,6 @@ static inline u32 hme_read_desc32(struct happy_meal *hp, hme32 *p)
 {
 	return le32_to_cpup((__le32 *)p);
 }
-#define hme_dma_map(__hp, __ptr, __size, __dir) \
-	pci_map_single((__hp)->dma_dev, (__ptr), (__size), (__dir))
-#define hme_dma_unmap(__hp, __addr, __size, __dir) \
-	pci_unmap_single((__hp)->dma_dev, (__addr), (__size), (__dir))
-#define hme_dma_sync_for_cpu(__hp, __addr, __size, __dir) \
-	pci_dma_sync_single_for_cpu((__hp)->dma_dev, (__addr), (__size), (__dir))
-#define hme_dma_sync_for_device(__hp, __addr, __size, __dir) \
-	pci_dma_sync_single_for_device((__hp)->dma_dev, (__addr), (__size), (__dir))
 #endif
 #endif
 
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c
index bc198eadfcab..49f8c6be9459 100644
--- a/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c
@@ -146,8 +146,11 @@ static void xlgmac_ethtool_get_channels(struct net_device *netdev,
 	channel->tx_count = pdata->tx_q_count;
 }
 
-static int xlgmac_ethtool_get_coalesce(struct net_device *netdev,
-				       struct ethtool_coalesce *ec)
+static int
+xlgmac_ethtool_get_coalesce(struct net_device *netdev,
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct xlgmac_pdata *pdata = netdev_priv(netdev);
 
@@ -158,8 +161,11 @@ static int xlgmac_ethtool_get_coalesce(struct net_device *netdev,
 	return 0;
 }
 
-static int xlgmac_ethtool_set_coalesce(struct net_device *netdev,
-				       struct ethtool_coalesce *ec)
+static int
+xlgmac_ethtool_set_coalesce(struct net_device *netdev,
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct xlgmac_pdata *pdata = netdev_priv(netdev);
 	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
index 26d178f8616b..1db7104fef3a 100644
--- a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
@@ -933,7 +933,7 @@ static const struct net_device_ops xlgmac_netdev_ops = {
 	.ndo_change_mtu		= xlgmac_change_mtu,
 	.ndo_set_mac_address	= xlgmac_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= xlgmac_ioctl,
+	.ndo_eth_ioctl		= xlgmac_ioctl,
 	.ndo_vlan_rx_add_vid	= xlgmac_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= xlgmac_vlan_rx_kill_vid,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index d054c6e83b1c..6b409f9c5863 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -637,7 +637,8 @@ static int bdx_range_check(struct bdx_priv *priv, u32 offset)
 		-EINVAL : 0;
 }
 
-static int bdx_ioctl_priv(struct net_device *ndev, struct ifreq *ifr, int cmd)
+static int bdx_siocdevprivate(struct net_device *ndev, struct ifreq *ifr,
+			      void __user *udata, int cmd)
 {
 	struct bdx_priv *priv = netdev_priv(ndev);
 	u32 data[3];
@@ -647,7 +648,7 @@ static int bdx_ioctl_priv(struct net_device *ndev, struct ifreq *ifr, int cmd)
 
 	DBG("jiffies=%ld cmd=%d\n", jiffies, cmd);
 	if (cmd != SIOCDEVPRIVATE) {
-		error = copy_from_user(data, ifr->ifr_data, sizeof(data));
+		error = copy_from_user(data, udata, sizeof(data));
 		if (error) {
 			pr_err("can't copy from user\n");
 			RET(-EFAULT);
@@ -669,7 +670,7 @@ static int bdx_ioctl_priv(struct net_device *ndev, struct ifreq *ifr, int cmd)
 		data[2] = READ_REG(priv, data[1]);
 		DBG("read_reg(0x%x)=0x%x (dec %d)\n", data[1], data[2],
 		    data[2]);
-		error = copy_to_user(ifr->ifr_data, data, sizeof(data));
+		error = copy_to_user(udata, data, sizeof(data));
 		if (error)
 			RET(-EFAULT);
 		break;
@@ -688,15 +689,6 @@ static int bdx_ioctl_priv(struct net_device *ndev, struct ifreq *ifr, int cmd)
 	return 0;
 }
 
-static int bdx_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
-{
-	ENTER;
-	if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))
-		RET(bdx_ioctl_priv(ndev, ifr, cmd));
-	else
-		RET(-EOPNOTSUPP);
-}
-
 /**
  * __bdx_vlan_rx_vid - private helper for adding/killing VLAN vid
  * @ndev: network device
@@ -1860,7 +1852,7 @@ static const struct net_device_ops bdx_netdev_ops = {
 	.ndo_stop		= bdx_close,
 	.ndo_start_xmit		= bdx_tx_transmit,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= bdx_ioctl,
+	.ndo_siocdevprivate	= bdx_siocdevprivate,
 	.ndo_set_rx_mode	= bdx_setmulti,
 	.ndo_change_mtu		= bdx_change_mtu,
 	.ndo_set_mac_address	= bdx_set_mac,
@@ -2159,8 +2151,10 @@ bdx_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
  * @netdev
  * @ecoal
  */
-static int
-bdx_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecoal)
+static int bdx_get_coalesce(struct net_device *netdev,
+			    struct ethtool_coalesce *ecoal,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	u32 rdintcm;
 	u32 tdintcm;
@@ -2188,8 +2182,10 @@ bdx_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecoal)
  * @netdev
  * @ecoal
  */
-static int
-bdx_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecoal)
+static int bdx_set_coalesce(struct net_device *netdev,
+			    struct ethtool_coalesce *ecoal,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	u32 rdintcm;
 	u32 tdintcm;
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 67a08cbba859..130346f74ee8 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -27,6 +27,7 @@
 #include <linux/sys_soc.h>
 #include <linux/dma/ti-cppi5.h>
 #include <linux/dma/k3-udma-glue.h>
+#include <net/switchdev.h>
 
 #include "cpsw_ale.h"
 #include "cpsw_sl.h"
@@ -518,6 +519,10 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common,
 	}
 
 	napi_enable(&common->napi_rx);
+	if (common->rx_irq_disabled) {
+		common->rx_irq_disabled = false;
+		enable_irq(common->rx_chns.irq);
+	}
 
 	dev_dbg(common->dev, "cpsw_nuss started\n");
 	return 0;
@@ -871,8 +876,12 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 
 	dev_dbg(common->dev, "%s num_rx:%d %d\n", __func__, num_rx, budget);
 
-	if (num_rx < budget && napi_complete_done(napi_rx, num_rx))
-		enable_irq(common->rx_chns.irq);
+	if (num_rx < budget && napi_complete_done(napi_rx, num_rx)) {
+		if (common->rx_irq_disabled) {
+			common->rx_irq_disabled = false;
+			enable_irq(common->rx_chns.irq);
+		}
+	}
 
 	return num_rx;
 }
@@ -1077,19 +1086,20 @@ static int am65_cpsw_nuss_tx_poll(struct napi_struct *napi_tx, int budget)
 	else
 		num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common, tx_chn->id, budget);
 
-	num_tx = min(num_tx, budget);
-	if (num_tx < budget) {
-		napi_complete(napi_tx);
+	if (num_tx >= budget)
+		return budget;
+
+	if (napi_complete_done(napi_tx, num_tx))
 		enable_irq(tx_chn->irq);
-	}
 
-	return num_tx;
+	return 0;
 }
 
 static irqreturn_t am65_cpsw_nuss_rx_irq(int irq, void *dev_id)
 {
 	struct am65_cpsw_common *common = dev_id;
 
+	common->rx_irq_disabled = true;
 	disable_irq_nosync(irq);
 	napi_schedule(&common->napi_rx);
 
@@ -1479,7 +1489,7 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops = {
 	.ndo_tx_timeout		= am65_cpsw_nuss_ndo_host_tx_timeout,
 	.ndo_vlan_rx_add_vid	= am65_cpsw_nuss_ndo_slave_add_vid,
 	.ndo_vlan_rx_kill_vid	= am65_cpsw_nuss_ndo_slave_kill_vid,
-	.ndo_do_ioctl		= am65_cpsw_nuss_ndo_slave_ioctl,
+	.ndo_eth_ioctl		= am65_cpsw_nuss_ndo_slave_ioctl,
 	.ndo_setup_tc           = am65_cpsw_qos_ndo_setup_tc,
 	.ndo_get_devlink_port   = am65_cpsw_ndo_get_devlink_port,
 };
@@ -2081,10 +2091,13 @@ bool am65_cpsw_port_dev_check(const struct net_device *ndev)
 	return false;
 }
 
-static int am65_cpsw_netdevice_port_link(struct net_device *ndev, struct net_device *br_ndev)
+static int am65_cpsw_netdevice_port_link(struct net_device *ndev,
+					 struct net_device *br_ndev,
+					 struct netlink_ext_ack *extack)
 {
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
 	struct am65_cpsw_ndev_priv *priv = am65_ndev_to_priv(ndev);
+	int err;
 
 	if (!common->br_members) {
 		common->hw_bridge_dev = br_ndev;
@@ -2096,6 +2109,11 @@ static int am65_cpsw_netdevice_port_link(struct net_device *ndev, struct net_dev
 			return -EOPNOTSUPP;
 	}
 
+	err = switchdev_bridge_port_offload(ndev, ndev, NULL, NULL, NULL,
+					    false, extack);
+	if (err)
+		return err;
+
 	common->br_members |= BIT(priv->port->port_id);
 
 	am65_cpsw_port_offload_fwd_mark_update(common);
@@ -2108,6 +2126,8 @@ static void am65_cpsw_netdevice_port_unlink(struct net_device *ndev)
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
 	struct am65_cpsw_ndev_priv *priv = am65_ndev_to_priv(ndev);
 
+	switchdev_bridge_port_unoffload(ndev, NULL, NULL, NULL);
+
 	common->br_members &= ~BIT(priv->port->port_id);
 
 	am65_cpsw_port_offload_fwd_mark_update(common);
@@ -2120,6 +2140,7 @@ static void am65_cpsw_netdevice_port_unlink(struct net_device *ndev)
 static int am65_cpsw_netdevice_event(struct notifier_block *unused,
 				     unsigned long event, void *ptr)
 {
+	struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr);
 	struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
 	struct netdev_notifier_changeupper_info *info;
 	int ret = NOTIFY_DONE;
@@ -2133,7 +2154,9 @@ static int am65_cpsw_netdevice_event(struct notifier_block *unused,
 
 		if (netif_is_bridge_master(info->upper_dev)) {
 			if (info->linking)
-				ret = am65_cpsw_netdevice_port_link(ndev, info->upper_dev);
+				ret = am65_cpsw_netdevice_port_link(ndev,
+								    info->upper_dev,
+								    extack);
 			else
 				am65_cpsw_netdevice_port_unlink(ndev);
 		}
@@ -2388,21 +2411,6 @@ static const struct devlink_param am65_cpsw_devlink_params[] = {
 			     am65_cpsw_dl_switch_mode_set, NULL),
 };
 
-static void am65_cpsw_unregister_devlink_ports(struct am65_cpsw_common *common)
-{
-	struct devlink_port *dl_port;
-	struct am65_cpsw_port *port;
-	int i;
-
-	for (i = 1; i <= common->port_num; i++) {
-		port = am65_common_get_port(common, i);
-		dl_port = &port->devlink_port;
-
-		if (dl_port->registered)
-			devlink_port_unregister(dl_port);
-	}
-}
-
 static int am65_cpsw_nuss_register_devlink(struct am65_cpsw_common *common)
 {
 	struct devlink_port_attrs attrs = {};
@@ -2414,14 +2422,14 @@ static int am65_cpsw_nuss_register_devlink(struct am65_cpsw_common *common)
 	int i;
 
 	common->devlink =
-		devlink_alloc(&am65_cpsw_devlink_ops, sizeof(*dl_priv));
+		devlink_alloc(&am65_cpsw_devlink_ops, sizeof(*dl_priv), dev);
 	if (!common->devlink)
 		return -ENOMEM;
 
 	dl_priv = devlink_priv(common->devlink);
 	dl_priv->common = common;
 
-	ret = devlink_register(common->devlink, dev);
+	ret = devlink_register(common->devlink);
 	if (ret) {
 		dev_err(dev, "devlink reg fail ret:%d\n", ret);
 		goto dl_free;
@@ -2464,7 +2472,12 @@ static int am65_cpsw_nuss_register_devlink(struct am65_cpsw_common *common)
 	return ret;
 
 dl_port_unreg:
-	am65_cpsw_unregister_devlink_ports(common);
+	for (i = i - 1; i >= 1; i--) {
+		port = am65_common_get_port(common, i);
+		dl_port = &port->devlink_port;
+
+		devlink_port_unregister(dl_port);
+	}
 dl_unreg:
 	devlink_unregister(common->devlink);
 dl_free:
@@ -2475,6 +2488,17 @@ dl_free:
 
 static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common)
 {
+	struct devlink_port *dl_port;
+	struct am65_cpsw_port *port;
+	int i;
+
+	for (i = 1; i <= common->port_num; i++) {
+		port = am65_common_get_port(common, i);
+		dl_port = &port->devlink_port;
+
+		devlink_port_unregister(dl_port);
+	}
+
 	if (!AM65_CPSW_IS_CPSW2G(common) &&
 	    IS_ENABLED(CONFIG_TI_K3_AM65_CPSW_SWITCHDEV)) {
 		devlink_params_unpublish(common->devlink);
@@ -2482,7 +2506,6 @@ static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common)
 					  ARRAY_SIZE(am65_cpsw_devlink_params));
 	}
 
-	am65_cpsw_unregister_devlink_ports(common);
 	devlink_unregister(common->devlink);
 	devlink_free(common->devlink);
 }
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index 5d93e346f05e..048ed10143c1 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -126,6 +126,8 @@ struct am65_cpsw_common {
 	struct am65_cpsw_rx_chn	rx_chns;
 	struct napi_struct	napi_rx;
 
+	bool			rx_irq_disabled;
+
 	u32			nuss_ver;
 	u32			cpsw_ver;
 	unsigned long		bus_freq;
diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c
index c20715107075..02d4e51f7306 100644
--- a/drivers/net/ethernet/ti/cpmac.c
+++ b/drivers/net/ethernet/ti/cpmac.c
@@ -1044,7 +1044,7 @@ static const struct net_device_ops cpmac_netdev_ops = {
 	.ndo_start_xmit		= cpmac_start_xmit,
 	.ndo_tx_timeout		= cpmac_tx_timeout,
 	.ndo_set_rx_mode	= cpmac_set_multicast_list,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 };
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index cbbd0f665796..66f7ddd9b1f9 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -431,7 +431,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	skb->protocol = eth_type_trans(skb, ndev);
 
 	/* mark skb for recycling */
-	skb_mark_for_recycle(skb, page, pool);
+	skb_mark_for_recycle(skb);
 	netif_receive_skb(skb);
 
 	ndev->stats.rx_bytes += len;
@@ -845,7 +845,7 @@ static int cpsw_ndo_open(struct net_device *ndev)
 		struct ethtool_coalesce coal;
 
 		coal.rx_coalesce_usecs = cpsw->coal_intvl;
-		cpsw_set_coalesce(ndev, &coal);
+		cpsw_set_coalesce(ndev, &coal, NULL, NULL);
 	}
 
 	cpdma_ctlr_start(cpsw->dma);
@@ -905,7 +905,7 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb,
 	struct cpdma_chan *txch;
 	int ret, q_idx;
 
-	if (skb_padto(skb, CPSW_MIN_PACKET_SIZE)) {
+	if (skb_put_padto(skb, CPSW_MIN_PACKET_SIZE)) {
 		cpsw_err(priv, tx_err, "packet pad failed\n");
 		ndev->stats.tx_dropped++;
 		return NET_XMIT_DROP;
@@ -1159,7 +1159,7 @@ 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_do_ioctl		= cpsw_ndo_ioctl,
+	.ndo_eth_ioctl		= cpsw_ndo_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_tx_timeout		= cpsw_ndo_tx_timeout,
 	.ndo_set_rx_mode	= cpsw_ndo_set_rx_mode,
diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index 4619c3a950b0..158c8d3793f4 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -152,7 +152,9 @@ void cpsw_set_msglevel(struct net_device *ndev, u32 value)
 	priv->msg_enable = value;
 }
 
-int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal)
+int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal,
+		      struct kernel_ethtool_coalesce *kernel_coal,
+		      struct netlink_ext_ack *extack)
 {
 	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
 
@@ -160,7 +162,9 @@ int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal)
 	return 0;
 }
 
-int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal)
+int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal,
+		      struct kernel_ethtool_coalesce *kernel_coal,
+		      struct netlink_ext_ack *extack)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
 	u32 int_ctrl;
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index d1d02001cef6..7968f24d99c8 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -28,6 +28,7 @@
 #include <linux/kmemleak.h>
 #include <linux/sys_soc.h>
 
+#include <net/switchdev.h>
 #include <net/page_pool.h>
 #include <net/pkt_cls.h>
 #include <net/devlink.h>
@@ -374,7 +375,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	skb->protocol = eth_type_trans(skb, ndev);
 
 	/* mark skb for recycling */
-	skb_mark_for_recycle(skb, page, pool);
+	skb_mark_for_recycle(skb);
 	netif_receive_skb(skb);
 
 	ndev->stats.rx_bytes += len;
@@ -501,7 +502,7 @@ static void cpsw_restore(struct cpsw_priv *priv)
 
 static void cpsw_init_stp_ale_entry(struct cpsw_common *cpsw)
 {
-	char stpa[] = {0x01, 0x80, 0xc2, 0x0, 0x0, 0x0};
+	static const char stpa[] = {0x01, 0x80, 0xc2, 0x0, 0x0, 0x0};
 
 	cpsw_ale_add_mcast(cpsw->ale, stpa,
 			   ALE_PORT_HOST, ALE_SUPER, 0,
@@ -893,7 +894,7 @@ static int cpsw_ndo_open(struct net_device *ndev)
 		struct ethtool_coalesce coal;
 
 		coal.rx_coalesce_usecs = cpsw->coal_intvl;
-		cpsw_set_coalesce(ndev, &coal);
+		cpsw_set_coalesce(ndev, &coal, NULL, NULL);
 	}
 
 	cpdma_ctlr_start(cpsw->dma);
@@ -1127,7 +1128,7 @@ 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_do_ioctl		= cpsw_ndo_ioctl,
+	.ndo_eth_ioctl		= cpsw_ndo_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_tx_timeout		= cpsw_ndo_tx_timeout,
 	.ndo_set_rx_mode	= cpsw_ndo_set_rx_mode,
@@ -1500,10 +1501,12 @@ static void cpsw_port_offload_fwd_mark_update(struct cpsw_common *cpsw)
 }
 
 static int cpsw_netdevice_port_link(struct net_device *ndev,
-				    struct net_device *br_ndev)
+				    struct net_device *br_ndev,
+				    struct netlink_ext_ack *extack)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
 	struct cpsw_common *cpsw = priv->cpsw;
+	int err;
 
 	if (!cpsw->br_members) {
 		cpsw->hw_bridge_dev = br_ndev;
@@ -1515,6 +1518,11 @@ static int cpsw_netdevice_port_link(struct net_device *ndev,
 			return -EOPNOTSUPP;
 	}
 
+	err = switchdev_bridge_port_offload(ndev, ndev, NULL, NULL, NULL,
+					    false, extack);
+	if (err)
+		return err;
+
 	cpsw->br_members |= BIT(priv->emac_port);
 
 	cpsw_port_offload_fwd_mark_update(cpsw);
@@ -1527,6 +1535,8 @@ static void cpsw_netdevice_port_unlink(struct net_device *ndev)
 	struct cpsw_priv *priv = netdev_priv(ndev);
 	struct cpsw_common *cpsw = priv->cpsw;
 
+	switchdev_bridge_port_unoffload(ndev, NULL, NULL, NULL);
+
 	cpsw->br_members &= ~BIT(priv->emac_port);
 
 	cpsw_port_offload_fwd_mark_update(cpsw);
@@ -1539,6 +1549,7 @@ static void cpsw_netdevice_port_unlink(struct net_device *ndev)
 static int cpsw_netdevice_event(struct notifier_block *unused,
 				unsigned long event, void *ptr)
 {
+	struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr);
 	struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
 	struct netdev_notifier_changeupper_info *info;
 	int ret = NOTIFY_DONE;
@@ -1553,7 +1564,8 @@ static int cpsw_netdevice_event(struct notifier_block *unused,
 		if (netif_is_bridge_master(info->upper_dev)) {
 			if (info->linking)
 				ret = cpsw_netdevice_port_link(ndev,
-							       info->upper_dev);
+							       info->upper_dev,
+							       extack);
 			else
 				cpsw_netdevice_port_unlink(ndev);
 		}
@@ -1791,14 +1803,14 @@ static int cpsw_register_devlink(struct cpsw_common *cpsw)
 	struct cpsw_devlink *dl_priv;
 	int ret = 0;
 
-	cpsw->devlink = devlink_alloc(&cpsw_devlink_ops, sizeof(*dl_priv));
+	cpsw->devlink = devlink_alloc(&cpsw_devlink_ops, sizeof(*dl_priv), dev);
 	if (!cpsw->devlink)
 		return -ENOMEM;
 
 	dl_priv = devlink_priv(cpsw->devlink);
 	dl_priv->cpsw = cpsw;
 
-	ret = devlink_register(cpsw->devlink, dev);
+	ret = devlink_register(cpsw->devlink);
 	if (ret) {
 		dev_err(dev, "DL reg fail ret:%d\n", ret);
 		goto dl_free;
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index 2951fb7b9dae..435668ee542d 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -464,8 +464,12 @@ void cpsw_mqprio_resume(struct cpsw_slave *slave, struct cpsw_priv *priv);
 /* ethtool */
 u32 cpsw_get_msglevel(struct net_device *ndev);
 void cpsw_set_msglevel(struct net_device *ndev, u32 value);
-int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal);
-int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal);
+int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal,
+		      struct kernel_ethtool_coalesce *kernel_coal,
+		      struct netlink_ext_ack *extack);
+int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal,
+		      struct kernel_ethtool_coalesce *kernel_coal,
+		      struct netlink_ext_ack *extack);
 int cpsw_get_sset_count(struct net_device *ndev, int sset);
 void cpsw_get_strings(struct net_device *ndev, u32 stringset, u8 *data);
 void cpsw_get_ethtool_stats(struct net_device *ndev,
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index c674e34b6839..e8291d848839 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -383,12 +383,16 @@ static void emac_get_drvinfo(struct net_device *ndev,
  * emac_get_coalesce - Get interrupt coalesce settings for this device
  * @ndev : The DaVinci EMAC network adapter
  * @coal : ethtool coalesce settings structure
+ * @kernel_coal: ethtool CQE mode setting structure
+ * @extack: extack for reporting error messages
  *
  * Fetch the current interrupt coalesce settings
  *
  */
 static int emac_get_coalesce(struct net_device *ndev,
-				struct ethtool_coalesce *coal)
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct emac_priv *priv = netdev_priv(ndev);
 
@@ -401,12 +405,16 @@ static int emac_get_coalesce(struct net_device *ndev,
  * emac_set_coalesce - Set interrupt coalesce settings for this device
  * @ndev : The DaVinci EMAC network adapter
  * @coal : ethtool coalesce settings structure
+ * @kernel_coal: ethtool CQE mode setting structure
+ * @extack: extack for reporting error messages
  *
  * Set interrupt coalesce parameters
  *
  */
 static int emac_set_coalesce(struct net_device *ndev,
-				struct ethtool_coalesce *coal)
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct emac_priv *priv = netdev_priv(ndev);
 	u32 int_ctrl, num_interrupts = 0;
@@ -943,7 +951,7 @@ static int emac_dev_xmit(struct sk_buff *skb, struct net_device *ndev)
 		goto fail_tx;
 	}
 
-	ret_code = skb_padto(skb, EMAC_DEF_MIN_ETHPKTSIZE);
+	ret_code = skb_put_padto(skb, EMAC_DEF_MIN_ETHPKTSIZE);
 	if (unlikely(ret_code < 0)) {
 		if (netif_msg_tx_err(priv) && net_ratelimit())
 			dev_err(emac_dev, "DaVinci EMAC: packet pad failed");
@@ -1462,7 +1470,7 @@ static int emac_dev_open(struct net_device *ndev)
 		struct ethtool_coalesce coal;
 
 		coal.rx_coalesce_usecs = (priv->coal_intvl << 4);
-		emac_set_coalesce(ndev, &coal);
+		emac_set_coalesce(ndev, &coal, NULL, NULL);
 	}
 
 	cpdma_ctlr_start(priv->dma);
@@ -1670,7 +1678,7 @@ static const struct net_device_ops emac_netdev_ops = {
 	.ndo_start_xmit		= emac_dev_xmit,
 	.ndo_set_rx_mode	= emac_dev_mcast_set,
 	.ndo_set_mac_address	= emac_dev_setmac_addr,
-	.ndo_do_ioctl		= emac_devioctl,
+	.ndo_eth_ioctl		= emac_devioctl,
 	.ndo_tx_timeout		= emac_dev_tx_timeout,
 	.ndo_get_stats		= emac_dev_getnetstats,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 97942b0e3897..eda2961c0fe2 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -1944,7 +1944,7 @@ static const struct net_device_ops netcp_netdev_ops = {
 	.ndo_stop		= netcp_ndo_stop,
 	.ndo_start_xmit		= netcp_ndo_start_xmit,
 	.ndo_set_rx_mode	= netcp_set_rx_mode,
-	.ndo_do_ioctl           = netcp_ndo_ioctl,
+	.ndo_eth_ioctl           = netcp_ndo_ioctl,
 	.ndo_get_stats64        = netcp_get_stats,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c
index e0cb713193ea..77c448ad67ce 100644
--- a/drivers/net/ethernet/ti/tlan.c
+++ b/drivers/net/ethernet/ti/tlan.c
@@ -749,7 +749,7 @@ static const struct net_device_ops tlan_netdev_ops = {
 	.ndo_tx_timeout		= tlan_tx_timeout,
 	.ndo_get_stats		= tlan_get_stats,
 	.ndo_set_rx_mode	= tlan_set_multicast_list,
-	.ndo_do_ioctl		= tlan_ioctl,
+	.ndo_eth_ioctl		= tlan_ioctl,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
index 226a76633e65..66d4e024d11e 100644
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ b/drivers/net/ethernet/toshiba/spider_net.c
@@ -354,9 +354,10 @@ spider_net_free_rx_chain_contents(struct spider_net_card *card)
 	descr = card->rx_chain.head;
 	do {
 		if (descr->skb) {
-			pci_unmap_single(card->pdev, descr->hwdescr->buf_addr,
+			dma_unmap_single(&card->pdev->dev,
+					 descr->hwdescr->buf_addr,
 					 SPIDER_NET_MAX_FRAME,
-					 PCI_DMA_BIDIRECTIONAL);
+					 DMA_BIDIRECTIONAL);
 			dev_kfree_skb(descr->skb);
 			descr->skb = NULL;
 		}
@@ -411,9 +412,9 @@ spider_net_prepare_rx_descr(struct spider_net_card *card,
 	if (offset)
 		skb_reserve(descr->skb, SPIDER_NET_RXBUF_ALIGN - offset);
 	/* iommu-map the skb */
-	buf = pci_map_single(card->pdev, descr->skb->data,
-			SPIDER_NET_MAX_FRAME, PCI_DMA_FROMDEVICE);
-	if (pci_dma_mapping_error(card->pdev, buf)) {
+	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())
@@ -653,8 +654,9 @@ spider_net_prepare_tx_descr(struct spider_net_card *card,
 	dma_addr_t buf;
 	unsigned long flags;
 
-	buf = pci_map_single(card->pdev, skb->data, skb->len, PCI_DMA_TODEVICE);
-	if (pci_dma_mapping_error(card->pdev, buf)) {
+	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);
@@ -666,7 +668,8 @@ spider_net_prepare_tx_descr(struct spider_net_card *card,
 	descr = card->tx_chain.head;
 	if (descr->next == chain->tail->prev) {
 		spin_unlock_irqrestore(&chain->lock, flags);
-		pci_unmap_single(card->pdev, buf, skb->len, PCI_DMA_TODEVICE);
+		dma_unmap_single(&card->pdev->dev, buf, skb->len,
+				 DMA_TO_DEVICE);
 		return -ENOMEM;
 	}
 	hwdescr = descr->hwdescr;
@@ -822,8 +825,8 @@ spider_net_release_tx_chain(struct spider_net_card *card, int brutal)
 
 		/* unmap the skb */
 		if (skb) {
-			pci_unmap_single(card->pdev, buf_addr, skb->len,
-					PCI_DMA_TODEVICE);
+			dma_unmap_single(&card->pdev->dev, buf_addr, skb->len,
+					 DMA_TO_DEVICE);
 			dev_consume_skb_any(skb);
 		}
 	}
@@ -1165,8 +1168,8 @@ spider_net_decode_one_descr(struct spider_net_card *card)
 	/* unmap descriptor */
 	hw_buf_addr = hwdescr->buf_addr;
 	hwdescr->buf_addr = 0xffffffff;
-	pci_unmap_single(card->pdev, hw_buf_addr,
-			SPIDER_NET_MAX_FRAME, PCI_DMA_FROMDEVICE);
+	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) ||
@@ -2214,7 +2217,7 @@ static const struct net_device_ops spider_net_ops = {
 	.ndo_start_xmit		= spider_net_xmit,
 	.ndo_set_rx_mode	= spider_net_set_multi,
 	.ndo_set_mac_address	= spider_net_set_mac,
-	.ndo_do_ioctl		= spider_net_do_ioctl,
+	.ndo_eth_ioctl		= spider_net_do_ioctl,
 	.ndo_tx_timeout		= spider_net_tx_timeout,
 	.ndo_validate_addr	= eth_validate_addr,
 	/* HW VLAN */
diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index fedb2bf69261..52245ac60fc7 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -750,7 +750,7 @@ static const struct net_device_ops tc35815_netdev_ops = {
 	.ndo_get_stats		= tc35815_get_stats,
 	.ndo_set_rx_mode	= tc35815_set_multicast_list,
 	.ndo_tx_timeout		= tc35815_tx_timeout,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c
index c62f474b6d08..cf0917b29e30 100644
--- a/drivers/net/ethernet/tundra/tsi108_eth.c
+++ b/drivers/net/ethernet/tundra/tsi108_eth.c
@@ -1538,7 +1538,7 @@ static const struct net_device_ops tsi108_netdev_ops = {
 	.ndo_start_xmit		= tsi108_send_packet,
 	.ndo_set_rx_mode	= tsi108_set_rx_mode,
 	.ndo_get_stats		= tsi108_get_stats,
-	.ndo_do_ioctl		= tsi108_do_ioctl,
+	.ndo_eth_ioctl		= tsi108_do_ioctl,
 	.ndo_set_mac_address	= tsi108_set_mac,
 	.ndo_validate_addr	= eth_validate_addr,
 };
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index 73ca597ebd1b..3b73a9c55a5a 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -884,7 +884,7 @@ static const struct net_device_ops rhine_netdev_ops = {
 	.ndo_set_rx_mode	 = rhine_set_rx_mode,
 	.ndo_validate_addr	 = eth_validate_addr,
 	.ndo_set_mac_address 	 = eth_mac_addr,
-	.ndo_do_ioctl		 = netdev_ioctl,
+	.ndo_eth_ioctl		 = netdev_ioctl,
 	.ndo_tx_timeout 	 = rhine_tx_timeout,
 	.ndo_vlan_rx_add_vid	 = rhine_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	 = rhine_vlan_rx_kill_vid,
@@ -1113,13 +1113,12 @@ err_out:
 
 static int rhine_init_one_platform(struct platform_device *pdev)
 {
-	const struct of_device_id *match;
 	const u32 *quirks;
 	int irq;
 	void __iomem *ioaddr;
 
-	match = of_match_device(rhine_of_tbl, &pdev->dev);
-	if (!match)
+	quirks = of_device_get_match_data(&pdev->dev);
+	if (!quirks)
 		return -EINVAL;
 
 	ioaddr = devm_platform_ioremap_resource(pdev, 0);
@@ -1130,10 +1129,6 @@ static int rhine_init_one_platform(struct platform_device *pdev)
 	if (!irq)
 		return -EINVAL;
 
-	quirks = match->data;
-	if (!quirks)
-		return -EINVAL;
-
 	return rhine_init_one_common(&pdev->dev, *quirks,
 				     (long)ioaddr, ioaddr, irq);
 }
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index 88426b5e410b..4b9c30f735b5 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -2637,7 +2637,7 @@ static const struct net_device_ops velocity_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_set_rx_mode	= velocity_set_multi,
 	.ndo_change_mtu		= velocity_change_mtu,
-	.ndo_do_ioctl		= velocity_ioctl,
+	.ndo_eth_ioctl		= velocity_ioctl,
 	.ndo_vlan_rx_add_vid	= velocity_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= velocity_vlan_rx_kill_vid,
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -2943,14 +2943,12 @@ static void velocity_pci_remove(struct pci_dev *pdev)
 
 static int velocity_platform_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *of_id;
 	const struct velocity_info_tbl *info;
 	int irq;
 
-	of_id = of_match_device(velocity_of_ids, &pdev->dev);
-	if (!of_id)
+	info = of_device_get_match_data(&pdev->dev);
+	if (!info)
 		return -EINVAL;
-	info = of_id->data;
 
 	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
 	if (!irq)
@@ -3520,7 +3518,9 @@ static void set_pending_timer_val(int *val, u32 us)
 
 
 static int velocity_get_coalesce(struct net_device *dev,
-		struct ethtool_coalesce *ecmd)
+				 struct ethtool_coalesce *ecmd,
+				 struct kernel_ethtool_coalesce *kernel_coal,
+				 struct netlink_ext_ack *extack)
 {
 	struct velocity_info *vptr = netdev_priv(dev);
 
@@ -3534,7 +3534,9 @@ static int velocity_get_coalesce(struct net_device *dev,
 }
 
 static int velocity_set_coalesce(struct net_device *dev,
-		struct ethtool_coalesce *ecmd)
+				 struct ethtool_coalesce *ecmd,
+				 struct kernel_ethtool_coalesce *kernel_coal,
+				 struct netlink_ext_ack *extack)
 {
 	struct velocity_info *vptr = netdev_priv(dev);
 	int max_us = 0x3f * 64;
diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index 811815f8cd3b..f974e70a82e8 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -1047,6 +1047,8 @@ static int w5100_mmio_probe(struct platform_device *pdev)
 		mac_addr = data->mac_addr;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem)
+		return -EINVAL;
 	if (resource_size(mem) < W5100_BUS_DIRECT_SIZE)
 		ops = &w5100_mmio_indirect_ops;
 	else
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 60a4f79b8fa1..463094ced104 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -1237,7 +1237,7 @@ static const struct net_device_ops temac_netdev_ops = {
 	.ndo_set_rx_mode = temac_set_multicast_list,
 	.ndo_set_mac_address = temac_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
-	.ndo_do_ioctl = phy_do_ioctl_running,
+	.ndo_eth_ioctl = phy_do_ioctl_running,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = temac_poll_controller,
 #endif
@@ -1310,8 +1310,11 @@ static int ll_temac_ethtools_set_ringparam(struct net_device *ndev,
 	return 0;
 }
 
-static int ll_temac_ethtools_get_coalesce(struct net_device *ndev,
-					  struct ethtool_coalesce *ec)
+static int
+ll_temac_ethtools_get_coalesce(struct net_device *ndev,
+			       struct ethtool_coalesce *ec,
+			       struct kernel_ethtool_coalesce *kernel_coal,
+			       struct netlink_ext_ack *extack)
 {
 	struct temac_local *lp = netdev_priv(ndev);
 
@@ -1322,8 +1325,11 @@ static int ll_temac_ethtools_get_coalesce(struct net_device *ndev,
 	return 0;
 }
 
-static int ll_temac_ethtools_set_coalesce(struct net_device *ndev,
-					  struct ethtool_coalesce *ec)
+static int
+ll_temac_ethtools_set_coalesce(struct net_device *ndev,
+			       struct ethtool_coalesce *ec,
+			       struct kernel_ethtool_coalesce *kernel_coal,
+			       struct netlink_ext_ack *extack)
 {
 	struct temac_local *lp = netdev_priv(ndev);
 
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 13cd799541aa..871b5ec3183d 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1227,7 +1227,7 @@ static const struct net_device_ops axienet_netdev_ops = {
 	.ndo_change_mtu	= axienet_change_mtu,
 	.ndo_set_mac_address = netdev_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
-	.ndo_do_ioctl = axienet_ioctl,
+	.ndo_eth_ioctl = axienet_ioctl,
 	.ndo_set_rx_mode = axienet_set_multicast_list,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = axienet_poll_controller,
@@ -1400,6 +1400,8 @@ axienet_ethtools_set_pauseparam(struct net_device *ndev,
  * axienet_ethtools_get_coalesce - Get DMA interrupt coalescing count.
  * @ndev:	Pointer to net_device structure
  * @ecoalesce:	Pointer to ethtool_coalesce structure
+ * @kernel_coal: ethtool CQE mode setting structure
+ * @extack:	extack for reporting error messages
  *
  * This implements ethtool command for getting the DMA interrupt coalescing
  * count on Tx and Rx paths. Issue "ethtool -c ethX" under linux prompt to
@@ -1407,8 +1409,11 @@ axienet_ethtools_set_pauseparam(struct net_device *ndev,
  *
  * Return: 0 always
  */
-static int axienet_ethtools_get_coalesce(struct net_device *ndev,
-					 struct ethtool_coalesce *ecoalesce)
+static int
+axienet_ethtools_get_coalesce(struct net_device *ndev,
+			      struct ethtool_coalesce *ecoalesce,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	u32 regval = 0;
 	struct axienet_local *lp = netdev_priv(ndev);
@@ -1425,6 +1430,8 @@ static int axienet_ethtools_get_coalesce(struct net_device *ndev,
  * axienet_ethtools_set_coalesce - Set DMA interrupt coalescing count.
  * @ndev:	Pointer to net_device structure
  * @ecoalesce:	Pointer to ethtool_coalesce structure
+ * @kernel_coal: ethtool CQE mode setting structure
+ * @extack:	extack for reporting error messages
  *
  * This implements ethtool command for setting the DMA interrupt coalescing
  * count on Tx and Rx paths. Issue "ethtool -C ethX rx-frames 5" under linux
@@ -1432,8 +1439,11 @@ static int axienet_ethtools_get_coalesce(struct net_device *ndev,
  *
  * Return: 0, on success, Non-zero error value on failure.
  */
-static int axienet_ethtools_set_coalesce(struct net_device *ndev,
-					 struct ethtool_coalesce *ecoalesce)
+static int
+axienet_ethtools_set_coalesce(struct net_device *ndev,
+			      struct ethtool_coalesce *ecoalesce,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
 {
 	struct axienet_local *lp = netdev_priv(ndev);
 
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index b06377fe7293..b780aad3550a 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -1263,7 +1263,7 @@ static const struct net_device_ops xemaclite_netdev_ops = {
 	.ndo_start_xmit		= xemaclite_send,
 	.ndo_set_mac_address	= xemaclite_set_mac_address,
 	.ndo_tx_timeout		= xemaclite_tx_timeout,
-	.ndo_do_ioctl		= xemaclite_ioctl,
+	.ndo_eth_ioctl		= xemaclite_ioctl,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = xemaclite_poll_controller,
 #endif
diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c
index 4f6db6f5c272..ae611e46da6a 100644
--- a/drivers/net/ethernet/xircom/xirc2ps_cs.c
+++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c
@@ -464,7 +464,7 @@ static const struct net_device_ops netdev_ops = {
 	.ndo_start_xmit		= do_start_xmit,
 	.ndo_tx_timeout 	= xirc_tx_timeout,
 	.ndo_set_config		= do_config,
-	.ndo_do_ioctl		= do_ioctl,
+	.ndo_eth_ioctl		= do_ioctl,
 	.ndo_set_rx_mode	= set_multicast_list,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/ethernet/xscale/Kconfig b/drivers/net/ethernet/xscale/Kconfig
index 468ffe3d1707..0e878fa6e322 100644
--- a/drivers/net/ethernet/xscale/Kconfig
+++ b/drivers/net/ethernet/xscale/Kconfig
@@ -29,9 +29,9 @@ config IXP4XX_ETH
 	  on IXP4xx processor.
 
 config PTP_1588_CLOCK_IXP46X
-	tristate "Intel IXP46x as PTP clock"
+	bool "Intel IXP46x as PTP clock"
 	depends on IXP4XX_ETH
-	depends on PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK=y || PTP_1588_CLOCK=IXP4XX_ETH
 	default y
 	help
 	  This driver adds support for using the IXP46X as a PTP
diff --git a/drivers/net/ethernet/xscale/Makefile b/drivers/net/ethernet/xscale/Makefile
index 607f91b1e878..e935f2a2979f 100644
--- a/drivers/net/ethernet/xscale/Makefile
+++ b/drivers/net/ethernet/xscale/Makefile
@@ -3,5 +3,9 @@
 # Makefile for the Intel XScale IXP device drivers.
 #
 
+# Keep this link order to avoid deferred probing
+ifdef CONFIG_PTP_1588_CLOCK_IXP46X
+obj-$(CONFIG_IXP4XX_ETH)		+= ptp_ixp46x.o
+endif
+
 obj-$(CONFIG_IXP4XX_ETH)		+= ixp4xx_eth.o
-obj-$(CONFIG_PTP_1588_CLOCK_IXP46X)	+= ptp_ixp46x.o
diff --git a/drivers/net/ethernet/xscale/ixp46x_ts.h b/drivers/net/ethernet/xscale/ixp46x_ts.h
index d792130e27b0..ee9b93ded20a 100644
--- a/drivers/net/ethernet/xscale/ixp46x_ts.h
+++ b/drivers/net/ethernet/xscale/ixp46x_ts.h
@@ -62,7 +62,16 @@ struct ixp46x_ts_regs {
 #define TX_SNAPSHOT_LOCKED (1<<0)
 #define RX_SNAPSHOT_LOCKED (1<<1)
 
-/* The ptp_ixp46x module will set this variable */
-extern int ixp46x_phc_index;
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK_IXP46X)
+int ixp46x_ptp_find(struct ixp46x_ts_regs *__iomem *regs, int *phc_index);
+#else
+static inline int ixp46x_ptp_find(struct ixp46x_ts_regs *__iomem *regs, int *phc_index)
+{
+	*regs = NULL;
+	*phc_index = -1;
+
+	return -ENODEV;
+}
+#endif
 
 #endif
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index 7ae754eadf22..931494cc1c39 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -37,7 +37,6 @@
 #include <linux/module.h>
 #include <linux/soc/ixp4xx/npe.h>
 #include <linux/soc/ixp4xx/qmgr.h>
-#include <mach/hardware.h>
 #include <linux/soc/ixp4xx/cpu.h>
 
 #include "ixp46x_ts.h"
@@ -169,13 +168,15 @@ struct eth_regs {
 
 struct port {
 	struct eth_regs __iomem *regs;
+	struct ixp46x_ts_regs __iomem *timesync_regs;
+	int phc_index;
 	struct npe *npe;
 	struct net_device *netdev;
 	struct napi_struct napi;
 	struct eth_plat_info *plat;
 	buffer_t *rx_buff_tab[RX_DESCS], *tx_buff_tab[TX_DESCS];
 	struct desc *desc_tab;	/* coherent */
-	u32 desc_tab_phys;
+	dma_addr_t desc_tab_phys;
 	int id;			/* logical port ID */
 	int speed, duplex;
 	u8 firmware[4];
@@ -295,7 +296,7 @@ static void ixp_rx_timestamp(struct port *port, struct sk_buff *skb)
 
 	ch = PORT2CHANNEL(port);
 
-	regs = (struct ixp46x_ts_regs __iomem *) IXP4XX_TIMESYNC_BASE_VIRT;
+	regs = port->timesync_regs;
 
 	val = __raw_readl(&regs->channel[ch].ch_event);
 
@@ -340,7 +341,7 @@ static void ixp_tx_timestamp(struct port *port, struct sk_buff *skb)
 
 	ch = PORT2CHANNEL(port);
 
-	regs = (struct ixp46x_ts_regs __iomem *) IXP4XX_TIMESYNC_BASE_VIRT;
+	regs = port->timesync_regs;
 
 	/*
 	 * This really stinks, but we have to poll for the Tx time stamp.
@@ -375,6 +376,7 @@ static int hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 	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)))
@@ -383,8 +385,12 @@ static int hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 	if (cfg.flags) /* reserved for future extensions */
 		return -EINVAL;
 
+	ret = ixp46x_ptp_find(&port->timesync_regs, &port->phc_index);
+	if (ret)
+		return ret;
+
 	ch = PORT2CHANNEL(port);
-	regs = (struct ixp46x_ts_regs __iomem *) IXP4XX_TIMESYNC_BASE_VIRT;
+	regs = port->timesync_regs;
 
 	if (cfg.tx_type != HWTSTAMP_TX_OFF && cfg.tx_type != HWTSTAMP_TX_ON)
 		return -ERANGE;
@@ -850,14 +856,14 @@ static int eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	bytes = len;
 	mem = skb->data;
 #else
-	offset = (int)skb->data & 3; /* keep 32-bit alignment */
+	offset = (uintptr_t)skb->data & 3; /* keep 32-bit alignment */
 	bytes = ALIGN(offset + len, 4);
 	if (!(mem = kmalloc(bytes, GFP_ATOMIC))) {
 		dev_kfree_skb(skb);
 		dev->stats.tx_dropped++;
 		return NETDEV_TX_OK;
 	}
-	memcpy_swab32(mem, (u32 *)((int)skb->data & ~3), bytes / 4);
+	memcpy_swab32(mem, (u32 *)((uintptr_t)skb->data & ~3), bytes / 4);
 #endif
 
 	phys = dma_map_single(&dev->dev, mem, bytes, DMA_TO_DEVICE);
@@ -988,25 +994,27 @@ static void ixp4xx_get_drvinfo(struct net_device *dev,
 	strlcpy(info->bus_info, "internal", sizeof(info->bus_info));
 }
 
-int ixp46x_phc_index = -1;
-EXPORT_SYMBOL_GPL(ixp46x_phc_index);
-
 static int ixp4xx_get_ts_info(struct net_device *dev,
 			      struct ethtool_ts_info *info)
 {
-	if (!cpu_is_ixp46x()) {
+	struct port *port = netdev_priv(dev);
+
+	if (port->phc_index < 0)
+		ixp46x_ptp_find(&port->timesync_regs, &port->phc_index);
+
+	info->phc_index = port->phc_index;
+
+	if (info->phc_index < 0) {
 		info->so_timestamping =
 			SOF_TIMESTAMPING_TX_SOFTWARE |
 			SOF_TIMESTAMPING_RX_SOFTWARE |
 			SOF_TIMESTAMPING_SOFTWARE;
-		info->phc_index = -1;
 		return 0;
 	}
 	info->so_timestamping =
 		SOF_TIMESTAMPING_TX_HARDWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
-	info->phc_index = ixp46x_phc_index;
 	info->tx_types =
 		(1 << HWTSTAMP_TX_OFF) |
 		(1 << HWTSTAMP_TX_ON);
@@ -1357,7 +1365,7 @@ static const struct net_device_ops ixp4xx_netdev_ops = {
 	.ndo_stop = eth_close,
 	.ndo_start_xmit = eth_xmit,
 	.ndo_set_rx_mode = eth_set_mcast_list,
-	.ndo_do_ioctl = eth_ioctl,
+	.ndo_eth_ioctl = eth_ioctl,
 	.ndo_set_mac_address = eth_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
 };
@@ -1481,6 +1489,7 @@ static int ixp4xx_eth_probe(struct platform_device *pdev)
 	port = netdev_priv(ndev);
 	port->netdev = ndev;
 	port->id = plat->npe;
+	port->phc_index = -1;
 
 	/* Get the port resource and remap */
 	port->regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
diff --git a/drivers/net/ethernet/xscale/ptp_ixp46x.c b/drivers/net/ethernet/xscale/ptp_ixp46x.c
index a6fb88fd42f7..ecece21315c3 100644
--- a/drivers/net/ethernet/xscale/ptp_ixp46x.c
+++ b/drivers/net/ethernet/xscale/ptp_ixp46x.c
@@ -5,14 +5,16 @@
  * Copyright (C) 2010 OMICRON electronics GmbH
  */
 #include <linux/device.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/err.h>
-#include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/ptp_clock_kernel.h>
+#include <linux/platform_device.h>
 #include <linux/soc/ixp4xx/cpu.h>
 #include <linux/module.h>
 #include <mach/ixp4xx-regs.h>
@@ -21,10 +23,6 @@
 
 #define DRIVER		"ptp_ixp46x"
 #define N_EXT_TS	2
-#define MASTER_GPIO	8
-#define MASTER_IRQ	25
-#define SLAVE_GPIO	7
-#define SLAVE_IRQ	24
 
 struct ixp_clock {
 	struct ixp46x_ts_regs *regs;
@@ -32,9 +30,11 @@ struct ixp_clock {
 	struct ptp_clock_info caps;
 	int exts0_enabled;
 	int exts1_enabled;
+	int slave_irq;
+	int master_irq;
 };
 
-DEFINE_SPINLOCK(register_lock);
+static DEFINE_SPINLOCK(register_lock);
 
 /*
  * Register access functions
@@ -243,53 +243,38 @@ static const struct ptp_clock_info ptp_ixp_caps = {
 
 static struct ixp_clock ixp_clock;
 
-static int setup_interrupt(int gpio)
+int ixp46x_ptp_find(struct ixp46x_ts_regs *__iomem *regs, int *phc_index)
 {
-	int irq;
-	int err;
-
-	err = gpio_request(gpio, "ixp4-ptp");
-	if (err)
-		return err;
-
-	err = gpio_direction_input(gpio);
-	if (err)
-		return err;
-
-	irq = gpio_to_irq(gpio);
-	if (irq < 0)
-		return irq;
+	*regs = ixp_clock.regs;
+	*phc_index = ptp_clock_index(ixp_clock.ptp_clock);
 
-	err = irq_set_irq_type(irq, IRQF_TRIGGER_FALLING);
-	if (err) {
-		pr_err("cannot set trigger type for irq %d\n", irq);
-		return err;
-	}
-
-	err = request_irq(irq, isr, 0, DRIVER, &ixp_clock);
-	if (err) {
-		pr_err("request_irq failed for irq %d\n", irq);
-		return err;
-	}
+	if (!ixp_clock.ptp_clock)
+		return -EPROBE_DEFER;
 
-	return irq;
+	return 0;
 }
+EXPORT_SYMBOL_GPL(ixp46x_ptp_find);
 
-static void __exit ptp_ixp_exit(void)
+/* Called from the registered devm action */
+static void ptp_ixp_unregister_action(void *d)
 {
-	free_irq(MASTER_IRQ, &ixp_clock);
-	free_irq(SLAVE_IRQ, &ixp_clock);
-	ixp46x_phc_index = -1;
-	ptp_clock_unregister(ixp_clock.ptp_clock);
+	struct ptp_clock *ptp_clock = d;
+
+	ptp_clock_unregister(ptp_clock);
+	ixp_clock.ptp_clock = NULL;
 }
 
-static int __init ptp_ixp_init(void)
+static int ptp_ixp_probe(struct platform_device *pdev)
 {
-	if (!cpu_is_ixp46x())
-		return -ENODEV;
+	struct device *dev = &pdev->dev;
+	int ret;
 
-	ixp_clock.regs =
-		(struct ixp46x_ts_regs __iomem *) IXP4XX_TIMESYNC_BASE_VIRT;
+	ixp_clock.regs = devm_platform_ioremap_resource(pdev, 0);
+	ixp_clock.master_irq = platform_get_irq(pdev, 0);
+	ixp_clock.slave_irq = platform_get_irq(pdev, 1);
+	if (IS_ERR(ixp_clock.regs) ||
+	    !ixp_clock.master_irq || !ixp_clock.slave_irq)
+		return -ENXIO;
 
 	ixp_clock.caps = ptp_ixp_caps;
 
@@ -298,32 +283,51 @@ static int __init ptp_ixp_init(void)
 	if (IS_ERR(ixp_clock.ptp_clock))
 		return PTR_ERR(ixp_clock.ptp_clock);
 
-	ixp46x_phc_index = ptp_clock_index(ixp_clock.ptp_clock);
+	ret = devm_add_action_or_reset(dev, ptp_ixp_unregister_action,
+				       ixp_clock.ptp_clock);
+	if (ret) {
+		dev_err(dev, "failed to install clock removal handler\n");
+		return ret;
+	}
 
 	__raw_writel(DEFAULT_ADDEND, &ixp_clock.regs->addend);
 	__raw_writel(1, &ixp_clock.regs->trgt_lo);
 	__raw_writel(0, &ixp_clock.regs->trgt_hi);
 	__raw_writel(TTIPEND, &ixp_clock.regs->event);
 
-	if (MASTER_IRQ != setup_interrupt(MASTER_GPIO)) {
-		pr_err("failed to setup gpio %d as irq\n", MASTER_GPIO);
-		goto no_master;
-	}
-	if (SLAVE_IRQ != setup_interrupt(SLAVE_GPIO)) {
-		pr_err("failed to setup gpio %d as irq\n", SLAVE_GPIO);
-		goto no_slave;
-	}
+	ret = devm_request_irq(dev, ixp_clock.master_irq, isr,
+			       0, DRIVER, &ixp_clock);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "request_irq failed for irq %d\n",
+				     ixp_clock.master_irq);
+
+	ret = devm_request_irq(dev, ixp_clock.slave_irq, isr,
+			       0, DRIVER, &ixp_clock);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "request_irq failed for irq %d\n",
+				     ixp_clock.slave_irq);
 
 	return 0;
-no_slave:
-	free_irq(MASTER_IRQ, &ixp_clock);
-no_master:
-	ptp_clock_unregister(ixp_clock.ptp_clock);
-	return -ENODEV;
 }
 
-module_init(ptp_ixp_init);
-module_exit(ptp_ixp_exit);
+static const struct of_device_id ptp_ixp_match[] = {
+	{
+		.compatible = "intel,ixp46x-ptp-timer",
+	},
+	{ },
+};
+
+static struct platform_driver ptp_ixp_driver = {
+	.driver = {
+		.name = "ptp-ixp46x",
+		.of_match_table = ptp_ixp_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = ptp_ixp_probe,
+};
+module_platform_driver(ptp_ixp_driver);
 
 MODULE_AUTHOR("Richard Cochran <richardcochran@gmail.com>");
 MODULE_DESCRIPTION("PTP clock using the IXP46X timer");
diff --git a/drivers/net/fddi/skfp/skfddi.c b/drivers/net/fddi/skfp/skfddi.c
index 69c29a2ef95d..c5cb421f9890 100644
--- a/drivers/net/fddi/skfp/skfddi.c
+++ b/drivers/net/fddi/skfp/skfddi.c
@@ -70,6 +70,7 @@ static const char * const boot_msg =
 /* Include files */
 
 #include <linux/capability.h>
+#include <linux/compat.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -103,7 +104,8 @@ static struct net_device_stats *skfp_ctl_get_stats(struct net_device *dev);
 static void skfp_ctl_set_multicast_list(struct net_device *dev);
 static void skfp_ctl_set_multicast_list_wo_lock(struct net_device *dev);
 static int skfp_ctl_set_mac_address(struct net_device *dev, void *addr);
-static int skfp_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
+static int skfp_siocdevprivate(struct net_device *dev, struct ifreq *rq,
+			       void __user *data, int cmd);
 static netdev_tx_t skfp_send_pkt(struct sk_buff *skb,
 				       struct net_device *dev);
 static void send_queued_packets(struct s_smc *smc);
@@ -164,7 +166,7 @@ static const struct net_device_ops skfp_netdev_ops = {
 	.ndo_get_stats		= skfp_ctl_get_stats,
 	.ndo_set_rx_mode	= skfp_ctl_set_multicast_list,
 	.ndo_set_mac_address	= skfp_ctl_set_mac_address,
-	.ndo_do_ioctl		= skfp_ioctl,
+	.ndo_siocdevprivate	= skfp_siocdevprivate,
 };
 
 /*
@@ -932,9 +934,9 @@ static int skfp_ctl_set_mac_address(struct net_device *dev, void *addr)
 
 
 /*
- * ==============
- * = skfp_ioctl =
- * ==============
+ * =======================
+ * = skfp_siocdevprivate =
+ * =======================
  *   
  * Overview:
  *
@@ -954,16 +956,19 @@ static int skfp_ctl_set_mac_address(struct net_device *dev, void *addr)
  */
 
 
-static int skfp_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+static int skfp_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *data, int cmd)
 {
 	struct s_smc *smc = netdev_priv(dev);
 	skfddi_priv *lp = &smc->os;
 	struct s_skfp_ioctl ioc;
 	int status = 0;
 
-	if (copy_from_user(&ioc, rq->ifr_data, sizeof(struct s_skfp_ioctl)))
+	if (copy_from_user(&ioc, data, sizeof(struct s_skfp_ioctl)))
 		return -EFAULT;
 
+	if (in_compat_syscall())
+		return -EOPNOTSUPP;
+
 	switch (ioc.cmd) {
 	case SKFP_GET_STATS:	/* Get the driver statistics */
 		ioc.len = sizeof(lp->MacStat);
@@ -1169,8 +1174,8 @@ static void send_queued_packets(struct s_smc *smc)
 
 		txd = (struct s_smt_fp_txd *) HWM_GET_CURR_TXD(smc, queue);
 
-		dma_address = pci_map_single(&bp->pdev, skb->data,
-					     skb->len, PCI_DMA_TODEVICE);
+		dma_address = dma_map_single(&(&bp->pdev)->dev, skb->data,
+					     skb->len, DMA_TO_DEVICE);
 		if (frame_status & LAN_TX) {
 			txd->txd_os.skb = skb;			// save skb
 			txd->txd_os.dma_addr = dma_address;	// save dma mapping
@@ -1179,8 +1184,8 @@ static void send_queued_packets(struct s_smc *smc)
                       frame_status | FIRST_FRAG | LAST_FRAG | EN_IRQ_EOF);
 
 		if (!(frame_status & LAN_TX)) {		// local only frame
-			pci_unmap_single(&bp->pdev, dma_address,
-					 skb->len, PCI_DMA_TODEVICE);
+			dma_unmap_single(&(&bp->pdev)->dev, dma_address,
+					 skb->len, DMA_TO_DEVICE);
 			dev_kfree_skb_irq(skb);
 		}
 		spin_unlock_irqrestore(&bp->DriverLock, Flags);
@@ -1462,8 +1467,9 @@ void dma_complete(struct s_smc *smc, volatile union s_fp_descr *descr, int flag)
 		if (r->rxd_os.skb && r->rxd_os.dma_addr) {
 			int MaxFrameSize = bp->MaxFrameSize;
 
-			pci_unmap_single(&bp->pdev, r->rxd_os.dma_addr,
-					 MaxFrameSize, PCI_DMA_FROMDEVICE);
+			dma_unmap_single(&(&bp->pdev)->dev,
+					 r->rxd_os.dma_addr, MaxFrameSize,
+					 DMA_FROM_DEVICE);
 			r->rxd_os.dma_addr = 0;
 		}
 	}
@@ -1498,8 +1504,8 @@ void mac_drv_tx_complete(struct s_smc *smc, volatile struct s_smt_fp_txd *txd)
 	txd->txd_os.skb = NULL;
 
 	// release the DMA mapping
-	pci_unmap_single(&smc->os.pdev, txd->txd_os.dma_addr,
-			 skb->len, PCI_DMA_TODEVICE);
+	dma_unmap_single(&(&smc->os.pdev)->dev, txd->txd_os.dma_addr,
+			 skb->len, DMA_TO_DEVICE);
 	txd->txd_os.dma_addr = 0;
 
 	smc->os.MacStat.gen.tx_packets++;	// Count transmitted packets.
@@ -1702,10 +1708,9 @@ void mac_drv_requeue_rxd(struct s_smc *smc, volatile struct s_smt_fp_rxd *rxd,
 				skb_reserve(skb, 3);
 				skb_put(skb, MaxFrameSize);
 				v_addr = skb->data;
-				b_addr = pci_map_single(&smc->os.pdev,
-							v_addr,
-							MaxFrameSize,
-							PCI_DMA_FROMDEVICE);
+				b_addr = dma_map_single(&(&smc->os.pdev)->dev,
+							v_addr, MaxFrameSize,
+							DMA_FROM_DEVICE);
 				rxd->rxd_os.dma_addr = b_addr;
 			} else {
 				// no skb available, use local buffer
@@ -1718,10 +1723,8 @@ void mac_drv_requeue_rxd(struct s_smc *smc, volatile struct s_smt_fp_rxd *rxd,
 			// we use skb from old rxd
 			rxd->rxd_os.skb = skb;
 			v_addr = skb->data;
-			b_addr = pci_map_single(&smc->os.pdev,
-						v_addr,
-						MaxFrameSize,
-						PCI_DMA_FROMDEVICE);
+			b_addr = dma_map_single(&(&smc->os.pdev)->dev, v_addr,
+						MaxFrameSize, DMA_FROM_DEVICE);
 			rxd->rxd_os.dma_addr = b_addr;
 		}
 		hwm_rx_frag(smc, v_addr, b_addr, MaxFrameSize,
@@ -1773,10 +1776,8 @@ void mac_drv_fill_rxd(struct s_smc *smc)
 			skb_reserve(skb, 3);
 			skb_put(skb, MaxFrameSize);
 			v_addr = skb->data;
-			b_addr = pci_map_single(&smc->os.pdev,
-						v_addr,
-						MaxFrameSize,
-						PCI_DMA_FROMDEVICE);
+			b_addr = dma_map_single(&(&smc->os.pdev)->dev, v_addr,
+						MaxFrameSize, DMA_FROM_DEVICE);
 			rxd->rxd_os.dma_addr = b_addr;
 		} else {
 			// no skb available, use local buffer
@@ -1833,8 +1834,9 @@ void mac_drv_clear_rxd(struct s_smc *smc, volatile struct s_smt_fp_rxd *rxd,
 			skfddi_priv *bp = &smc->os;
 			int MaxFrameSize = bp->MaxFrameSize;
 
-			pci_unmap_single(&bp->pdev, rxd->rxd_os.dma_addr,
-					 MaxFrameSize, PCI_DMA_FROMDEVICE);
+			dma_unmap_single(&(&bp->pdev)->dev,
+					 rxd->rxd_os.dma_addr, MaxFrameSize,
+					 DMA_FROM_DEVICE);
 
 			dev_kfree_skb(skb);
 			rxd->rxd_os.skb = NULL;
diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c
index 4435a1195194..775dcf4ebde5 100644
--- a/drivers/net/hamradio/baycom_epp.c
+++ b/drivers/net/hamradio/baycom_epp.c
@@ -1005,7 +1005,8 @@ static int baycom_setmode(struct baycom_state *bc, const char *modestr)
 
 /* --------------------------------------------------------------------- */
 
-static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int baycom_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+				 void __user *data, int cmd)
 {
 	struct baycom_state *bc = netdev_priv(dev);
 	struct hdlcdrv_ioctl hi;
@@ -1013,7 +1014,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	if (cmd != SIOCDEVPRIVATE)
 		return -ENOIOCTLCMD;
 
-	if (copy_from_user(&hi, ifr->ifr_data, sizeof(hi)))
+	if (copy_from_user(&hi, data, sizeof(hi)))
 		return -EFAULT;
 	switch (hi.cmd) {
 	default:
@@ -1104,7 +1105,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		return HDLCDRV_PARMASK_IOBASE;
 
 	}
-	if (copy_to_user(ifr->ifr_data, &hi, sizeof(hi)))
+	if (copy_to_user(data, &hi, sizeof(hi)))
 		return -EFAULT;
 	return 0;
 }
@@ -1114,7 +1115,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 static const struct net_device_ops baycom_netdev_ops = {
 	.ndo_open	     = epp_open,
 	.ndo_stop	     = epp_close,
-	.ndo_do_ioctl	     = baycom_ioctl,
+	.ndo_siocdevprivate  = baycom_siocdevprivate,
 	.ndo_start_xmit      = baycom_send_packet,
 	.ndo_set_mac_address = baycom_set_mac_address,
 };
diff --git a/drivers/net/hamradio/baycom_par.c b/drivers/net/hamradio/baycom_par.c
index 6a3dc7b3f28a..fd7da5bb1fa5 100644
--- a/drivers/net/hamradio/baycom_par.c
+++ b/drivers/net/hamradio/baycom_par.c
@@ -380,7 +380,7 @@ static int par96_close(struct net_device *dev)
  * ===================== hdlcdrv driver interface =========================
  */
 
-static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
+static int baycom_ioctl(struct net_device *dev, void __user *data,
 			struct hdlcdrv_ioctl *hi, int cmd);
 
 /* --------------------------------------------------------------------- */
@@ -408,7 +408,7 @@ static int baycom_setmode(struct baycom_state *bc, const char *modestr)
 
 /* --------------------------------------------------------------------- */
 
-static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
+static int baycom_ioctl(struct net_device *dev, void __user *data,
 			struct hdlcdrv_ioctl *hi, int cmd)
 {
 	struct baycom_state *bc;
@@ -428,7 +428,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
 
 	case HDLCDRVCTL_GETMODE:
 		strcpy(hi->data.modename, bc->options ? "par96" : "picpar");
-		if (copy_to_user(ifr->ifr_data, hi, sizeof(struct hdlcdrv_ioctl)))
+		if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl)))
 			return -EFAULT;
 		return 0;
 
@@ -440,7 +440,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
 
 	case HDLCDRVCTL_MODELIST:
 		strcpy(hi->data.modename, "par96,picpar");
-		if (copy_to_user(ifr->ifr_data, hi, sizeof(struct hdlcdrv_ioctl)))
+		if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl)))
 			return -EFAULT;
 		return 0;
 
@@ -449,7 +449,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
 
 	}
 
-	if (copy_from_user(&bi, ifr->ifr_data, sizeof(bi)))
+	if (copy_from_user(&bi, data, sizeof(bi)))
 		return -EFAULT;
 	switch (bi.cmd) {
 	default:
@@ -464,7 +464,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
 #endif /* BAYCOM_DEBUG */
 
 	}
-	if (copy_to_user(ifr->ifr_data, &bi, sizeof(bi)))
+	if (copy_to_user(data, &bi, sizeof(bi)))
 		return -EFAULT;
 	return 0;
 
diff --git a/drivers/net/hamradio/baycom_ser_fdx.c b/drivers/net/hamradio/baycom_ser_fdx.c
index 04bb409707fc..646f605e358f 100644
--- a/drivers/net/hamradio/baycom_ser_fdx.c
+++ b/drivers/net/hamradio/baycom_ser_fdx.c
@@ -462,7 +462,7 @@ static int ser12_close(struct net_device *dev)
 
 /* --------------------------------------------------------------------- */
 
-static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
+static int baycom_ioctl(struct net_device *dev, void __user *data,
 			struct hdlcdrv_ioctl *hi, int cmd);
 
 /* --------------------------------------------------------------------- */
@@ -497,7 +497,7 @@ static int baycom_setmode(struct baycom_state *bc, const char *modestr)
 
 /* --------------------------------------------------------------------- */
 
-static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
+static int baycom_ioctl(struct net_device *dev, void __user *data,
 			struct hdlcdrv_ioctl *hi, int cmd)
 {
 	struct baycom_state *bc;
@@ -519,7 +519,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
 		sprintf(hi->data.modename, "ser%u", bc->baud / 100);
 		if (bc->opt_dcd <= 0)
 			strcat(hi->data.modename, (!bc->opt_dcd) ? "*" : "+");
-		if (copy_to_user(ifr->ifr_data, hi, sizeof(struct hdlcdrv_ioctl)))
+		if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl)))
 			return -EFAULT;
 		return 0;
 
@@ -531,7 +531,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
 
 	case HDLCDRVCTL_MODELIST:
 		strcpy(hi->data.modename, "ser12,ser3,ser24");
-		if (copy_to_user(ifr->ifr_data, hi, sizeof(struct hdlcdrv_ioctl)))
+		if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl)))
 			return -EFAULT;
 		return 0;
 
@@ -540,7 +540,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
 
 	}
 
-	if (copy_from_user(&bi, ifr->ifr_data, sizeof(bi)))
+	if (copy_from_user(&bi, data, sizeof(bi)))
 		return -EFAULT;
 	switch (bi.cmd) {
 	default:
@@ -555,7 +555,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
 #endif /* BAYCOM_DEBUG */
 
 	}
-	if (copy_to_user(ifr->ifr_data, &bi, sizeof(bi)))
+	if (copy_to_user(data, &bi, sizeof(bi)))
 		return -EFAULT;
 	return 0;
 
diff --git a/drivers/net/hamradio/baycom_ser_hdx.c b/drivers/net/hamradio/baycom_ser_hdx.c
index a1acb3a47bdb..5d1ab4840753 100644
--- a/drivers/net/hamradio/baycom_ser_hdx.c
+++ b/drivers/net/hamradio/baycom_ser_hdx.c
@@ -521,7 +521,7 @@ static int ser12_close(struct net_device *dev)
 
 /* --------------------------------------------------------------------- */
 
-static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
+static int baycom_ioctl(struct net_device *dev, void __user *data,
 			struct hdlcdrv_ioctl *hi, int cmd);
 
 /* --------------------------------------------------------------------- */
@@ -551,7 +551,7 @@ static int baycom_setmode(struct baycom_state *bc, const char *modestr)
 
 /* --------------------------------------------------------------------- */
 
-static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
+static int baycom_ioctl(struct net_device *dev, void __user *data,
 			struct hdlcdrv_ioctl *hi, int cmd)
 {
 	struct baycom_state *bc;
@@ -573,7 +573,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
 		strcpy(hi->data.modename, "ser12");
 		if (bc->opt_dcd <= 0)
 			strcat(hi->data.modename, (!bc->opt_dcd) ? "*" : (bc->opt_dcd == -2) ? "@" : "+");
-		if (copy_to_user(ifr->ifr_data, hi, sizeof(struct hdlcdrv_ioctl)))
+		if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl)))
 			return -EFAULT;
 		return 0;
 
@@ -585,7 +585,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
 
 	case HDLCDRVCTL_MODELIST:
 		strcpy(hi->data.modename, "ser12");
-		if (copy_to_user(ifr->ifr_data, hi, sizeof(struct hdlcdrv_ioctl)))
+		if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl)))
 			return -EFAULT;
 		return 0;
 
@@ -594,7 +594,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
 
 	}
 
-	if (copy_from_user(&bi, ifr->ifr_data, sizeof(bi)))
+	if (copy_from_user(&bi, data, sizeof(bi)))
 		return -EFAULT;
 	switch (bi.cmd) {
 	default:
@@ -609,7 +609,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr,
 #endif /* BAYCOM_DEBUG */
 
 	}
-	if (copy_to_user(ifr->ifr_data, &bi, sizeof(bi)))
+	if (copy_to_user(data, &bi, sizeof(bi)))
 		return -EFAULT;
 	return 0;
 
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index 0e623c2e8b2d..d967b0748773 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -314,9 +314,10 @@ static int bpq_set_mac_address(struct net_device *dev, void *addr)
  *					source ethernet address (broadcast
  *					or multicast: accept all)
  */
-static int bpq_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int bpq_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			      void __user *data, int cmd)
 {
-	struct bpq_ethaddr __user *ethaddr = ifr->ifr_data;
+	struct bpq_ethaddr __user *ethaddr = data;
 	struct bpqdev *bpq = netdev_priv(dev);
 	struct bpq_req req;
 
@@ -325,7 +326,7 @@ static int bpq_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 	switch (cmd) {
 		case SIOCSBPQETHOPT:
-			if (copy_from_user(&req, ifr->ifr_data, sizeof(struct bpq_req)))
+			if (copy_from_user(&req, data, sizeof(struct bpq_req)))
 				return -EFAULT;
 			switch (req.cmd) {
 				case SIOCGBPQETHPARAM:
@@ -448,7 +449,7 @@ static const struct net_device_ops bpq_netdev_ops = {
 	.ndo_stop	     = bpq_close,
 	.ndo_start_xmit	     = bpq_xmit,
 	.ndo_set_mac_address = bpq_set_mac_address,
-	.ndo_do_ioctl	     = bpq_ioctl,
+	.ndo_siocdevprivate  = bpq_siocdevprivate,
 };
 
 static void bpq_setup(struct net_device *dev)
diff --git a/drivers/net/hamradio/dmascc.c b/drivers/net/hamradio/dmascc.c
index c25c8c99c5c7..b50b7fafd8d6 100644
--- a/drivers/net/hamradio/dmascc.c
+++ b/drivers/net/hamradio/dmascc.c
@@ -225,7 +225,8 @@ static int read_scc_data(struct scc_priv *priv);
 
 static int scc_open(struct net_device *dev);
 static int scc_close(struct net_device *dev);
-static int scc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
+static int scc_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			      void __user *data, int cmd);
 static int scc_send_packet(struct sk_buff *skb, struct net_device *dev);
 static int scc_set_mac_address(struct net_device *dev, void *sa);
 
@@ -432,7 +433,7 @@ static const struct net_device_ops scc_netdev_ops = {
 	.ndo_open = scc_open,
 	.ndo_stop = scc_close,
 	.ndo_start_xmit = scc_send_packet,
-	.ndo_do_ioctl = scc_ioctl,
+	.ndo_siocdevprivate = scc_siocdevprivate,
 	.ndo_set_mac_address = scc_set_mac_address,
 };
 
@@ -881,15 +882,13 @@ static int scc_close(struct net_device *dev)
 }
 
 
-static int scc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int scc_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd)
 {
 	struct scc_priv *priv = dev->ml_priv;
 
 	switch (cmd) {
 	case SIOCGSCCPARAM:
-		if (copy_to_user
-		    (ifr->ifr_data, &priv->param,
-		     sizeof(struct scc_param)))
+		if (copy_to_user(data, &priv->param, sizeof(struct scc_param)))
 			return -EFAULT;
 		return 0;
 	case SIOCSSCCPARAM:
@@ -897,13 +896,12 @@ static int scc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			return -EPERM;
 		if (netif_running(dev))
 			return -EAGAIN;
-		if (copy_from_user
-		    (&priv->param, ifr->ifr_data,
-		     sizeof(struct scc_param)))
+		if (copy_from_user(&priv->param, data,
+				   sizeof(struct scc_param)))
 			return -EFAULT;
 		return 0;
 	default:
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 }
 
diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c
index cbaf1cdde7cb..5805cfc83854 100644
--- a/drivers/net/hamradio/hdlcdrv.c
+++ b/drivers/net/hamradio/hdlcdrv.c
@@ -483,23 +483,25 @@ static int hdlcdrv_close(struct net_device *dev)
 
 /* --------------------------------------------------------------------- */
 
-static int hdlcdrv_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int hdlcdrv_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+				  void __user *data, int cmd)
 {
 	struct hdlcdrv_state *s = netdev_priv(dev);
 	struct hdlcdrv_ioctl bi;
 
-	if (cmd != SIOCDEVPRIVATE) {
-		if (s->ops && s->ops->ioctl)
-			return s->ops->ioctl(dev, ifr, &bi, cmd);
+	if (cmd != SIOCDEVPRIVATE)
 		return -ENOIOCTLCMD;
-	}
-	if (copy_from_user(&bi, ifr->ifr_data, sizeof(bi)))
+
+	if (in_compat_syscall()) /* to be implemented */
+		return -ENOIOCTLCMD;
+
+	if (copy_from_user(&bi, data, sizeof(bi)))
 		return -EFAULT;
 
 	switch (bi.cmd) {
 	default:
 		if (s->ops && s->ops->ioctl)
-			return s->ops->ioctl(dev, ifr, &bi, cmd);
+			return s->ops->ioctl(dev, data, &bi, cmd);
 		return -ENOIOCTLCMD;
 
 	case HDLCDRVCTL_GETCHANNELPAR:
@@ -605,7 +607,7 @@ static int hdlcdrv_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		break;
 		
 	}
-	if (copy_to_user(ifr->ifr_data, &bi, sizeof(bi)))
+	if (copy_to_user(data, &bi, sizeof(bi)))
 		return -EFAULT;
 	return 0;
 
@@ -617,7 +619,7 @@ static const struct net_device_ops hdlcdrv_netdev = {
 	.ndo_open	= hdlcdrv_open,
 	.ndo_stop	= hdlcdrv_close,
 	.ndo_start_xmit = hdlcdrv_send_packet,
-	.ndo_do_ioctl	= hdlcdrv_ioctl,
+	.ndo_siocdevprivate  = hdlcdrv_siocdevprivate,
 	.ndo_set_mac_address = hdlcdrv_set_mac_address,
 };
 
diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c
index 3f1edd0526a4..e0bb131a33d7 100644
--- a/drivers/net/hamradio/scc.c
+++ b/drivers/net/hamradio/scc.c
@@ -210,7 +210,8 @@ static int scc_net_close(struct net_device *dev);
 static void scc_net_rx(struct scc_channel *scc, struct sk_buff *skb);
 static netdev_tx_t scc_net_tx(struct sk_buff *skb,
 			      struct net_device *dev);
-static int scc_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
+static int scc_net_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+				  void __user *data, int cmd);
 static int scc_net_set_mac_address(struct net_device *dev, void *addr);
 static struct net_device_stats * scc_net_get_stats(struct net_device *dev);
 
@@ -1550,7 +1551,7 @@ static const struct net_device_ops scc_netdev_ops = {
 	.ndo_start_xmit	     = scc_net_tx,
 	.ndo_set_mac_address = scc_net_set_mac_address,
 	.ndo_get_stats       = scc_net_get_stats,
-	.ndo_do_ioctl        = scc_net_ioctl,
+	.ndo_siocdevprivate  = scc_net_siocdevprivate,
 };
 
 /* ----> Initialize device <----- */
@@ -1703,7 +1704,8 @@ static netdev_tx_t scc_net_tx(struct sk_buff *skb, struct net_device *dev)
  * SIOCSCCCAL		- send calib. pattern	arg: (struct scc_calibrate *) arg
  */
 
-static int scc_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int scc_net_siocdevprivate(struct net_device *dev,
+				  struct ifreq *ifr, void __user *arg, int cmd)
 {
 	struct scc_kiss_cmd kiss_cmd;
 	struct scc_mem_config memcfg;
@@ -1712,8 +1714,6 @@ static int scc_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	struct scc_channel *scc = (struct scc_channel *) dev->ml_priv;
 	int chan;
 	unsigned char device_name[IFNAMSIZ];
-	void __user *arg = ifr->ifr_data;
-	
 	
 	if (!Driver_Initialized)
 	{
@@ -1722,6 +1722,9 @@ static int scc_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			int found = 1;
 
 			if (!capable(CAP_SYS_RAWIO)) return -EPERM;
+			if (in_compat_syscall())
+				return -EOPNOTSUPP;
+
 			if (!arg) return -EFAULT;
 
 			if (Nchips >= SCC_MAXCHIPS) 
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index d4911041596c..6ddacbdb224b 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -920,15 +920,15 @@ static int yam_close(struct net_device *dev)
 
 /* --------------------------------------------------------------------- */
 
-static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int yam_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd)
 {
 	struct yam_port *yp = netdev_priv(dev);
 	struct yamdrv_ioctl_cfg yi;
 	struct yamdrv_ioctl_mcs *ym;
 	int ioctl_cmd;
 
-	if (copy_from_user(&ioctl_cmd, ifr->ifr_data, sizeof(int)))
-		 return -EFAULT;
+	if (copy_from_user(&ioctl_cmd, data, sizeof(int)))
+		return -EFAULT;
 
 	if (yp->magic != YAM_MAGIC)
 		return -EINVAL;
@@ -947,8 +947,7 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCYAMSMCS:
 		if (netif_running(dev))
 			return -EINVAL;		/* Cannot change this parameter when up */
-		ym = memdup_user(ifr->ifr_data,
-				 sizeof(struct yamdrv_ioctl_mcs));
+		ym = memdup_user(data, sizeof(struct yamdrv_ioctl_mcs));
 		if (IS_ERR(ym))
 			return PTR_ERR(ym);
 		if (ym->cmd != SIOCYAMSMCS)
@@ -965,8 +964,8 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCYAMSCFG:
 		if (!capable(CAP_SYS_RAWIO))
 			return -EPERM;
-		if (copy_from_user(&yi, ifr->ifr_data, sizeof(struct yamdrv_ioctl_cfg)))
-			 return -EFAULT;
+		if (copy_from_user(&yi, data, sizeof(struct yamdrv_ioctl_cfg)))
+			return -EFAULT;
 
 		if (yi.cmd != SIOCYAMSCFG)
 			return -EINVAL;
@@ -1045,8 +1044,8 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		yi.cfg.txtail = yp->txtail;
 		yi.cfg.persist = yp->pers;
 		yi.cfg.slottime = yp->slot;
-		if (copy_to_user(ifr->ifr_data, &yi, sizeof(struct yamdrv_ioctl_cfg)))
-			 return -EFAULT;
+		if (copy_to_user(data, &yi, sizeof(struct yamdrv_ioctl_cfg)))
+			return -EFAULT;
 		break;
 
 	default:
@@ -1074,7 +1073,7 @@ static const struct net_device_ops yam_netdev_ops = {
 	.ndo_open	     = yam_open,
 	.ndo_stop	     = yam_close,
 	.ndo_start_xmit      = yam_send_packet,
-	.ndo_do_ioctl 	     = yam_ioctl,
+	.ndo_siocdevprivate  = yam_siocdevprivate,
 	.ndo_set_mac_address = yam_set_mac_address,
 };
 
diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c
index 22010384c4a3..7661dbb31162 100644
--- a/drivers/net/hippi/rrunner.c
+++ b/drivers/net/hippi/rrunner.c
@@ -63,7 +63,7 @@ static const char version[] =
 static const struct net_device_ops rr_netdev_ops = {
 	.ndo_open 		= rr_open,
 	.ndo_stop		= rr_close,
-	.ndo_do_ioctl		= rr_ioctl,
+	.ndo_siocdevprivate	= rr_siocdevprivate,
 	.ndo_start_xmit		= rr_start_xmit,
 	.ndo_set_mac_address	= hippi_mac_addr,
 };
@@ -1568,7 +1568,8 @@ out:
 }
 
 
-static int rr_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+static int rr_siocdevprivate(struct net_device *dev, struct ifreq *rq,
+			     void __user *data, int cmd)
 {
 	struct rr_private *rrpriv;
 	unsigned char *image, *oldimage;
@@ -1603,7 +1604,7 @@ static int rr_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 			error = -EFAULT;
 			goto gf_out;
 		}
-		error = copy_to_user(rq->ifr_data, image, EEPROM_BYTES);
+		error = copy_to_user(data, image, EEPROM_BYTES);
 		if (error)
 			error = -EFAULT;
 	gf_out:
@@ -1615,7 +1616,7 @@ static int rr_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 			return -EPERM;
 		}
 
-		image = memdup_user(rq->ifr_data, EEPROM_BYTES);
+		image = memdup_user(data, EEPROM_BYTES);
 		if (IS_ERR(image))
 			return PTR_ERR(image);
 
@@ -1658,7 +1659,7 @@ static int rr_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		return error;
 
 	case SIOCRRID:
-		return put_user(0x52523032, (int __user *)rq->ifr_data);
+		return put_user(0x52523032, (int __user *)data);
 	default:
 		return error;
 	}
diff --git a/drivers/net/hippi/rrunner.h b/drivers/net/hippi/rrunner.h
index 87533784604f..55377614e752 100644
--- a/drivers/net/hippi/rrunner.h
+++ b/drivers/net/hippi/rrunner.h
@@ -835,7 +835,8 @@ static int rr_open(struct net_device *dev);
 static netdev_tx_t rr_start_xmit(struct sk_buff *skb,
 				 struct net_device *dev);
 static int rr_close(struct net_device *dev);
-static int rr_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
+static int rr_siocdevprivate(struct net_device *dev, struct ifreq *rq,
+			     void __user *data, int cmd);
 static unsigned int rr_read_eeprom(struct rr_private *rrpriv,
 				   unsigned long offset,
 				   unsigned char *buf,
diff --git a/drivers/net/ipa/Makefile b/drivers/net/ipa/Makefile
index 506f8d5cd4ee..bdfb2430ab2c 100644
--- a/drivers/net/ipa/Makefile
+++ b/drivers/net/ipa/Makefile
@@ -1,9 +1,6 @@
-# Un-comment the next line if you want to validate configuration data
-#ccflags-y		+=	-DIPA_VALIDATE
-
 obj-$(CONFIG_QCOM_IPA)	+=	ipa.o
 
-ipa-y			:=	ipa_main.o ipa_clock.o ipa_reg.o ipa_mem.o \
+ipa-y			:=	ipa_main.o ipa_power.o ipa_reg.o ipa_mem.o \
 				ipa_table.o ipa_interrupt.o gsi.o gsi_trans.o \
 				ipa_gsi.o ipa_smp2p.o ipa_uc.o \
 				ipa_endpoint.o ipa_cmd.o ipa_modem.o \
diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c
index 427c68b2ad8f..a2fcdb1abdb9 100644
--- a/drivers/net/ipa/gsi.c
+++ b/drivers/net/ipa/gsi.c
@@ -198,77 +198,6 @@ static void gsi_irq_type_disable(struct gsi *gsi, enum gsi_irq_type_id type_id)
 	gsi_irq_type_update(gsi, gsi->type_enabled_bitmap & ~BIT(type_id));
 }
 
-/* Turn off all GSI interrupts initially; there is no gsi_irq_teardown() */
-static void gsi_irq_setup(struct gsi *gsi)
-{
-	/* Disable all interrupt types */
-	gsi_irq_type_update(gsi, 0);
-
-	/* Clear all type-specific interrupt masks */
-	iowrite32(0, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_MSK_OFFSET);
-	iowrite32(0, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_MSK_OFFSET);
-	iowrite32(0, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET);
-	iowrite32(0, gsi->virt + GSI_CNTXT_SRC_IEOB_IRQ_MSK_OFFSET);
-
-	/* The inter-EE interrupts are not supported for IPA v3.0-v3.1 */
-	if (gsi->version > IPA_VERSION_3_1) {
-		u32 offset;
-
-		/* These registers are in the non-adjusted address range */
-		offset = GSI_INTER_EE_SRC_CH_IRQ_MSK_OFFSET;
-		iowrite32(0, gsi->virt_raw + offset);
-		offset = GSI_INTER_EE_SRC_EV_CH_IRQ_MSK_OFFSET;
-		iowrite32(0, gsi->virt_raw + offset);
-	}
-
-	iowrite32(0, gsi->virt + GSI_CNTXT_GSI_IRQ_EN_OFFSET);
-}
-
-/* Get # supported channel and event rings; there is no gsi_ring_teardown() */
-static int gsi_ring_setup(struct gsi *gsi)
-{
-	struct device *dev = gsi->dev;
-	u32 count;
-	u32 val;
-
-	if (gsi->version < IPA_VERSION_3_5_1) {
-		/* No HW_PARAM_2 register prior to IPA v3.5.1, assume the max */
-		gsi->channel_count = GSI_CHANNEL_COUNT_MAX;
-		gsi->evt_ring_count = GSI_EVT_RING_COUNT_MAX;
-
-		return 0;
-	}
-
-	val = ioread32(gsi->virt + GSI_GSI_HW_PARAM_2_OFFSET);
-
-	count = u32_get_bits(val, NUM_CH_PER_EE_FMASK);
-	if (!count) {
-		dev_err(dev, "GSI reports zero channels supported\n");
-		return -EINVAL;
-	}
-	if (count > GSI_CHANNEL_COUNT_MAX) {
-		dev_warn(dev, "limiting to %u channels; hardware supports %u\n",
-			 GSI_CHANNEL_COUNT_MAX, count);
-		count = GSI_CHANNEL_COUNT_MAX;
-	}
-	gsi->channel_count = count;
-
-	count = u32_get_bits(val, NUM_EV_PER_EE_FMASK);
-	if (!count) {
-		dev_err(dev, "GSI reports zero event rings supported\n");
-		return -EINVAL;
-	}
-	if (count > GSI_EVT_RING_COUNT_MAX) {
-		dev_warn(dev,
-			 "limiting to %u event rings; hardware supports %u\n",
-			 GSI_EVT_RING_COUNT_MAX, count);
-		count = GSI_EVT_RING_COUNT_MAX;
-	}
-	gsi->evt_ring_count = count;
-
-	return 0;
-}
-
 /* Event ring commands are performed one at a time.  Their completion
  * is signaled by the event ring control GSI interrupt type, which is
  * only enabled when we issue an event ring command.  Only the event
@@ -920,12 +849,13 @@ static void gsi_channel_program(struct gsi_channel *channel, bool doorbell)
 	/* All done! */
 }
 
-static int __gsi_channel_start(struct gsi_channel *channel, bool start)
+static int __gsi_channel_start(struct gsi_channel *channel, bool resume)
 {
 	struct gsi *gsi = channel->gsi;
 	int ret;
 
-	if (!start)
+	/* Prior to IPA v4.0 suspend/resume is not implemented by GSI */
+	if (resume && gsi->version < IPA_VERSION_4_0)
 		return 0;
 
 	mutex_lock(&gsi->mutex);
@@ -947,7 +877,7 @@ int gsi_channel_start(struct gsi *gsi, u32 channel_id)
 	napi_enable(&channel->napi);
 	gsi_irq_ieob_enable_one(gsi, channel->evt_ring_id);
 
-	ret = __gsi_channel_start(channel, true);
+	ret = __gsi_channel_start(channel, false);
 	if (ret) {
 		gsi_irq_ieob_disable_one(gsi, channel->evt_ring_id);
 		napi_disable(&channel->napi);
@@ -971,7 +901,7 @@ static int gsi_channel_stop_retry(struct gsi_channel *channel)
 	return ret;
 }
 
-static int __gsi_channel_stop(struct gsi_channel *channel, bool stop)
+static int __gsi_channel_stop(struct gsi_channel *channel, bool suspend)
 {
 	struct gsi *gsi = channel->gsi;
 	int ret;
@@ -979,7 +909,8 @@ static int __gsi_channel_stop(struct gsi_channel *channel, bool stop)
 	/* Wait for any underway transactions to complete before stopping. */
 	gsi_channel_trans_quiesce(channel);
 
-	if (!stop)
+	/* Prior to IPA v4.0 suspend/resume is not implemented by GSI */
+	if (suspend && gsi->version < IPA_VERSION_4_0)
 		return 0;
 
 	mutex_lock(&gsi->mutex);
@@ -997,7 +928,7 @@ int gsi_channel_stop(struct gsi *gsi, u32 channel_id)
 	struct gsi_channel *channel = &gsi->channel[channel_id];
 	int ret;
 
-	ret = __gsi_channel_stop(channel, true);
+	ret = __gsi_channel_stop(channel, false);
 	if (ret)
 		return ret;
 
@@ -1026,13 +957,13 @@ void gsi_channel_reset(struct gsi *gsi, u32 channel_id, bool doorbell)
 	mutex_unlock(&gsi->mutex);
 }
 
-/* Stop a STARTED channel for suspend (using stop if requested) */
-int gsi_channel_suspend(struct gsi *gsi, u32 channel_id, bool stop)
+/* Stop a started channel for suspend */
+int gsi_channel_suspend(struct gsi *gsi, u32 channel_id)
 {
 	struct gsi_channel *channel = &gsi->channel[channel_id];
 	int ret;
 
-	ret = __gsi_channel_stop(channel, stop);
+	ret = __gsi_channel_stop(channel, true);
 	if (ret)
 		return ret;
 
@@ -1042,12 +973,24 @@ int gsi_channel_suspend(struct gsi *gsi, u32 channel_id, bool stop)
 	return 0;
 }
 
-/* Resume a suspended channel (starting will be requested if STOPPED) */
-int gsi_channel_resume(struct gsi *gsi, u32 channel_id, bool start)
+/* Resume a suspended channel (starting if stopped) */
+int gsi_channel_resume(struct gsi *gsi, u32 channel_id)
 {
 	struct gsi_channel *channel = &gsi->channel[channel_id];
 
-	return __gsi_channel_start(channel, start);
+	return __gsi_channel_start(channel, true);
+}
+
+/* Prevent all GSI interrupts while suspended */
+void gsi_suspend(struct gsi *gsi)
+{
+	disable_irq(gsi->irq);
+}
+
+/* Allow all GSI interrupts again when resuming */
+void gsi_resume(struct gsi *gsi)
+{
+	enable_irq(gsi->irq);
 }
 
 /**
@@ -1372,33 +1315,20 @@ static irqreturn_t gsi_isr(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+/* Init function for GSI IRQ lookup; there is no gsi_irq_exit() */
 static int gsi_irq_init(struct gsi *gsi, struct platform_device *pdev)
 {
-	struct device *dev = &pdev->dev;
-	unsigned int irq;
 	int ret;
 
 	ret = platform_get_irq_byname(pdev, "gsi");
 	if (ret <= 0)
 		return ret ? : -EINVAL;
 
-	irq = ret;
-
-	ret = request_irq(irq, gsi_isr, 0, "gsi", gsi);
-	if (ret) {
-		dev_err(dev, "error %d requesting \"gsi\" IRQ\n", ret);
-		return ret;
-	}
-	gsi->irq = irq;
+	gsi->irq = ret;
 
 	return 0;
 }
 
-static void gsi_irq_exit(struct gsi *gsi)
-{
-	free_irq(gsi->irq, gsi);
-}
-
 /* Return the transaction associated with a transfer completion event */
 static struct gsi_trans *gsi_event_trans(struct gsi_channel *channel,
 					 struct gsi_event *event)
@@ -1876,6 +1806,93 @@ static void gsi_channel_teardown(struct gsi *gsi)
 	gsi_irq_disable(gsi);
 }
 
+/* Turn off all GSI interrupts initially */
+static int gsi_irq_setup(struct gsi *gsi)
+{
+	int ret;
+
+	/* Writing 1 indicates IRQ interrupts; 0 would be MSI */
+	iowrite32(1, gsi->virt + GSI_CNTXT_INTSET_OFFSET);
+
+	/* Disable all interrupt types */
+	gsi_irq_type_update(gsi, 0);
+
+	/* Clear all type-specific interrupt masks */
+	iowrite32(0, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_MSK_OFFSET);
+	iowrite32(0, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_MSK_OFFSET);
+	iowrite32(0, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET);
+	iowrite32(0, gsi->virt + GSI_CNTXT_SRC_IEOB_IRQ_MSK_OFFSET);
+
+	/* The inter-EE interrupts are not supported for IPA v3.0-v3.1 */
+	if (gsi->version > IPA_VERSION_3_1) {
+		u32 offset;
+
+		/* These registers are in the non-adjusted address range */
+		offset = GSI_INTER_EE_SRC_CH_IRQ_MSK_OFFSET;
+		iowrite32(0, gsi->virt_raw + offset);
+		offset = GSI_INTER_EE_SRC_EV_CH_IRQ_MSK_OFFSET;
+		iowrite32(0, gsi->virt_raw + offset);
+	}
+
+	iowrite32(0, gsi->virt + GSI_CNTXT_GSI_IRQ_EN_OFFSET);
+
+	ret = request_irq(gsi->irq, gsi_isr, 0, "gsi", gsi);
+	if (ret)
+		dev_err(gsi->dev, "error %d requesting \"gsi\" IRQ\n", ret);
+
+	return ret;
+}
+
+static void gsi_irq_teardown(struct gsi *gsi)
+{
+	free_irq(gsi->irq, gsi);
+}
+
+/* Get # supported channel and event rings; there is no gsi_ring_teardown() */
+static int gsi_ring_setup(struct gsi *gsi)
+{
+	struct device *dev = gsi->dev;
+	u32 count;
+	u32 val;
+
+	if (gsi->version < IPA_VERSION_3_5_1) {
+		/* No HW_PARAM_2 register prior to IPA v3.5.1, assume the max */
+		gsi->channel_count = GSI_CHANNEL_COUNT_MAX;
+		gsi->evt_ring_count = GSI_EVT_RING_COUNT_MAX;
+
+		return 0;
+	}
+
+	val = ioread32(gsi->virt + GSI_GSI_HW_PARAM_2_OFFSET);
+
+	count = u32_get_bits(val, NUM_CH_PER_EE_FMASK);
+	if (!count) {
+		dev_err(dev, "GSI reports zero channels supported\n");
+		return -EINVAL;
+	}
+	if (count > GSI_CHANNEL_COUNT_MAX) {
+		dev_warn(dev, "limiting to %u channels; hardware supports %u\n",
+			 GSI_CHANNEL_COUNT_MAX, count);
+		count = GSI_CHANNEL_COUNT_MAX;
+	}
+	gsi->channel_count = count;
+
+	count = u32_get_bits(val, NUM_EV_PER_EE_FMASK);
+	if (!count) {
+		dev_err(dev, "GSI reports zero event rings supported\n");
+		return -EINVAL;
+	}
+	if (count > GSI_EVT_RING_COUNT_MAX) {
+		dev_warn(dev,
+			 "limiting to %u event rings; hardware supports %u\n",
+			 GSI_EVT_RING_COUNT_MAX, count);
+		count = GSI_EVT_RING_COUNT_MAX;
+	}
+	gsi->evt_ring_count = count;
+
+	return 0;
+}
+
 /* Setup function for GSI.  GSI firmware must be loaded and initialized */
 int gsi_setup(struct gsi *gsi)
 {
@@ -1889,25 +1906,34 @@ int gsi_setup(struct gsi *gsi)
 		return -EIO;
 	}
 
-	gsi_irq_setup(gsi);		/* No matching teardown required */
+	ret = gsi_irq_setup(gsi);
+	if (ret)
+		return ret;
 
 	ret = gsi_ring_setup(gsi);	/* No matching teardown required */
 	if (ret)
-		return ret;
+		goto err_irq_teardown;
 
 	/* Initialize the error log */
 	iowrite32(0, gsi->virt + GSI_ERROR_LOG_OFFSET);
 
-	/* Writing 1 indicates IRQ interrupts; 0 would be MSI */
-	iowrite32(1, gsi->virt + GSI_CNTXT_INTSET_OFFSET);
+	ret = gsi_channel_setup(gsi);
+	if (ret)
+		goto err_irq_teardown;
 
-	return gsi_channel_setup(gsi);
+	return 0;
+
+err_irq_teardown:
+	gsi_irq_teardown(gsi);
+
+	return ret;
 }
 
 /* Inverse of gsi_setup() */
 void gsi_teardown(struct gsi *gsi)
 {
 	gsi_channel_teardown(gsi);
+	gsi_irq_teardown(gsi);
 }
 
 /* Initialize a channel's event ring */
@@ -1964,7 +1990,6 @@ static void gsi_evt_ring_init(struct gsi *gsi)
 static bool gsi_channel_data_valid(struct gsi *gsi,
 				   const struct ipa_gsi_endpoint_data *data)
 {
-#ifdef IPA_VALIDATION
 	u32 channel_id = data->channel_id;
 	struct device *dev = gsi->dev;
 
@@ -2010,7 +2035,6 @@ static bool gsi_channel_data_valid(struct gsi *gsi,
 			channel_id, data->channel.event_count);
 		return false;
 	}
-#endif /* IPA_VALIDATION */
 
 	return true;
 }
@@ -2206,20 +2230,18 @@ int gsi_init(struct gsi *gsi, struct platform_device *pdev,
 
 	init_completion(&gsi->completion);
 
-	ret = gsi_irq_init(gsi, pdev);
+	ret = gsi_irq_init(gsi, pdev);	/* No matching exit required */
 	if (ret)
 		goto err_iounmap;
 
 	ret = gsi_channel_init(gsi, count, data);
 	if (ret)
-		goto err_irq_exit;
+		goto err_iounmap;
 
 	mutex_init(&gsi->mutex);
 
 	return 0;
 
-err_irq_exit:
-	gsi_irq_exit(gsi);
 err_iounmap:
 	iounmap(gsi->virt_raw);
 
@@ -2231,7 +2253,6 @@ void gsi_exit(struct gsi *gsi)
 {
 	mutex_destroy(&gsi->mutex);
 	gsi_channel_exit(gsi);
-	gsi_irq_exit(gsi);
 	iounmap(gsi->virt_raw);
 }
 
diff --git a/drivers/net/ipa/gsi.h b/drivers/net/ipa/gsi.h
index 81cd7b07f6e1..88b80dc3db79 100644
--- a/drivers/net/ipa/gsi.h
+++ b/drivers/net/ipa/gsi.h
@@ -232,8 +232,35 @@ int gsi_channel_stop(struct gsi *gsi, u32 channel_id);
  */
 void gsi_channel_reset(struct gsi *gsi, u32 channel_id, bool doorbell);
 
-int gsi_channel_suspend(struct gsi *gsi, u32 channel_id, bool stop);
-int gsi_channel_resume(struct gsi *gsi, u32 channel_id, bool start);
+/**
+ * gsi_suspend() - Prepare the GSI subsystem for suspend
+ * @gsi:	GSI pointer
+ */
+void gsi_suspend(struct gsi *gsi);
+
+/**
+ * gsi_resume() - Resume the GSI subsystem following suspend
+ * @gsi:	GSI pointer
+ */
+void gsi_resume(struct gsi *gsi);
+
+/**
+ * gsi_channel_suspend() - Suspend a GSI channel
+ * @gsi:	GSI pointer
+ * @channel_id:	Channel to suspend
+ *
+ * For IPA v4.0+, suspend is implemented by stopping the channel.
+ */
+int gsi_channel_suspend(struct gsi *gsi, u32 channel_id);
+
+/**
+ * gsi_channel_resume() - Resume a suspended GSI channel
+ * @gsi:	GSI pointer
+ * @channel_id:	Channel to resume
+ *
+ * For IPA v4.0+, the stopped channel is started again.
+ */
+int gsi_channel_resume(struct gsi *gsi, u32 channel_id);
 
 /**
  * gsi_init() - Initialize the GSI subsystem
diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c
index 8c795a6a8598..1544564bc283 100644
--- a/drivers/net/ipa/gsi_trans.c
+++ b/drivers/net/ipa/gsi_trans.c
@@ -90,14 +90,12 @@ int gsi_trans_pool_init(struct gsi_trans_pool *pool, size_t size, u32 count,
 {
 	void *virt;
 
-#ifdef IPA_VALIDATE
 	if (!size)
 		return -EINVAL;
 	if (count < max_alloc)
 		return -EINVAL;
 	if (!max_alloc)
 		return -EINVAL;
-#endif /* IPA_VALIDATE */
 
 	/* By allocating a few extra entries in our pool (one less
 	 * than the maximum number that will be requested in a
@@ -140,14 +138,12 @@ int gsi_trans_pool_init_dma(struct device *dev, struct gsi_trans_pool *pool,
 	dma_addr_t addr;
 	void *virt;
 
-#ifdef IPA_VALIDATE
 	if (!size)
 		return -EINVAL;
 	if (count < max_alloc)
 		return -EINVAL;
 	if (!max_alloc)
 		return -EINVAL;
-#endif /* IPA_VALIDATE */
 
 	/* Don't let allocations cross a power-of-two boundary */
 	size = __roundup_pow_of_two(size);
@@ -188,8 +184,8 @@ static u32 gsi_trans_pool_alloc_common(struct gsi_trans_pool *pool, u32 count)
 {
 	u32 offset;
 
-	/* assert(count > 0); */
-	/* assert(count <= pool->max_alloc); */
+	WARN_ON(!count);
+	WARN_ON(count > pool->max_alloc);
 
 	/* Allocate from beginning if wrap would occur */
 	if (count > pool->count - pool->free)
@@ -225,9 +221,10 @@ void *gsi_trans_pool_next(struct gsi_trans_pool *pool, void *element)
 {
 	void *end = pool->base + pool->count * pool->size;
 
-	/* assert(element >= pool->base); */
-	/* assert(element < end); */
-	/* assert(pool->max_alloc == 1); */
+	WARN_ON(element < pool->base);
+	WARN_ON(element >= end);
+	WARN_ON(pool->max_alloc != 1);
+
 	element += pool->size;
 
 	return element < end ? element : pool->base;
@@ -332,7 +329,8 @@ struct gsi_trans *gsi_channel_trans_alloc(struct gsi *gsi, u32 channel_id,
 	struct gsi_trans_info *trans_info;
 	struct gsi_trans *trans;
 
-	/* assert(tre_count <= gsi_channel_trans_tre_max(gsi, channel_id)); */
+	if (WARN_ON(tre_count > gsi_channel_trans_tre_max(gsi, channel_id)))
+		return NULL;
 
 	trans_info = &channel->trans_info;
 
@@ -408,7 +406,7 @@ void gsi_trans_cmd_add(struct gsi_trans *trans, void *buf, u32 size,
 	u32 which = trans->used++;
 	struct scatterlist *sg;
 
-	/* assert(which < trans->tre_count); */
+	WARN_ON(which >= trans->tre_count);
 
 	/* Commands are quite different from data transfer requests.
 	 * Their payloads come from a pool whose memory is allocated
@@ -441,8 +439,10 @@ int gsi_trans_page_add(struct gsi_trans *trans, struct page *page, u32 size,
 	struct scatterlist *sg = &trans->sgl[0];
 	int ret;
 
-	/* assert(trans->tre_count == 1); */
-	/* assert(!trans->used); */
+	if (WARN_ON(trans->tre_count != 1))
+		return -EINVAL;
+	if (WARN_ON(trans->used))
+		return -EINVAL;
 
 	sg_set_page(sg, page, size, offset);
 	ret = dma_map_sg(trans->gsi->dev, sg, 1, trans->direction);
@@ -461,8 +461,10 @@ int gsi_trans_skb_add(struct gsi_trans *trans, struct sk_buff *skb)
 	u32 used;
 	int ret;
 
-	/* assert(trans->tre_count == 1); */
-	/* assert(!trans->used); */
+	if (WARN_ON(trans->tre_count != 1))
+		return -EINVAL;
+	if (WARN_ON(trans->used))
+		return -EINVAL;
 
 	/* skb->len will not be 0 (checked early) */
 	ret = skb_to_sgvec(skb, sg, 0, skb->len);
@@ -550,7 +552,7 @@ static void __gsi_trans_commit(struct gsi_trans *trans, bool ring_db)
 	u32 avail;
 	u32 i;
 
-	/* assert(trans->used > 0); */
+	WARN_ON(!trans->used);
 
 	/* Consume the entries.  If we cross the end of the ring while
 	 * filling them we'll switch to the beginning to finish.
diff --git a/drivers/net/ipa/ipa.h b/drivers/net/ipa/ipa.h
index 744406832a77..9fc880eb7e3a 100644
--- a/drivers/net/ipa/ipa.h
+++ b/drivers/net/ipa/ipa.h
@@ -23,34 +23,24 @@ struct icc_path;
 struct net_device;
 struct platform_device;
 
-struct ipa_clock;
+struct ipa_power;
 struct ipa_smp2p;
 struct ipa_interrupt;
 
 /**
- * enum ipa_flag - IPA state flags
- * @IPA_FLAG_RESUMED:	Whether resume from suspend has been signaled
- * @IPA_FLAG_COUNT:	Number of defined IPA flags
- */
-enum ipa_flag {
-	IPA_FLAG_RESUMED,
-	IPA_FLAG_COUNT,		/* Last; not a flag */
-};
-
-/**
  * struct ipa - IPA information
  * @gsi:		Embedded GSI structure
- * @flags:		Boolean state flags
  * @version:		IPA hardware version
  * @pdev:		Platform device
  * @completion:		Used to signal pipeline clear transfer complete
  * @nb:			Notifier block used for remoteproc SSR
  * @notifier:		Remoteproc SSR notifier
  * @smp2p:		SMP2P information
- * @clock:		IPA clocking information
+ * @power:		IPA power information
  * @table_addr:		DMA address of filter/route table content
  * @table_virt:		Virtual address of filter/route table content
  * @interrupt:		IPA Interrupt information
+ * @uc_powered:		true if power is active by proxy for microcontroller
  * @uc_loaded:		true after microcontroller has reported it's ready
  * @reg_addr:		DMA address used for IPA register access
  * @reg_virt:		Virtual address used for IPA register access
@@ -82,19 +72,19 @@ enum ipa_flag {
  */
 struct ipa {
 	struct gsi gsi;
-	DECLARE_BITMAP(flags, IPA_FLAG_COUNT);
 	enum ipa_version version;
 	struct platform_device *pdev;
 	struct completion completion;
 	struct notifier_block nb;
 	void *notifier;
 	struct ipa_smp2p *smp2p;
-	struct ipa_clock *clock;
+	struct ipa_power *power;
 
 	dma_addr_t table_addr;
 	__le64 *table_virt;
 
 	struct ipa_interrupt *interrupt;
+	bool uc_powered;
 	bool uc_loaded;
 
 	dma_addr_t reg_addr;
@@ -144,11 +134,11 @@ struct ipa {
  *
  * Activities performed at the init stage can be done without requiring
  * any access to IPA hardware.  Activities performed at the config stage
- * require the IPA clock to be running, because they involve access
- * to IPA registers.  The setup stage is performed only after the GSI
- * hardware is ready (more on this below).  The setup stage allows
- * the AP to perform more complex initialization by issuing "immediate
- * commands" using a special interface to the IPA.
+ * require IPA power, because they involve access to IPA registers.
+ * The setup stage is performed only after the GSI hardware is ready
+ * (more on this below).  The setup stage allows the AP to perform
+ * more complex initialization by issuing "immediate commands" using
+ * a special interface to the IPA.
  *
  * This function, @ipa_setup(), starts the setup stage.
  *
diff --git a/drivers/net/ipa/ipa_clock.c b/drivers/net/ipa/ipa_clock.c
deleted file mode 100644
index 69ef6ea41e61..000000000000
--- a/drivers/net/ipa/ipa_clock.c
+++ /dev/null
@@ -1,331 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-/* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved.
- * Copyright (C) 2018-2021 Linaro Ltd.
- */
-
-#include <linux/refcount.h>
-#include <linux/mutex.h>
-#include <linux/clk.h>
-#include <linux/device.h>
-#include <linux/interconnect.h>
-
-#include "ipa.h"
-#include "ipa_clock.h"
-#include "ipa_modem.h"
-#include "ipa_data.h"
-
-/**
- * DOC: IPA Clocking
- *
- * The "IPA Clock" manages both the IPA core clock and the interconnects
- * (buses) the IPA depends on as a single logical entity.  A reference count
- * is incremented by "get" operations and decremented by "put" operations.
- * Transitions of that count from 0 to 1 result in the clock and interconnects
- * being enabled, and transitions of the count from 1 to 0 cause them to be
- * disabled.  We currently operate the core clock at a fixed clock rate, and
- * all buses at a fixed average and peak bandwidth.  As more advanced IPA
- * features are enabled, we can make better use of clock and bus scaling.
- *
- * An IPA clock reference must be held for any access to IPA hardware.
- */
-
-/**
- * struct ipa_interconnect - IPA interconnect information
- * @path:		Interconnect path
- * @average_bandwidth:	Average interconnect bandwidth (KB/second)
- * @peak_bandwidth:	Peak interconnect bandwidth (KB/second)
- */
-struct ipa_interconnect {
-	struct icc_path *path;
-	u32 average_bandwidth;
-	u32 peak_bandwidth;
-};
-
-/**
- * struct ipa_clock - IPA clocking information
- * @count:		Clocking reference count
- * @mutex:		Protects clock enable/disable
- * @core:		IPA core clock
- * @interconnect_count:	Number of elements in interconnect[]
- * @interconnect:	Interconnect array
- */
-struct ipa_clock {
-	refcount_t count;
-	struct mutex mutex; /* protects clock enable/disable */
-	struct clk *core;
-	u32 interconnect_count;
-	struct ipa_interconnect *interconnect;
-};
-
-static int ipa_interconnect_init_one(struct device *dev,
-				     struct ipa_interconnect *interconnect,
-				     const struct ipa_interconnect_data *data)
-{
-	struct icc_path *path;
-
-	path = of_icc_get(dev, data->name);
-	if (IS_ERR(path)) {
-		int ret = PTR_ERR(path);
-
-		dev_err_probe(dev, ret, "error getting %s interconnect\n",
-			      data->name);
-
-		return ret;
-	}
-
-	interconnect->path = path;
-	interconnect->average_bandwidth = data->average_bandwidth;
-	interconnect->peak_bandwidth = data->peak_bandwidth;
-
-	return 0;
-}
-
-static void ipa_interconnect_exit_one(struct ipa_interconnect *interconnect)
-{
-	icc_put(interconnect->path);
-	memset(interconnect, 0, sizeof(*interconnect));
-}
-
-/* Initialize interconnects required for IPA operation */
-static int ipa_interconnect_init(struct ipa_clock *clock, struct device *dev,
-				 const struct ipa_interconnect_data *data)
-{
-	struct ipa_interconnect *interconnect;
-	u32 count;
-	int ret;
-
-	count = clock->interconnect_count;
-	interconnect = kcalloc(count, sizeof(*interconnect), GFP_KERNEL);
-	if (!interconnect)
-		return -ENOMEM;
-	clock->interconnect = interconnect;
-
-	while (count--) {
-		ret = ipa_interconnect_init_one(dev, interconnect, data++);
-		if (ret)
-			goto out_unwind;
-		interconnect++;
-	}
-
-	return 0;
-
-out_unwind:
-	while (interconnect-- > clock->interconnect)
-		ipa_interconnect_exit_one(interconnect);
-	kfree(clock->interconnect);
-	clock->interconnect = NULL;
-
-	return ret;
-}
-
-/* Inverse of ipa_interconnect_init() */
-static void ipa_interconnect_exit(struct ipa_clock *clock)
-{
-	struct ipa_interconnect *interconnect;
-
-	interconnect = clock->interconnect + clock->interconnect_count;
-	while (interconnect-- > clock->interconnect)
-		ipa_interconnect_exit_one(interconnect);
-	kfree(clock->interconnect);
-	clock->interconnect = NULL;
-}
-
-/* Currently we only use one bandwidth level, so just "enable" interconnects */
-static int ipa_interconnect_enable(struct ipa *ipa)
-{
-	struct ipa_interconnect *interconnect;
-	struct ipa_clock *clock = ipa->clock;
-	int ret;
-	u32 i;
-
-	interconnect = clock->interconnect;
-	for (i = 0; i < clock->interconnect_count; i++) {
-		ret = icc_set_bw(interconnect->path,
-				 interconnect->average_bandwidth,
-				 interconnect->peak_bandwidth);
-		if (ret)
-			goto out_unwind;
-		interconnect++;
-	}
-
-	return 0;
-
-out_unwind:
-	while (interconnect-- > clock->interconnect)
-		(void)icc_set_bw(interconnect->path, 0, 0);
-
-	return ret;
-}
-
-/* To disable an interconnect, we just its bandwidth to 0 */
-static void ipa_interconnect_disable(struct ipa *ipa)
-{
-	struct ipa_interconnect *interconnect;
-	struct ipa_clock *clock = ipa->clock;
-	int result = 0;
-	u32 count;
-	int ret;
-
-	count = clock->interconnect_count;
-	interconnect = clock->interconnect + count;
-	while (count--) {
-		interconnect--;
-		ret = icc_set_bw(interconnect->path, 0, 0);
-		if (ret && !result)
-			result = ret;
-	}
-
-	if (result)
-		dev_err(&ipa->pdev->dev,
-			"error %d disabling IPA interconnects\n", ret);
-}
-
-/* Turn on IPA clocks, including interconnects */
-static int ipa_clock_enable(struct ipa *ipa)
-{
-	int ret;
-
-	ret = ipa_interconnect_enable(ipa);
-	if (ret)
-		return ret;
-
-	ret = clk_prepare_enable(ipa->clock->core);
-	if (ret)
-		ipa_interconnect_disable(ipa);
-
-	return ret;
-}
-
-/* Inverse of ipa_clock_enable() */
-static void ipa_clock_disable(struct ipa *ipa)
-{
-	clk_disable_unprepare(ipa->clock->core);
-	ipa_interconnect_disable(ipa);
-}
-
-/* Get an IPA clock reference, but only if the reference count is
- * already non-zero.  Returns true if the additional reference was
- * added successfully, or false otherwise.
- */
-bool ipa_clock_get_additional(struct ipa *ipa)
-{
-	return refcount_inc_not_zero(&ipa->clock->count);
-}
-
-/* Get an IPA clock reference.  If the reference count is non-zero, it is
- * incremented and return is immediate.  Otherwise it is checked again
- * under protection of the mutex, and if appropriate the IPA clock
- * is enabled.
- *
- * Incrementing the reference count is intentionally deferred until
- * after the clock is running and endpoints are resumed.
- */
-void ipa_clock_get(struct ipa *ipa)
-{
-	struct ipa_clock *clock = ipa->clock;
-	int ret;
-
-	/* If the clock is running, just bump the reference count */
-	if (ipa_clock_get_additional(ipa))
-		return;
-
-	/* Otherwise get the mutex and check again */
-	mutex_lock(&clock->mutex);
-
-	/* A reference might have been added before we got the mutex. */
-	if (ipa_clock_get_additional(ipa))
-		goto out_mutex_unlock;
-
-	ret = ipa_clock_enable(ipa);
-	if (ret) {
-		dev_err(&ipa->pdev->dev, "error %d enabling IPA clock\n", ret);
-		goto out_mutex_unlock;
-	}
-
-	refcount_set(&clock->count, 1);
-
-out_mutex_unlock:
-	mutex_unlock(&clock->mutex);
-}
-
-/* Attempt to remove an IPA clock reference.  If this represents the
- * last reference, disable the IPA clock under protection of the mutex.
- */
-void ipa_clock_put(struct ipa *ipa)
-{
-	struct ipa_clock *clock = ipa->clock;
-
-	/* If this is not the last reference there's nothing more to do */
-	if (!refcount_dec_and_mutex_lock(&clock->count, &clock->mutex))
-		return;
-
-	ipa_clock_disable(ipa);
-
-	mutex_unlock(&clock->mutex);
-}
-
-/* Return the current IPA core clock rate */
-u32 ipa_clock_rate(struct ipa *ipa)
-{
-	return ipa->clock ? (u32)clk_get_rate(ipa->clock->core) : 0;
-}
-
-/* Initialize IPA clocking */
-struct ipa_clock *
-ipa_clock_init(struct device *dev, const struct ipa_clock_data *data)
-{
-	struct ipa_clock *clock;
-	struct clk *clk;
-	int ret;
-
-	clk = clk_get(dev, "core");
-	if (IS_ERR(clk)) {
-		dev_err_probe(dev, PTR_ERR(clk), "error getting core clock\n");
-
-		return ERR_CAST(clk);
-	}
-
-	ret = clk_set_rate(clk, data->core_clock_rate);
-	if (ret) {
-		dev_err(dev, "error %d setting core clock rate to %u\n",
-			ret, data->core_clock_rate);
-		goto err_clk_put;
-	}
-
-	clock = kzalloc(sizeof(*clock), GFP_KERNEL);
-	if (!clock) {
-		ret = -ENOMEM;
-		goto err_clk_put;
-	}
-	clock->core = clk;
-	clock->interconnect_count = data->interconnect_count;
-
-	ret = ipa_interconnect_init(clock, dev, data->interconnect_data);
-	if (ret)
-		goto err_kfree;
-
-	mutex_init(&clock->mutex);
-	refcount_set(&clock->count, 0);
-
-	return clock;
-
-err_kfree:
-	kfree(clock);
-err_clk_put:
-	clk_put(clk);
-
-	return ERR_PTR(ret);
-}
-
-/* Inverse of ipa_clock_init() */
-void ipa_clock_exit(struct ipa_clock *clock)
-{
-	struct clk *clk = clock->core;
-
-	WARN_ON(refcount_read(&clock->count) != 0);
-	mutex_destroy(&clock->mutex);
-	ipa_interconnect_exit(clock);
-	kfree(clock);
-	clk_put(clk);
-}
diff --git a/drivers/net/ipa/ipa_clock.h b/drivers/net/ipa/ipa_clock.h
deleted file mode 100644
index 1fe634760e59..000000000000
--- a/drivers/net/ipa/ipa_clock.h
+++ /dev/null
@@ -1,64 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-/* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved.
- * Copyright (C) 2018-2020 Linaro Ltd.
- */
-#ifndef _IPA_CLOCK_H_
-#define _IPA_CLOCK_H_
-
-struct device;
-
-struct ipa;
-struct ipa_clock_data;
-
-/**
- * ipa_clock_rate() - Return the current IPA core clock rate
- * @ipa:	IPA structure
- *
- * Return: The current clock rate (in Hz), or 0.
- */
-u32 ipa_clock_rate(struct ipa *ipa);
-
-/**
- * ipa_clock_init() - Initialize IPA clocking
- * @dev:	IPA device
- * @data:	Clock configuration data
- *
- * Return:	A pointer to an ipa_clock structure, or a pointer-coded error
- */
-struct ipa_clock *ipa_clock_init(struct device *dev,
-				 const struct ipa_clock_data *data);
-
-/**
- * ipa_clock_exit() - Inverse of ipa_clock_init()
- * @clock:	IPA clock pointer
- */
-void ipa_clock_exit(struct ipa_clock *clock);
-
-/**
- * ipa_clock_get() - Get an IPA clock reference
- * @ipa:	IPA pointer
- *
- * This call blocks if this is the first reference.
- */
-void ipa_clock_get(struct ipa *ipa);
-
-/**
- * ipa_clock_get_additional() - Get an IPA clock reference if not first
- * @ipa:	IPA pointer
- *
- * This returns immediately, and only takes a reference if not the first
- */
-bool ipa_clock_get_additional(struct ipa *ipa);
-
-/**
- * ipa_clock_put() - Drop an IPA clock reference
- * @ipa:	IPA pointer
- *
- * This drops a clock reference.  If the last reference is being dropped,
- * the clock is stopped and RX endpoints are suspended.  This call will
- * not block unless the last reference is dropped.
- */
-void ipa_clock_put(struct ipa *ipa);
-
-#endif /* _IPA_CLOCK_H_ */
diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c
index af44ca41189e..cff51731195a 100644
--- a/drivers/net/ipa/ipa_cmd.c
+++ b/drivers/net/ipa/ipa_cmd.c
@@ -159,35 +159,49 @@ static void ipa_cmd_validate_build(void)
 	BUILD_BUG_ON(TABLE_SIZE > field_max(IP_FLTRT_FLAGS_NHASH_SIZE_FMASK));
 #undef TABLE_COUNT_MAX
 #undef TABLE_SIZE
-}
 
-#ifdef IPA_VALIDATE
+	/* Hashed and non-hashed fields are assumed to be the same size */
+	BUILD_BUG_ON(field_max(IP_FLTRT_FLAGS_HASH_SIZE_FMASK) !=
+		     field_max(IP_FLTRT_FLAGS_NHASH_SIZE_FMASK));
+	BUILD_BUG_ON(field_max(IP_FLTRT_FLAGS_HASH_ADDR_FMASK) !=
+		     field_max(IP_FLTRT_FLAGS_NHASH_ADDR_FMASK));
+
+	/* Valid endpoint numbers must fit in the IP packet init command */
+	BUILD_BUG_ON(field_max(IPA_PACKET_INIT_DEST_ENDPOINT_FMASK) <
+		     IPA_ENDPOINT_MAX - 1);
+}
 
 /* Validate a memory region holding a table */
-bool ipa_cmd_table_valid(struct ipa *ipa, const struct ipa_mem *mem,
-			 bool route, bool ipv6, bool hashed)
+bool ipa_cmd_table_valid(struct ipa *ipa, const struct ipa_mem *mem, bool route)
 {
+	u32 offset_max = field_max(IP_FLTRT_FLAGS_NHASH_ADDR_FMASK);
+	u32 size_max = field_max(IP_FLTRT_FLAGS_NHASH_SIZE_FMASK);
+	const char *table = route ? "route" : "filter";
 	struct device *dev = &ipa->pdev->dev;
-	u32 offset_max;
 
-	offset_max = hashed ? field_max(IP_FLTRT_FLAGS_HASH_ADDR_FMASK)
-			    : field_max(IP_FLTRT_FLAGS_NHASH_ADDR_FMASK);
+	/* Size must fit in the immediate command field that holds it */
+	if (mem->size > size_max) {
+		dev_err(dev, "%s table region size too large\n", table);
+		dev_err(dev, "    (0x%04x > 0x%04x)\n",
+			mem->size, size_max);
+
+		return false;
+	}
+
+	/* Offset must fit in the immediate command field that holds it */
 	if (mem->offset > offset_max ||
 	    ipa->mem_offset > offset_max - mem->offset) {
-		dev_err(dev, "IPv%c %s%s table region offset too large\n",
-			ipv6 ? '6' : '4', hashed ? "hashed " : "",
-			route ? "route" : "filter");
+		dev_err(dev, "%s table region offset too large\n", table);
 		dev_err(dev, "    (0x%04x + 0x%04x > 0x%04x)\n",
 			ipa->mem_offset, mem->offset, offset_max);
 
 		return false;
 	}
 
+	/* Entire memory range must fit within IPA-local memory */
 	if (mem->offset > ipa->mem_size ||
 	    mem->size > ipa->mem_size - mem->offset) {
-		dev_err(dev, "IPv%c %s%s table region out of range\n",
-			ipv6 ? '6' : '4', hashed ? "hashed " : "",
-			route ? "route" : "filter");
+		dev_err(dev, "%s table region out of range\n", table);
 		dev_err(dev, "    (0x%04x + 0x%04x > 0x%04x)\n",
 			mem->offset, mem->size, ipa->mem_size);
 
@@ -331,7 +345,6 @@ bool ipa_cmd_data_valid(struct ipa *ipa)
 	return true;
 }
 
-#endif /* IPA_VALIDATE */
 
 int ipa_cmd_pool_init(struct gsi_channel *channel, u32 tre_max)
 {
@@ -522,9 +535,6 @@ static void ipa_cmd_ip_packet_init_add(struct gsi_trans *trans, u8 endpoint_id)
 	union ipa_cmd_payload *cmd_payload;
 	dma_addr_t payload_addr;
 
-	/* assert(endpoint_id <
-		  field_max(IPA_PACKET_INIT_DEST_ENDPOINT_FMASK)); */
-
 	cmd_payload = ipa_cmd_payload_alloc(ipa, &payload_addr);
 	payload = &cmd_payload->ip_packet_init;
 
@@ -548,8 +558,9 @@ void ipa_cmd_dma_shared_mem_add(struct gsi_trans *trans, u32 offset, u16 size,
 	u16 flags;
 
 	/* size and offset must fit in 16 bit fields */
-	/* assert(size > 0 && size <= U16_MAX); */
-	/* assert(offset <= U16_MAX && ipa->mem_offset <= U16_MAX - offset); */
+	WARN_ON(!size);
+	WARN_ON(size > U16_MAX);
+	WARN_ON(offset > U16_MAX || ipa->mem_offset > U16_MAX - offset);
 
 	offset += ipa->mem_offset;
 
@@ -588,8 +599,6 @@ static void ipa_cmd_ip_tag_status_add(struct gsi_trans *trans)
 	union ipa_cmd_payload *cmd_payload;
 	dma_addr_t payload_addr;
 
-	/* assert(tag <= field_max(IP_PACKET_TAG_STATUS_TAG_FMASK)); */
-
 	cmd_payload = ipa_cmd_payload_alloc(ipa, &payload_addr);
 	payload = &cmd_payload->ip_packet_tag_status;
 
diff --git a/drivers/net/ipa/ipa_cmd.h b/drivers/net/ipa/ipa_cmd.h
index b99262281f41..69cd085d427d 100644
--- a/drivers/net/ipa/ipa_cmd.h
+++ b/drivers/net/ipa/ipa_cmd.h
@@ -57,20 +57,16 @@ struct ipa_cmd_info {
 	enum dma_data_direction direction;
 };
 
-#ifdef IPA_VALIDATE
-
 /**
  * ipa_cmd_table_valid() - Validate a memory region holding a table
  * @ipa:	- IPA pointer
  * @mem:	- IPA memory region descriptor
  * @route:	- Whether the region holds a route or filter table
- * @ipv6:	- Whether the table is for IPv6 or IPv4
- * @hashed:	- Whether the table is hashed or non-hashed
  *
  * Return:	true if region is valid, false otherwise
  */
 bool ipa_cmd_table_valid(struct ipa *ipa, const struct ipa_mem *mem,
-			    bool route, bool ipv6, bool hashed);
+			    bool route);
 
 /**
  * ipa_cmd_data_valid() - Validate command-realted configuration is valid
@@ -80,22 +76,6 @@ bool ipa_cmd_table_valid(struct ipa *ipa, const struct ipa_mem *mem,
  */
 bool ipa_cmd_data_valid(struct ipa *ipa);
 
-#else /* !IPA_VALIDATE */
-
-static inline bool ipa_cmd_table_valid(struct ipa *ipa,
-				       const struct ipa_mem *mem, bool route,
-				       bool ipv6, bool hashed)
-{
-	return true;
-}
-
-static inline bool ipa_cmd_data_valid(struct ipa *ipa)
-{
-	return true;
-}
-
-#endif /* !IPA_VALIDATE */
-
 /**
  * ipa_cmd_pool_init() - initialize command channel pools
  * @channel:	AP->IPA command TX GSI channel pointer
diff --git a/drivers/net/ipa/ipa_data-v3.1.c b/drivers/net/ipa/ipa_data-v3.1.c
index 4c28189462a7..06ddb85f39b2 100644
--- a/drivers/net/ipa/ipa_data-v3.1.c
+++ b/drivers/net/ipa/ipa_data-v3.1.c
@@ -513,7 +513,7 @@ static const struct ipa_interconnect_data ipa_interconnect_data[] = {
 };
 
 /* Clock and interconnect configuration data for an SoC having IPA v3.1 */
-static const struct ipa_clock_data ipa_clock_data = {
+static const struct ipa_power_data ipa_power_data = {
 	.core_clock_rate	= 16 * 1000 * 1000,	/* Hz */
 	.interconnect_count	= ARRAY_SIZE(ipa_interconnect_data),
 	.interconnect_data	= ipa_interconnect_data,
@@ -529,5 +529,5 @@ const struct ipa_data ipa_data_v3_1 = {
 	.endpoint_data	= ipa_gsi_endpoint_data,
 	.resource_data	= &ipa_resource_data,
 	.mem_data	= &ipa_mem_data,
-	.clock_data	= &ipa_clock_data,
+	.power_data	= &ipa_power_data,
 };
diff --git a/drivers/net/ipa/ipa_data-v3.5.1.c b/drivers/net/ipa/ipa_data-v3.5.1.c
index af536ef8c120..760c22bbdf70 100644
--- a/drivers/net/ipa/ipa_data-v3.5.1.c
+++ b/drivers/net/ipa/ipa_data-v3.5.1.c
@@ -394,7 +394,7 @@ static const struct ipa_interconnect_data ipa_interconnect_data[] = {
 };
 
 /* Clock and interconnect configuration data for an SoC having IPA v3.5.1 */
-static const struct ipa_clock_data ipa_clock_data = {
+static const struct ipa_power_data ipa_power_data = {
 	.core_clock_rate	= 75 * 1000 * 1000,	/* Hz */
 	.interconnect_count	= ARRAY_SIZE(ipa_interconnect_data),
 	.interconnect_data	= ipa_interconnect_data,
@@ -414,5 +414,5 @@ const struct ipa_data ipa_data_v3_5_1 = {
 	.endpoint_data	= ipa_gsi_endpoint_data,
 	.resource_data	= &ipa_resource_data,
 	.mem_data	= &ipa_mem_data,
-	.clock_data	= &ipa_clock_data,
+	.power_data	= &ipa_power_data,
 };
diff --git a/drivers/net/ipa/ipa_data-v4.11.c b/drivers/net/ipa/ipa_data-v4.11.c
index 9353efbd504f..fea91451a0c3 100644
--- a/drivers/net/ipa/ipa_data-v4.11.c
+++ b/drivers/net/ipa/ipa_data-v4.11.c
@@ -105,6 +105,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 			.filter_support	= true,
 			.config = {
 				.resource_group	= IPA_RSRC_GROUP_SRC_UL_DL,
+				.checksum       = true,
 				.qmap		= true,
 				.status_enable	= true,
 				.tx = {
@@ -128,6 +129,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 		.endpoint = {
 			.config = {
 				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL_DPL,
+				.checksum       = true,
 				.qmap		= true,
 				.aggregation	= true,
 				.rx = {
@@ -368,24 +370,19 @@ static const struct ipa_mem_data ipa_mem_data = {
 static const struct ipa_interconnect_data ipa_interconnect_data[] = {
 	{
 		.name			= "memory",
-		.peak_bandwidth		= 465000,	/* 465 MBps */
-		.average_bandwidth	= 80000,	/* 80 MBps */
-	},
-	/* Average rate is unused for the next two interconnects */
-	{
-		.name			= "imem",
-		.peak_bandwidth		= 68570,	/* 68.57 MBps */
-		.average_bandwidth	= 80000,	/* 80 MBps (unused?) */
+		.peak_bandwidth		= 600000,	/* 600 MBps */
+		.average_bandwidth	= 150000,	/* 150 MBps */
 	},
+	/* Average rate is unused for the next interconnect */
 	{
 		.name			= "config",
-		.peak_bandwidth		= 30000,	/* 30 MBps */
+		.peak_bandwidth		= 74000,	/* 74 MBps */
 		.average_bandwidth	= 0,		/* unused */
 	},
 };
 
 /* Clock and interconnect configuration data for an SoC having IPA v4.11 */
-static const struct ipa_clock_data ipa_clock_data = {
+static const struct ipa_power_data ipa_power_data = {
 	.core_clock_rate	= 60 * 1000 * 1000,	/* Hz */
 	.interconnect_count	= ARRAY_SIZE(ipa_interconnect_data),
 	.interconnect_data	= ipa_interconnect_data,
@@ -400,5 +397,5 @@ const struct ipa_data ipa_data_v4_11 = {
 	.endpoint_data	= ipa_gsi_endpoint_data,
 	.resource_data	= &ipa_resource_data,
 	.mem_data	= &ipa_mem_data,
-	.clock_data	= &ipa_clock_data,
+	.power_data	= &ipa_power_data,
 };
diff --git a/drivers/net/ipa/ipa_data-v4.2.c b/drivers/net/ipa/ipa_data-v4.2.c
index 3b09b7baa95f..2a231e79d5e1 100644
--- a/drivers/net/ipa/ipa_data-v4.2.c
+++ b/drivers/net/ipa/ipa_data-v4.2.c
@@ -360,7 +360,7 @@ static const struct ipa_interconnect_data ipa_interconnect_data[] = {
 };
 
 /* Clock and interconnect configuration data for an SoC having IPA v4.2 */
-static const struct ipa_clock_data ipa_clock_data = {
+static const struct ipa_power_data ipa_power_data = {
 	.core_clock_rate	= 100 * 1000 * 1000,	/* Hz */
 	.interconnect_count	= ARRAY_SIZE(ipa_interconnect_data),
 	.interconnect_data	= ipa_interconnect_data,
@@ -376,5 +376,5 @@ const struct ipa_data ipa_data_v4_2 = {
 	.endpoint_data	= ipa_gsi_endpoint_data,
 	.resource_data	= &ipa_resource_data,
 	.mem_data	= &ipa_mem_data,
-	.clock_data	= &ipa_clock_data,
+	.power_data	= &ipa_power_data,
 };
diff --git a/drivers/net/ipa/ipa_data-v4.5.c b/drivers/net/ipa/ipa_data-v4.5.c
index a99b6478fa3a..e62ab9c3ac67 100644
--- a/drivers/net/ipa/ipa_data-v4.5.c
+++ b/drivers/net/ipa/ipa_data-v4.5.c
@@ -114,6 +114,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 			.filter_support	= true,
 			.config = {
 				.resource_group	= IPA_RSRC_GROUP_SRC_UL_DL,
+				.checksum       = true,
 				.qmap		= true,
 				.status_enable	= true,
 				.tx = {
@@ -137,6 +138,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 		.endpoint = {
 			.config = {
 				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL_DPL,
+				.checksum       = true,
 				.qmap		= true,
 				.aggregation	= true,
 				.rx = {
@@ -441,7 +443,7 @@ static const struct ipa_interconnect_data ipa_interconnect_data[] = {
 };
 
 /* Clock and interconnect configuration data for an SoC having IPA v4.5 */
-static const struct ipa_clock_data ipa_clock_data = {
+static const struct ipa_power_data ipa_power_data = {
 	.core_clock_rate	= 150 * 1000 * 1000,	/* Hz (150?  60?) */
 	.interconnect_count	= ARRAY_SIZE(ipa_interconnect_data),
 	.interconnect_data	= ipa_interconnect_data,
@@ -456,5 +458,5 @@ const struct ipa_data ipa_data_v4_5 = {
 	.endpoint_data	= ipa_gsi_endpoint_data,
 	.resource_data	= &ipa_resource_data,
 	.mem_data	= &ipa_mem_data,
-	.clock_data	= &ipa_clock_data,
+	.power_data	= &ipa_power_data,
 };
diff --git a/drivers/net/ipa/ipa_data-v4.9.c b/drivers/net/ipa/ipa_data-v4.9.c
index 798d43e1eb13..2421b5abb5d4 100644
--- a/drivers/net/ipa/ipa_data-v4.9.c
+++ b/drivers/net/ipa/ipa_data-v4.9.c
@@ -106,6 +106,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 			.filter_support	= true,
 			.config = {
 				.resource_group	= IPA_RSRC_GROUP_SRC_UL_DL,
+				.checksum       = true,
 				.qmap		= true,
 				.status_enable	= true,
 				.tx = {
@@ -129,6 +130,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 		.endpoint = {
 			.config = {
 				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL_DPL,
+				.checksum       = true,
 				.qmap		= true,
 				.aggregation	= true,
 				.rx = {
@@ -416,18 +418,13 @@ static const struct ipa_mem_data ipa_mem_data = {
 /* Interconnect rates are in 1000 byte/second units */
 static const struct ipa_interconnect_data ipa_interconnect_data[] = {
 	{
-		.name			= "ipa_to_llcc",
+		.name			= "memory",
 		.peak_bandwidth		= 600000,	/* 600 MBps */
 		.average_bandwidth	= 150000,	/* 150 MBps */
 	},
-	{
-		.name			= "llcc_to_ebi1",
-		.peak_bandwidth		= 1804000,	/* 1.804 GBps */
-		.average_bandwidth	= 150000,	/* 150 MBps */
-	},
 	/* Average rate is unused for the next interconnect */
 	{
-		.name			= "appss_to_ipa",
+		.name			= "config",
 		.peak_bandwidth		= 74000,	/* 74 MBps */
 		.average_bandwidth	= 0,		/* unused */
 	},
@@ -435,7 +432,7 @@ static const struct ipa_interconnect_data ipa_interconnect_data[] = {
 };
 
 /* Clock and interconnect configuration data for an SoC having IPA v4.9 */
-static const struct ipa_clock_data ipa_clock_data = {
+static const struct ipa_power_data ipa_power_data = {
 	.core_clock_rate	= 60 * 1000 * 1000,	/* Hz */
 	.interconnect_count	= ARRAY_SIZE(ipa_interconnect_data),
 	.interconnect_data	= ipa_interconnect_data,
@@ -450,5 +447,5 @@ const struct ipa_data ipa_data_v4_9 = {
 	.endpoint_data	= ipa_gsi_endpoint_data,
 	.resource_data	= &ipa_resource_data,
 	.mem_data	= &ipa_mem_data,
-	.clock_data	= &ipa_clock_data,
+	.power_data	= &ipa_power_data,
 };
diff --git a/drivers/net/ipa/ipa_data.h b/drivers/net/ipa/ipa_data.h
index 5bc244c8f94e..6d329e9ce5d2 100644
--- a/drivers/net/ipa/ipa_data.h
+++ b/drivers/net/ipa/ipa_data.h
@@ -19,7 +19,7 @@
  * IPA and GSI resources to use for a given platform.  This data is supplied
  * via the Device Tree match table, associated with a particular compatible
  * string.  The data defines information about how resources, endpoints and
- * channels, memory, clocking and so on are allocated and used for the
+ * channels, memory, power and so on are allocated and used for the
  * platform.
  *
  * Resources are data structures used internally by the IPA hardware.  The
@@ -265,12 +265,12 @@ struct ipa_interconnect_data {
 };
 
 /**
- * struct ipa_clock_data - description of IPA clock and interconnect rates
+ * struct ipa_power_data - description of IPA power configuration data
  * @core_clock_rate:	Core clock rate (Hz)
  * @interconnect_count:	Number of entries in the interconnect_data array
  * @interconnect_data:	IPA interconnect configuration data
  */
-struct ipa_clock_data {
+struct ipa_power_data {
 	u32 core_clock_rate;
 	u32 interconnect_count;		/* # entries in interconnect_data[] */
 	const struct ipa_interconnect_data *interconnect_data;
@@ -286,7 +286,7 @@ struct ipa_clock_data {
  * @endpoint_data:	IPA endpoint/GSI channel data
  * @resource_data:	IPA resource configuration data
  * @mem_data:		IPA memory region data
- * @clock_data:		IPA clock and interconnect data
+ * @power_data:		IPA power data
  */
 struct ipa_data {
 	enum ipa_version version;
@@ -297,7 +297,7 @@ struct ipa_data {
 	const struct ipa_gsi_endpoint_data *endpoint_data;
 	const struct ipa_resource_data *resource_data;
 	const struct ipa_mem_data *mem_data;
-	const struct ipa_clock_data *clock_data;
+	const struct ipa_power_data *power_data;
 };
 
 extern const struct ipa_data ipa_data_v3_1;
diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c
index ab02669bae4e..5528d97110d5 100644
--- a/drivers/net/ipa/ipa_endpoint.c
+++ b/drivers/net/ipa/ipa_endpoint.c
@@ -21,7 +21,7 @@
 #include "ipa_modem.h"
 #include "ipa_table.h"
 #include "ipa_gsi.h"
-#include "ipa_clock.h"
+#include "ipa_power.h"
 
 #define atomic_dec_not_zero(v)	atomic_add_unless((v), -1, 0)
 
@@ -250,17 +250,18 @@ ipa_endpoint_init_ctrl(struct ipa_endpoint *endpoint, bool suspend_delay)
 
 	/* Suspend is not supported for IPA v4.0+.  Delay doesn't work
 	 * correctly on IPA v4.2.
-	 *
-	 * if (endpoint->toward_ipa)
-	 * 	assert(ipa->version != IPA_VERSION_4.2);
-	 * else
-	 *	assert(ipa->version < IPA_VERSION_4_0);
 	 */
+	if (endpoint->toward_ipa)
+		WARN_ON(ipa->version == IPA_VERSION_4_2);
+	else
+		WARN_ON(ipa->version >= IPA_VERSION_4_0);
+
 	mask = endpoint->toward_ipa ? ENDP_DELAY_FMASK : ENDP_SUSPEND_FMASK;
 
 	val = ioread32(ipa->reg_virt + offset);
-	/* Don't bother if it's already in the requested state */
 	state = !!(val & mask);
+
+	/* Don't bother if it's already in the requested state */
 	if (suspend_delay != state) {
 		val ^= mask;
 		iowrite32(val, ipa->reg_virt + offset);
@@ -273,7 +274,7 @@ ipa_endpoint_init_ctrl(struct ipa_endpoint *endpoint, bool suspend_delay)
 static void
 ipa_endpoint_program_delay(struct ipa_endpoint *endpoint, bool enable)
 {
-	/* assert(endpoint->toward_ipa); */
+	WARN_ON(!endpoint->toward_ipa);
 
 	/* Delay mode doesn't work properly for IPA v4.2 */
 	if (endpoint->ipa->version != IPA_VERSION_4_2)
@@ -287,7 +288,8 @@ static bool ipa_endpoint_aggr_active(struct ipa_endpoint *endpoint)
 	u32 offset;
 	u32 val;
 
-	/* assert(mask & ipa->available); */
+	WARN_ON(!(mask & ipa->available));
+
 	offset = ipa_reg_state_aggr_active_offset(ipa->version);
 	val = ioread32(ipa->reg_virt + offset);
 
@@ -299,7 +301,8 @@ static void ipa_endpoint_force_close(struct ipa_endpoint *endpoint)
 	u32 mask = BIT(endpoint->endpoint_id);
 	struct ipa *ipa = endpoint->ipa;
 
-	/* assert(mask & ipa->available); */
+	WARN_ON(!(mask & ipa->available));
+
 	iowrite32(mask, ipa->reg_virt + IPA_REG_AGGR_FORCE_CLOSE_OFFSET);
 }
 
@@ -338,7 +341,7 @@ ipa_endpoint_program_suspend(struct ipa_endpoint *endpoint, bool enable)
 	if (endpoint->ipa->version >= IPA_VERSION_4_0)
 		return enable;	/* For IPA v4.0+, no change made */
 
-	/* assert(!endpoint->toward_ipa); */
+	WARN_ON(endpoint->toward_ipa);
 
 	suspended = ipa_endpoint_init_ctrl(endpoint, enable);
 
@@ -807,7 +810,7 @@ static u32 hol_block_timer_val(struct ipa *ipa, u32 microseconds)
 		return hol_block_timer_qtime_val(ipa, microseconds);
 
 	/* Use 64 bit arithmetic to avoid overflow... */
-	rate = ipa_clock_rate(ipa);
+	rate = ipa_core_clock_rate(ipa);
 	ticks = DIV_ROUND_CLOSEST(microseconds * rate, 128 * USEC_PER_SEC);
 	/* ...but we still need to fit into a 32-bit register */
 	WARN_ON(ticks > U32_MAX);
@@ -1156,7 +1159,8 @@ static bool ipa_endpoint_skb_build(struct ipa_endpoint *endpoint,
 	if (!endpoint->netdev)
 		return false;
 
-	/* assert(len <= SKB_WITH_OVERHEAD(IPA_RX_BUFFER_SIZE-NET_SKB_PAD)); */
+	WARN_ON(len > SKB_WITH_OVERHEAD(IPA_RX_BUFFER_SIZE - NET_SKB_PAD));
+
 	skb = build_skb(page_address(page), IPA_RX_BUFFER_SIZE);
 	if (skb) {
 		/* Reserve the headroom and account for the data */
@@ -1583,7 +1587,6 @@ void ipa_endpoint_suspend_one(struct ipa_endpoint *endpoint)
 {
 	struct device *dev = &endpoint->ipa->pdev->dev;
 	struct gsi *gsi = &endpoint->ipa->gsi;
-	bool stop_channel;
 	int ret;
 
 	if (!(endpoint->ipa->enabled & BIT(endpoint->endpoint_id)))
@@ -1594,11 +1597,7 @@ void ipa_endpoint_suspend_one(struct ipa_endpoint *endpoint)
 		(void)ipa_endpoint_program_suspend(endpoint, true);
 	}
 
-	/* Starting with IPA v4.0, endpoints are suspended by stopping the
-	 * underlying GSI channel rather than using endpoint suspend mode.
-	 */
-	stop_channel = endpoint->ipa->version >= IPA_VERSION_4_0;
-	ret = gsi_channel_suspend(gsi, endpoint->channel_id, stop_channel);
+	ret = gsi_channel_suspend(gsi, endpoint->channel_id);
 	if (ret)
 		dev_err(dev, "error %d suspending channel %u\n", ret,
 			endpoint->channel_id);
@@ -1608,7 +1607,6 @@ void ipa_endpoint_resume_one(struct ipa_endpoint *endpoint)
 {
 	struct device *dev = &endpoint->ipa->pdev->dev;
 	struct gsi *gsi = &endpoint->ipa->gsi;
-	bool start_channel;
 	int ret;
 
 	if (!(endpoint->ipa->enabled & BIT(endpoint->endpoint_id)))
@@ -1617,11 +1615,7 @@ void ipa_endpoint_resume_one(struct ipa_endpoint *endpoint)
 	if (!endpoint->toward_ipa)
 		(void)ipa_endpoint_program_suspend(endpoint, false);
 
-	/* Starting with IPA v4.0, the underlying GSI channel must be
-	 * restarted for resume.
-	 */
-	start_channel = endpoint->ipa->version >= IPA_VERSION_4_0;
-	ret = gsi_channel_resume(gsi, endpoint->channel_id, start_channel);
+	ret = gsi_channel_resume(gsi, endpoint->channel_id);
 	if (ret)
 		dev_err(dev, "error %d resuming channel %u\n", ret,
 			endpoint->channel_id);
diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c
index c46df0b7c4e5..b35170a93b0f 100644
--- a/drivers/net/ipa/ipa_interrupt.c
+++ b/drivers/net/ipa/ipa_interrupt.c
@@ -21,9 +21,9 @@
 
 #include <linux/types.h>
 #include <linux/interrupt.h>
+#include <linux/pm_runtime.h>
 
 #include "ipa.h"
-#include "ipa_clock.h"
 #include "ipa_reg.h"
 #include "ipa_endpoint.h"
 #include "ipa_interrupt.h"
@@ -74,21 +74,30 @@ static void ipa_interrupt_process(struct ipa_interrupt *interrupt, u32 irq_id)
 		iowrite32(mask, ipa->reg_virt + offset);
 }
 
-/* Process all IPA interrupt types that have been signaled */
-static void ipa_interrupt_process_all(struct ipa_interrupt *interrupt)
+/* IPA IRQ handler is threaded */
+static irqreturn_t ipa_isr_thread(int irq, void *dev_id)
 {
+	struct ipa_interrupt *interrupt = dev_id;
 	struct ipa *ipa = interrupt->ipa;
 	u32 enabled = interrupt->enabled;
+	struct device *dev;
+	u32 pending;
 	u32 offset;
 	u32 mask;
+	int ret;
+
+	dev = &ipa->pdev->dev;
+	ret = pm_runtime_get_sync(dev);
+	if (WARN_ON(ret < 0))
+		goto out_power_put;
 
 	/* The status register indicates which conditions are present,
 	 * including conditions whose interrupt is not enabled.  Handle
 	 * only the enabled ones.
 	 */
 	offset = ipa_reg_irq_stts_offset(ipa->version);
-	mask = ioread32(ipa->reg_virt + offset);
-	while ((mask &= enabled)) {
+	pending = ioread32(ipa->reg_virt + offset);
+	while ((mask = pending & enabled)) {
 		do {
 			u32 irq_id = __ffs(mask);
 
@@ -96,43 +105,19 @@ static void ipa_interrupt_process_all(struct ipa_interrupt *interrupt)
 
 			ipa_interrupt_process(interrupt, irq_id);
 		} while (mask);
-		mask = ioread32(ipa->reg_virt + offset);
+		pending = ioread32(ipa->reg_virt + offset);
 	}
-}
-
-/* Threaded part of the IPA IRQ handler */
-static irqreturn_t ipa_isr_thread(int irq, void *dev_id)
-{
-	struct ipa_interrupt *interrupt = dev_id;
-
-	ipa_clock_get(interrupt->ipa);
-
-	ipa_interrupt_process_all(interrupt);
-
-	ipa_clock_put(interrupt->ipa);
-
-	return IRQ_HANDLED;
-}
-
-/* Hard part (i.e., "real" IRQ handler) of the IRQ handler */
-static irqreturn_t ipa_isr(int irq, void *dev_id)
-{
-	struct ipa_interrupt *interrupt = dev_id;
-	struct ipa *ipa = interrupt->ipa;
-	u32 offset;
-	u32 mask;
 
-	offset = ipa_reg_irq_stts_offset(ipa->version);
-	mask = ioread32(ipa->reg_virt + offset);
-	if (mask & interrupt->enabled)
-		return IRQ_WAKE_THREAD;
-
-	/* Nothing in the mask was supposed to cause an interrupt */
-	offset = ipa_reg_irq_clr_offset(ipa->version);
-	iowrite32(mask, ipa->reg_virt + offset);
-
-	dev_err(&ipa->pdev->dev, "%s: unexpected interrupt, mask 0x%08x\n",
-		__func__, mask);
+	/* If any disabled interrupts are pending, clear them */
+	if (pending) {
+		dev_dbg(dev, "clearing disabled IPA interrupts 0x%08x\n",
+			pending);
+		offset = ipa_reg_irq_clr_offset(ipa->version);
+		iowrite32(pending, ipa->reg_virt + offset);
+	}
+out_power_put:
+	pm_runtime_mark_last_busy(dev);
+	(void)pm_runtime_put_autosuspend(dev);
 
 	return IRQ_HANDLED;
 }
@@ -146,7 +131,7 @@ static void ipa_interrupt_suspend_control(struct ipa_interrupt *interrupt,
 	u32 offset;
 	u32 val;
 
-	/* assert(mask & ipa->available); */
+	WARN_ON(!(mask & ipa->available));
 
 	/* IPA version 3.0 does not support TX_SUSPEND interrupt control */
 	if (ipa->version == IPA_VERSION_3_0)
@@ -206,7 +191,8 @@ void ipa_interrupt_add(struct ipa_interrupt *interrupt,
 	struct ipa *ipa = interrupt->ipa;
 	u32 offset;
 
-	/* assert(ipa_irq < IPA_IRQ_COUNT); */
+	WARN_ON(ipa_irq >= IPA_IRQ_COUNT);
+
 	interrupt->handler[ipa_irq] = handler;
 
 	/* Update the IPA interrupt mask to enable it */
@@ -222,7 +208,8 @@ ipa_interrupt_remove(struct ipa_interrupt *interrupt, enum ipa_irq_id ipa_irq)
 	struct ipa *ipa = interrupt->ipa;
 	u32 offset;
 
-	/* assert(ipa_irq < IPA_IRQ_COUNT); */
+	WARN_ON(ipa_irq >= IPA_IRQ_COUNT);
+
 	/* Update the IPA interrupt mask to disable it */
 	interrupt->enabled &= ~BIT(ipa_irq);
 	offset = ipa_reg_irq_en_offset(ipa->version);
@@ -231,8 +218,8 @@ ipa_interrupt_remove(struct ipa_interrupt *interrupt, enum ipa_irq_id ipa_irq)
 	interrupt->handler[ipa_irq] = NULL;
 }
 
-/* Set up the IPA interrupt framework */
-struct ipa_interrupt *ipa_interrupt_setup(struct ipa *ipa)
+/* Configure the IPA interrupt framework */
+struct ipa_interrupt *ipa_interrupt_config(struct ipa *ipa)
 {
 	struct device *dev = &ipa->pdev->dev;
 	struct ipa_interrupt *interrupt;
@@ -258,7 +245,7 @@ struct ipa_interrupt *ipa_interrupt_setup(struct ipa *ipa)
 	offset = ipa_reg_irq_en_offset(ipa->version);
 	iowrite32(0, ipa->reg_virt + offset);
 
-	ret = request_threaded_irq(irq, ipa_isr, ipa_isr_thread, IRQF_ONESHOT,
+	ret = request_threaded_irq(irq, NULL, ipa_isr_thread, IRQF_ONESHOT,
 				   "ipa", interrupt);
 	if (ret) {
 		dev_err(dev, "error %d requesting \"ipa\" IRQ\n", ret);
@@ -281,8 +268,8 @@ err_kfree:
 	return ERR_PTR(ret);
 }
 
-/* Tear down the IPA interrupt framework */
-void ipa_interrupt_teardown(struct ipa_interrupt *interrupt)
+/* Inverse of ipa_interrupt_config() */
+void ipa_interrupt_deconfig(struct ipa_interrupt *interrupt)
 {
 	struct device *dev = &interrupt->ipa->pdev->dev;
 	int ret;
diff --git a/drivers/net/ipa/ipa_interrupt.h b/drivers/net/ipa/ipa_interrupt.h
index d5c486a6800d..231390cea52a 100644
--- a/drivers/net/ipa/ipa_interrupt.h
+++ b/drivers/net/ipa/ipa_interrupt.h
@@ -86,17 +86,17 @@ void ipa_interrupt_suspend_clear_all(struct ipa_interrupt *interrupt);
 void ipa_interrupt_simulate_suspend(struct ipa_interrupt *interrupt);
 
 /**
- * ipa_interrupt_setup() - Set up the IPA interrupt framework
+ * ipa_interrupt_config() - Configure the IPA interrupt framework
  * @ipa:	IPA pointer
  *
  * Return:	Pointer to IPA SMP2P info, or a pointer-coded error
  */
-struct ipa_interrupt *ipa_interrupt_setup(struct ipa *ipa);
+struct ipa_interrupt *ipa_interrupt_config(struct ipa *ipa);
 
 /**
- * ipa_interrupt_teardown() - Tear down the IPA interrupt framework
+ * ipa_interrupt_deconfig() - Inverse of ipa_interrupt_config()
  * @interrupt:	IPA interrupt structure
  */
-void ipa_interrupt_teardown(struct ipa_interrupt *interrupt);
+void ipa_interrupt_deconfig(struct ipa_interrupt *interrupt);
 
 #endif /* _IPA_INTERRUPT_H_ */
diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c
index 9810c61a0320..cdfa98a76e1f 100644
--- a/drivers/net/ipa/ipa_main.c
+++ b/drivers/net/ipa/ipa_main.c
@@ -15,11 +15,12 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_address.h>
+#include <linux/pm_runtime.h>
 #include <linux/qcom_scm.h>
 #include <linux/soc/qcom/mdt_loader.h>
 
 #include "ipa.h"
-#include "ipa_clock.h"
+#include "ipa_power.h"
 #include "ipa_data.h"
 #include "ipa_endpoint.h"
 #include "ipa_resource.h"
@@ -80,29 +81,6 @@
 #define IPA_XO_CLOCK_DIVIDER	192	/* 1 is subtracted where used */
 
 /**
- * ipa_suspend_handler() - Handle the suspend IPA interrupt
- * @ipa:	IPA pointer
- * @irq_id:	IPA interrupt type (unused)
- *
- * If an RX endpoint is in suspend state, and the IPA has a packet
- * destined for that endpoint, the IPA generates a SUSPEND interrupt
- * to inform the AP that it should resume the endpoint.  If we get
- * one of these interrupts we just resume everything.
- */
-static void ipa_suspend_handler(struct ipa *ipa, enum ipa_irq_id irq_id)
-{
-	/* Just report the event, and let system resume handle the rest.
-	 * More than one endpoint could signal this; if so, ignore
-	 * all but the first.
-	 */
-	if (!test_and_set_bit(IPA_FLAG_RESUMED, ipa->flags))
-		pm_wakeup_dev_event(&ipa->pdev->dev, 0, true);
-
-	/* Acknowledge/clear the suspend interrupt on all endpoints */
-	ipa_interrupt_suspend_clear_all(ipa->interrupt);
-}
-
-/**
  * ipa_setup() - Set up IPA hardware
  * @ipa:	IPA pointer
  *
@@ -124,19 +102,9 @@ int ipa_setup(struct ipa *ipa)
 	if (ret)
 		return ret;
 
-	ipa->interrupt = ipa_interrupt_setup(ipa);
-	if (IS_ERR(ipa->interrupt)) {
-		ret = PTR_ERR(ipa->interrupt);
-		goto err_gsi_teardown;
-	}
-	ipa_interrupt_add(ipa->interrupt, IPA_IRQ_TX_SUSPEND,
-			  ipa_suspend_handler);
-
-	ipa_uc_setup(ipa);
-
-	ret = device_init_wakeup(dev, true);
+	ret = ipa_power_setup(ipa);
 	if (ret)
-		goto err_uc_teardown;
+		goto err_gsi_teardown;
 
 	ipa_endpoint_setup(ipa);
 
@@ -167,7 +135,7 @@ int ipa_setup(struct ipa *ipa)
 	ipa_endpoint_default_route_set(ipa, exception_endpoint->endpoint_id);
 
 	/* We're all set.  Now prepare for communication with the modem */
-	ret = ipa_modem_setup(ipa);
+	ret = ipa_qmi_setup(ipa);
 	if (ret)
 		goto err_default_route_clear;
 
@@ -184,11 +152,7 @@ err_command_disable:
 	ipa_endpoint_disable_one(command_endpoint);
 err_endpoint_teardown:
 	ipa_endpoint_teardown(ipa);
-	(void)device_init_wakeup(dev, false);
-err_uc_teardown:
-	ipa_uc_teardown(ipa);
-	ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_TX_SUSPEND);
-	ipa_interrupt_teardown(ipa->interrupt);
+	ipa_power_teardown(ipa);
 err_gsi_teardown:
 	gsi_teardown(&ipa->gsi);
 
@@ -204,17 +168,17 @@ static void ipa_teardown(struct ipa *ipa)
 	struct ipa_endpoint *exception_endpoint;
 	struct ipa_endpoint *command_endpoint;
 
-	ipa_modem_teardown(ipa);
+	/* We're going to tear everything down, as if setup never completed */
+	ipa->setup_complete = false;
+
+	ipa_qmi_teardown(ipa);
 	ipa_endpoint_default_route_clear(ipa);
 	exception_endpoint = ipa->name_map[IPA_ENDPOINT_AP_LAN_RX];
 	ipa_endpoint_disable_one(exception_endpoint);
 	command_endpoint = ipa->name_map[IPA_ENDPOINT_AP_COMMAND_TX];
 	ipa_endpoint_disable_one(command_endpoint);
 	ipa_endpoint_teardown(ipa);
-	(void)device_init_wakeup(&ipa->pdev->dev, false);
-	ipa_uc_teardown(ipa);
-	ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_TX_SUSPEND);
-	ipa_interrupt_teardown(ipa->interrupt);
+	ipa_power_teardown(ipa);
 	gsi_teardown(&ipa->gsi);
 }
 
@@ -253,9 +217,6 @@ ipa_hardware_config_qsb(struct ipa *ipa, const struct ipa_data *data)
 	const struct ipa_qsb_data *data1;
 	u32 val;
 
-	/* assert(data->qsb_count > 0); */
-	/* assert(data->qsb_count < 3); */
-
 	/* QMB 0 represents DDR; QMB 1 (if present) represents PCIe */
 	data0 = &data->qsb_data[IPA_QSB_MASTER_DDR];
 	if (data->qsb_count > 1)
@@ -289,12 +250,11 @@ ipa_hardware_config_qsb(struct ipa *ipa, const struct ipa_data *data)
 /* Compute the value to use in the COUNTER_CFG register AGGR_GRANULARITY
  * field to represent the given number of microseconds.  The value is one
  * less than the number of timer ticks in the requested period.  0 is not
- * a valid granularity value.
+ * a valid granularity value (so for example @usec must be at least 16 for
+ * a TIMER_FREQUENCY of 32000).
  */
-static u32 ipa_aggr_granularity_val(u32 usec)
+static __always_inline u32 ipa_aggr_granularity_val(u32 usec)
 {
-	/* assert(usec != 0); */
-
 	return DIV_ROUND_CLOSEST(usec * TIMER_FREQUENCY, USEC_PER_SEC) - 1;
 }
 
@@ -366,8 +326,8 @@ static void ipa_idle_indication_cfg(struct ipa *ipa,
  * @ipa:	IPA pointer
  *
  * Configures when the IPA signals it is idle to the global clock
- * controller, which can respond by scalling down the clock to
- * save power.
+ * controller, which can respond by scaling down the clock to save
+ * power.
  */
 static void ipa_hardware_dcd_config(struct ipa *ipa)
 {
@@ -457,48 +417,54 @@ static void ipa_hardware_deconfig(struct ipa *ipa)
  * @ipa:	IPA pointer
  * @data:	IPA configuration data
  *
- * Perform initialization requiring IPA clock to be enabled.
+ * Perform initialization requiring IPA power to be enabled.
  */
 static int ipa_config(struct ipa *ipa, const struct ipa_data *data)
 {
 	int ret;
 
-	/* Get a clock reference to allow initialization.  This reference
-	 * is held after initialization completes, and won't get dropped
-	 * unless/until a system suspend request arrives.
-	 */
-	ipa_clock_get(ipa);
-
 	ipa_hardware_config(ipa, data);
 
-	ret = ipa_endpoint_config(ipa);
+	ret = ipa_mem_config(ipa);
 	if (ret)
 		goto err_hardware_deconfig;
 
-	ret = ipa_mem_config(ipa);
+	ipa->interrupt = ipa_interrupt_config(ipa);
+	if (IS_ERR(ipa->interrupt)) {
+		ret = PTR_ERR(ipa->interrupt);
+		ipa->interrupt = NULL;
+		goto err_mem_deconfig;
+	}
+
+	ipa_uc_config(ipa);
+
+	ret = ipa_endpoint_config(ipa);
 	if (ret)
-		goto err_endpoint_deconfig;
+		goto err_uc_deconfig;
 
 	ipa_table_config(ipa);		/* No deconfig required */
 
 	/* Assign resource limitation to each group; no deconfig required */
 	ret = ipa_resource_config(ipa, data->resource_data);
 	if (ret)
-		goto err_mem_deconfig;
+		goto err_endpoint_deconfig;
 
 	ret = ipa_modem_config(ipa);
 	if (ret)
-		goto err_mem_deconfig;
+		goto err_endpoint_deconfig;
 
 	return 0;
 
-err_mem_deconfig:
-	ipa_mem_deconfig(ipa);
 err_endpoint_deconfig:
 	ipa_endpoint_deconfig(ipa);
+err_uc_deconfig:
+	ipa_uc_deconfig(ipa);
+	ipa_interrupt_deconfig(ipa->interrupt);
+	ipa->interrupt = NULL;
+err_mem_deconfig:
+	ipa_mem_deconfig(ipa);
 err_hardware_deconfig:
 	ipa_hardware_deconfig(ipa);
-	ipa_clock_put(ipa);
 
 	return ret;
 }
@@ -510,10 +476,12 @@ err_hardware_deconfig:
 static void ipa_deconfig(struct ipa *ipa)
 {
 	ipa_modem_deconfig(ipa);
-	ipa_mem_deconfig(ipa);
 	ipa_endpoint_deconfig(ipa);
+	ipa_uc_deconfig(ipa);
+	ipa_interrupt_deconfig(ipa->interrupt);
+	ipa->interrupt = NULL;
+	ipa_mem_deconfig(ipa);
 	ipa_hardware_deconfig(ipa);
-	ipa_clock_put(ipa);
 }
 
 static int ipa_firmware_load(struct device *dev)
@@ -612,7 +580,6 @@ MODULE_DEVICE_TABLE(of, ipa_match);
  * */
 static void ipa_validate_build(void)
 {
-#ifdef IPA_VALIDATE
 	/* At one time we assumed a 64-bit build, allowing some do_div()
 	 * calls to be replaced by simple division or modulo operations.
 	 * We currently only perform divide and modulo operations on u32,
@@ -646,7 +613,6 @@ static void ipa_validate_build(void)
 	BUILD_BUG_ON(!ipa_aggr_granularity_val(IPA_AGGR_GRANULARITY));
 	BUILD_BUG_ON(ipa_aggr_granularity_val(IPA_AGGR_GRANULARITY) >
 			field_max(AGGR_GRANULARITY_FMASK));
-#endif /* IPA_VALIDATE */
 }
 
 static bool ipa_version_valid(enum ipa_version version)
@@ -681,7 +647,7 @@ static bool ipa_version_valid(enum ipa_version version)
  * in several stages:
  *   - The "init" stage involves activities that can be initialized without
  *     access to the IPA hardware.
- *   - The "config" stage requires the IPA clock to be active so IPA registers
+ *   - The "config" stage requires IPA power to be active so IPA registers
  *     can be accessed, but does not require the use of IPA immediate commands.
  *   - The "setup" stage uses IPA immediate commands, and so requires the GSI
  *     layer to be initialized.
@@ -697,14 +663,14 @@ static int ipa_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	const struct ipa_data *data;
-	struct ipa_clock *clock;
+	struct ipa_power *power;
 	bool modem_init;
 	struct ipa *ipa;
 	int ret;
 
 	ipa_validate_build();
 
-	/* Get configuration data early; needed for clock initialization */
+	/* Get configuration data early; needed for power initialization */
 	data = of_device_get_match_data(dev);
 	if (!data) {
 		dev_err(dev, "matched hardware not supported\n");
@@ -725,20 +691,20 @@ static int ipa_probe(struct platform_device *pdev)
 	/* The clock and interconnects might not be ready when we're
 	 * probed, so might return -EPROBE_DEFER.
 	 */
-	clock = ipa_clock_init(dev, data->clock_data);
-	if (IS_ERR(clock))
-		return PTR_ERR(clock);
+	power = ipa_power_init(dev, data->power_data);
+	if (IS_ERR(power))
+		return PTR_ERR(power);
 
 	/* No more EPROBE_DEFER.  Allocate and initialize the IPA structure */
 	ipa = kzalloc(sizeof(*ipa), GFP_KERNEL);
 	if (!ipa) {
 		ret = -ENOMEM;
-		goto err_clock_exit;
+		goto err_power_exit;
 	}
 
 	ipa->pdev = pdev;
 	dev_set_drvdata(dev, ipa);
-	ipa->clock = clock;
+	ipa->power = power;
 	ipa->version = data->version;
 	init_completion(&ipa->completion);
 
@@ -771,18 +737,23 @@ static int ipa_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_table_exit;
 
+	/* Power needs to be active for config and setup */
+	ret = pm_runtime_get_sync(dev);
+	if (WARN_ON(ret < 0))
+		goto err_power_put;
+
 	ret = ipa_config(ipa, data);
 	if (ret)
-		goto err_modem_exit;
+		goto err_power_put;
 
 	dev_info(dev, "IPA driver initialized");
 
 	/* If the modem is doing early initialization, it will trigger a
-	 * call to ipa_setup() call when it has finished.  In that case
-	 * we're done here.
+	 * call to ipa_setup() when it has finished.  In that case we're
+	 * done here.
 	 */
 	if (modem_init)
-		return 0;
+		goto done;
 
 	/* Otherwise we need to load the firmware and have Trust Zone validate
 	 * and install it.  If that succeeds we can proceed with setup.
@@ -794,12 +765,16 @@ static int ipa_probe(struct platform_device *pdev)
 	ret = ipa_setup(ipa);
 	if (ret)
 		goto err_deconfig;
+done:
+	pm_runtime_mark_last_busy(dev);
+	(void)pm_runtime_put_autosuspend(dev);
 
 	return 0;
 
 err_deconfig:
 	ipa_deconfig(ipa);
-err_modem_exit:
+err_power_put:
+	pm_runtime_put_noidle(dev);
 	ipa_modem_exit(ipa);
 err_table_exit:
 	ipa_table_exit(ipa);
@@ -813,8 +788,8 @@ err_reg_exit:
 	ipa_reg_exit(ipa);
 err_kfree_ipa:
 	kfree(ipa);
-err_clock_exit:
-	ipa_clock_exit(clock);
+err_power_exit:
+	ipa_power_exit(power);
 
 	return ret;
 }
@@ -822,9 +797,14 @@ err_clock_exit:
 static int ipa_remove(struct platform_device *pdev)
 {
 	struct ipa *ipa = dev_get_drvdata(&pdev->dev);
-	struct ipa_clock *clock = ipa->clock;
+	struct ipa_power *power = ipa->power;
+	struct device *dev = &pdev->dev;
 	int ret;
 
+	ret = pm_runtime_get_sync(dev);
+	if (WARN_ON(ret < 0))
+		goto out_power_put;
+
 	if (ipa->setup_complete) {
 		ret = ipa_modem_stop(ipa);
 		/* If starting or stopping is in progress, try once more */
@@ -839,6 +819,8 @@ static int ipa_remove(struct platform_device *pdev)
 	}
 
 	ipa_deconfig(ipa);
+out_power_put:
+	pm_runtime_put_noidle(dev);
 	ipa_modem_exit(ipa);
 	ipa_table_exit(ipa);
 	ipa_endpoint_exit(ipa);
@@ -846,7 +828,7 @@ static int ipa_remove(struct platform_device *pdev)
 	ipa_mem_exit(ipa);
 	ipa_reg_exit(ipa);
 	kfree(ipa);
-	ipa_clock_exit(clock);
+	ipa_power_exit(power);
 
 	return 0;
 }
@@ -860,62 +842,6 @@ static void ipa_shutdown(struct platform_device *pdev)
 		dev_err(&pdev->dev, "shutdown: remove returned %d\n", ret);
 }
 
-/**
- * ipa_suspend() - Power management system suspend callback
- * @dev:	IPA device structure
- *
- * Return:	Always returns zero
- *
- * Called by the PM framework when a system suspend operation is invoked.
- * Suspends endpoints and releases the clock reference held to keep
- * the IPA clock running until this point.
- */
-static int ipa_suspend(struct device *dev)
-{
-	struct ipa *ipa = dev_get_drvdata(dev);
-
-	/* When a suspended RX endpoint has a packet ready to receive, we
-	 * get an IPA SUSPEND interrupt.  We trigger a system resume in
-	 * that case, but only on the first such interrupt since suspend.
-	 */
-	__clear_bit(IPA_FLAG_RESUMED, ipa->flags);
-
-	ipa_endpoint_suspend(ipa);
-
-	ipa_clock_put(ipa);
-
-	return 0;
-}
-
-/**
- * ipa_resume() - Power management system resume callback
- * @dev:	IPA device structure
- *
- * Return:	Always returns 0
- *
- * Called by the PM framework when a system resume operation is invoked.
- * Takes an IPA clock reference to keep the clock running until suspend,
- * and resumes endpoints.
- */
-static int ipa_resume(struct device *dev)
-{
-	struct ipa *ipa = dev_get_drvdata(dev);
-
-	/* This clock reference will keep the IPA out of suspend
-	 * until we get a power management suspend request.
-	 */
-	ipa_clock_get(ipa);
-
-	ipa_endpoint_resume(ipa);
-
-	return 0;
-}
-
-static const struct dev_pm_ops ipa_pm_ops = {
-	.suspend	= ipa_suspend,
-	.resume		= ipa_resume,
-};
-
 static const struct attribute_group *ipa_attribute_groups[] = {
 	&ipa_attribute_group,
 	&ipa_feature_attribute_group,
diff --git a/drivers/net/ipa/ipa_modem.c b/drivers/net/ipa/ipa_modem.c
index af9aedbde717..ad116bcc0580 100644
--- a/drivers/net/ipa/ipa_modem.c
+++ b/drivers/net/ipa/ipa_modem.c
@@ -9,6 +9,7 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/if_rmnet.h>
+#include <linux/pm_runtime.h>
 #include <linux/remoteproc/qcom_rproc.h>
 
 #include "ipa.h"
@@ -19,6 +20,8 @@
 #include "ipa_modem.h"
 #include "ipa_smp2p.h"
 #include "ipa_qmi.h"
+#include "ipa_uc.h"
+#include "ipa_power.h"
 
 #define IPA_NETDEV_NAME		"rmnet_ipa%d"
 #define IPA_NETDEV_TAILROOM	0	/* for padding by mux layer */
@@ -31,9 +34,14 @@ enum ipa_modem_state {
 	IPA_MODEM_STATE_STOPPING,
 };
 
-/** struct ipa_priv - IPA network device private data */
+/**
+ * struct ipa_priv - IPA network device private data
+ * @ipa:	IPA pointer
+ * @work:	Work structure used to wake the modem netdev TX queue
+ */
 struct ipa_priv {
 	struct ipa *ipa;
+	struct work_struct work;
 };
 
 /** ipa_open() - Opens the modem network interface */
@@ -41,21 +49,33 @@ static int ipa_open(struct net_device *netdev)
 {
 	struct ipa_priv *priv = netdev_priv(netdev);
 	struct ipa *ipa = priv->ipa;
+	struct device *dev;
 	int ret;
 
+	dev = &ipa->pdev->dev;
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0)
+		goto err_power_put;
+
 	ret = ipa_endpoint_enable_one(ipa->name_map[IPA_ENDPOINT_AP_MODEM_TX]);
 	if (ret)
-		return ret;
+		goto err_power_put;
+
 	ret = ipa_endpoint_enable_one(ipa->name_map[IPA_ENDPOINT_AP_MODEM_RX]);
 	if (ret)
 		goto err_disable_tx;
 
 	netif_start_queue(netdev);
 
+	pm_runtime_mark_last_busy(dev);
+	(void)pm_runtime_put_autosuspend(dev);
+
 	return 0;
 
 err_disable_tx:
 	ipa_endpoint_disable_one(ipa->name_map[IPA_ENDPOINT_AP_MODEM_TX]);
+err_power_put:
+	pm_runtime_put_noidle(dev);
 
 	return ret;
 }
@@ -65,11 +85,21 @@ static int ipa_stop(struct net_device *netdev)
 {
 	struct ipa_priv *priv = netdev_priv(netdev);
 	struct ipa *ipa = priv->ipa;
+	struct device *dev;
+	int ret;
+
+	dev = &ipa->pdev->dev;
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0)
+		goto out_power_put;
 
 	netif_stop_queue(netdev);
 
 	ipa_endpoint_disable_one(ipa->name_map[IPA_ENDPOINT_AP_MODEM_RX]);
 	ipa_endpoint_disable_one(ipa->name_map[IPA_ENDPOINT_AP_MODEM_TX]);
+out_power_put:
+	pm_runtime_mark_last_busy(dev);
+	(void)pm_runtime_put_autosuspend(dev);
 
 	return 0;
 }
@@ -82,13 +112,15 @@ static int ipa_stop(struct net_device *netdev)
  * NETDEV_TX_OK: Success
  * NETDEV_TX_BUSY: Error while transmitting the skb. Try again later
  */
-static int ipa_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t
+ipa_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct net_device_stats *stats = &netdev->stats;
 	struct ipa_priv *priv = netdev_priv(netdev);
 	struct ipa_endpoint *endpoint;
 	struct ipa *ipa = priv->ipa;
 	u32 skb_len = skb->len;
+	struct device *dev;
 	int ret;
 
 	if (!skb_len)
@@ -98,7 +130,35 @@ static int ipa_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	if (endpoint->data->qmap && skb->protocol != htons(ETH_P_MAP))
 		goto err_drop_skb;
 
+	/* The hardware must be powered for us to transmit */
+	dev = &ipa->pdev->dev;
+	ret = pm_runtime_get(dev);
+	if (ret < 1) {
+		/* If a resume won't happen, just drop the packet */
+		if (ret < 0 && ret != -EINPROGRESS) {
+			ipa_power_modem_queue_active(ipa);
+			pm_runtime_put_noidle(dev);
+			goto err_drop_skb;
+		}
+
+		/* No power (yet).  Stop the network stack from transmitting
+		 * until we're resumed; ipa_modem_resume() arranges for the
+		 * TX queue to be started again.
+		 */
+		ipa_power_modem_queue_stop(ipa);
+
+		pm_runtime_put_noidle(dev);
+
+		return NETDEV_TX_BUSY;
+	}
+
+	ipa_power_modem_queue_active(ipa);
+
 	ret = ipa_endpoint_skb_tx(endpoint, skb);
+
+	pm_runtime_mark_last_busy(dev);
+	(void)pm_runtime_put_autosuspend(dev);
+
 	if (ret) {
 		if (ret != -E2BIG)
 			return NETDEV_TX_BUSY;
@@ -169,12 +229,31 @@ void ipa_modem_suspend(struct net_device *netdev)
 	struct ipa_priv *priv = netdev_priv(netdev);
 	struct ipa *ipa = priv->ipa;
 
-	netif_stop_queue(netdev);
+	if (!(netdev->flags & IFF_UP))
+		return;
 
 	ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_MODEM_RX]);
 	ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_MODEM_TX]);
 }
 
+/**
+ * ipa_modem_wake_queue_work() - enable modem netdev queue
+ * @work:	Work structure
+ *
+ * Re-enable transmit on the modem network device.  This is called
+ * in (power management) work queue context, scheduled when resuming
+ * the modem.  We can't enable the queue directly in ipa_modem_resume()
+ * because transmits restart the instant the queue is awakened; but the
+ * device power state won't be ACTIVE until *after* ipa_modem_resume()
+ * returns.
+ */
+static void ipa_modem_wake_queue_work(struct work_struct *work)
+{
+	struct ipa_priv *priv = container_of(work, struct ipa_priv, work);
+
+	ipa_power_modem_queue_wake(priv->ipa);
+}
+
 /** ipa_modem_resume() - resume callback for runtime_pm
  * @dev: pointer to device
  *
@@ -185,10 +264,14 @@ void ipa_modem_resume(struct net_device *netdev)
 	struct ipa_priv *priv = netdev_priv(netdev);
 	struct ipa *ipa = priv->ipa;
 
+	if (!(netdev->flags & IFF_UP))
+		return;
+
 	ipa_endpoint_resume_one(ipa->name_map[IPA_ENDPOINT_AP_MODEM_TX]);
 	ipa_endpoint_resume_one(ipa->name_map[IPA_ENDPOINT_AP_MODEM_RX]);
 
-	netif_wake_queue(netdev);
+	/* Arrange for the TX queue to be restarted */
+	(void)queue_pm_work(&priv->work);
 }
 
 int ipa_modem_start(struct ipa *ipa)
@@ -216,13 +299,16 @@ int ipa_modem_start(struct ipa *ipa)
 	SET_NETDEV_DEV(netdev, &ipa->pdev->dev);
 	priv = netdev_priv(netdev);
 	priv->ipa = ipa;
+	INIT_WORK(&priv->work, ipa_modem_wake_queue_work);
+	ipa->name_map[IPA_ENDPOINT_AP_MODEM_TX]->netdev = netdev;
+	ipa->name_map[IPA_ENDPOINT_AP_MODEM_RX]->netdev = netdev;
+	ipa->modem_netdev = netdev;
 
 	ret = register_netdev(netdev);
-	if (!ret) {
-		ipa->modem_netdev = netdev;
-		ipa->name_map[IPA_ENDPOINT_AP_MODEM_TX]->netdev = netdev;
-		ipa->name_map[IPA_ENDPOINT_AP_MODEM_RX]->netdev = netdev;
-	} else {
+	if (ret) {
+		ipa->modem_netdev = NULL;
+		ipa->name_map[IPA_ENDPOINT_AP_MODEM_RX]->netdev = NULL;
+		ipa->name_map[IPA_ENDPOINT_AP_MODEM_TX]->netdev = NULL;
 		free_netdev(netdev);
 	}
 
@@ -256,13 +342,18 @@ int ipa_modem_stop(struct ipa *ipa)
 	/* Prevent the modem from triggering a call to ipa_setup() */
 	ipa_smp2p_disable(ipa);
 
-	/* Stop the queue and disable the endpoints if it's open */
+	/* Clean up the netdev and endpoints if it was started */
 	if (netdev) {
-		(void)ipa_stop(netdev);
+		struct ipa_priv *priv = netdev_priv(netdev);
+
+		cancel_work_sync(&priv->work);
+		/* If it was opened, stop it first */
+		if (netdev->flags & IFF_UP)
+			(void)ipa_stop(netdev);
+		unregister_netdev(netdev);
+		ipa->modem_netdev = NULL;
 		ipa->name_map[IPA_ENDPOINT_AP_MODEM_RX]->netdev = NULL;
 		ipa->name_map[IPA_ENDPOINT_AP_MODEM_TX]->netdev = NULL;
-		ipa->modem_netdev = NULL;
-		unregister_netdev(netdev);
 		free_netdev(netdev);
 	}
 
@@ -278,6 +369,12 @@ static void ipa_modem_crashed(struct ipa *ipa)
 	struct device *dev = &ipa->pdev->dev;
 	int ret;
 
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "error %d getting power to handle crash\n", ret);
+		goto out_power_put;
+	}
+
 	ipa_endpoint_modem_pause_all(ipa, true);
 
 	ipa_endpoint_modem_hol_block_clear_all(ipa);
@@ -302,6 +399,10 @@ static void ipa_modem_crashed(struct ipa *ipa)
 	ret = ipa_mem_zero_modem(ipa);
 	if (ret)
 		dev_err(dev, "error %d zeroing modem memory regions\n", ret);
+
+out_power_put:
+	pm_runtime_mark_last_busy(dev);
+	(void)pm_runtime_put_autosuspend(dev);
 }
 
 static int ipa_modem_notify(struct notifier_block *nb, unsigned long action,
@@ -314,6 +415,7 @@ static int ipa_modem_notify(struct notifier_block *nb, unsigned long action,
 	switch (action) {
 	case QCOM_SSR_BEFORE_POWERUP:
 		dev_info(dev, "received modem starting event\n");
+		ipa_uc_power(ipa);
 		ipa_smp2p_notify_reset(ipa);
 		break;
 
@@ -377,13 +479,3 @@ void ipa_modem_deconfig(struct ipa *ipa)
 	ipa->notifier = NULL;
 	memset(&ipa->nb, 0, sizeof(ipa->nb));
 }
-
-int ipa_modem_setup(struct ipa *ipa)
-{
-	return ipa_qmi_setup(ipa);
-}
-
-void ipa_modem_teardown(struct ipa *ipa)
-{
-	ipa_qmi_teardown(ipa);
-}
diff --git a/drivers/net/ipa/ipa_modem.h b/drivers/net/ipa/ipa_modem.h
index 2de3e216d1d4..5e6e3d234454 100644
--- a/drivers/net/ipa/ipa_modem.h
+++ b/drivers/net/ipa/ipa_modem.h
@@ -7,7 +7,6 @@
 #define _IPA_MODEM_H_
 
 struct ipa;
-struct ipa_endpoint;
 struct net_device;
 struct sk_buff;
 
@@ -25,7 +24,4 @@ void ipa_modem_exit(struct ipa *ipa);
 int ipa_modem_config(struct ipa *ipa);
 void ipa_modem_deconfig(struct ipa *ipa);
 
-int ipa_modem_setup(struct ipa *ipa);
-void ipa_modem_teardown(struct ipa *ipa);
-
 #endif /* _IPA_MODEM_H_ */
diff --git a/drivers/net/ipa/ipa_power.c b/drivers/net/ipa/ipa_power.c
new file mode 100644
index 000000000000..b1c6c0fcb654
--- /dev/null
+++ b/drivers/net/ipa/ipa_power.c
@@ -0,0 +1,473 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2018-2021 Linaro Ltd.
+ */
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/interconnect.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/bitops.h>
+
+#include "ipa.h"
+#include "ipa_power.h"
+#include "ipa_endpoint.h"
+#include "ipa_modem.h"
+#include "ipa_data.h"
+
+/**
+ * DOC: IPA Power Management
+ *
+ * The IPA hardware is enabled when the IPA core clock and all the
+ * interconnects (buses) it depends on are enabled.  Runtime power
+ * management is used to determine whether the core clock and
+ * interconnects are enabled, and if not in use to be suspended
+ * automatically.
+ *
+ * The core clock currently runs at a fixed clock rate when enabled,
+ * an all interconnects use a fixed average and peak bandwidth.
+ */
+
+#define IPA_AUTOSUSPEND_DELAY	500	/* milliseconds */
+
+/**
+ * struct ipa_interconnect - IPA interconnect information
+ * @path:		Interconnect path
+ * @average_bandwidth:	Average interconnect bandwidth (KB/second)
+ * @peak_bandwidth:	Peak interconnect bandwidth (KB/second)
+ */
+struct ipa_interconnect {
+	struct icc_path *path;
+	u32 average_bandwidth;
+	u32 peak_bandwidth;
+};
+
+/**
+ * enum ipa_power_flag - IPA power flags
+ * @IPA_POWER_FLAG_RESUMED:	Whether resume from suspend has been signaled
+ * @IPA_POWER_FLAG_SYSTEM:	Hardware is system (not runtime) suspended
+ * @IPA_POWER_FLAG_STOPPED:	Modem TX is disabled by ipa_start_xmit()
+ * @IPA_POWER_FLAG_STARTED:	Modem TX was enabled by ipa_runtime_resume()
+ * @IPA_POWER_FLAG_COUNT:	Number of defined power flags
+ */
+enum ipa_power_flag {
+	IPA_POWER_FLAG_RESUMED,
+	IPA_POWER_FLAG_SYSTEM,
+	IPA_POWER_FLAG_STOPPED,
+	IPA_POWER_FLAG_STARTED,
+	IPA_POWER_FLAG_COUNT,		/* Last; not a flag */
+};
+
+/**
+ * struct ipa_power - IPA power management information
+ * @dev:		IPA device pointer
+ * @core:		IPA core clock
+ * @spinlock:		Protects modem TX queue enable/disable
+ * @flags:		Boolean state flags
+ * @interconnect_count:	Number of elements in interconnect[]
+ * @interconnect:	Interconnect array
+ */
+struct ipa_power {
+	struct device *dev;
+	struct clk *core;
+	spinlock_t spinlock;	/* used with STOPPED/STARTED power flags */
+	DECLARE_BITMAP(flags, IPA_POWER_FLAG_COUNT);
+	u32 interconnect_count;
+	struct ipa_interconnect *interconnect;
+};
+
+static int ipa_interconnect_init_one(struct device *dev,
+				     struct ipa_interconnect *interconnect,
+				     const struct ipa_interconnect_data *data)
+{
+	struct icc_path *path;
+
+	path = of_icc_get(dev, data->name);
+	if (IS_ERR(path)) {
+		int ret = PTR_ERR(path);
+
+		dev_err_probe(dev, ret, "error getting %s interconnect\n",
+			      data->name);
+
+		return ret;
+	}
+
+	interconnect->path = path;
+	interconnect->average_bandwidth = data->average_bandwidth;
+	interconnect->peak_bandwidth = data->peak_bandwidth;
+
+	return 0;
+}
+
+static void ipa_interconnect_exit_one(struct ipa_interconnect *interconnect)
+{
+	icc_put(interconnect->path);
+	memset(interconnect, 0, sizeof(*interconnect));
+}
+
+/* Initialize interconnects required for IPA operation */
+static int ipa_interconnect_init(struct ipa_power *power, struct device *dev,
+				 const struct ipa_interconnect_data *data)
+{
+	struct ipa_interconnect *interconnect;
+	u32 count;
+	int ret;
+
+	count = power->interconnect_count;
+	interconnect = kcalloc(count, sizeof(*interconnect), GFP_KERNEL);
+	if (!interconnect)
+		return -ENOMEM;
+	power->interconnect = interconnect;
+
+	while (count--) {
+		ret = ipa_interconnect_init_one(dev, interconnect, data++);
+		if (ret)
+			goto out_unwind;
+		interconnect++;
+	}
+
+	return 0;
+
+out_unwind:
+	while (interconnect-- > power->interconnect)
+		ipa_interconnect_exit_one(interconnect);
+	kfree(power->interconnect);
+	power->interconnect = NULL;
+
+	return ret;
+}
+
+/* Inverse of ipa_interconnect_init() */
+static void ipa_interconnect_exit(struct ipa_power *power)
+{
+	struct ipa_interconnect *interconnect;
+
+	interconnect = power->interconnect + power->interconnect_count;
+	while (interconnect-- > power->interconnect)
+		ipa_interconnect_exit_one(interconnect);
+	kfree(power->interconnect);
+	power->interconnect = NULL;
+}
+
+/* Currently we only use one bandwidth level, so just "enable" interconnects */
+static int ipa_interconnect_enable(struct ipa *ipa)
+{
+	struct ipa_interconnect *interconnect;
+	struct ipa_power *power = ipa->power;
+	int ret;
+	u32 i;
+
+	interconnect = power->interconnect;
+	for (i = 0; i < power->interconnect_count; i++) {
+		ret = icc_set_bw(interconnect->path,
+				 interconnect->average_bandwidth,
+				 interconnect->peak_bandwidth);
+		if (ret) {
+			dev_err(&ipa->pdev->dev,
+				"error %d enabling %s interconnect\n",
+				ret, icc_get_name(interconnect->path));
+			goto out_unwind;
+		}
+		interconnect++;
+	}
+
+	return 0;
+
+out_unwind:
+	while (interconnect-- > power->interconnect)
+		(void)icc_set_bw(interconnect->path, 0, 0);
+
+	return ret;
+}
+
+/* To disable an interconnect, we just its bandwidth to 0 */
+static int ipa_interconnect_disable(struct ipa *ipa)
+{
+	struct ipa_interconnect *interconnect;
+	struct ipa_power *power = ipa->power;
+	struct device *dev = &ipa->pdev->dev;
+	int result = 0;
+	u32 count;
+	int ret;
+
+	count = power->interconnect_count;
+	interconnect = power->interconnect + count;
+	while (count--) {
+		interconnect--;
+		ret = icc_set_bw(interconnect->path, 0, 0);
+		if (ret) {
+			dev_err(dev, "error %d disabling %s interconnect\n",
+				ret, icc_get_name(interconnect->path));
+			/* Try to disable all; record only the first error */
+			if (!result)
+				result = ret;
+		}
+	}
+
+	return result;
+}
+
+/* Enable IPA power, enabling interconnects and the core clock */
+static int ipa_power_enable(struct ipa *ipa)
+{
+	int ret;
+
+	ret = ipa_interconnect_enable(ipa);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(ipa->power->core);
+	if (ret) {
+		dev_err(&ipa->pdev->dev, "error %d enabling core clock\n", ret);
+		(void)ipa_interconnect_disable(ipa);
+	}
+
+	return ret;
+}
+
+/* Inverse of ipa_power_enable() */
+static int ipa_power_disable(struct ipa *ipa)
+{
+	clk_disable_unprepare(ipa->power->core);
+
+	return ipa_interconnect_disable(ipa);
+}
+
+static int ipa_runtime_suspend(struct device *dev)
+{
+	struct ipa *ipa = dev_get_drvdata(dev);
+
+	/* Endpoints aren't usable until setup is complete */
+	if (ipa->setup_complete) {
+		__clear_bit(IPA_POWER_FLAG_RESUMED, ipa->power->flags);
+		ipa_endpoint_suspend(ipa);
+		gsi_suspend(&ipa->gsi);
+	}
+
+	return ipa_power_disable(ipa);
+}
+
+static int ipa_runtime_resume(struct device *dev)
+{
+	struct ipa *ipa = dev_get_drvdata(dev);
+	int ret;
+
+	ret = ipa_power_enable(ipa);
+	if (WARN_ON(ret < 0))
+		return ret;
+
+	/* Endpoints aren't usable until setup is complete */
+	if (ipa->setup_complete) {
+		gsi_resume(&ipa->gsi);
+		ipa_endpoint_resume(ipa);
+	}
+
+	return 0;
+}
+
+static int ipa_suspend(struct device *dev)
+{
+	struct ipa *ipa = dev_get_drvdata(dev);
+
+	__set_bit(IPA_POWER_FLAG_SYSTEM, ipa->power->flags);
+
+	return pm_runtime_force_suspend(dev);
+}
+
+static int ipa_resume(struct device *dev)
+{
+	struct ipa *ipa = dev_get_drvdata(dev);
+	int ret;
+
+	ret = pm_runtime_force_resume(dev);
+
+	__clear_bit(IPA_POWER_FLAG_SYSTEM, ipa->power->flags);
+
+	return ret;
+}
+
+/* Return the current IPA core clock rate */
+u32 ipa_core_clock_rate(struct ipa *ipa)
+{
+	return ipa->power ? (u32)clk_get_rate(ipa->power->core) : 0;
+}
+
+/**
+ * ipa_suspend_handler() - Handle the suspend IPA interrupt
+ * @ipa:	IPA pointer
+ * @irq_id:	IPA interrupt type (unused)
+ *
+ * If an RX endpoint is suspended, and the IPA has a packet destined for
+ * that endpoint, the IPA generates a SUSPEND interrupt to inform the AP
+ * that it should resume the endpoint.  If we get one of these interrupts
+ * we just wake up the system.
+ */
+static void ipa_suspend_handler(struct ipa *ipa, enum ipa_irq_id irq_id)
+{
+	/* To handle an IPA interrupt we will have resumed the hardware
+	 * just to handle the interrupt, so we're done.  If we are in a
+	 * system suspend, trigger a system resume.
+	 */
+	if (!__test_and_set_bit(IPA_POWER_FLAG_RESUMED, ipa->power->flags))
+		if (test_bit(IPA_POWER_FLAG_SYSTEM, ipa->power->flags))
+			pm_wakeup_dev_event(&ipa->pdev->dev, 0, true);
+
+	/* Acknowledge/clear the suspend interrupt on all endpoints */
+	ipa_interrupt_suspend_clear_all(ipa->interrupt);
+}
+
+/* The next few functions coordinate stopping and starting the modem
+ * network device transmit queue.
+ *
+ * Transmit can be running concurrent with power resume, and there's a
+ * chance the resume completes before the transmit path stops the queue,
+ * leaving the queue in a stopped state.  The next two functions are used
+ * to avoid this: ipa_power_modem_queue_stop() is used by ipa_start_xmit()
+ * to conditionally stop the TX queue; and ipa_power_modem_queue_start()
+ * is used by ipa_runtime_resume() to conditionally restart it.
+ *
+ * Two flags and a spinlock are used.  If the queue is stopped, the STOPPED
+ * power flag is set.  And if the queue is started, the STARTED flag is set.
+ * The queue is only started on resume if the STOPPED flag is set.  And the
+ * queue is only started in ipa_start_xmit() if the STARTED flag is *not*
+ * set.  As a result, the queue remains operational if the two activites
+ * happen concurrently regardless of the order they complete.  The spinlock
+ * ensures the flag and TX queue operations are done atomically.
+ *
+ * The first function stops the modem netdev transmit queue, but only if
+ * the STARTED flag is *not* set.  That flag is cleared if it was set.
+ * If the queue is stopped, the STOPPED flag is set.  This is called only
+ * from the power ->runtime_resume operation.
+ */
+void ipa_power_modem_queue_stop(struct ipa *ipa)
+{
+	struct ipa_power *power = ipa->power;
+	unsigned long flags;
+
+	spin_lock_irqsave(&power->spinlock, flags);
+
+	if (!__test_and_clear_bit(IPA_POWER_FLAG_STARTED, power->flags)) {
+		netif_stop_queue(ipa->modem_netdev);
+		__set_bit(IPA_POWER_FLAG_STOPPED, power->flags);
+	}
+
+	spin_unlock_irqrestore(&power->spinlock, flags);
+}
+
+/* This function starts the modem netdev transmit queue, but only if the
+ * STOPPED flag is set.  That flag is cleared if it was set.  If the queue
+ * was restarted, the STARTED flag is set; this allows ipa_start_xmit()
+ * to skip stopping the queue in the event of a race.
+ */
+void ipa_power_modem_queue_wake(struct ipa *ipa)
+{
+	struct ipa_power *power = ipa->power;
+	unsigned long flags;
+
+	spin_lock_irqsave(&power->spinlock, flags);
+
+	if (__test_and_clear_bit(IPA_POWER_FLAG_STOPPED, power->flags)) {
+		__set_bit(IPA_POWER_FLAG_STARTED, power->flags);
+		netif_wake_queue(ipa->modem_netdev);
+	}
+
+	spin_unlock_irqrestore(&power->spinlock, flags);
+}
+
+/* This function clears the STARTED flag once the TX queue is operating */
+void ipa_power_modem_queue_active(struct ipa *ipa)
+{
+	clear_bit(IPA_POWER_FLAG_STARTED, ipa->power->flags);
+}
+
+int ipa_power_setup(struct ipa *ipa)
+{
+	int ret;
+
+	ipa_interrupt_add(ipa->interrupt, IPA_IRQ_TX_SUSPEND,
+			  ipa_suspend_handler);
+
+	ret = device_init_wakeup(&ipa->pdev->dev, true);
+	if (ret)
+		ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_TX_SUSPEND);
+
+	return ret;
+}
+
+void ipa_power_teardown(struct ipa *ipa)
+{
+	(void)device_init_wakeup(&ipa->pdev->dev, false);
+	ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_TX_SUSPEND);
+}
+
+/* Initialize IPA power management */
+struct ipa_power *
+ipa_power_init(struct device *dev, const struct ipa_power_data *data)
+{
+	struct ipa_power *power;
+	struct clk *clk;
+	int ret;
+
+	clk = clk_get(dev, "core");
+	if (IS_ERR(clk)) {
+		dev_err_probe(dev, PTR_ERR(clk), "error getting core clock\n");
+
+		return ERR_CAST(clk);
+	}
+
+	ret = clk_set_rate(clk, data->core_clock_rate);
+	if (ret) {
+		dev_err(dev, "error %d setting core clock rate to %u\n",
+			ret, data->core_clock_rate);
+		goto err_clk_put;
+	}
+
+	power = kzalloc(sizeof(*power), GFP_KERNEL);
+	if (!power) {
+		ret = -ENOMEM;
+		goto err_clk_put;
+	}
+	power->dev = dev;
+	power->core = clk;
+	spin_lock_init(&power->spinlock);
+	power->interconnect_count = data->interconnect_count;
+
+	ret = ipa_interconnect_init(power, dev, data->interconnect_data);
+	if (ret)
+		goto err_kfree;
+
+	pm_runtime_set_autosuspend_delay(dev, IPA_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_enable(dev);
+
+	return power;
+
+err_kfree:
+	kfree(power);
+err_clk_put:
+	clk_put(clk);
+
+	return ERR_PTR(ret);
+}
+
+/* Inverse of ipa_power_init() */
+void ipa_power_exit(struct ipa_power *power)
+{
+	struct device *dev = power->dev;
+	struct clk *clk = power->core;
+
+	pm_runtime_disable(dev);
+	pm_runtime_dont_use_autosuspend(dev);
+	ipa_interconnect_exit(power);
+	kfree(power);
+	clk_put(clk);
+}
+
+const struct dev_pm_ops ipa_pm_ops = {
+	.suspend		= ipa_suspend,
+	.resume			= ipa_resume,
+	.runtime_suspend	= ipa_runtime_suspend,
+	.runtime_resume		= ipa_runtime_resume,
+};
diff --git a/drivers/net/ipa/ipa_power.h b/drivers/net/ipa/ipa_power.h
new file mode 100644
index 000000000000..2151805d7fbb
--- /dev/null
+++ b/drivers/net/ipa/ipa_power.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2018-2020 Linaro Ltd.
+ */
+#ifndef _IPA_POWER_H_
+#define _IPA_POWER_H_
+
+struct device;
+
+struct ipa;
+struct ipa_power_data;
+
+/* IPA device power management function block */
+extern const struct dev_pm_ops ipa_pm_ops;
+
+/**
+ * ipa_core_clock_rate() - Return the current IPA core clock rate
+ * @ipa:	IPA structure
+ *
+ * Return: The current clock rate (in Hz), or 0.
+ */
+u32 ipa_core_clock_rate(struct ipa *ipa);
+
+/**
+ * ipa_power_modem_queue_stop() - Possibly stop the modem netdev TX queue
+ * @ipa:	IPA pointer
+ */
+void ipa_power_modem_queue_stop(struct ipa *ipa);
+
+/**
+ * ipa_power_modem_queue_wake() - Possibly wake the modem netdev TX queue
+ * @ipa:	IPA pointer
+ */
+void ipa_power_modem_queue_wake(struct ipa *ipa);
+
+/**
+ * ipa_power_modem_queue_active() - Report modem netdev TX queue active
+ * @ipa:	IPA pointer
+ */
+void ipa_power_modem_queue_active(struct ipa *ipa);
+
+/**
+ * ipa_power_setup() - Set up IPA power management
+ * @ipa:	IPA pointer
+ *
+ * Return:	0 if successful, or a negative error code
+ */
+int ipa_power_setup(struct ipa *ipa);
+
+/**
+ * ipa_power_teardown() - Inverse of ipa_power_setup()
+ * @ipa:	IPA pointer
+ */
+void ipa_power_teardown(struct ipa *ipa);
+
+/**
+ * ipa_power_init() - Initialize IPA power management
+ * @dev:	IPA device
+ * @data:	Clock configuration data
+ *
+ * Return:	A pointer to an ipa_power structure, or a pointer-coded error
+ */
+struct ipa_power *ipa_power_init(struct device *dev,
+				 const struct ipa_power_data *data);
+
+/**
+ * ipa_power_exit() - Inverse of ipa_power_init()
+ * @power:	IPA power pointer
+ */
+void ipa_power_exit(struct ipa_power *power);
+
+#endif /* _IPA_POWER_H_ */
diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c
index 4661105ce7ab..90f3aec55b36 100644
--- a/drivers/net/ipa/ipa_qmi.c
+++ b/drivers/net/ipa/ipa_qmi.c
@@ -467,10 +467,7 @@ static const struct qmi_ops ipa_client_ops = {
 	.new_server	= ipa_client_new_server,
 };
 
-/* This is called by ipa_setup().  We can be informed via remoteproc that
- * the modem has shut down, in which case this function will be called
- * again to prepare for it coming back up again.
- */
+/* Set up for QMI message exchange */
 int ipa_qmi_setup(struct ipa *ipa)
 {
 	struct ipa_qmi *ipa_qmi = &ipa->qmi;
@@ -526,6 +523,7 @@ err_server_handle_release:
 	return ret;
 }
 
+/* Tear down IPA QMI handles */
 void ipa_qmi_teardown(struct ipa *ipa)
 {
 	cancel_work_sync(&ipa->qmi.init_driver_work);
diff --git a/drivers/net/ipa/ipa_qmi.h b/drivers/net/ipa/ipa_qmi.h
index b6f2055d35a6..856ef629ccc8 100644
--- a/drivers/net/ipa/ipa_qmi.h
+++ b/drivers/net/ipa/ipa_qmi.h
@@ -39,7 +39,26 @@ struct ipa_qmi {
 	bool indication_sent;
 };
 
+/**
+ * ipa_qmi_setup() - Set up for QMI message exchange
+ * @ipa:		IPA pointer
+ *
+ * This is called at the end of ipa_setup(), to prepare for the exchange
+ * of QMI messages that perform a "handshake" between the AP and modem.
+ * When the modem QMI server announces its presence, an AP request message
+ * supplies operating parameters to be used to the modem, and the modem
+ * acknowledges receipt of those parameters.  The modem will not touch the
+ * IPA hardware until this handshake is complete.
+ *
+ * If the modem crashes (or shuts down) a new handshake begins when the
+ * modem's QMI server is started again.
+ */
 int ipa_qmi_setup(struct ipa *ipa);
+
+/**
+ * ipa_qmi_teardown() - Tear down IPA QMI handles
+ * @ipa:		IPA pointer
+ */
 void ipa_qmi_teardown(struct ipa *ipa);
 
 #endif /* !_IPA_QMI_H_ */
diff --git a/drivers/net/ipa/ipa_reg.h b/drivers/net/ipa/ipa_reg.h
index b89dec5865a5..a5b355384d4a 100644
--- a/drivers/net/ipa/ipa_reg.h
+++ b/drivers/net/ipa/ipa_reg.h
@@ -99,7 +99,7 @@ struct ipa;
 static inline u32 arbitration_lock_disable_encoded(enum ipa_version version,
 						   u32 mask)
 {
-	/* assert(version >= IPA_VERSION_4_0); */
+	WARN_ON(version < IPA_VERSION_4_0);
 
 	if (version < IPA_VERSION_4_9)
 		return u32_encode_bits(mask, GENMASK(20, 17));
@@ -116,7 +116,7 @@ static inline u32 full_flush_rsc_closure_en_encoded(enum ipa_version version,
 {
 	u32 val = enable ? 1 : 0;
 
-	/* assert(version >= IPA_VERSION_4_5); */
+	WARN_ON(version < IPA_VERSION_4_5);
 
 	if (version == IPA_VERSION_4_5 || version == IPA_VERSION_4_7)
 		return u32_encode_bits(val, GENMASK(21, 21));
@@ -409,7 +409,7 @@ static inline u32 ipa_header_size_encoded(enum ipa_version version,
 
 	val = u32_encode_bits(size, HDR_LEN_FMASK);
 	if (version < IPA_VERSION_4_5) {
-		/* ipa_assert(header_size == size); */
+		WARN_ON(header_size != size);
 		return val;
 	}
 
@@ -429,7 +429,7 @@ static inline u32 ipa_metadata_offset_encoded(enum ipa_version version,
 
 	val = u32_encode_bits(off, HDR_OFST_METADATA_FMASK);
 	if (version < IPA_VERSION_4_5) {
-		/* ipa_assert(offset == off); */
+		WARN_ON(offset != off);
 		return val;
 	}
 
@@ -812,7 +812,7 @@ ipa_reg_irq_suspend_info_offset(enum ipa_version version)
 static inline u32
 ipa_reg_irq_suspend_en_ee_n_offset(enum ipa_version version, u32 ee)
 {
-	/* assert(version != IPA_VERSION_3_0); */
+	WARN_ON(version == IPA_VERSION_3_0);
 
 	if (version < IPA_VERSION_4_9)
 		return 0x00003034 + 0x1000 * ee;
@@ -830,7 +830,7 @@ ipa_reg_irq_suspend_en_offset(enum ipa_version version)
 static inline u32
 ipa_reg_irq_suspend_clr_ee_n_offset(enum ipa_version version, u32 ee)
 {
-	/* assert(version != IPA_VERSION_3_0); */
+	WARN_ON(version == IPA_VERSION_3_0);
 
 	if (version < IPA_VERSION_4_9)
 		return 0x00003038 + 0x1000 * ee;
diff --git a/drivers/net/ipa/ipa_resource.c b/drivers/net/ipa/ipa_resource.c
index 3b2dc216d3a6..e3da95d69409 100644
--- a/drivers/net/ipa/ipa_resource.c
+++ b/drivers/net/ipa/ipa_resource.c
@@ -29,7 +29,6 @@
 static bool ipa_resource_limits_valid(struct ipa *ipa,
 				      const struct ipa_resource_data *data)
 {
-#ifdef IPA_VALIDATION
 	u32 group_count;
 	u32 i;
 	u32 j;
@@ -65,7 +64,7 @@ static bool ipa_resource_limits_valid(struct ipa *ipa,
 			if (resource->limits[j].min || resource->limits[j].max)
 				return false;
 	}
-#endif /* !IPA_VALIDATION */
+
 	return true;
 }
 
diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c
index 93270e50b6b3..df7639c39d71 100644
--- a/drivers/net/ipa/ipa_smp2p.c
+++ b/drivers/net/ipa/ipa_smp2p.c
@@ -9,13 +9,13 @@
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
 #include <linux/panic_notifier.h>
+#include <linux/pm_runtime.h>
 #include <linux/soc/qcom/smem.h>
 #include <linux/soc/qcom/smem_state.h>
 
 #include "ipa_smp2p.h"
 #include "ipa.h"
 #include "ipa_uc.h"
-#include "ipa_clock.h"
 
 /**
  * DOC: IPA SMP2P communication with the modem
@@ -23,19 +23,19 @@
  * SMP2P is a primitive communication mechanism available between the AP and
  * the modem.  The IPA driver uses this for two purposes:  to enable the modem
  * to state that the GSI hardware is ready to use; and to communicate the
- * state of the IPA clock in the event of a crash.
+ * state of IPA power in the event of a crash.
  *
  * GSI needs to have early initialization completed before it can be used.
  * This initialization is done either by Trust Zone or by the modem.  In the
  * latter case, the modem uses an SMP2P interrupt to tell the AP IPA driver
  * when the GSI is ready to use.
  *
- * The modem is also able to inquire about the current state of the IPA
- * clock by trigging another SMP2P interrupt to the AP.  We communicate
- * whether the clock is enabled using two SMP2P state bits--one to
- * indicate the clock state (on or off), and a second to indicate the
- * clock state bit is valid.  The modem will poll the valid bit until it
- * is set, and at that time records whether the AP has the IPA clock enabled.
+ * The modem is also able to inquire about the current state of IPA
+ * power by trigging another SMP2P interrupt to the AP.  We communicate
+ * whether power is enabled using two SMP2P state bits--one to indicate
+ * the power state (on or off), and a second to indicate the power state
+ * bit is valid.  The modem will poll the valid bit until it is set, and
+ * at that time records whether the AP has IPA power enabled.
  *
  * Finally, if the AP kernel panics, we update the SMP2P state bits even if
  * we never receive an interrupt from the modem requesting this.
@@ -45,14 +45,14 @@
  * struct ipa_smp2p - IPA SMP2P information
  * @ipa:		IPA pointer
  * @valid_state:	SMEM state indicating enabled state is valid
- * @enabled_state:	SMEM state to indicate clock is enabled
+ * @enabled_state:	SMEM state to indicate power is enabled
  * @valid_bit:		Valid bit in 32-bit SMEM state mask
  * @enabled_bit:	Enabled bit in 32-bit SMEM state mask
  * @enabled_bit:	Enabled bit in 32-bit SMEM state mask
- * @clock_query_irq:	IPA interrupt triggered by modem for clock query
+ * @clock_query_irq:	IPA interrupt triggered by modem for power query
  * @setup_ready_irq:	IPA interrupt triggered by modem to signal GSI ready
- * @clock_on:		Whether IPA clock is on
- * @notified:		Whether modem has been notified of clock state
+ * @power_on:		Whether IPA power is on
+ * @notified:		Whether modem has been notified of power state
  * @disabled:		Whether setup ready interrupt handling is disabled
  * @mutex:		Mutex protecting ready-interrupt/shutdown interlock
  * @panic_notifier:	Panic notifier structure
@@ -65,7 +65,7 @@ struct ipa_smp2p {
 	u32 enabled_bit;
 	u32 clock_query_irq;
 	u32 setup_ready_irq;
-	bool clock_on;
+	bool power_on;
 	bool notified;
 	bool disabled;
 	struct mutex mutex;
@@ -73,28 +73,30 @@ struct ipa_smp2p {
 };
 
 /**
- * ipa_smp2p_notify() - use SMP2P to tell modem about IPA clock state
+ * ipa_smp2p_notify() - use SMP2P to tell modem about IPA power state
  * @smp2p:	SMP2P information
  *
  * This is called either when the modem has requested it (by triggering
- * the modem clock query IPA interrupt) or whenever the AP is shutting down
+ * the modem power query IPA interrupt) or whenever the AP is shutting down
  * (via a panic notifier).  It sets the two SMP2P state bits--one saying
- * whether the IPA clock is running, and the other indicating the first bit
+ * whether the IPA power is on, and the other indicating the first bit
  * is valid.
  */
 static void ipa_smp2p_notify(struct ipa_smp2p *smp2p)
 {
+	struct device *dev;
 	u32 value;
 	u32 mask;
 
 	if (smp2p->notified)
 		return;
 
-	smp2p->clock_on = ipa_clock_get_additional(smp2p->ipa);
+	dev = &smp2p->ipa->pdev->dev;
+	smp2p->power_on = pm_runtime_get_if_active(dev, true) > 0;
 
-	/* Signal whether the clock is enabled */
+	/* Signal whether the IPA power is enabled */
 	mask = BIT(smp2p->enabled_bit);
-	value = smp2p->clock_on ? mask : 0;
+	value = smp2p->power_on ? mask : 0;
 	qcom_smem_state_update_bits(smp2p->enabled_state, mask, value);
 
 	/* Now indicate that the enabled flag is valid */
@@ -124,7 +126,7 @@ static int ipa_smp2p_panic_notifier(struct notifier_block *nb,
 
 	ipa_smp2p_notify(smp2p);
 
-	if (smp2p->clock_on)
+	if (smp2p->power_on)
 		ipa_uc_panic_notifier(smp2p->ipa);
 
 	return NOTIFY_DONE;
@@ -150,19 +152,31 @@ static void ipa_smp2p_panic_notifier_unregister(struct ipa_smp2p *smp2p)
 static irqreturn_t ipa_smp2p_modem_setup_ready_isr(int irq, void *dev_id)
 {
 	struct ipa_smp2p *smp2p = dev_id;
+	struct device *dev;
+	int ret;
 
 	mutex_lock(&smp2p->mutex);
 
-	if (!smp2p->disabled) {
-		int ret;
+	if (smp2p->disabled)
+		goto out_mutex_unlock;
+	smp2p->disabled = true;		/* If any others arrive, ignore them */
 
-		ret = ipa_setup(smp2p->ipa);
-		if (ret)
-			dev_err(&smp2p->ipa->pdev->dev,
-				"error %d from ipa_setup()\n", ret);
-		smp2p->disabled = true;
+	/* Power needs to be active for setup */
+	dev = &smp2p->ipa->pdev->dev;
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "error %d getting power for setup\n", ret);
+		goto out_power_put;
 	}
 
+	/* An error here won't cause driver shutdown, so warn if one occurs */
+	ret = ipa_setup(smp2p->ipa);
+	WARN(ret != 0, "error %d from ipa_setup()\n", ret);
+
+out_power_put:
+	pm_runtime_mark_last_busy(dev);
+	(void)pm_runtime_put_autosuspend(dev);
+out_mutex_unlock:
 	mutex_unlock(&smp2p->mutex);
 
 	return IRQ_HANDLED;
@@ -195,14 +209,17 @@ static void ipa_smp2p_irq_exit(struct ipa_smp2p *smp2p, u32 irq)
 	free_irq(irq, smp2p);
 }
 
-/* Drop the clock reference if it was taken in ipa_smp2p_notify() */
-static void ipa_smp2p_clock_release(struct ipa *ipa)
+/* Drop the power reference if it was taken in ipa_smp2p_notify() */
+static void ipa_smp2p_power_release(struct ipa *ipa)
 {
-	if (!ipa->smp2p->clock_on)
+	struct device *dev = &ipa->pdev->dev;
+
+	if (!ipa->smp2p->power_on)
 		return;
 
-	ipa_clock_put(ipa);
-	ipa->smp2p->clock_on = false;
+	pm_runtime_mark_last_busy(dev);
+	(void)pm_runtime_put_autosuspend(dev);
+	ipa->smp2p->power_on = false;
 }
 
 /* Initialize the IPA SMP2P subsystem */
@@ -236,7 +253,7 @@ int ipa_smp2p_init(struct ipa *ipa, bool modem_init)
 
 	smp2p->ipa = ipa;
 
-	/* These fields are needed by the clock query interrupt
+	/* These fields are needed by the power query interrupt
 	 * handler, so initialize them now.
 	 */
 	mutex_init(&smp2p->mutex);
@@ -289,8 +306,8 @@ void ipa_smp2p_exit(struct ipa *ipa)
 		ipa_smp2p_irq_exit(smp2p, smp2p->setup_ready_irq);
 	ipa_smp2p_panic_notifier_unregister(smp2p);
 	ipa_smp2p_irq_exit(smp2p, smp2p->clock_query_irq);
-	/* We won't get notified any more; drop clock reference (if any) */
-	ipa_smp2p_clock_release(ipa);
+	/* We won't get notified any more; drop power reference (if any) */
+	ipa_smp2p_power_release(ipa);
 	ipa->smp2p = NULL;
 	mutex_destroy(&smp2p->mutex);
 	kfree(smp2p);
@@ -319,13 +336,13 @@ void ipa_smp2p_notify_reset(struct ipa *ipa)
 	if (!smp2p->notified)
 		return;
 
-	ipa_smp2p_clock_release(ipa);
+	ipa_smp2p_power_release(ipa);
 
-	/* Reset the clock enabled valid flag */
+	/* Reset the power enabled valid flag */
 	mask = BIT(smp2p->valid_bit);
 	qcom_smem_state_update_bits(smp2p->valid_state, mask, 0);
 
-	/* Mark the clock disabled for good measure... */
+	/* Mark the power disabled for good measure... */
 	mask = BIT(smp2p->enabled_bit);
 	qcom_smem_state_update_bits(smp2p->enabled_state, mask, 0);
 
diff --git a/drivers/net/ipa/ipa_smp2p.h b/drivers/net/ipa/ipa_smp2p.h
index 20319438a841..99a956789638 100644
--- a/drivers/net/ipa/ipa_smp2p.h
+++ b/drivers/net/ipa/ipa_smp2p.h
@@ -39,7 +39,7 @@ void ipa_smp2p_disable(struct ipa *ipa);
  * ipa_smp2p_notify_reset() - Reset modem notification state
  * @ipa:	IPA pointer
  *
- * If the modem crashes it queries the IPA clock state.  In cleaning
+ * If the modem crashes it queries the IPA power state.  In cleaning
  * up after such a crash this is used to reset some state maintained
  * for managing this notification.
  */
diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c
index c617a9156f26..2324e1b93e37 100644
--- a/drivers/net/ipa/ipa_table.c
+++ b/drivers/net/ipa/ipa_table.c
@@ -120,8 +120,6 @@
  */
 #define IPA_ZERO_RULE_SIZE		(2 * sizeof(__le32))
 
-#ifdef IPA_VALIDATE
-
 /* Check things that can be validated at build time. */
 static void ipa_table_validate_build(void)
 {
@@ -161,7 +159,7 @@ ipa_table_valid_one(struct ipa *ipa, enum ipa_mem_id mem_id, bool route)
 	else
 		size = (1 + IPA_FILTER_COUNT_MAX) * sizeof(__le64);
 
-	if (!ipa_cmd_table_valid(ipa, mem, route, ipv6, hashed))
+	if (!ipa_cmd_table_valid(ipa, mem, route))
 		return false;
 
 	/* mem->size >= size is sufficient, but we'll demand more */
@@ -169,7 +167,7 @@ ipa_table_valid_one(struct ipa *ipa, enum ipa_mem_id mem_id, bool route)
 		return true;
 
 	/* Hashed table regions can be zero size if hashing is not supported */
-	if (hashed && !mem->size)
+	if (ipa_table_hash_support(ipa) && !mem->size)
 		return true;
 
 	dev_err(dev, "%s table region %u size 0x%02x, expected 0x%02x\n",
@@ -183,14 +181,22 @@ bool ipa_table_valid(struct ipa *ipa)
 {
 	bool valid;
 
-	valid = ipa_table_valid_one(IPA_MEM_V4_FILTER, false);
-	valid = valid && ipa_table_valid_one(IPA_MEM_V4_FILTER_HASHED, false);
-	valid = valid && ipa_table_valid_one(IPA_MEM_V6_FILTER, false);
-	valid = valid && ipa_table_valid_one(IPA_MEM_V6_FILTER_HASHED, false);
-	valid = valid && ipa_table_valid_one(IPA_MEM_V4_ROUTE, true);
-	valid = valid && ipa_table_valid_one(IPA_MEM_V4_ROUTE_HASHED, true);
-	valid = valid && ipa_table_valid_one(IPA_MEM_V6_ROUTE, true);
-	valid = valid && ipa_table_valid_one(IPA_MEM_V6_ROUTE_HASHED, true);
+	valid = ipa_table_valid_one(ipa, IPA_MEM_V4_FILTER, false);
+	valid = valid && ipa_table_valid_one(ipa, IPA_MEM_V6_FILTER, false);
+	valid = valid && ipa_table_valid_one(ipa, IPA_MEM_V4_ROUTE, true);
+	valid = valid && ipa_table_valid_one(ipa, IPA_MEM_V6_ROUTE, true);
+
+	if (!ipa_table_hash_support(ipa))
+		return valid;
+
+	valid = valid && ipa_table_valid_one(ipa, IPA_MEM_V4_FILTER_HASHED,
+					     false);
+	valid = valid && ipa_table_valid_one(ipa, IPA_MEM_V6_FILTER_HASHED,
+					     false);
+	valid = valid && ipa_table_valid_one(ipa, IPA_MEM_V4_ROUTE_HASHED,
+					     true);
+	valid = valid && ipa_table_valid_one(ipa, IPA_MEM_V6_ROUTE_HASHED,
+					     true);
 
 	return valid;
 }
@@ -217,14 +223,6 @@ bool ipa_filter_map_valid(struct ipa *ipa, u32 filter_map)
 	return true;
 }
 
-#else /* !IPA_VALIDATE */
-static void ipa_table_validate_build(void)
-
-{
-}
-
-#endif /* !IPA_VALIDATE */
-
 /* Zero entry count means no table, so just return a 0 address */
 static dma_addr_t ipa_table_addr(struct ipa *ipa, bool filter_mask, u16 count)
 {
@@ -233,7 +231,7 @@ static dma_addr_t ipa_table_addr(struct ipa *ipa, bool filter_mask, u16 count)
 	if (!count)
 		return 0;
 
-/* assert(count <= max_t(u32, IPA_FILTER_COUNT_MAX, IPA_ROUTE_COUNT_MAX)); */
+	WARN_ON(count > max_t(u32, IPA_FILTER_COUNT_MAX, IPA_ROUTE_COUNT_MAX));
 
 	/* Skip over the zero rule and possibly the filter mask */
 	skip = filter_mask ? 1 : 2;
diff --git a/drivers/net/ipa/ipa_table.h b/drivers/net/ipa/ipa_table.h
index 1e2be9fce2f8..b6a9a0d79d68 100644
--- a/drivers/net/ipa/ipa_table.h
+++ b/drivers/net/ipa/ipa_table.h
@@ -16,8 +16,6 @@ struct ipa;
 /* The maximum number of route table entries (IPv4, IPv6; hashed or not) */
 #define IPA_ROUTE_COUNT_MAX	15
 
-#ifdef IPA_VALIDATE
-
 /**
  * ipa_table_valid() - Validate route and filter table memory regions
  * @ipa:	IPA pointer
@@ -35,20 +33,6 @@ bool ipa_table_valid(struct ipa *ipa);
  */
 bool ipa_filter_map_valid(struct ipa *ipa, u32 filter_mask);
 
-#else /* !IPA_VALIDATE */
-
-static inline bool ipa_table_valid(struct ipa *ipa)
-{
-	return true;
-}
-
-static inline bool ipa_filter_map_valid(struct ipa *ipa, u32 filter_mask)
-{
-	return true;
-}
-
-#endif /* !IPA_VALIDATE */
-
 /**
  * ipa_table_hash_support() - Return true if hashed tables are supported
  * @ipa:	IPA pointer
diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c
index fd9219863234..856e55a080a7 100644
--- a/drivers/net/ipa/ipa_uc.c
+++ b/drivers/net/ipa/ipa_uc.c
@@ -7,9 +7,9 @@
 #include <linux/types.h>
 #include <linux/io.h>
 #include <linux/delay.h>
+#include <linux/pm_runtime.h>
 
 #include "ipa.h"
-#include "ipa_clock.h"
 #include "ipa_uc.h"
 
 /**
@@ -131,7 +131,7 @@ static void ipa_uc_event_handler(struct ipa *ipa, enum ipa_irq_id irq_id)
 	if (shared->event == IPA_UC_EVENT_ERROR)
 		dev_err(dev, "microcontroller error event\n");
 	else if (shared->event != IPA_UC_EVENT_LOG_INFO)
-		dev_err(dev, "unsupported microcontroller event %hhu\n",
+		dev_err(dev, "unsupported microcontroller event %u\n",
 			shared->event);
 	/* The LOG_INFO event can be safely ignored */
 }
@@ -140,53 +140,77 @@ static void ipa_uc_event_handler(struct ipa *ipa, enum ipa_irq_id irq_id)
 static void ipa_uc_response_hdlr(struct ipa *ipa, enum ipa_irq_id irq_id)
 {
 	struct ipa_uc_mem_area *shared = ipa_uc_shared(ipa);
+	struct device *dev = &ipa->pdev->dev;
 
 	/* An INIT_COMPLETED response message is sent to the AP by the
 	 * microcontroller when it is operational.  Other than this, the AP
 	 * should only receive responses from the microcontroller when it has
 	 * sent it a request message.
 	 *
-	 * We can drop the clock reference taken in ipa_uc_setup() once we
+	 * We can drop the power reference taken in ipa_uc_power() once we
 	 * know the microcontroller has finished its initialization.
 	 */
 	switch (shared->response) {
 	case IPA_UC_RESPONSE_INIT_COMPLETED:
-		ipa->uc_loaded = true;
-		ipa_clock_put(ipa);
+		if (ipa->uc_powered) {
+			ipa->uc_loaded = true;
+			pm_runtime_mark_last_busy(dev);
+			(void)pm_runtime_put_autosuspend(dev);
+			ipa->uc_powered = false;
+		} else {
+			dev_warn(dev, "unexpected init_completed response\n");
+		}
 		break;
 	default:
-		dev_warn(&ipa->pdev->dev,
-			 "unsupported microcontroller response %hhu\n",
+		dev_warn(dev, "unsupported microcontroller response %u\n",
 			 shared->response);
 		break;
 	}
 }
 
-/* ipa_uc_setup() - Set up the microcontroller */
-void ipa_uc_setup(struct ipa *ipa)
+/* Configure the IPA microcontroller subsystem */
+void ipa_uc_config(struct ipa *ipa)
 {
-	/* The microcontroller needs the IPA clock running until it has
-	 * completed its initialization.  It signals this by sending an
-	 * INIT_COMPLETED response message to the AP.  This could occur after
-	 * we have finished doing the rest of the IPA initialization, so we
-	 * need to take an extra "proxy" reference, and hold it until we've
-	 * received that signal.  (This reference is dropped in
-	 * ipa_uc_response_hdlr(), above.)
-	 */
-	ipa_clock_get(ipa);
-
+	ipa->uc_powered = false;
 	ipa->uc_loaded = false;
 	ipa_interrupt_add(ipa->interrupt, IPA_IRQ_UC_0, ipa_uc_event_handler);
 	ipa_interrupt_add(ipa->interrupt, IPA_IRQ_UC_1, ipa_uc_response_hdlr);
 }
 
-/* Inverse of ipa_uc_setup() */
-void ipa_uc_teardown(struct ipa *ipa)
+/* Inverse of ipa_uc_config() */
+void ipa_uc_deconfig(struct ipa *ipa)
 {
+	struct device *dev = &ipa->pdev->dev;
+
 	ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_UC_1);
 	ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_UC_0);
-	if (!ipa->uc_loaded)
-		ipa_clock_put(ipa);
+	if (!ipa->uc_powered)
+		return;
+
+	pm_runtime_mark_last_busy(dev);
+	(void)pm_runtime_put_autosuspend(dev);
+}
+
+/* Take a proxy power reference for the microcontroller */
+void ipa_uc_power(struct ipa *ipa)
+{
+	static bool already;
+	struct device *dev;
+	int ret;
+
+	if (already)
+		return;
+	already = true;		/* Only do this on first boot */
+
+	/* This power reference dropped in ipa_uc_response_hdlr() above */
+	dev = &ipa->pdev->dev;
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(dev);
+		dev_err(dev, "error %d getting proxy power\n", ret);
+	} else {
+		ipa->uc_powered = true;
+	}
 }
 
 /* Send a command to the microcontroller */
diff --git a/drivers/net/ipa/ipa_uc.h b/drivers/net/ipa/ipa_uc.h
index e8510899a3f0..23847f934d64 100644
--- a/drivers/net/ipa/ipa_uc.h
+++ b/drivers/net/ipa/ipa_uc.h
@@ -9,16 +9,30 @@
 struct ipa;
 
 /**
- * ipa_uc_setup() - set up the IPA microcontroller subsystem
+ * ipa_uc_config() - Configure the IPA microcontroller subsystem
  * @ipa:	IPA pointer
  */
-void ipa_uc_setup(struct ipa *ipa);
+void ipa_uc_config(struct ipa *ipa);
 
 /**
- * ipa_uc_teardown() - inverse of ipa_uc_setup()
+ * ipa_uc_deconfig() - Inverse of ipa_uc_config()
  * @ipa:	IPA pointer
  */
-void ipa_uc_teardown(struct ipa *ipa);
+void ipa_uc_deconfig(struct ipa *ipa);
+
+/**
+ * ipa_uc_power() - Take a proxy power reference for the microcontroller
+ * @ipa:	IPA pointer
+ *
+ * The first time the modem boots, it loads firmware for and starts the
+ * IPA-resident microcontroller.  The microcontroller signals that it
+ * has completed its initialization by sending an INIT_COMPLETED response
+ * message to the AP.  The AP must ensure the IPA is powered until
+ * it receives this message, and to do so we take a "proxy" clock
+ * reference on its behalf here.  Once we receive the INIT_COMPLETED
+ * message (in ipa_uc_response_hdlr()) we drop this power reference.
+ */
+void ipa_uc_power(struct ipa *ipa);
 
 /**
  * ipa_uc_panic_notifier()
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index a707502a0c0f..c0b21a5580d5 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -732,6 +732,7 @@ static int ipvlan_device_event(struct notifier_block *unused,
 	port = ipvlan_port_get_rtnl(dev);
 
 	switch (event) {
+	case NETDEV_UP:
 	case NETDEV_CHANGE:
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode)
 			netif_stacked_transfer_operstate(ipvlan->phy_dev,
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 80de9768ecd4..35f46ad040b0 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -829,7 +829,7 @@ static int macvlan_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
-static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int macvlan_eth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct net_device *real_dev = macvlan_dev_real_dev(dev);
 	const struct net_device_ops *ops = real_dev->netdev_ops;
@@ -845,8 +845,8 @@ static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			break;
 		fallthrough;
 	case SIOCGHWTSTAMP:
-		if (netif_device_present(real_dev) && ops->ndo_do_ioctl)
-			err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd);
+		if (netif_device_present(real_dev) && ops->ndo_eth_ioctl)
+			err = ops->ndo_eth_ioctl(real_dev, &ifrr, cmd);
 		break;
 	}
 
@@ -1151,7 +1151,7 @@ static const struct net_device_ops macvlan_netdev_ops = {
 	.ndo_stop		= macvlan_stop,
 	.ndo_start_xmit		= macvlan_start_xmit,
 	.ndo_change_mtu		= macvlan_change_mtu,
-	.ndo_do_ioctl		= macvlan_do_ioctl,
+	.ndo_eth_ioctl		= macvlan_eth_ioctl,
 	.ndo_fix_features	= macvlan_fix_features,
 	.ndo_change_rx_flags	= macvlan_change_rx_flags,
 	.ndo_set_mac_address	= macvlan_set_mac_address,
diff --git a/drivers/net/mctp/Kconfig b/drivers/net/mctp/Kconfig
new file mode 100644
index 000000000000..d8f966cedc89
--- /dev/null
+++ b/drivers/net/mctp/Kconfig
@@ -0,0 +1,8 @@
+
+if MCTP
+
+menu "MCTP Device Drivers"
+
+endmenu
+
+endif
diff --git a/drivers/net/mctp/Makefile b/drivers/net/mctp/Makefile
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/drivers/net/mctp/Makefile
diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig
index 99a6c13a11af..6da1fcb25847 100644
--- a/drivers/net/mdio/Kconfig
+++ b/drivers/net/mdio/Kconfig
@@ -169,9 +169,10 @@ config MDIO_OCTEON
 config MDIO_IPQ4019
 	tristate "Qualcomm IPQ4019 MDIO interface support"
 	depends on HAS_IOMEM && OF_MDIO
+	depends on COMMON_CLK
 	help
 	  This driver supports the MDIO interface found in Qualcomm
-	  IPQ40xx series Soc-s.
+	  IPQ40xx, IPQ60xx, IPQ807x and IPQ50xx series Soc-s.
 
 config MDIO_IPQ8064
 	tristate "Qualcomm IPQ8064 MDIO interface support"
diff --git a/drivers/net/mdio/mdio-ipq4019.c b/drivers/net/mdio/mdio-ipq4019.c
index 9cd71d896963..0d7d3e15d2f0 100644
--- a/drivers/net/mdio/mdio-ipq4019.c
+++ b/drivers/net/mdio/mdio-ipq4019.c
@@ -11,6 +11,7 @@
 #include <linux/of_mdio.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
+#include <linux/clk.h>
 
 #define MDIO_MODE_REG				0x40
 #define MDIO_ADDR_REG				0x44
@@ -31,8 +32,15 @@
 #define IPQ4019_MDIO_TIMEOUT	10000
 #define IPQ4019_MDIO_SLEEP		10
 
+/* MDIO clock source frequency is fixed to 100M */
+#define IPQ_MDIO_CLK_RATE	100000000
+
+#define IPQ_PHY_SET_DELAY_US	100000
+
 struct ipq4019_mdio_data {
 	void __iomem	*membase;
+	void __iomem *eth_ldo_rdy;
+	struct clk *mdio_clk;
 };
 
 static int ipq4019_mdio_wait_busy(struct mii_bus *bus)
@@ -171,6 +179,30 @@ static int ipq4019_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	return 0;
 }
 
+static int ipq_mdio_reset(struct mii_bus *bus)
+{
+	struct ipq4019_mdio_data *priv = bus->priv;
+	u32 val;
+	int ret;
+
+	/* To indicate CMN_PLL that ethernet_ldo has been ready if platform resource 1
+	 * is specified in the device tree.
+	 */
+	if (priv->eth_ldo_rdy) {
+		val = readl(priv->eth_ldo_rdy);
+		val |= BIT(0);
+		writel(val, priv->eth_ldo_rdy);
+		fsleep(IPQ_PHY_SET_DELAY_US);
+	}
+
+	/* Configure MDIO clock source frequency if clock is specified in the device tree */
+	ret = clk_set_rate(priv->mdio_clk, IPQ_MDIO_CLK_RATE);
+	if (ret)
+		return ret;
+
+	return clk_prepare_enable(priv->mdio_clk);
+}
+
 static int ipq4019_mdio_probe(struct platform_device *pdev)
 {
 	struct ipq4019_mdio_data *priv;
@@ -187,9 +219,17 @@ static int ipq4019_mdio_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->membase))
 		return PTR_ERR(priv->membase);
 
+	priv->mdio_clk = devm_clk_get_optional(&pdev->dev, "gcc_mdio_ahb_clk");
+	if (IS_ERR(priv->mdio_clk))
+		return PTR_ERR(priv->mdio_clk);
+
+	/* The platform resource is provided on the chipset IPQ5018 */
+	priv->eth_ldo_rdy = devm_platform_ioremap_resource(pdev, 1);
+
 	bus->name = "ipq4019_mdio";
 	bus->read = ipq4019_mdio_read;
 	bus->write = ipq4019_mdio_write;
+	bus->reset = ipq_mdio_reset;
 	bus->parent = &pdev->dev;
 	snprintf(bus->id, MII_BUS_ID_SIZE, "%s%d", pdev->name, pdev->id);
 
@@ -215,6 +255,7 @@ static int ipq4019_mdio_remove(struct platform_device *pdev)
 
 static const struct of_device_id ipq4019_mdio_dt_ids[] = {
 	{ .compatible = "qcom,ipq4019-mdio" },
+	{ .compatible = "qcom,ipq5018-mdio" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, ipq4019_mdio_dt_ids);
diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c
index 2d67e12c8262..1ee592d3eae4 100644
--- a/drivers/net/mdio/mdio-mscc-miim.c
+++ b/drivers/net/mdio/mdio-mscc-miim.c
@@ -134,7 +134,6 @@ static int mscc_miim_reset(struct mii_bus *bus)
 
 static int mscc_miim_probe(struct platform_device *pdev)
 {
-	struct resource *res;
 	struct mii_bus *bus;
 	struct mscc_miim_dev *dev;
 	int ret;
@@ -157,13 +156,10 @@ static int mscc_miim_probe(struct platform_device *pdev)
 		return PTR_ERR(dev->regs);
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (res) {
-		dev->phy_regs = devm_ioremap_resource(&pdev->dev, res);
-		if (IS_ERR(dev->phy_regs)) {
-			dev_err(&pdev->dev, "Unable to map internal phy registers\n");
-			return PTR_ERR(dev->phy_regs);
-		}
+	dev->phy_regs = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(dev->phy_regs)) {
+		dev_err(&pdev->dev, "Unable to map internal phy registers\n");
+		return PTR_ERR(dev->phy_regs);
 	}
 
 	ret = of_mdiobus_register(bus, pdev->dev.of_node);
diff --git a/drivers/net/mhi/Makefile b/drivers/net/mhi/Makefile
deleted file mode 100644
index f71b9f8f3c4f..000000000000
--- a/drivers/net/mhi/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-obj-$(CONFIG_MHI_NET) += mhi_net.o
-
-mhi_net-y := net.o proto_mbim.o
diff --git a/drivers/net/mhi/mhi.h b/drivers/net/mhi/mhi.h
deleted file mode 100644
index 1d0c499d27a3..000000000000
--- a/drivers/net/mhi/mhi.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* MHI Network driver - Network over MHI bus
- *
- * Copyright (C) 2021 Linaro Ltd <loic.poulain@linaro.org>
- */
-
-struct mhi_net_stats {
-	u64_stats_t rx_packets;
-	u64_stats_t rx_bytes;
-	u64_stats_t rx_errors;
-	u64_stats_t rx_dropped;
-	u64_stats_t rx_length_errors;
-	u64_stats_t tx_packets;
-	u64_stats_t tx_bytes;
-	u64_stats_t tx_errors;
-	u64_stats_t tx_dropped;
-	struct u64_stats_sync tx_syncp;
-	struct u64_stats_sync rx_syncp;
-};
-
-struct mhi_net_dev {
-	struct mhi_device *mdev;
-	struct net_device *ndev;
-	struct sk_buff *skbagg_head;
-	struct sk_buff *skbagg_tail;
-	const struct mhi_net_proto *proto;
-	void *proto_data;
-	struct delayed_work rx_refill;
-	struct mhi_net_stats stats;
-	u32 rx_queue_sz;
-	int msg_enable;
-	unsigned int mru;
-};
-
-struct mhi_net_proto {
-	int (*init)(struct mhi_net_dev *mhi_netdev);
-	struct sk_buff * (*tx_fixup)(struct mhi_net_dev *mhi_netdev, struct sk_buff *skb);
-	void (*rx)(struct mhi_net_dev *mhi_netdev, struct sk_buff *skb);
-};
-
-extern const struct mhi_net_proto proto_mbim;
diff --git a/drivers/net/mhi/proto_mbim.c b/drivers/net/mhi/proto_mbim.c
deleted file mode 100644
index bf1ad863237d..000000000000
--- a/drivers/net/mhi/proto_mbim.c
+++ /dev/null
@@ -1,304 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/* MHI Network driver - Network over MHI bus
- *
- * Copyright (C) 2021 Linaro Ltd <loic.poulain@linaro.org>
- *
- * This driver copy some code from cdc_ncm, which is:
- * Copyright (C) ST-Ericsson 2010-2012
- * and cdc_mbim, which is:
- * Copyright (c) 2012  Smith Micro Software, Inc.
- * Copyright (c) 2012  Bjørn Mork <bjorn@mork.no>
- *
- */
-
-#include <linux/ethtool.h>
-#include <linux/if_vlan.h>
-#include <linux/ip.h>
-#include <linux/mii.h>
-#include <linux/netdevice.h>
-#include <linux/wwan.h>
-#include <linux/skbuff.h>
-#include <linux/usb.h>
-#include <linux/usb/cdc.h>
-#include <linux/usb/usbnet.h>
-#include <linux/usb/cdc_ncm.h>
-
-#include "mhi.h"
-
-#define MBIM_NDP16_SIGN_MASK 0x00ffffff
-
-/* Usual WWAN MTU */
-#define MHI_MBIM_DEFAULT_MTU 1500
-
-/* 3500 allows to optimize skb allocation, the skbs will basically fit in
- * one 4K page. Large MBIM packets will simply be split over several MHI
- * transfers and chained by the MHI net layer (zerocopy).
- */
-#define MHI_MBIM_DEFAULT_MRU 3500
-
-struct mbim_context {
-	u16 rx_seq;
-	u16 tx_seq;
-};
-
-static void __mbim_length_errors_inc(struct mhi_net_dev *dev)
-{
-	u64_stats_update_begin(&dev->stats.rx_syncp);
-	u64_stats_inc(&dev->stats.rx_length_errors);
-	u64_stats_update_end(&dev->stats.rx_syncp);
-}
-
-static void __mbim_errors_inc(struct mhi_net_dev *dev)
-{
-	u64_stats_update_begin(&dev->stats.rx_syncp);
-	u64_stats_inc(&dev->stats.rx_errors);
-	u64_stats_update_end(&dev->stats.rx_syncp);
-}
-
-static int mbim_rx_verify_nth16(struct sk_buff *skb)
-{
-	struct mhi_net_dev *dev = wwan_netdev_drvpriv(skb->dev);
-	struct mbim_context *ctx = dev->proto_data;
-	struct usb_cdc_ncm_nth16 *nth16;
-	int len;
-
-	if (skb->len < sizeof(struct usb_cdc_ncm_nth16) +
-			sizeof(struct usb_cdc_ncm_ndp16)) {
-		netif_dbg(dev, rx_err, dev->ndev, "frame too short\n");
-		__mbim_length_errors_inc(dev);
-		return -EINVAL;
-	}
-
-	nth16 = (struct usb_cdc_ncm_nth16 *)skb->data;
-
-	if (nth16->dwSignature != cpu_to_le32(USB_CDC_NCM_NTH16_SIGN)) {
-		netif_dbg(dev, rx_err, dev->ndev,
-			  "invalid NTH16 signature <%#010x>\n",
-			  le32_to_cpu(nth16->dwSignature));
-		__mbim_errors_inc(dev);
-		return -EINVAL;
-	}
-
-	/* No limit on the block length, except the size of the data pkt */
-	len = le16_to_cpu(nth16->wBlockLength);
-	if (len > skb->len) {
-		netif_dbg(dev, rx_err, dev->ndev,
-			  "NTB does not fit into the skb %u/%u\n", len,
-			  skb->len);
-		__mbim_length_errors_inc(dev);
-		return -EINVAL;
-	}
-
-	if (ctx->rx_seq + 1 != le16_to_cpu(nth16->wSequence) &&
-	    (ctx->rx_seq || le16_to_cpu(nth16->wSequence)) &&
-	    !(ctx->rx_seq == 0xffff && !le16_to_cpu(nth16->wSequence))) {
-		netif_dbg(dev, rx_err, dev->ndev,
-			  "sequence number glitch prev=%d curr=%d\n",
-			  ctx->rx_seq, le16_to_cpu(nth16->wSequence));
-	}
-	ctx->rx_seq = le16_to_cpu(nth16->wSequence);
-
-	return le16_to_cpu(nth16->wNdpIndex);
-}
-
-static int mbim_rx_verify_ndp16(struct sk_buff *skb, struct usb_cdc_ncm_ndp16 *ndp16)
-{
-	struct mhi_net_dev *dev = wwan_netdev_drvpriv(skb->dev);
-	int ret;
-
-	if (le16_to_cpu(ndp16->wLength) < USB_CDC_NCM_NDP16_LENGTH_MIN) {
-		netif_dbg(dev, rx_err, dev->ndev, "invalid DPT16 length <%u>\n",
-			  le16_to_cpu(ndp16->wLength));
-		return -EINVAL;
-	}
-
-	ret = ((le16_to_cpu(ndp16->wLength) - sizeof(struct usb_cdc_ncm_ndp16))
-			/ sizeof(struct usb_cdc_ncm_dpe16));
-	ret--; /* Last entry is always a NULL terminator */
-
-	if (sizeof(struct usb_cdc_ncm_ndp16) +
-	     ret * sizeof(struct usb_cdc_ncm_dpe16) > skb->len) {
-		netif_dbg(dev, rx_err, dev->ndev,
-			  "Invalid nframes = %d\n", ret);
-		return -EINVAL;
-	}
-
-	return ret;
-}
-
-static void mbim_rx(struct mhi_net_dev *mhi_netdev, struct sk_buff *skb)
-{
-	struct net_device *ndev = mhi_netdev->ndev;
-	int ndpoffset;
-
-	/* Check NTB header and retrieve first NDP offset */
-	ndpoffset = mbim_rx_verify_nth16(skb);
-	if (ndpoffset < 0) {
-		net_err_ratelimited("%s: Incorrect NTB header\n", ndev->name);
-		goto error;
-	}
-
-	/* Process each NDP */
-	while (1) {
-		struct usb_cdc_ncm_ndp16 ndp16;
-		struct usb_cdc_ncm_dpe16 dpe16;
-		int nframes, n, dpeoffset;
-
-		if (skb_copy_bits(skb, ndpoffset, &ndp16, sizeof(ndp16))) {
-			net_err_ratelimited("%s: Incorrect NDP offset (%u)\n",
-					    ndev->name, ndpoffset);
-			__mbim_length_errors_inc(mhi_netdev);
-			goto error;
-		}
-
-		/* Check NDP header and retrieve number of datagrams */
-		nframes = mbim_rx_verify_ndp16(skb, &ndp16);
-		if (nframes < 0) {
-			net_err_ratelimited("%s: Incorrect NDP16\n", ndev->name);
-			__mbim_length_errors_inc(mhi_netdev);
-			goto error;
-		}
-
-		 /* Only IP data type supported, no DSS in MHI context */
-		if ((ndp16.dwSignature & cpu_to_le32(MBIM_NDP16_SIGN_MASK))
-				!= cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN)) {
-			net_err_ratelimited("%s: Unsupported NDP type\n", ndev->name);
-			__mbim_errors_inc(mhi_netdev);
-			goto next_ndp;
-		}
-
-		/* Only primary IP session 0 (0x00) supported for now */
-		if (ndp16.dwSignature & ~cpu_to_le32(MBIM_NDP16_SIGN_MASK)) {
-			net_err_ratelimited("%s: bad packet session\n", ndev->name);
-			__mbim_errors_inc(mhi_netdev);
-			goto next_ndp;
-		}
-
-		/* de-aggregate and deliver IP packets */
-		dpeoffset = ndpoffset + sizeof(struct usb_cdc_ncm_ndp16);
-		for (n = 0; n < nframes; n++, dpeoffset += sizeof(dpe16)) {
-			u16 dgram_offset, dgram_len;
-			struct sk_buff *skbn;
-
-			if (skb_copy_bits(skb, dpeoffset, &dpe16, sizeof(dpe16)))
-				break;
-
-			dgram_offset = le16_to_cpu(dpe16.wDatagramIndex);
-			dgram_len = le16_to_cpu(dpe16.wDatagramLength);
-
-			if (!dgram_offset || !dgram_len)
-				break; /* null terminator */
-
-			skbn = netdev_alloc_skb(ndev, dgram_len);
-			if (!skbn)
-				continue;
-
-			skb_put(skbn, dgram_len);
-			skb_copy_bits(skb, dgram_offset, skbn->data, dgram_len);
-
-			switch (skbn->data[0] & 0xf0) {
-			case 0x40:
-				skbn->protocol = htons(ETH_P_IP);
-				break;
-			case 0x60:
-				skbn->protocol = htons(ETH_P_IPV6);
-				break;
-			default:
-				net_err_ratelimited("%s: unknown protocol\n",
-						    ndev->name);
-				__mbim_errors_inc(mhi_netdev);
-				dev_kfree_skb_any(skbn);
-				continue;
-			}
-
-			netif_rx(skbn);
-		}
-next_ndp:
-		/* Other NDP to process? */
-		ndpoffset = (int)le16_to_cpu(ndp16.wNextNdpIndex);
-		if (!ndpoffset)
-			break;
-	}
-
-	/* free skb */
-	dev_consume_skb_any(skb);
-	return;
-error:
-	dev_kfree_skb_any(skb);
-}
-
-struct mbim_tx_hdr {
-	struct usb_cdc_ncm_nth16 nth16;
-	struct usb_cdc_ncm_ndp16 ndp16;
-	struct usb_cdc_ncm_dpe16 dpe16[2];
-} __packed;
-
-static struct sk_buff *mbim_tx_fixup(struct mhi_net_dev *mhi_netdev,
-				     struct sk_buff *skb)
-{
-	struct mbim_context *ctx = mhi_netdev->proto_data;
-	unsigned int dgram_size = skb->len;
-	struct usb_cdc_ncm_nth16 *nth16;
-	struct usb_cdc_ncm_ndp16 *ndp16;
-	struct mbim_tx_hdr *mbim_hdr;
-
-	/* For now, this is a partial implementation of CDC MBIM, only one NDP
-	 * is sent, containing the IP packet (no aggregation).
-	 */
-
-	/* Ensure we have enough headroom for crafting MBIM header */
-	if (skb_cow_head(skb, sizeof(struct mbim_tx_hdr))) {
-		dev_kfree_skb_any(skb);
-		return NULL;
-	}
-
-	mbim_hdr = skb_push(skb, sizeof(struct mbim_tx_hdr));
-
-	/* Fill NTB header */
-	nth16 = &mbim_hdr->nth16;
-	nth16->dwSignature = cpu_to_le32(USB_CDC_NCM_NTH16_SIGN);
-	nth16->wHeaderLength = cpu_to_le16(sizeof(struct usb_cdc_ncm_nth16));
-	nth16->wSequence = cpu_to_le16(ctx->tx_seq++);
-	nth16->wBlockLength = cpu_to_le16(skb->len);
-	nth16->wNdpIndex = cpu_to_le16(sizeof(struct usb_cdc_ncm_nth16));
-
-	/* Fill the unique NDP */
-	ndp16 = &mbim_hdr->ndp16;
-	ndp16->dwSignature = cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN);
-	ndp16->wLength = cpu_to_le16(sizeof(struct usb_cdc_ncm_ndp16)
-					+ sizeof(struct usb_cdc_ncm_dpe16) * 2);
-	ndp16->wNextNdpIndex = 0;
-
-	/* Datagram follows the mbim header */
-	ndp16->dpe16[0].wDatagramIndex = cpu_to_le16(sizeof(struct mbim_tx_hdr));
-	ndp16->dpe16[0].wDatagramLength = cpu_to_le16(dgram_size);
-
-	/* null termination */
-	ndp16->dpe16[1].wDatagramIndex = 0;
-	ndp16->dpe16[1].wDatagramLength = 0;
-
-	return skb;
-}
-
-static int mbim_init(struct mhi_net_dev *mhi_netdev)
-{
-	struct net_device *ndev = mhi_netdev->ndev;
-
-	mhi_netdev->proto_data = devm_kzalloc(&ndev->dev,
-					      sizeof(struct mbim_context),
-					      GFP_KERNEL);
-	if (!mhi_netdev->proto_data)
-		return -ENOMEM;
-
-	ndev->needed_headroom = sizeof(struct mbim_tx_hdr);
-	ndev->mtu = MHI_MBIM_DEFAULT_MTU;
-	mhi_netdev->mru = MHI_MBIM_DEFAULT_MRU;
-
-	return 0;
-}
-
-const struct mhi_net_proto proto_mbim = {
-	.init = mbim_init,
-	.rx = mbim_rx,
-	.tx_fixup = mbim_tx_fixup,
-};
diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi_net.c
index e60e38c1f09d..d127eb6e9257 100644
--- a/drivers/net/mhi/net.c
+++ b/drivers/net/mhi_net.c
@@ -11,28 +11,42 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/u64_stats_sync.h>
-#include <linux/wwan.h>
-
-#include "mhi.h"
 
 #define MHI_NET_MIN_MTU		ETH_MIN_MTU
 #define MHI_NET_MAX_MTU		0xffff
 #define MHI_NET_DEFAULT_MTU	0x4000
 
-/* When set to false, the default netdev (link 0) is not created, and it's up
- * to user to create the link (via wwan rtnetlink).
- */
-static bool create_default_iface = true;
-module_param(create_default_iface, bool, 0);
+struct mhi_net_stats {
+	u64_stats_t rx_packets;
+	u64_stats_t rx_bytes;
+	u64_stats_t rx_errors;
+	u64_stats_t tx_packets;
+	u64_stats_t tx_bytes;
+	u64_stats_t tx_errors;
+	u64_stats_t tx_dropped;
+	struct u64_stats_sync tx_syncp;
+	struct u64_stats_sync rx_syncp;
+};
+
+struct mhi_net_dev {
+	struct mhi_device *mdev;
+	struct net_device *ndev;
+	struct sk_buff *skbagg_head;
+	struct sk_buff *skbagg_tail;
+	struct delayed_work rx_refill;
+	struct mhi_net_stats stats;
+	u32 rx_queue_sz;
+	int msg_enable;
+	unsigned int mru;
+};
 
 struct mhi_device_info {
 	const char *netname;
-	const struct mhi_net_proto *proto;
 };
 
 static int mhi_ndo_open(struct net_device *ndev)
 {
-	struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev);
+	struct mhi_net_dev *mhi_netdev = netdev_priv(ndev);
 
 	/* Feed the rx buffer pool */
 	schedule_delayed_work(&mhi_netdev->rx_refill, 0);
@@ -47,7 +61,7 @@ static int mhi_ndo_open(struct net_device *ndev)
 
 static int mhi_ndo_stop(struct net_device *ndev)
 {
-	struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev);
+	struct mhi_net_dev *mhi_netdev = netdev_priv(ndev);
 
 	netif_stop_queue(ndev);
 	netif_carrier_off(ndev);
@@ -58,17 +72,10 @@ static int mhi_ndo_stop(struct net_device *ndev)
 
 static netdev_tx_t mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
-	struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev);
-	const struct mhi_net_proto *proto = mhi_netdev->proto;
+	struct mhi_net_dev *mhi_netdev = netdev_priv(ndev);
 	struct mhi_device *mdev = mhi_netdev->mdev;
 	int err;
 
-	if (proto && proto->tx_fixup) {
-		skb = proto->tx_fixup(mhi_netdev, skb);
-		if (unlikely(!skb))
-			goto exit_drop;
-	}
-
 	err = mhi_queue_skb(mdev, DMA_TO_DEVICE, skb, skb->len, MHI_EOT);
 	if (unlikely(err)) {
 		net_err_ratelimited("%s: Failed to queue TX buf (%d)\n",
@@ -93,7 +100,7 @@ exit_drop:
 static void mhi_ndo_get_stats64(struct net_device *ndev,
 				struct rtnl_link_stats64 *stats)
 {
-	struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev);
+	struct mhi_net_dev *mhi_netdev = netdev_priv(ndev);
 	unsigned int start;
 
 	do {
@@ -101,8 +108,6 @@ static void mhi_ndo_get_stats64(struct net_device *ndev,
 		stats->rx_packets = u64_stats_read(&mhi_netdev->stats.rx_packets);
 		stats->rx_bytes = u64_stats_read(&mhi_netdev->stats.rx_bytes);
 		stats->rx_errors = u64_stats_read(&mhi_netdev->stats.rx_errors);
-		stats->rx_dropped = u64_stats_read(&mhi_netdev->stats.rx_dropped);
-		stats->rx_length_errors = u64_stats_read(&mhi_netdev->stats.rx_length_errors);
 	} while (u64_stats_fetch_retry_irq(&mhi_netdev->stats.rx_syncp, start));
 
 	do {
@@ -165,7 +170,6 @@ static void mhi_net_dl_callback(struct mhi_device *mhi_dev,
 				struct mhi_result *mhi_res)
 {
 	struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev);
-	const struct mhi_net_proto *proto = mhi_netdev->proto;
 	struct sk_buff *skb = mhi_res->buf_addr;
 	int free_desc_count;
 
@@ -205,11 +209,6 @@ static void mhi_net_dl_callback(struct mhi_device *mhi_dev,
 			mhi_netdev->skbagg_head = NULL;
 		}
 
-		u64_stats_update_begin(&mhi_netdev->stats.rx_syncp);
-		u64_stats_inc(&mhi_netdev->stats.rx_packets);
-		u64_stats_add(&mhi_netdev->stats.rx_bytes, skb->len);
-		u64_stats_update_end(&mhi_netdev->stats.rx_syncp);
-
 		switch (skb->data[0] & 0xf0) {
 		case 0x40:
 			skb->protocol = htons(ETH_P_IP);
@@ -222,10 +221,11 @@ static void mhi_net_dl_callback(struct mhi_device *mhi_dev,
 			break;
 		}
 
-		if (proto && proto->rx)
-			proto->rx(mhi_netdev, skb);
-		else
-			netif_rx(skb);
+		u64_stats_update_begin(&mhi_netdev->stats.rx_syncp);
+		u64_stats_inc(&mhi_netdev->stats.rx_packets);
+		u64_stats_add(&mhi_netdev->stats.rx_bytes, skb->len);
+		u64_stats_update_end(&mhi_netdev->stats.rx_syncp);
+		netif_rx(skb);
 	}
 
 	/* Refill if RX buffers queue becomes low */
@@ -248,7 +248,6 @@ static void mhi_net_ul_callback(struct mhi_device *mhi_dev,
 
 	u64_stats_update_begin(&mhi_netdev->stats.tx_syncp);
 	if (unlikely(mhi_res->transaction_status)) {
-
 		/* MHI layer stopping/resetting the UL channel */
 		if (mhi_res->transaction_status == -ENOTCONN) {
 			u64_stats_update_end(&mhi_netdev->stats.tx_syncp);
@@ -302,33 +301,18 @@ static void mhi_net_rx_refill_work(struct work_struct *work)
 		schedule_delayed_work(&mhi_netdev->rx_refill, HZ / 2);
 }
 
-static int mhi_net_newlink(void *ctxt, struct net_device *ndev, u32 if_id,
-			   struct netlink_ext_ack *extack)
+static int mhi_net_newlink(struct mhi_device *mhi_dev, struct net_device *ndev)
 {
-	const struct mhi_device_info *info;
-	struct mhi_device *mhi_dev = ctxt;
 	struct mhi_net_dev *mhi_netdev;
 	int err;
 
-	info = (struct mhi_device_info *)mhi_dev->id->driver_data;
-
-	/* For now we only support one link (link context 0), driver must be
-	 * reworked to break 1:1 relationship for net MBIM and to forward setup
-	 * call to rmnet(QMAP) otherwise.
-	 */
-	if (if_id != 0)
-		return -EINVAL;
-
-	if (dev_get_drvdata(&mhi_dev->dev))
-		return -EBUSY;
-
-	mhi_netdev = wwan_netdev_drvpriv(ndev);
+	mhi_netdev = netdev_priv(ndev);
 
 	dev_set_drvdata(&mhi_dev->dev, mhi_netdev);
 	mhi_netdev->ndev = ndev;
 	mhi_netdev->mdev = mhi_dev;
 	mhi_netdev->skbagg_head = NULL;
-	mhi_netdev->proto = info->proto;
+	mhi_netdev->mru = mhi_dev->mhi_cntrl->mru;
 
 	INIT_DELAYED_WORK(&mhi_netdev->rx_refill, mhi_net_rx_refill_work);
 	u64_stats_init(&mhi_netdev->stats.rx_syncp);
@@ -342,38 +326,22 @@ static int mhi_net_newlink(void *ctxt, struct net_device *ndev, u32 if_id,
 	/* Number of transfer descriptors determines size of the queue */
 	mhi_netdev->rx_queue_sz = mhi_get_free_desc_count(mhi_dev, DMA_FROM_DEVICE);
 
-	if (extack)
-		err = register_netdevice(ndev);
-	else
-		err = register_netdev(ndev);
+	err = register_netdev(ndev);
 	if (err)
-		goto out_err;
-
-	if (mhi_netdev->proto) {
-		err = mhi_netdev->proto->init(mhi_netdev);
-		if (err)
-			goto out_err_proto;
-	}
+		return err;
 
 	return 0;
 
-out_err_proto:
-	unregister_netdevice(ndev);
 out_err:
 	free_netdev(ndev);
 	return err;
 }
 
-static void mhi_net_dellink(void *ctxt, struct net_device *ndev,
-			    struct list_head *head)
+static void mhi_net_dellink(struct mhi_device *mhi_dev, struct net_device *ndev)
 {
-	struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev);
-	struct mhi_device *mhi_dev = ctxt;
+	struct mhi_net_dev *mhi_netdev = netdev_priv(ndev);
 
-	if (head)
-		unregister_netdevice_queue(ndev, head);
-	else
-		unregister_netdev(ndev);
+	unregister_netdev(ndev);
 
 	mhi_unprepare_from_transfer(mhi_dev);
 
@@ -382,65 +350,34 @@ static void mhi_net_dellink(void *ctxt, struct net_device *ndev,
 	dev_set_drvdata(&mhi_dev->dev, NULL);
 }
 
-static const struct wwan_ops mhi_wwan_ops = {
-	.priv_size = sizeof(struct mhi_net_dev),
-	.setup = mhi_net_setup,
-	.newlink = mhi_net_newlink,
-	.dellink = mhi_net_dellink,
-};
-
 static int mhi_net_probe(struct mhi_device *mhi_dev,
 			 const struct mhi_device_id *id)
 {
 	const struct mhi_device_info *info = (struct mhi_device_info *)id->driver_data;
-	struct mhi_controller *cntrl = mhi_dev->mhi_cntrl;
 	struct net_device *ndev;
 	int err;
 
-	err = wwan_register_ops(&cntrl->mhi_dev->dev, &mhi_wwan_ops, mhi_dev,
-				WWAN_NO_DEFAULT_LINK);
-	if (err)
-		return err;
-
-	if (!create_default_iface)
-		return 0;
-
-	/* Create a default interface which is used as either RMNET real-dev,
-	 * MBIM link 0 or ip link 0)
-	 */
 	ndev = alloc_netdev(sizeof(struct mhi_net_dev), info->netname,
 			    NET_NAME_PREDICTABLE, mhi_net_setup);
-	if (!ndev) {
-		err = -ENOMEM;
-		goto err_unregister;
-	}
+	if (!ndev)
+		return -ENOMEM;
 
 	SET_NETDEV_DEV(ndev, &mhi_dev->dev);
 
-	err = mhi_net_newlink(mhi_dev, ndev, 0, NULL);
-	if (err)
-		goto err_release;
+	err = mhi_net_newlink(mhi_dev, ndev);
+	if (err) {
+		free_netdev(ndev);
+		return err;
+	}
 
 	return 0;
-
-err_release:
-	free_netdev(ndev);
-err_unregister:
-	wwan_unregister_ops(&cntrl->mhi_dev->dev);
-
-	return err;
 }
 
 static void mhi_net_remove(struct mhi_device *mhi_dev)
 {
 	struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev);
-	struct mhi_controller *cntrl = mhi_dev->mhi_cntrl;
-
-	/* WWAN core takes care of removing remaining links */
-	wwan_unregister_ops(&cntrl->mhi_dev->dev);
 
-	if (create_default_iface)
-		mhi_net_dellink(mhi_dev, mhi_netdev->ndev, NULL);
+	mhi_net_dellink(mhi_dev, mhi_netdev->ndev);
 }
 
 static const struct mhi_device_info mhi_hwip0 = {
@@ -451,18 +388,11 @@ static const struct mhi_device_info mhi_swip0 = {
 	.netname = "mhi_swip%d",
 };
 
-static const struct mhi_device_info mhi_hwip0_mbim = {
-	.netname = "mhi_mbim%d",
-	.proto = &proto_mbim,
-};
-
 static const struct mhi_device_id mhi_net_id_table[] = {
 	/* Hardware accelerated data PATH (to modem IPA), protocol agnostic */
 	{ .chan = "IP_HW0", .driver_data = (kernel_ulong_t)&mhi_hwip0 },
 	/* Software data PATH (to modem CPU) */
 	{ .chan = "IP_SW0", .driver_data = (kernel_ulong_t)&mhi_swip0 },
-	/* Hardware accelerated data PATH (to modem IPA), MBIM protocol */
-	{ .chan = "IP_HW0_MBIM", .driver_data = (kernel_ulong_t)&mhi_hwip0_mbim },
 	{}
 };
 MODULE_DEVICE_TABLE(mhi, mhi_net_id_table);
diff --git a/drivers/net/mii.c b/drivers/net/mii.c
index 779c3a96dba7..22680f47385d 100644
--- a/drivers/net/mii.c
+++ b/drivers/net/mii.c
@@ -49,10 +49,8 @@ static u32 mii_get_an(struct mii_if_info *mii, u16 addr)
  *
  * The @ecmd parameter is expected to have been cleared before calling
  * mii_ethtool_gset().
- *
- * Returns 0 for success, negative on error.
  */
-int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd)
+void mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd)
 {
 	struct net_device *dev = mii->dev;
 	u16 bmcr, bmsr, ctrl1000 = 0, stat1000 = 0;
@@ -131,8 +129,6 @@ int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd)
 	mii->full_duplex = ecmd->duplex;
 
 	/* ignore maxtxpkt, maxrxpkt for now */
-
-	return 0;
 }
 
 /**
diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c
index ccec29970d5b..62d033a1a557 100644
--- a/drivers/net/netdevsim/bus.c
+++ b/drivers/net/netdevsim/bus.c
@@ -183,8 +183,6 @@ new_port_store(struct device *dev, struct device_attribute *attr,
 	       const char *buf, size_t count)
 {
 	struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
-	struct nsim_dev *nsim_dev = dev_get_drvdata(dev);
-	struct devlink *devlink;
 	unsigned int port_index;
 	int ret;
 
@@ -195,12 +193,15 @@ new_port_store(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	devlink = priv_to_devlink(nsim_dev);
+	if (!mutex_trylock(&nsim_bus_dev->nsim_bus_reload_lock))
+		return -EBUSY;
+
+	if (nsim_bus_dev->in_reload) {
+		mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
+		return -EBUSY;
+	}
 
-	mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock);
-	devlink_reload_disable(devlink);
 	ret = nsim_dev_port_add(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index);
-	devlink_reload_enable(devlink);
 	mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
 	return ret ? ret : count;
 }
@@ -212,8 +213,6 @@ del_port_store(struct device *dev, struct device_attribute *attr,
 	       const char *buf, size_t count)
 {
 	struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
-	struct nsim_dev *nsim_dev = dev_get_drvdata(dev);
-	struct devlink *devlink;
 	unsigned int port_index;
 	int ret;
 
@@ -224,12 +223,15 @@ del_port_store(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	devlink = priv_to_devlink(nsim_dev);
+	if (!mutex_trylock(&nsim_bus_dev->nsim_bus_reload_lock))
+		return -EBUSY;
+
+	if (nsim_bus_dev->in_reload) {
+		mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
+		return -EBUSY;
+	}
 
-	mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock);
-	devlink_reload_disable(devlink);
 	ret = nsim_dev_port_del(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index);
-	devlink_reload_enable(devlink);
 	mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
 	return ret ? ret : count;
 }
@@ -262,29 +264,31 @@ static struct device_type nsim_bus_dev_type = {
 };
 
 static struct nsim_bus_dev *
-nsim_bus_dev_new(unsigned int id, unsigned int port_count);
+nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queues);
 
 static ssize_t
 new_device_store(struct bus_type *bus, const char *buf, size_t count)
 {
+	unsigned int id, port_count, num_queues;
 	struct nsim_bus_dev *nsim_bus_dev;
-	unsigned int port_count;
-	unsigned int id;
 	int err;
 
-	err = sscanf(buf, "%u %u", &id, &port_count);
+	err = sscanf(buf, "%u %u %u", &id, &port_count, &num_queues);
 	switch (err) {
 	case 1:
 		port_count = 1;
 		fallthrough;
 	case 2:
+		num_queues = 1;
+		fallthrough;
+	case 3:
 		if (id > INT_MAX) {
 			pr_err("Value of \"id\" is too big.\n");
 			return -EINVAL;
 		}
 		break;
 	default:
-		pr_err("Format for adding new device is \"id port_count\" (uint uint).\n");
+		pr_err("Format for adding new device is \"id port_count num_queues\" (uint uint unit).\n");
 		return -EINVAL;
 	}
 
@@ -295,7 +299,7 @@ new_device_store(struct bus_type *bus, const char *buf, size_t count)
 		goto err;
 	}
 
-	nsim_bus_dev = nsim_bus_dev_new(id, port_count);
+	nsim_bus_dev = nsim_bus_dev_new(id, port_count, num_queues);
 	if (IS_ERR(nsim_bus_dev)) {
 		err = PTR_ERR(nsim_bus_dev);
 		goto err;
@@ -397,7 +401,7 @@ static struct bus_type nsim_bus = {
 #define NSIM_BUS_DEV_MAX_VFS 4
 
 static struct nsim_bus_dev *
-nsim_bus_dev_new(unsigned int id, unsigned int port_count)
+nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queues)
 {
 	struct nsim_bus_dev *nsim_bus_dev;
 	int err;
@@ -413,6 +417,7 @@ nsim_bus_dev_new(unsigned int id, unsigned int port_count)
 	nsim_bus_dev->dev.bus = &nsim_bus;
 	nsim_bus_dev->dev.type = &nsim_bus_dev_type;
 	nsim_bus_dev->port_count = port_count;
+	nsim_bus_dev->num_queues = num_queues;
 	nsim_bus_dev->initial_net = current->nsproxy->net_ns;
 	nsim_bus_dev->max_vfs = NSIM_BUS_DEV_MAX_VFS;
 	mutex_init(&nsim_bus_dev->nsim_bus_reload_lock);
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 6348307bfa84..54313bd57797 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -864,16 +864,24 @@ static int nsim_dev_reload_down(struct devlink *devlink, bool netns_change,
 				struct netlink_ext_ack *extack)
 {
 	struct nsim_dev *nsim_dev = devlink_priv(devlink);
+	struct nsim_bus_dev *nsim_bus_dev;
+
+	nsim_bus_dev = nsim_dev->nsim_bus_dev;
+	if (!mutex_trylock(&nsim_bus_dev->nsim_bus_reload_lock))
+		return -EOPNOTSUPP;
 
 	if (nsim_dev->dont_allow_reload) {
 		/* For testing purposes, user set debugfs dont_allow_reload
 		 * value to true. So forbid it.
 		 */
 		NL_SET_ERR_MSG_MOD(extack, "User forbid the reload for testing purposes");
+		mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
 		return -EOPNOTSUPP;
 	}
+	nsim_bus_dev->in_reload = true;
 
 	nsim_dev_reload_destroy(nsim_dev);
+	mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
 	return 0;
 }
 
@@ -882,17 +890,26 @@ static int nsim_dev_reload_up(struct devlink *devlink, enum devlink_reload_actio
 			      struct netlink_ext_ack *extack)
 {
 	struct nsim_dev *nsim_dev = devlink_priv(devlink);
+	struct nsim_bus_dev *nsim_bus_dev;
+	int ret;
+
+	nsim_bus_dev = nsim_dev->nsim_bus_dev;
+	mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock);
+	nsim_bus_dev->in_reload = false;
 
 	if (nsim_dev->fail_reload) {
 		/* For testing purposes, user set debugfs fail_reload
 		 * value to true. Fail right away.
 		 */
 		NL_SET_ERR_MSG_MOD(extack, "User setup the reload to fail for testing purposes");
+		mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
 		return -EINVAL;
 	}
 
 	*actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
-	return nsim_dev_reload_create(nsim_dev, extack);
+	ret = nsim_dev_reload_create(nsim_dev, extack);
+	mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
+	return ret;
 }
 
 static int nsim_dev_info_get(struct devlink *devlink,
@@ -1431,10 +1448,10 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev)
 	struct devlink *devlink;
 	int err;
 
-	devlink = devlink_alloc(&nsim_dev_devlink_ops, sizeof(*nsim_dev));
+	devlink = devlink_alloc_ns(&nsim_dev_devlink_ops, sizeof(*nsim_dev),
+				 nsim_bus_dev->initial_net, &nsim_bus_dev->dev);
 	if (!devlink)
 		return -ENOMEM;
-	devlink_net_set(devlink, nsim_bus_dev->initial_net);
 	nsim_dev = devlink_priv(devlink);
 	nsim_dev->nsim_bus_dev = nsim_bus_dev;
 	nsim_dev->switch_id.id_len = sizeof(nsim_dev->switch_id.id);
@@ -1453,7 +1470,7 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev)
 	if (err)
 		goto err_devlink_free;
 
-	err = devlink_register(devlink, &nsim_bus_dev->dev);
+	err = devlink_register(devlink);
 	if (err)
 		goto err_resources_unregister;
 
diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c
index c9ae52595a8f..b03a0513eb7e 100644
--- a/drivers/net/netdevsim/ethtool.c
+++ b/drivers/net/netdevsim/ethtool.c
@@ -43,7 +43,9 @@ nsim_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause)
 }
 
 static int nsim_get_coalesce(struct net_device *dev,
-			     struct ethtool_coalesce *coal)
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
@@ -52,7 +54,9 @@ static int nsim_get_coalesce(struct net_device *dev,
 }
 
 static int nsim_set_coalesce(struct net_device *dev,
-			     struct ethtool_coalesce *coal)
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c
index 213d3e5056c8..4300261e2f9e 100644
--- a/drivers/net/netdevsim/fib.c
+++ b/drivers/net/netdevsim/fib.c
@@ -1441,7 +1441,7 @@ static u64 nsim_fib_nexthops_res_occ_get(void *priv)
 static void nsim_fib_set_max_all(struct nsim_fib_data *data,
 				 struct devlink *devlink)
 {
-	enum nsim_resource_id res_ids[] = {
+	static const enum nsim_resource_id res_ids[] = {
 		NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES,
 		NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES,
 		NSIM_RESOURCE_NEXTHOPS,
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index c3aeb15843e2..50572e0f1f52 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -347,7 +347,8 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 	struct netdevsim *ns;
 	int err;
 
-	dev = alloc_netdev(sizeof(*ns), "eth%d", NET_NAME_UNKNOWN, nsim_setup);
+	dev = alloc_netdev_mq(sizeof(*ns), "eth%d", NET_NAME_UNKNOWN, nsim_setup,
+			      nsim_dev->nsim_bus_dev->num_queues);
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
@@ -392,7 +393,8 @@ void nsim_destroy(struct netdevsim *ns)
 static int nsim_validate(struct nlattr *tb[], struct nlattr *data[],
 			 struct netlink_ext_ack *extack)
 {
-	NL_SET_ERR_MSG_MOD(extack, "Please use: echo \"[ID] [PORT_COUNT]\" > /sys/bus/netdevsim/new_device");
+	NL_SET_ERR_MSG_MOD(extack,
+			   "Please use: echo \"[ID] [PORT_COUNT] [NUM_QUEUES]\" > /sys/bus/netdevsim/new_device");
 	return -EOPNOTSUPP;
 }
 
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index ae462957dcee..793c86dc5a9c 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -352,6 +352,7 @@ struct nsim_bus_dev {
 	struct device dev;
 	struct list_head list;
 	unsigned int port_count;
+	unsigned int num_queues; /* Number of queues for each port on this bus */
 	struct net *initial_net; /* Purpose of this is to carry net pointer
 				  * during the probe time only.
 				  */
@@ -361,6 +362,7 @@ struct nsim_bus_dev {
 	struct nsim_vf_config *vfconfigs;
 	/* Lock for devlink->reload_enabled in netdevsim module */
 	struct mutex nsim_bus_reload_lock;
+	bool in_reload;
 	bool init;
 };
 
diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 4bd61339823c..fb0a83dc09ac 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -65,6 +65,9 @@ static const int xpcs_xlgmii_features[] = {
 };
 
 static const int xpcs_sgmii_features[] = {
+	ETHTOOL_LINK_MODE_Pause_BIT,
+	ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+	ETHTOOL_LINK_MODE_Autoneg_BIT,
 	ETHTOOL_LINK_MODE_10baseT_Half_BIT,
 	ETHTOOL_LINK_MODE_10baseT_Full_BIT,
 	ETHTOOL_LINK_MODE_100baseT_Half_BIT,
@@ -75,6 +78,7 @@ static const int xpcs_sgmii_features[] = {
 };
 
 static const int xpcs_2500basex_features[] = {
+	ETHTOOL_LINK_MODE_Pause_BIT,
 	ETHTOOL_LINK_MODE_Asym_Pause_BIT,
 	ETHTOOL_LINK_MODE_Autoneg_BIT,
 	ETHTOOL_LINK_MODE_2500baseX_Full_BIT,
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index c56f703ae998..902495afcb38 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -207,6 +207,12 @@ config MARVELL_88X2222_PHY
 	  Support for the Marvell 88X2222 Dual-port Multi-speed Ethernet
 	  Transceiver.
 
+config MAXLINEAR_GPHY
+	tristate "Maxlinear Ethernet PHYs"
+	help
+	  Support for the Maxlinear GPY115, GPY211, GPY212, GPY215,
+	  GPY241, GPY245 PHYs.
+
 config MEDIATEK_GE_PHY
 	tristate "MediaTek Gigabit Ethernet PHYs"
 	help
@@ -230,6 +236,7 @@ config MICROCHIP_T1_PHY
 config MICROSEMI_PHY
 	tristate "Microsemi PHYs"
 	depends on MACSEC || MACSEC=n
+	depends on PTP_1588_CLOCK_OPTIONAL || !NETWORK_PHY_TIMESTAMPING
 	select CRYPTO_LIB_AES if MACSEC
 	help
 	  Currently supports VSC8514, VSC8530, VSC8531, VSC8540 and VSC8541 PHYs
@@ -247,6 +254,7 @@ config NATIONAL_PHY
 
 config NXP_C45_TJA11XX_PHY
 	tristate "NXP C45 TJA11XX PHYs"
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  Enable support for NXP C45 TJA11XX PHYs.
 	  Currently supports only the TJA1103 PHY.
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 172bb193ae6a..b2728d00fc9a 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -64,6 +64,7 @@ obj-$(CONFIG_LXT_PHY)		+= lxt.o
 obj-$(CONFIG_MARVELL_10G_PHY)	+= marvell10g.o
 obj-$(CONFIG_MARVELL_PHY)	+= marvell.o
 obj-$(CONFIG_MARVELL_88X2222_PHY)	+= marvell-88x2222.o
+obj-$(CONFIG_MAXLINEAR_GPHY)	+= mxl-gpy.o
 obj-$(CONFIG_MEDIATEK_GE_PHY)	+= mediatek-ge.o
 obj-$(CONFIG_MESON_GXL_PHY)	+= meson-gxl.o
 obj-$(CONFIG_MICREL_KS8995MA)	+= spi_ks8995.o
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 5d62b85a4024..bdac087058b2 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -532,12 +532,6 @@ static int at8031_register_regulators(struct phy_device *phydev)
 	return 0;
 }
 
-static bool at803x_match_phy_id(struct phy_device *phydev, u32 phy_id)
-{
-	return (phydev->phy_id & phydev->drv->phy_id_mask)
-		== (phy_id & phydev->drv->phy_id_mask);
-}
-
 static int at803x_parse_dt(struct phy_device *phydev)
 {
 	struct device_node *node = phydev->mdio.dev.of_node;
@@ -602,8 +596,8 @@ static int at803x_parse_dt(struct phy_device *phydev)
 		 *   to the AR8030 so there might be a good chance it works on
 		 *   the AR8030 too.
 		 */
-		if (at803x_match_phy_id(phydev, ATH8030_PHY_ID) ||
-		    at803x_match_phy_id(phydev, ATH8035_PHY_ID)) {
+		if (phydev->drv->phy_id == ATH8030_PHY_ID ||
+		    phydev->drv->phy_id == ATH8035_PHY_ID) {
 			priv->clk_25m_reg &= AT8035_CLK_OUT_MASK;
 			priv->clk_25m_mask &= AT8035_CLK_OUT_MASK;
 		}
@@ -631,7 +625,7 @@ static int at803x_parse_dt(struct phy_device *phydev)
 	/* Only supported on AR8031/AR8033, the AR8030/AR8035 use strapping
 	 * options.
 	 */
-	if (at803x_match_phy_id(phydev, ATH8031_PHY_ID)) {
+	if (phydev->drv->phy_id == ATH8031_PHY_ID) {
 		if (of_property_read_bool(node, "qca,keep-pll-enabled"))
 			priv->flags |= AT803X_KEEP_PLL_ENABLED;
 
@@ -676,7 +670,7 @@ static int at803x_probe(struct phy_device *phydev)
 	 * Switch to the copper page, as otherwise we read
 	 * the PHY capabilities from the fiber side.
 	 */
-	if (at803x_match_phy_id(phydev, ATH8031_PHY_ID)) {
+	if (phydev->drv->phy_id == ATH8031_PHY_ID) {
 		phy_lock_mdio_bus(phydev);
 		ret = at803x_write_page(phydev, AT803X_PAGE_COPPER);
 		phy_unlock_mdio_bus(phydev);
@@ -709,7 +703,7 @@ static int at803x_get_features(struct phy_device *phydev)
 	if (err)
 		return err;
 
-	if (!at803x_match_phy_id(phydev, ATH8031_PHY_ID))
+	if (phydev->drv->phy_id != ATH8031_PHY_ID)
 		return 0;
 
 	/* AR8031/AR8033 have different status registers
@@ -820,7 +814,7 @@ static int at803x_config_init(struct phy_device *phydev)
 	if (ret < 0)
 		return ret;
 
-	if (at803x_match_phy_id(phydev, ATH8031_PHY_ID)) {
+	if (phydev->drv->phy_id == ATH8031_PHY_ID) {
 		ret = at8031_pll_config(phydev);
 		if (ret < 0)
 			return ret;
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index f7a2ec150e54..211b5476a6f5 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -326,11 +326,9 @@ static irqreturn_t dp83822_handle_interrupt(struct phy_device *phydev)
 
 static int dp8382x_disable_wol(struct phy_device *phydev)
 {
-	int value = DP83822_WOL_EN | DP83822_WOL_MAGIC_EN |
-		    DP83822_WOL_SECURE_ON;
-
-	return phy_clear_bits_mmd(phydev, DP83822_DEVADDR,
-				  MII_DP83822_WOL_CFG, value);
+	return phy_clear_bits_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG,
+				  DP83822_WOL_EN | DP83822_WOL_MAGIC_EN |
+				  DP83822_WOL_SECURE_ON);
 }
 
 static int dp83822_read_status(struct phy_device *phydev)
diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c
index d453ec016168..3c032868ef04 100644
--- a/drivers/net/phy/intel-xway.c
+++ b/drivers/net/phy/intel-xway.c
@@ -8,11 +8,16 @@
 #include <linux/module.h>
 #include <linux/phy.h>
 #include <linux/of.h>
+#include <linux/bitfield.h>
 
+#define XWAY_MDIO_MIICTRL		0x17	/* mii control */
 #define XWAY_MDIO_IMASK			0x19	/* interrupt mask */
 #define XWAY_MDIO_ISTAT			0x1A	/* interrupt status */
 #define XWAY_MDIO_LED			0x1B	/* led control */
 
+#define XWAY_MDIO_MIICTRL_RXSKEW_MASK	GENMASK(14, 12)
+#define XWAY_MDIO_MIICTRL_TXSKEW_MASK	GENMASK(10, 8)
+
 /* bit 15:12 are reserved */
 #define XWAY_MDIO_LED_LED3_EN		BIT(11)	/* Enable the integrated function of LED3 */
 #define XWAY_MDIO_LED_LED2_EN		BIT(10)	/* Enable the integrated function of LED2 */
@@ -157,6 +162,73 @@
 #define PHY_ID_PHY11G_VR9_1_2		0xD565A409
 #define PHY_ID_PHY22F_VR9_1_2		0xD565A419
 
+static const int xway_internal_delay[] = {0, 500, 1000, 1500, 2000, 2500,
+					 3000, 3500};
+
+static int xway_gphy_rgmii_init(struct phy_device *phydev)
+{
+	struct device *dev = &phydev->mdio.dev;
+	unsigned int delay_size = ARRAY_SIZE(xway_internal_delay);
+	s32 int_delay;
+	int val = 0;
+
+	if (!phy_interface_is_rgmii(phydev))
+		return 0;
+
+	/* Existing behavior was to use default pin strapping delay in rgmii
+	 * mode, but rgmii should have meant no delay.  Warn existing users,
+	 * but do not change anything at the moment.
+	 */
+	if (phydev->interface == PHY_INTERFACE_MODE_RGMII) {
+		u16 txskew, rxskew;
+
+		val = phy_read(phydev, XWAY_MDIO_MIICTRL);
+		if (val < 0)
+			return val;
+
+		txskew = FIELD_GET(XWAY_MDIO_MIICTRL_TXSKEW_MASK, val);
+		rxskew = FIELD_GET(XWAY_MDIO_MIICTRL_RXSKEW_MASK, val);
+
+		if (txskew > 0 || rxskew > 0)
+			phydev_warn(phydev,
+				    "PHY has delays (e.g. via pin strapping), but phy-mode = 'rgmii'\n"
+				    "Should be 'rgmii-id' to use internal delays txskew:%d ps rxskew:%d ps\n",
+				    xway_internal_delay[txskew],
+				    xway_internal_delay[rxskew]);
+		return 0;
+	}
+
+	if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+	    phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) {
+		int_delay = phy_get_internal_delay(phydev, dev,
+						   xway_internal_delay,
+						   delay_size, true);
+
+		/* if rx-internal-delay-ps is missing, use default of 2.0 ns */
+		if (int_delay < 0)
+			int_delay = 4; /* 2000 ps */
+
+		val |= FIELD_PREP(XWAY_MDIO_MIICTRL_RXSKEW_MASK, int_delay);
+	}
+
+	if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+	    phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) {
+		int_delay = phy_get_internal_delay(phydev, dev,
+						   xway_internal_delay,
+						   delay_size, false);
+
+		/* if tx-internal-delay-ps is missing, use default of 2.0 ns */
+		if (int_delay < 0)
+			int_delay = 4; /* 2000 ps */
+
+		val |= FIELD_PREP(XWAY_MDIO_MIICTRL_TXSKEW_MASK, int_delay);
+	}
+
+	return phy_modify(phydev, XWAY_MDIO_MIICTRL,
+			  XWAY_MDIO_MIICTRL_RXSKEW_MASK |
+			  XWAY_MDIO_MIICTRL_TXSKEW_MASK, val);
+}
+
 static int xway_gphy_config_init(struct phy_device *phydev)
 {
 	int err;
@@ -204,6 +276,10 @@ static int xway_gphy_config_init(struct phy_device *phydev)
 	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED2H, ledxh);
 	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED2L, ledxl);
 
+	err = xway_gphy_rgmii_init(phydev);
+	if (err)
+		return err;
+
 	return 0;
 }
 
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 3de93c9f2744..4fcfca4e1702 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -32,6 +32,7 @@
 #include <linux/marvell_phy.h>
 #include <linux/bitfield.h>
 #include <linux/of.h>
+#include <linux/sfp.h>
 
 #include <linux/io.h>
 #include <asm/irq.h>
@@ -46,6 +47,7 @@
 #define MII_MARVELL_MISC_TEST_PAGE	0x06
 #define MII_MARVELL_VCT7_PAGE		0x07
 #define MII_MARVELL_WOL_PAGE		0x11
+#define MII_MARVELL_MODE_PAGE		0x12
 
 #define MII_M1011_IEVENT		0x13
 #define MII_M1011_IEVENT_CLEAR		0x0000
@@ -155,6 +157,7 @@
 
 #define MII_88E1318S_PHY_WOL_CTRL				0x10
 #define MII_88E1318S_PHY_WOL_CTRL_CLEAR_WOL_STATUS		BIT(12)
+#define MII_88E1318S_PHY_WOL_CTRL_LINK_UP_ENABLE		BIT(13)
 #define MII_88E1318S_PHY_WOL_CTRL_MAGIC_PACKET_MATCH_ENABLE	BIT(14)
 
 #define MII_PHY_LED_CTRL	        16
@@ -176,7 +179,14 @@
 
 #define MII_88E1510_GEN_CTRL_REG_1		0x14
 #define MII_88E1510_GEN_CTRL_REG_1_MODE_MASK	0x7
+#define MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII	0x0	/* RGMII to copper */
 #define MII_88E1510_GEN_CTRL_REG_1_MODE_SGMII	0x1	/* SGMII to copper */
+/* RGMII to 1000BASE-X */
+#define MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_1000X	0x2
+/* RGMII to 100BASE-FX */
+#define MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_100FX	0x3
+/* RGMII to SGMII */
+#define MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_SGMII	0x4
 #define MII_88E1510_GEN_CTRL_REG_1_RESET	0x8000	/* Soft reset */
 
 #define MII_VCT5_TX_RX_MDI0_COUPLING	0x10
@@ -1746,13 +1756,19 @@ static void m88e1318_get_wol(struct phy_device *phydev,
 {
 	int ret;
 
-	wol->supported = WAKE_MAGIC;
+	wol->supported = WAKE_MAGIC | WAKE_PHY;
 	wol->wolopts = 0;
 
 	ret = phy_read_paged(phydev, MII_MARVELL_WOL_PAGE,
 			     MII_88E1318S_PHY_WOL_CTRL);
-	if (ret >= 0 && ret & MII_88E1318S_PHY_WOL_CTRL_MAGIC_PACKET_MATCH_ENABLE)
+	if (ret < 0)
+		return;
+
+	if (ret & MII_88E1318S_PHY_WOL_CTRL_MAGIC_PACKET_MATCH_ENABLE)
 		wol->wolopts |= WAKE_MAGIC;
+
+	if (ret & MII_88E1318S_PHY_WOL_CTRL_LINK_UP_ENABLE)
+		wol->wolopts |= WAKE_PHY;
 }
 
 static int m88e1318_set_wol(struct phy_device *phydev,
@@ -1764,7 +1780,7 @@ static int m88e1318_set_wol(struct phy_device *phydev,
 	if (oldpage < 0)
 		goto error;
 
-	if (wol->wolopts & WAKE_MAGIC) {
+	if (wol->wolopts & (WAKE_MAGIC | WAKE_PHY)) {
 		/* Explicitly switch to page 0x00, just to be sure */
 		err = marvell_write_page(phydev, MII_MARVELL_COPPER_PAGE);
 		if (err < 0)
@@ -1796,7 +1812,9 @@ static int m88e1318_set_wol(struct phy_device *phydev,
 				   MII_88E1318S_PHY_LED_TCR_INT_ACTIVE_LOW);
 		if (err < 0)
 			goto error;
+	}
 
+	if (wol->wolopts & WAKE_MAGIC) {
 		err = marvell_write_page(phydev, MII_MARVELL_WOL_PAGE);
 		if (err < 0)
 			goto error;
@@ -1837,6 +1855,30 @@ static int m88e1318_set_wol(struct phy_device *phydev,
 			goto error;
 	}
 
+	if (wol->wolopts & WAKE_PHY) {
+		err = marvell_write_page(phydev, MII_MARVELL_WOL_PAGE);
+		if (err < 0)
+			goto error;
+
+		/* Clear WOL status and enable link up event */
+		err = __phy_modify(phydev, MII_88E1318S_PHY_WOL_CTRL, 0,
+				   MII_88E1318S_PHY_WOL_CTRL_CLEAR_WOL_STATUS |
+				   MII_88E1318S_PHY_WOL_CTRL_LINK_UP_ENABLE);
+		if (err < 0)
+			goto error;
+	} else {
+		err = marvell_write_page(phydev, MII_MARVELL_WOL_PAGE);
+		if (err < 0)
+			goto error;
+
+		/* Clear WOL status and disable link up event */
+		err = __phy_modify(phydev, MII_88E1318S_PHY_WOL_CTRL,
+				   MII_88E1318S_PHY_WOL_CTRL_LINK_UP_ENABLE,
+				   MII_88E1318S_PHY_WOL_CTRL_CLEAR_WOL_STATUS);
+		if (err < 0)
+			goto error;
+	}
+
 error:
 	return phy_restore_page(phydev, oldpage, err);
 }
@@ -2701,6 +2743,100 @@ static int marvell_probe(struct phy_device *phydev)
 	return marvell_hwmon_probe(phydev);
 }
 
+static int m88e1510_sfp_insert(void *upstream, const struct sfp_eeprom_id *id)
+{
+	struct phy_device *phydev = upstream;
+	phy_interface_t interface;
+	struct device *dev;
+	int oldpage;
+	int ret = 0;
+	u16 mode;
+
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
+
+	dev = &phydev->mdio.dev;
+
+	sfp_parse_support(phydev->sfp_bus, id, supported);
+	interface = sfp_select_interface(phydev->sfp_bus, supported);
+
+	dev_info(dev, "%s SFP module inserted\n", phy_modes(interface));
+
+	switch (interface) {
+	case PHY_INTERFACE_MODE_1000BASEX:
+		mode = MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_1000X;
+
+		break;
+	case PHY_INTERFACE_MODE_100BASEX:
+		mode = MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_100FX;
+
+		break;
+	case PHY_INTERFACE_MODE_SGMII:
+		mode = MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_SGMII;
+
+		break;
+	default:
+		dev_err(dev, "Incompatible SFP module inserted\n");
+
+		return -EINVAL;
+	}
+
+	oldpage = phy_select_page(phydev, MII_MARVELL_MODE_PAGE);
+	if (oldpage < 0)
+		goto error;
+
+	ret = __phy_modify(phydev, MII_88E1510_GEN_CTRL_REG_1,
+			   MII_88E1510_GEN_CTRL_REG_1_MODE_MASK, mode);
+	if (ret < 0)
+		goto error;
+
+	ret = __phy_set_bits(phydev, MII_88E1510_GEN_CTRL_REG_1,
+			     MII_88E1510_GEN_CTRL_REG_1_RESET);
+
+error:
+	return phy_restore_page(phydev, oldpage, ret);
+}
+
+static void m88e1510_sfp_remove(void *upstream)
+{
+	struct phy_device *phydev = upstream;
+	int oldpage;
+	int ret = 0;
+
+	oldpage = phy_select_page(phydev, MII_MARVELL_MODE_PAGE);
+	if (oldpage < 0)
+		goto error;
+
+	ret = __phy_modify(phydev, MII_88E1510_GEN_CTRL_REG_1,
+			   MII_88E1510_GEN_CTRL_REG_1_MODE_MASK,
+			   MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII);
+	if (ret < 0)
+		goto error;
+
+	ret = __phy_set_bits(phydev, MII_88E1510_GEN_CTRL_REG_1,
+			     MII_88E1510_GEN_CTRL_REG_1_RESET);
+
+error:
+	phy_restore_page(phydev, oldpage, ret);
+}
+
+static const struct sfp_upstream_ops m88e1510_sfp_ops = {
+	.module_insert = m88e1510_sfp_insert,
+	.module_remove = m88e1510_sfp_remove,
+	.attach = phy_sfp_attach,
+	.detach = phy_sfp_detach,
+};
+
+static int m88e1510_probe(struct phy_device *phydev)
+{
+	int err;
+
+	err = marvell_probe(phydev);
+	if (err)
+		return err;
+
+	return phy_sfp_probe(phydev, &m88e1510_sfp_ops);
+}
+
 static struct phy_driver marvell_drivers[] = {
 	{
 		.phy_id = MARVELL_PHY_ID_88E1101,
@@ -2927,7 +3063,7 @@ static struct phy_driver marvell_drivers[] = {
 		.driver_data = DEF_MARVELL_HWMON_OPS(m88e1510_hwmon_ops),
 		.features = PHY_GBIT_FIBRE_FEATURES,
 		.flags = PHY_POLL_CABLE_TEST,
-		.probe = marvell_probe,
+		.probe = m88e1510_probe,
 		.config_init = m88e1510_config_init,
 		.config_aneg = m88e1510_config_aneg,
 		.read_status = marvell_read_status,
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 53a433442803..bd310e8d5e43 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -28,6 +28,7 @@
 #include <linux/marvell_phy.h>
 #include <linux/phy.h>
 #include <linux/sfp.h>
+#include <linux/netdevice.h>
 
 #define MV_PHY_ALASKA_NBT_QUIRK_MASK	0xfffffffe
 #define MV_PHY_ALASKA_NBT_QUIRK_REV	(MARVELL_PHY_ID_88X3310 | 0xa)
@@ -104,6 +105,16 @@ enum {
 	MV_V2_33X0_PORT_CTRL_MACTYPE_10GBASER_NO_SGMII_AN	= 0x5,
 	MV_V2_33X0_PORT_CTRL_MACTYPE_10GBASER_RATE_MATCH	= 0x6,
 	MV_V2_33X0_PORT_CTRL_MACTYPE_USXGMII			= 0x7,
+	MV_V2_PORT_INTR_STS     = 0xf040,
+	MV_V2_PORT_INTR_MASK    = 0xf043,
+	MV_V2_PORT_INTR_STS_WOL_EN      = BIT(8),
+	MV_V2_MAGIC_PKT_WORD0   = 0xf06b,
+	MV_V2_MAGIC_PKT_WORD1   = 0xf06c,
+	MV_V2_MAGIC_PKT_WORD2   = 0xf06d,
+	/* Wake on LAN registers */
+	MV_V2_WOL_CTRL          = 0xf06e,
+	MV_V2_WOL_CTRL_CLEAR_STS        = BIT(15),
+	MV_V2_WOL_CTRL_MAGIC_PKT_EN     = BIT(0),
 	/* Temperature control/read registers (88X3310 only) */
 	MV_V2_TEMP_CTRL		= 0xf08a,
 	MV_V2_TEMP_CTRL_MASK	= 0xc000,
@@ -987,11 +998,19 @@ static int mv3310_get_number_of_ports(struct phy_device *phydev)
 
 static int mv3310_match_phy_device(struct phy_device *phydev)
 {
+	if ((phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] &
+	     MARVELL_PHY_ID_MASK) != MARVELL_PHY_ID_88X3310)
+		return 0;
+
 	return mv3310_get_number_of_ports(phydev) == 1;
 }
 
 static int mv3340_match_phy_device(struct phy_device *phydev)
 {
+	if ((phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] &
+	     MARVELL_PHY_ID_MASK) != MARVELL_PHY_ID_88X3310)
+		return 0;
+
 	return mv3310_get_number_of_ports(phydev) == 4;
 }
 
@@ -1020,6 +1039,80 @@ static int mv2111_match_phy_device(struct phy_device *phydev)
 	return mv211x_match_phy_device(phydev, false);
 }
 
+static void mv3110_get_wol(struct phy_device *phydev,
+			   struct ethtool_wolinfo *wol)
+{
+	int ret;
+
+	wol->supported = WAKE_MAGIC;
+	wol->wolopts = 0;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, MV_V2_WOL_CTRL);
+	if (ret < 0)
+		return;
+
+	if (ret & MV_V2_WOL_CTRL_MAGIC_PKT_EN)
+		wol->wolopts |= WAKE_MAGIC;
+}
+
+static int mv3110_set_wol(struct phy_device *phydev,
+			  struct ethtool_wolinfo *wol)
+{
+	int ret;
+
+	if (wol->wolopts & WAKE_MAGIC) {
+		/* Enable the WOL interrupt */
+		ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2,
+				       MV_V2_PORT_INTR_MASK,
+				       MV_V2_PORT_INTR_STS_WOL_EN);
+		if (ret < 0)
+			return ret;
+
+		/* Store the device address for the magic packet */
+		ret = phy_write_mmd(phydev, MDIO_MMD_VEND2,
+				    MV_V2_MAGIC_PKT_WORD2,
+				    ((phydev->attached_dev->dev_addr[5] << 8) |
+				    phydev->attached_dev->dev_addr[4]));
+		if (ret < 0)
+			return ret;
+
+		ret = phy_write_mmd(phydev, MDIO_MMD_VEND2,
+				    MV_V2_MAGIC_PKT_WORD1,
+				    ((phydev->attached_dev->dev_addr[3] << 8) |
+				    phydev->attached_dev->dev_addr[2]));
+		if (ret < 0)
+			return ret;
+
+		ret = phy_write_mmd(phydev, MDIO_MMD_VEND2,
+				    MV_V2_MAGIC_PKT_WORD0,
+				    ((phydev->attached_dev->dev_addr[1] << 8) |
+				    phydev->attached_dev->dev_addr[0]));
+		if (ret < 0)
+			return ret;
+
+		/* Clear WOL status and enable magic packet matching */
+		ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2,
+				       MV_V2_WOL_CTRL,
+				       MV_V2_WOL_CTRL_MAGIC_PKT_EN |
+				       MV_V2_WOL_CTRL_CLEAR_STS);
+		if (ret < 0)
+			return ret;
+	} else {
+		/* Disable magic packet matching & reset WOL status bit */
+		ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2,
+				     MV_V2_WOL_CTRL,
+				     MV_V2_WOL_CTRL_MAGIC_PKT_EN,
+				     MV_V2_WOL_CTRL_CLEAR_STS);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* Reset the clear WOL status bit as it does not self-clear */
+	return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2,
+				  MV_V2_WOL_CTRL,
+				  MV_V2_WOL_CTRL_CLEAR_STS);
+}
+
 static struct phy_driver mv3310_drivers[] = {
 	{
 		.phy_id		= MARVELL_PHY_ID_88X3310,
@@ -1039,6 +1132,8 @@ static struct phy_driver mv3310_drivers[] = {
 		.set_tunable	= mv3310_set_tunable,
 		.remove		= mv3310_remove,
 		.set_loopback	= genphy_c45_loopback,
+		.get_wol	= mv3110_get_wol,
+		.set_wol	= mv3110_set_wol,
 	},
 	{
 		.phy_id		= MARVELL_PHY_ID_88X3310,
@@ -1076,6 +1171,8 @@ static struct phy_driver mv3310_drivers[] = {
 		.set_tunable	= mv3310_set_tunable,
 		.remove		= mv3310_remove,
 		.set_loopback	= genphy_c45_loopback,
+		.get_wol	= mv3110_get_wol,
+		.set_wol	= mv3110_set_wol,
 	},
 	{
 		.phy_id		= MARVELL_PHY_ID_88E2110,
diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c
index 924ed5b034a4..edb951695b13 100644
--- a/drivers/net/phy/mscc/mscc_ptp.c
+++ b/drivers/net/phy/mscc/mscc_ptp.c
@@ -506,7 +506,7 @@ static int vsc85xx_ptp_cmp_init(struct phy_device *phydev, enum ts_blk blk)
 {
 	struct vsc8531_private *vsc8531 = phydev->priv;
 	bool base = phydev->mdio.addr == vsc8531->ts_base_addr;
-	u8 msgs[] = {
+	static const u8 msgs[] = {
 		PTP_MSGTYPE_SYNC,
 		PTP_MSGTYPE_DELAY_REQ
 	};
@@ -847,7 +847,7 @@ static int vsc85xx_ts_ptp_action_flow(struct phy_device *phydev, enum ts_blk blk
 static int vsc85xx_ptp_conf(struct phy_device *phydev, enum ts_blk blk,
 			    bool one_step, bool enable)
 {
-	u8 msgs[] = {
+	static const u8 msgs[] = {
 		PTP_MSGTYPE_SYNC,
 		PTP_MSGTYPE_DELAY_REQ
 	};
@@ -1268,8 +1268,8 @@ static void vsc8584_set_input_clk_configured(struct phy_device *phydev)
 static int __vsc8584_init_ptp(struct phy_device *phydev)
 {
 	struct vsc8531_private *vsc8531 = phydev->priv;
-	u32 ltc_seq_e[] = { 0, 400000, 0, 0, 0 };
-	u8  ltc_seq_a[] = { 8, 6, 5, 4, 2 };
+	static const u32 ltc_seq_e[] = { 0, 400000, 0, 0, 0 };
+	static const u8  ltc_seq_a[] = { 8, 6, 5, 4, 2 };
 	u32 val;
 
 	if (!vsc8584_is_1588_input_clk_configured(phydev)) {
diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c
new file mode 100644
index 000000000000..2d5d5081c3b6
--- /dev/null
+++ b/drivers/net/phy/mxl-gpy.c
@@ -0,0 +1,727 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2021 Maxlinear Corporation
+ * Copyright (C) 2020 Intel Corporation
+ *
+ * Drivers for Maxlinear Ethernet GPY
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/bitfield.h>
+#include <linux/phy.h>
+#include <linux/netdevice.h>
+
+/* PHY ID */
+#define PHY_ID_GPYx15B_MASK	0xFFFFFFFC
+#define PHY_ID_GPY21xB_MASK	0xFFFFFFF9
+#define PHY_ID_GPY2xx		0x67C9DC00
+#define PHY_ID_GPY115B		0x67C9DF00
+#define PHY_ID_GPY115C		0x67C9DF10
+#define PHY_ID_GPY211B		0x67C9DE08
+#define PHY_ID_GPY211C		0x67C9DE10
+#define PHY_ID_GPY212B		0x67C9DE09
+#define PHY_ID_GPY212C		0x67C9DE20
+#define PHY_ID_GPY215B		0x67C9DF04
+#define PHY_ID_GPY215C		0x67C9DF20
+#define PHY_ID_GPY241B		0x67C9DE40
+#define PHY_ID_GPY241BM		0x67C9DE80
+#define PHY_ID_GPY245B		0x67C9DEC0
+
+#define PHY_MIISTAT		0x18	/* MII state */
+#define PHY_IMASK		0x19	/* interrupt mask */
+#define PHY_ISTAT		0x1A	/* interrupt status */
+#define PHY_FWV			0x1E	/* firmware version */
+
+#define PHY_MIISTAT_SPD_MASK	GENMASK(2, 0)
+#define PHY_MIISTAT_DPX		BIT(3)
+#define PHY_MIISTAT_LS		BIT(10)
+
+#define PHY_MIISTAT_SPD_10	0
+#define PHY_MIISTAT_SPD_100	1
+#define PHY_MIISTAT_SPD_1000	2
+#define PHY_MIISTAT_SPD_2500	4
+
+#define PHY_IMASK_WOL		BIT(15)	/* Wake-on-LAN */
+#define PHY_IMASK_ANC		BIT(10)	/* Auto-Neg complete */
+#define PHY_IMASK_ADSC		BIT(5)	/* Link auto-downspeed detect */
+#define PHY_IMASK_DXMC		BIT(2)	/* Duplex mode change */
+#define PHY_IMASK_LSPC		BIT(1)	/* Link speed change */
+#define PHY_IMASK_LSTC		BIT(0)	/* Link state change */
+#define PHY_IMASK_MASK		(PHY_IMASK_LSTC | \
+				 PHY_IMASK_LSPC | \
+				 PHY_IMASK_DXMC | \
+				 PHY_IMASK_ADSC | \
+				 PHY_IMASK_ANC)
+
+#define PHY_FWV_REL_MASK	BIT(15)
+#define PHY_FWV_TYPE_MASK	GENMASK(11, 8)
+#define PHY_FWV_MINOR_MASK	GENMASK(7, 0)
+
+/* SGMII */
+#define VSPEC1_SGMII_CTRL	0x08
+#define VSPEC1_SGMII_CTRL_ANEN	BIT(12)		/* Aneg enable */
+#define VSPEC1_SGMII_CTRL_ANRS	BIT(9)		/* Restart Aneg */
+#define VSPEC1_SGMII_ANEN_ANRS	(VSPEC1_SGMII_CTRL_ANEN | \
+				 VSPEC1_SGMII_CTRL_ANRS)
+
+/* WoL */
+#define VPSPEC2_WOL_CTL		0x0E06
+#define VPSPEC2_WOL_AD01	0x0E08
+#define VPSPEC2_WOL_AD23	0x0E09
+#define VPSPEC2_WOL_AD45	0x0E0A
+#define WOL_EN			BIT(0)
+
+static const struct {
+	int type;
+	int minor;
+} ver_need_sgmii_reaneg[] = {
+	{7, 0x6D},
+	{8, 0x6D},
+	{9, 0x73},
+};
+
+static int gpy_config_init(struct phy_device *phydev)
+{
+	int ret;
+
+	/* Mask all interrupts */
+	ret = phy_write(phydev, PHY_IMASK, 0);
+	if (ret)
+		return ret;
+
+	/* Clear all pending interrupts */
+	ret = phy_read(phydev, PHY_ISTAT);
+	return ret < 0 ? ret : 0;
+}
+
+static int gpy_probe(struct phy_device *phydev)
+{
+	int ret;
+
+	if (!phydev->is_c45) {
+		ret = phy_get_c45_ids(phydev);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* Show GPY PHY FW version in dmesg */
+	ret = phy_read(phydev, PHY_FWV);
+	if (ret < 0)
+		return ret;
+
+	phydev_info(phydev, "Firmware Version: 0x%04X (%s)\n", ret,
+		    (ret & PHY_FWV_REL_MASK) ? "release" : "test");
+
+	return 0;
+}
+
+static bool gpy_sgmii_need_reaneg(struct phy_device *phydev)
+{
+	int fw_ver, fw_type, fw_minor;
+	size_t i;
+
+	fw_ver = phy_read(phydev, PHY_FWV);
+	if (fw_ver < 0)
+		return true;
+
+	fw_type = FIELD_GET(PHY_FWV_TYPE_MASK, fw_ver);
+	fw_minor = FIELD_GET(PHY_FWV_MINOR_MASK, fw_ver);
+
+	for (i = 0; i < ARRAY_SIZE(ver_need_sgmii_reaneg); i++) {
+		if (fw_type != ver_need_sgmii_reaneg[i].type)
+			continue;
+		if (fw_minor < ver_need_sgmii_reaneg[i].minor)
+			return true;
+		break;
+	}
+
+	return false;
+}
+
+static bool gpy_2500basex_chk(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = phy_read(phydev, PHY_MIISTAT);
+	if (ret < 0) {
+		phydev_err(phydev, "Error: MDIO register access failed: %d\n",
+			   ret);
+		return false;
+	}
+
+	if (!(ret & PHY_MIISTAT_LS) ||
+	    FIELD_GET(PHY_MIISTAT_SPD_MASK, ret) != PHY_MIISTAT_SPD_2500)
+		return false;
+
+	phydev->speed = SPEED_2500;
+	phydev->interface = PHY_INTERFACE_MODE_2500BASEX;
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, VSPEC1_SGMII_CTRL,
+		       VSPEC1_SGMII_CTRL_ANEN, 0);
+	return true;
+}
+
+static bool gpy_sgmii_aneg_en(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VSPEC1_SGMII_CTRL);
+	if (ret < 0) {
+		phydev_err(phydev, "Error: MMD register access failed: %d\n",
+			   ret);
+		return true;
+	}
+
+	return (ret & VSPEC1_SGMII_CTRL_ANEN) ? true : false;
+}
+
+static int gpy_config_aneg(struct phy_device *phydev)
+{
+	bool changed = false;
+	u32 adv;
+	int ret;
+
+	if (phydev->autoneg == AUTONEG_DISABLE) {
+		/* Configure half duplex with genphy_setup_forced,
+		 * because genphy_c45_pma_setup_forced does not support.
+		 */
+		return phydev->duplex != DUPLEX_FULL
+			? genphy_setup_forced(phydev)
+			: genphy_c45_pma_setup_forced(phydev);
+	}
+
+	ret = genphy_c45_an_config_aneg(phydev);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		changed = true;
+
+	adv = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising);
+	ret = phy_modify_changed(phydev, MII_CTRL1000,
+				 ADVERTISE_1000FULL | ADVERTISE_1000HALF,
+				 adv);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		changed = true;
+
+	ret = genphy_c45_check_and_restart_aneg(phydev, changed);
+	if (ret < 0)
+		return ret;
+
+	if (phydev->interface == PHY_INTERFACE_MODE_USXGMII ||
+	    phydev->interface == PHY_INTERFACE_MODE_INTERNAL)
+		return 0;
+
+	/* No need to trigger re-ANEG if link speed is 2.5G or SGMII ANEG is
+	 * disabled.
+	 */
+	if (!gpy_sgmii_need_reaneg(phydev) || gpy_2500basex_chk(phydev) ||
+	    !gpy_sgmii_aneg_en(phydev))
+		return 0;
+
+	/* There is a design constraint in GPY2xx device where SGMII AN is
+	 * only triggered when there is change of speed. If, PHY link
+	 * partner`s speed is still same even after PHY TPI is down and up
+	 * again, SGMII AN is not triggered and hence no new in-band message
+	 * from GPY to MAC side SGMII.
+	 * This could cause an issue during power up, when PHY is up prior to
+	 * MAC. At this condition, once MAC side SGMII is up, MAC side SGMII
+	 * wouldn`t receive new in-band message from GPY with correct link
+	 * status, speed and duplex info.
+	 *
+	 * 1) If PHY is already up and TPI link status is still down (such as
+	 *    hard reboot), TPI link status is polled for 4 seconds before
+	 *    retriggerring SGMII AN.
+	 * 2) If PHY is already up and TPI link status is also up (such as soft
+	 *    reboot), polling of TPI link status is not needed and SGMII AN is
+	 *    immediately retriggered.
+	 * 3) Other conditions such as PHY is down, speed change etc, skip
+	 *    retriggering SGMII AN. Note: in case of speed change, GPY FW will
+	 *    initiate SGMII AN.
+	 */
+
+	if (phydev->state != PHY_UP)
+		return 0;
+
+	ret = phy_read_poll_timeout(phydev, MII_BMSR, ret, ret & BMSR_LSTATUS,
+				    20000, 4000000, false);
+	if (ret == -ETIMEDOUT)
+		return 0;
+	else if (ret < 0)
+		return ret;
+
+	/* Trigger SGMII AN. */
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND1, VSPEC1_SGMII_CTRL,
+			      VSPEC1_SGMII_CTRL_ANRS, VSPEC1_SGMII_CTRL_ANRS);
+}
+
+static void gpy_update_interface(struct phy_device *phydev)
+{
+	int ret;
+
+	/* Interface mode is fixed for USXGMII and integrated PHY */
+	if (phydev->interface == PHY_INTERFACE_MODE_USXGMII ||
+	    phydev->interface == PHY_INTERFACE_MODE_INTERNAL)
+		return;
+
+	/* Automatically switch SERDES interface between SGMII and 2500-BaseX
+	 * according to speed. Disable ANEG in 2500-BaseX mode.
+	 */
+	switch (phydev->speed) {
+	case SPEED_2500:
+		phydev->interface = PHY_INTERFACE_MODE_2500BASEX;
+		ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, VSPEC1_SGMII_CTRL,
+				     VSPEC1_SGMII_CTRL_ANEN, 0);
+		if (ret < 0)
+			phydev_err(phydev,
+				   "Error: Disable of SGMII ANEG failed: %d\n",
+				   ret);
+		break;
+	case SPEED_1000:
+	case SPEED_100:
+	case SPEED_10:
+		phydev->interface = PHY_INTERFACE_MODE_SGMII;
+		if (gpy_sgmii_aneg_en(phydev))
+			break;
+		/* Enable and restart SGMII ANEG for 10/100/1000Mbps link speed
+		 * if ANEG is disabled (in 2500-BaseX mode).
+		 */
+		ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, VSPEC1_SGMII_CTRL,
+				     VSPEC1_SGMII_ANEN_ANRS,
+				     VSPEC1_SGMII_ANEN_ANRS);
+		if (ret < 0)
+			phydev_err(phydev,
+				   "Error: Enable of SGMII ANEG failed: %d\n",
+				   ret);
+		break;
+	}
+}
+
+static int gpy_read_status(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_update_link(phydev);
+	if (ret)
+		return ret;
+
+	phydev->speed = SPEED_UNKNOWN;
+	phydev->duplex = DUPLEX_UNKNOWN;
+	phydev->pause = 0;
+	phydev->asym_pause = 0;
+
+	if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) {
+		ret = genphy_c45_read_lpa(phydev);
+		if (ret < 0)
+			return ret;
+
+		/* Read the link partner's 1G advertisement */
+		ret = phy_read(phydev, MII_STAT1000);
+		if (ret < 0)
+			return ret;
+		mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, ret);
+	} else if (phydev->autoneg == AUTONEG_DISABLE) {
+		linkmode_zero(phydev->lp_advertising);
+	}
+
+	ret = phy_read(phydev, PHY_MIISTAT);
+	if (ret < 0)
+		return ret;
+
+	phydev->link = (ret & PHY_MIISTAT_LS) ? 1 : 0;
+	phydev->duplex = (ret & PHY_MIISTAT_DPX) ? DUPLEX_FULL : DUPLEX_HALF;
+	switch (FIELD_GET(PHY_MIISTAT_SPD_MASK, ret)) {
+	case PHY_MIISTAT_SPD_10:
+		phydev->speed = SPEED_10;
+		break;
+	case PHY_MIISTAT_SPD_100:
+		phydev->speed = SPEED_100;
+		break;
+	case PHY_MIISTAT_SPD_1000:
+		phydev->speed = SPEED_1000;
+		break;
+	case PHY_MIISTAT_SPD_2500:
+		phydev->speed = SPEED_2500;
+		break;
+	}
+
+	if (phydev->link)
+		gpy_update_interface(phydev);
+
+	return 0;
+}
+
+static int gpy_config_intr(struct phy_device *phydev)
+{
+	u16 mask = 0;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+		mask = PHY_IMASK_MASK;
+
+	return phy_write(phydev, PHY_IMASK, mask);
+}
+
+static irqreturn_t gpy_handle_interrupt(struct phy_device *phydev)
+{
+	int reg;
+
+	reg = phy_read(phydev, PHY_ISTAT);
+	if (reg < 0) {
+		phy_error(phydev);
+		return IRQ_NONE;
+	}
+
+	if (!(reg & PHY_IMASK_MASK))
+		return IRQ_NONE;
+
+	phy_trigger_machine(phydev);
+
+	return IRQ_HANDLED;
+}
+
+static int gpy_set_wol(struct phy_device *phydev,
+		       struct ethtool_wolinfo *wol)
+{
+	struct net_device *attach_dev = phydev->attached_dev;
+	int ret;
+
+	if (wol->wolopts & WAKE_MAGIC) {
+		/* MAC address - Byte0:Byte1:Byte2:Byte3:Byte4:Byte5
+		 * VPSPEC2_WOL_AD45 = Byte0:Byte1
+		 * VPSPEC2_WOL_AD23 = Byte2:Byte3
+		 * VPSPEC2_WOL_AD01 = Byte4:Byte5
+		 */
+		ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2,
+				       VPSPEC2_WOL_AD45,
+				       ((attach_dev->dev_addr[0] << 8) |
+				       attach_dev->dev_addr[1]));
+		if (ret < 0)
+			return ret;
+
+		ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2,
+				       VPSPEC2_WOL_AD23,
+				       ((attach_dev->dev_addr[2] << 8) |
+				       attach_dev->dev_addr[3]));
+		if (ret < 0)
+			return ret;
+
+		ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2,
+				       VPSPEC2_WOL_AD01,
+				       ((attach_dev->dev_addr[4] << 8) |
+				       attach_dev->dev_addr[5]));
+		if (ret < 0)
+			return ret;
+
+		/* Enable the WOL interrupt */
+		ret = phy_write(phydev, PHY_IMASK, PHY_IMASK_WOL);
+		if (ret < 0)
+			return ret;
+
+		/* Enable magic packet matching */
+		ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2,
+				       VPSPEC2_WOL_CTL,
+				       WOL_EN);
+		if (ret < 0)
+			return ret;
+
+		/* Clear the interrupt status register.
+		 * Only WoL is enabled so clear all.
+		 */
+		ret = phy_read(phydev, PHY_ISTAT);
+		if (ret < 0)
+			return ret;
+	} else {
+		/* Disable magic packet matching */
+		ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2,
+					 VPSPEC2_WOL_CTL,
+					 WOL_EN);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (wol->wolopts & WAKE_PHY) {
+		/* Enable the link state change interrupt */
+		ret = phy_set_bits(phydev, PHY_IMASK, PHY_IMASK_LSTC);
+		if (ret < 0)
+			return ret;
+
+		/* Clear the interrupt status register */
+		ret = phy_read(phydev, PHY_ISTAT);
+		if (ret < 0)
+			return ret;
+
+		if (ret & (PHY_IMASK_MASK & ~PHY_IMASK_LSTC))
+			phy_trigger_machine(phydev);
+
+		return 0;
+	}
+
+	/* Disable the link state change interrupt */
+	return phy_clear_bits(phydev, PHY_IMASK, PHY_IMASK_LSTC);
+}
+
+static void gpy_get_wol(struct phy_device *phydev,
+			struct ethtool_wolinfo *wol)
+{
+	int ret;
+
+	wol->supported = WAKE_MAGIC | WAKE_PHY;
+	wol->wolopts = 0;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, VPSPEC2_WOL_CTL);
+	if (ret & WOL_EN)
+		wol->wolopts |= WAKE_MAGIC;
+
+	ret = phy_read(phydev, PHY_IMASK);
+	if (ret & PHY_IMASK_LSTC)
+		wol->wolopts |= WAKE_PHY;
+}
+
+static int gpy_loopback(struct phy_device *phydev, bool enable)
+{
+	int ret;
+
+	ret = phy_modify(phydev, MII_BMCR, BMCR_LOOPBACK,
+			 enable ? BMCR_LOOPBACK : 0);
+	if (!ret) {
+		/* It takes some time for PHY device to switch
+		 * into/out-of loopback mode.
+		 */
+		msleep(100);
+	}
+
+	return ret;
+}
+
+static struct phy_driver gpy_drivers[] = {
+	{
+		PHY_ID_MATCH_MODEL(PHY_ID_GPY2xx),
+		.name		= "Maxlinear Ethernet GPY2xx",
+		.get_features	= genphy_c45_pma_read_abilities,
+		.config_init	= gpy_config_init,
+		.probe		= gpy_probe,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.config_aneg	= gpy_config_aneg,
+		.aneg_done	= genphy_c45_aneg_done,
+		.read_status	= gpy_read_status,
+		.config_intr	= gpy_config_intr,
+		.handle_interrupt = gpy_handle_interrupt,
+		.set_wol	= gpy_set_wol,
+		.get_wol	= gpy_get_wol,
+		.set_loopback	= gpy_loopback,
+	},
+	{
+		.phy_id		= PHY_ID_GPY115B,
+		.phy_id_mask	= PHY_ID_GPYx15B_MASK,
+		.name		= "Maxlinear Ethernet GPY115B",
+		.get_features	= genphy_c45_pma_read_abilities,
+		.config_init	= gpy_config_init,
+		.probe		= gpy_probe,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.config_aneg	= gpy_config_aneg,
+		.aneg_done	= genphy_c45_aneg_done,
+		.read_status	= gpy_read_status,
+		.config_intr	= gpy_config_intr,
+		.handle_interrupt = gpy_handle_interrupt,
+		.set_wol	= gpy_set_wol,
+		.get_wol	= gpy_get_wol,
+		.set_loopback	= gpy_loopback,
+	},
+	{
+		PHY_ID_MATCH_MODEL(PHY_ID_GPY115C),
+		.name		= "Maxlinear Ethernet GPY115C",
+		.get_features	= genphy_c45_pma_read_abilities,
+		.config_init	= gpy_config_init,
+		.probe		= gpy_probe,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.config_aneg	= gpy_config_aneg,
+		.aneg_done	= genphy_c45_aneg_done,
+		.read_status	= gpy_read_status,
+		.config_intr	= gpy_config_intr,
+		.handle_interrupt = gpy_handle_interrupt,
+		.set_wol	= gpy_set_wol,
+		.get_wol	= gpy_get_wol,
+		.set_loopback	= gpy_loopback,
+	},
+	{
+		.phy_id		= PHY_ID_GPY211B,
+		.phy_id_mask	= PHY_ID_GPY21xB_MASK,
+		.name		= "Maxlinear Ethernet GPY211B",
+		.get_features	= genphy_c45_pma_read_abilities,
+		.config_init	= gpy_config_init,
+		.probe		= gpy_probe,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.config_aneg	= gpy_config_aneg,
+		.aneg_done	= genphy_c45_aneg_done,
+		.read_status	= gpy_read_status,
+		.config_intr	= gpy_config_intr,
+		.handle_interrupt = gpy_handle_interrupt,
+		.set_wol	= gpy_set_wol,
+		.get_wol	= gpy_get_wol,
+		.set_loopback	= gpy_loopback,
+	},
+	{
+		PHY_ID_MATCH_MODEL(PHY_ID_GPY211C),
+		.name		= "Maxlinear Ethernet GPY211C",
+		.get_features	= genphy_c45_pma_read_abilities,
+		.config_init	= gpy_config_init,
+		.probe		= gpy_probe,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.config_aneg	= gpy_config_aneg,
+		.aneg_done	= genphy_c45_aneg_done,
+		.read_status	= gpy_read_status,
+		.config_intr	= gpy_config_intr,
+		.handle_interrupt = gpy_handle_interrupt,
+		.set_wol	= gpy_set_wol,
+		.get_wol	= gpy_get_wol,
+		.set_loopback	= gpy_loopback,
+	},
+	{
+		.phy_id		= PHY_ID_GPY212B,
+		.phy_id_mask	= PHY_ID_GPY21xB_MASK,
+		.name		= "Maxlinear Ethernet GPY212B",
+		.get_features	= genphy_c45_pma_read_abilities,
+		.config_init	= gpy_config_init,
+		.probe		= gpy_probe,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.config_aneg	= gpy_config_aneg,
+		.aneg_done	= genphy_c45_aneg_done,
+		.read_status	= gpy_read_status,
+		.config_intr	= gpy_config_intr,
+		.handle_interrupt = gpy_handle_interrupt,
+		.set_wol	= gpy_set_wol,
+		.get_wol	= gpy_get_wol,
+		.set_loopback	= gpy_loopback,
+	},
+	{
+		PHY_ID_MATCH_MODEL(PHY_ID_GPY212C),
+		.name		= "Maxlinear Ethernet GPY212C",
+		.get_features	= genphy_c45_pma_read_abilities,
+		.config_init	= gpy_config_init,
+		.probe		= gpy_probe,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.config_aneg	= gpy_config_aneg,
+		.aneg_done	= genphy_c45_aneg_done,
+		.read_status	= gpy_read_status,
+		.config_intr	= gpy_config_intr,
+		.handle_interrupt = gpy_handle_interrupt,
+		.set_wol	= gpy_set_wol,
+		.get_wol	= gpy_get_wol,
+		.set_loopback	= gpy_loopback,
+	},
+	{
+		.phy_id		= PHY_ID_GPY215B,
+		.phy_id_mask	= PHY_ID_GPYx15B_MASK,
+		.name		= "Maxlinear Ethernet GPY215B",
+		.get_features	= genphy_c45_pma_read_abilities,
+		.config_init	= gpy_config_init,
+		.probe		= gpy_probe,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.config_aneg	= gpy_config_aneg,
+		.aneg_done	= genphy_c45_aneg_done,
+		.read_status	= gpy_read_status,
+		.config_intr	= gpy_config_intr,
+		.handle_interrupt = gpy_handle_interrupt,
+		.set_wol	= gpy_set_wol,
+		.get_wol	= gpy_get_wol,
+		.set_loopback	= gpy_loopback,
+	},
+	{
+		PHY_ID_MATCH_MODEL(PHY_ID_GPY215C),
+		.name		= "Maxlinear Ethernet GPY215C",
+		.get_features	= genphy_c45_pma_read_abilities,
+		.config_init	= gpy_config_init,
+		.probe		= gpy_probe,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.config_aneg	= gpy_config_aneg,
+		.aneg_done	= genphy_c45_aneg_done,
+		.read_status	= gpy_read_status,
+		.config_intr	= gpy_config_intr,
+		.handle_interrupt = gpy_handle_interrupt,
+		.set_wol	= gpy_set_wol,
+		.get_wol	= gpy_get_wol,
+		.set_loopback	= gpy_loopback,
+	},
+	{
+		PHY_ID_MATCH_MODEL(PHY_ID_GPY241B),
+		.name		= "Maxlinear Ethernet GPY241B",
+		.get_features	= genphy_c45_pma_read_abilities,
+		.config_init	= gpy_config_init,
+		.probe		= gpy_probe,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.config_aneg	= gpy_config_aneg,
+		.aneg_done	= genphy_c45_aneg_done,
+		.read_status	= gpy_read_status,
+		.config_intr	= gpy_config_intr,
+		.handle_interrupt = gpy_handle_interrupt,
+		.set_wol	= gpy_set_wol,
+		.get_wol	= gpy_get_wol,
+		.set_loopback	= gpy_loopback,
+	},
+	{
+		PHY_ID_MATCH_MODEL(PHY_ID_GPY241BM),
+		.name		= "Maxlinear Ethernet GPY241BM",
+		.get_features	= genphy_c45_pma_read_abilities,
+		.config_init	= gpy_config_init,
+		.probe		= gpy_probe,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.config_aneg	= gpy_config_aneg,
+		.aneg_done	= genphy_c45_aneg_done,
+		.read_status	= gpy_read_status,
+		.config_intr	= gpy_config_intr,
+		.handle_interrupt = gpy_handle_interrupt,
+		.set_wol	= gpy_set_wol,
+		.get_wol	= gpy_get_wol,
+		.set_loopback	= gpy_loopback,
+	},
+	{
+		PHY_ID_MATCH_MODEL(PHY_ID_GPY245B),
+		.name		= "Maxlinear Ethernet GPY245B",
+		.get_features	= genphy_c45_pma_read_abilities,
+		.config_init	= gpy_config_init,
+		.probe		= gpy_probe,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.config_aneg	= gpy_config_aneg,
+		.aneg_done	= genphy_c45_aneg_done,
+		.read_status	= gpy_read_status,
+		.config_intr	= gpy_config_intr,
+		.handle_interrupt = gpy_handle_interrupt,
+		.set_wol	= gpy_set_wol,
+		.get_wol	= gpy_get_wol,
+		.set_loopback	= gpy_loopback,
+	},
+};
+module_phy_driver(gpy_drivers);
+
+static struct mdio_device_id __maybe_unused gpy_tbl[] = {
+	{PHY_ID_MATCH_MODEL(PHY_ID_GPY2xx)},
+	{PHY_ID_GPY115B, PHY_ID_GPYx15B_MASK},
+	{PHY_ID_MATCH_MODEL(PHY_ID_GPY115C)},
+	{PHY_ID_GPY211B, PHY_ID_GPY21xB_MASK},
+	{PHY_ID_MATCH_MODEL(PHY_ID_GPY211C)},
+	{PHY_ID_GPY212B, PHY_ID_GPY21xB_MASK},
+	{PHY_ID_MATCH_MODEL(PHY_ID_GPY212C)},
+	{PHY_ID_GPY215B, PHY_ID_GPYx15B_MASK},
+	{PHY_ID_MATCH_MODEL(PHY_ID_GPY215C)},
+	{PHY_ID_MATCH_MODEL(PHY_ID_GPY241B)},
+	{PHY_ID_MATCH_MODEL(PHY_ID_GPY241BM)},
+	{PHY_ID_MATCH_MODEL(PHY_ID_GPY245B)},
+	{ }
+};
+MODULE_DEVICE_TABLE(mdio, gpy_tbl);
+
+MODULE_DESCRIPTION("Maxlinear Ethernet GPY Driver");
+MODULE_AUTHOR("Xu Liang");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/nxp-tja11xx.c b/drivers/net/phy/nxp-tja11xx.c
index afd7afa1f498..9944cc501806 100644
--- a/drivers/net/phy/nxp-tja11xx.c
+++ b/drivers/net/phy/nxp-tja11xx.c
@@ -47,12 +47,14 @@
 #define MII_INTSRC_LINK_FAIL		BIT(10)
 #define MII_INTSRC_LINK_UP		BIT(9)
 #define MII_INTSRC_MASK			(MII_INTSRC_LINK_FAIL | MII_INTSRC_LINK_UP)
-#define MII_INTSRC_TEMP_ERR		BIT(1)
 #define MII_INTSRC_UV_ERR		BIT(3)
+#define MII_INTSRC_TEMP_ERR		BIT(1)
 
 #define MII_INTEN			22
 #define MII_INTEN_LINK_FAIL		BIT(10)
 #define MII_INTEN_LINK_UP		BIT(9)
+#define MII_INTEN_UV_ERR		BIT(3)
+#define MII_INTEN_TEMP_ERR		BIT(1)
 
 #define MII_COMMSTAT			23
 #define MII_COMMSTAT_LINK_UP		BIT(15)
@@ -607,7 +609,8 @@ static int tja11xx_config_intr(struct phy_device *phydev)
 		if (err)
 			return err;
 
-		value = MII_INTEN_LINK_FAIL | MII_INTEN_LINK_UP;
+		value = MII_INTEN_LINK_FAIL | MII_INTEN_LINK_UP |
+			MII_INTEN_UV_ERR | MII_INTEN_TEMP_ERR;
 		err = phy_write(phydev, MII_INTEN, value);
 	} else {
 		err = phy_write(phydev, MII_INTEN, value);
@@ -622,6 +625,7 @@ static int tja11xx_config_intr(struct phy_device *phydev)
 
 static irqreturn_t tja11xx_handle_interrupt(struct phy_device *phydev)
 {
+	struct device *dev = &phydev->mdio.dev;
 	int irq_status;
 
 	irq_status = phy_read(phydev, MII_INTSRC);
@@ -630,6 +634,11 @@ static irqreturn_t tja11xx_handle_interrupt(struct phy_device *phydev)
 		return IRQ_NONE;
 	}
 
+	if (irq_status & MII_INTSRC_TEMP_ERR)
+		dev_warn(dev, "Overtemperature error detected (temp > 155C°).\n");
+	if (irq_status & MII_INTSRC_UV_ERR)
+		dev_warn(dev, "Undervoltage error detected.\n");
+
 	if (!(irq_status & MII_INTSRC_MASK))
 		return IRQ_NONE;
 
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 8eeb26d8aeb7..f124a8a58bd4 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -426,7 +426,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 EXPORT_SYMBOL(phy_mii_ioctl);
 
 /**
- * phy_do_ioctl - generic ndo_do_ioctl implementation
+ * phy_do_ioctl - generic ndo_eth_ioctl implementation
  * @dev: the net_device struct
  * @ifr: &struct ifreq for socket ioctl's
  * @cmd: ioctl cmd to execute
@@ -441,7 +441,7 @@ int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 EXPORT_SYMBOL(phy_do_ioctl);
 
 /**
- * phy_do_ioctl_running - generic ndo_do_ioctl implementation but test first
+ * phy_do_ioctl_running - generic ndo_eth_ioctl implementation but test first
  *
  * @dev: the net_device struct
  * @ifr: &struct ifreq for socket ioctl's
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 5d5f9a9ee768..9e2891d8e8dd 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -233,11 +233,9 @@ static DEFINE_MUTEX(phy_fixup_lock);
 
 static bool mdio_bus_phy_may_suspend(struct phy_device *phydev)
 {
-	struct device_driver *drv = phydev->mdio.dev.driver;
-	struct phy_driver *phydrv = to_phy_driver(drv);
 	struct net_device *netdev = phydev->attached_dev;
 
-	if (!drv || !phydrv->suspend)
+	if (!phydev->drv->suspend)
 		return false;
 
 	/* PHY not attached? May suspend if the PHY has not already been
@@ -969,6 +967,20 @@ void phy_device_remove(struct phy_device *phydev)
 EXPORT_SYMBOL(phy_device_remove);
 
 /**
+ * phy_get_c45_ids - Read 802.3-c45 IDs for phy device.
+ * @phydev: phy_device structure to read 802.3-c45 IDs
+ *
+ * Returns zero on success, %-EIO on bus access error, or %-ENODEV if
+ * the "devices in package" is invalid.
+ */
+int phy_get_c45_ids(struct phy_device *phydev)
+{
+	return get_phy_c45_ids(phydev->mdio.bus, phydev->mdio.addr,
+			       &phydev->c45_ids);
+}
+EXPORT_SYMBOL(phy_get_c45_ids);
+
+/**
  * phy_find_first - finds the first PHY device on the bus
  * @bus: the target MII bus
  */
@@ -1807,11 +1819,10 @@ EXPORT_SYMBOL(phy_resume);
 
 int phy_loopback(struct phy_device *phydev, bool enable)
 {
-	struct phy_driver *phydrv = to_phy_driver(phydev->mdio.dev.driver);
 	int ret = 0;
 
-	if (!phydrv)
-		return -ENODEV;
+	if (!phydev->drv)
+		return -EIO;
 
 	mutex_lock(&phydev->lock);
 
@@ -1825,8 +1836,8 @@ int phy_loopback(struct phy_device *phydev, bool enable)
 		goto out;
 	}
 
-	if (phydrv->set_loopback)
-		ret = phydrv->set_loopback(phydev, enable);
+	if (phydev->drv->set_loopback)
+		ret = phydev->drv->set_loopback(phydev, enable);
 	else
 		ret = genphy_loopback(phydev, enable);
 
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index eb29ef53d971..2cdf9f989dec 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -942,10 +942,11 @@ static void phylink_phy_change(struct phy_device *phydev, bool up)
 
 	phylink_run_resolve(pl);
 
-	phylink_dbg(pl, "phy link %s %s/%s/%s\n", up ? "up" : "down",
+	phylink_dbg(pl, "phy link %s %s/%s/%s/%s\n", up ? "up" : "down",
 		    phy_modes(phydev->interface),
 		    phy_speed_to_str(phydev->speed),
-		    phy_duplex_to_str(phydev->duplex));
+		    phy_duplex_to_str(phydev->duplex),
+		    phylink_pause_to_str(pl->phy_state.pause));
 }
 
 static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
@@ -1457,15 +1458,11 @@ int phylink_ethtool_ksettings_set(struct phylink *pl,
 		return phy_ethtool_ksettings_set(pl->phydev, kset);
 	}
 
-	linkmode_copy(support, pl->supported);
 	config = pl->link_config;
-	config.an_enabled = kset->base.autoneg == AUTONEG_ENABLE;
 
-	/* Mask out unsupported advertisements, and force the autoneg bit */
+	/* Mask out unsupported advertisements */
 	linkmode_and(config.advertising, kset->link_modes.advertising,
-		     support);
-	linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, config.advertising,
-			 config.an_enabled);
+		     pl->supported);
 
 	/* FIXME: should we reject autoneg if phy/mac does not support it? */
 	switch (kset->base.autoneg) {
@@ -1474,7 +1471,7 @@ int phylink_ethtool_ksettings_set(struct phylink *pl,
 		 * duplex.
 		 */
 		s = phy_lookup_setting(kset->base.speed, kset->base.duplex,
-				       support, false);
+				       pl->supported, false);
 		if (!s)
 			return -EINVAL;
 
@@ -1515,6 +1512,12 @@ int phylink_ethtool_ksettings_set(struct phylink *pl,
 	/* We have ruled out the case with a PHY attached, and the
 	 * fixed-link cases.  All that is left are in-band links.
 	 */
+	config.an_enabled = kset->base.autoneg == AUTONEG_ENABLE;
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, config.advertising,
+			 config.an_enabled);
+
+	/* Validate without changing the current supported mask. */
+	linkmode_copy(support, pl->supported);
 	if (phylink_validate(pl, support, &config))
 		return -EINVAL;
 
diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index 151c2a3f0b3a..8dcb49ed1f3d 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -27,12 +27,28 @@ struct gmii2rgmii {
 	struct mdio_device *mdio;
 };
 
-static int xgmiitorgmii_read_status(struct phy_device *phydev)
+static void xgmiitorgmii_configure(struct gmii2rgmii *priv, int speed)
 {
-	struct gmii2rgmii *priv = mdiodev_get_drvdata(&phydev->mdio);
 	struct mii_bus *bus = priv->mdio->bus;
 	int addr = priv->mdio->addr;
-	u16 val = 0;
+	u16 val;
+
+	val = mdiobus_read(bus, addr, XILINX_GMII2RGMII_REG);
+	val &= ~XILINX_GMII2RGMII_SPEED_MASK;
+
+	if (speed == SPEED_1000)
+		val |= BMCR_SPEED1000;
+	else if (speed == SPEED_100)
+		val |= BMCR_SPEED100;
+	else
+		val |= BMCR_SPEED10;
+
+	mdiobus_write(bus, addr, XILINX_GMII2RGMII_REG, val);
+}
+
+static int xgmiitorgmii_read_status(struct phy_device *phydev)
+{
+	struct gmii2rgmii *priv = mdiodev_get_drvdata(&phydev->mdio);
 	int err;
 
 	if (priv->phy_drv->read_status)
@@ -42,17 +58,24 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
-	val = mdiobus_read(bus, addr, XILINX_GMII2RGMII_REG);
-	val &= ~XILINX_GMII2RGMII_SPEED_MASK;
+	xgmiitorgmii_configure(priv, phydev->speed);
 
-	if (phydev->speed == SPEED_1000)
-		val |= BMCR_SPEED1000;
-	else if (phydev->speed == SPEED_100)
-		val |= BMCR_SPEED100;
+	return 0;
+}
+
+static int xgmiitorgmii_set_loopback(struct phy_device *phydev, bool enable)
+{
+	struct gmii2rgmii *priv = mdiodev_get_drvdata(&phydev->mdio);
+	int err;
+
+	if (priv->phy_drv->set_loopback)
+		err = priv->phy_drv->set_loopback(phydev, enable);
 	else
-		val |= BMCR_SPEED10;
+		err = genphy_loopback(phydev, enable);
+	if (err < 0)
+		return err;
 
-	mdiobus_write(bus, addr, XILINX_GMII2RGMII_REG, val);
+	xgmiitorgmii_configure(priv, phydev->speed);
 
 	return 0;
 }
@@ -90,6 +113,7 @@ static int xgmiitorgmii_probe(struct mdio_device *mdiodev)
 	memcpy(&priv->conv_phy_drv, priv->phy_dev->drv,
 	       sizeof(struct phy_driver));
 	priv->conv_phy_drv.read_status = xgmiitorgmii_read_status;
+	priv->conv_phy_drv.set_loopback = xgmiitorgmii_set_loopback;
 	mdiodev_set_drvdata(&priv->phy_dev->mdio, priv);
 	priv->phy_dev->drv = &priv->conv_phy_drv;
 
diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c
index e26cf91bdec2..82d609401711 100644
--- a/drivers/net/plip/plip.c
+++ b/drivers/net/plip/plip.c
@@ -84,6 +84,7 @@ static const char version[] = "NET3 PLIP version 2.4-parport gniibe@mri.co.jp\n"
     extra grounds are 18,19,20,21,22,23,24
 */
 
+#include <linux/compat.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -150,7 +151,8 @@ static int plip_hard_header_cache(const struct neighbour *neigh,
                                   struct hh_cache *hh, __be16 type);
 static int plip_open(struct net_device *dev);
 static int plip_close(struct net_device *dev);
-static int plip_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
+static int plip_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			       void __user *data, int cmd);
 static int plip_preempt(void *handle);
 static void plip_wakeup(void *handle);
 
@@ -265,7 +267,7 @@ static const struct net_device_ops plip_netdev_ops = {
 	.ndo_open		 = plip_open,
 	.ndo_stop		 = plip_close,
 	.ndo_start_xmit		 = plip_tx_packet,
-	.ndo_do_ioctl		 = plip_ioctl,
+	.ndo_siocdevprivate	 = plip_siocdevprivate,
 	.ndo_set_mac_address	 = eth_mac_addr,
 	.ndo_validate_addr	 = eth_validate_addr,
 };
@@ -1207,7 +1209,8 @@ plip_wakeup(void *handle)
 }
 
 static int
-plip_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+plip_siocdevprivate(struct net_device *dev, struct ifreq *rq,
+		    void __user *data, int cmd)
 {
 	struct net_local *nl = netdev_priv(dev);
 	struct plipconf *pc = (struct plipconf *) &rq->ifr_ifru;
@@ -1215,6 +1218,9 @@ plip_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	if (cmd != SIOCDEVPLIP)
 		return -EOPNOTSUPP;
 
+	if (in_compat_syscall())
+		return -EOPNOTSUPP;
+
 	switch(pc->pcmd) {
 	case PLIP_GET_TIMEOUT:
 		pc->trigger = nl->trigger;
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 7a099c37527f..fb52cd175b45 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1463,11 +1463,11 @@ ppp_start_xmit(struct sk_buff *skb, struct net_device *dev)
 }
 
 static int
-ppp_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+ppp_net_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+		       void __user *addr, int cmd)
 {
 	struct ppp *ppp = netdev_priv(dev);
 	int err = -EFAULT;
-	void __user *addr = (void __user *) ifr->ifr_ifru.ifru_data;
 	struct ppp_stats stats;
 	struct ppp_comp_stats cstats;
 	char *vers;
@@ -1596,7 +1596,7 @@ static const struct net_device_ops ppp_netdev_ops = {
 	.ndo_init	 = ppp_dev_init,
 	.ndo_uninit      = ppp_dev_uninit,
 	.ndo_start_xmit  = ppp_start_xmit,
-	.ndo_do_ioctl    = ppp_net_ioctl,
+	.ndo_siocdevprivate = ppp_net_siocdevprivate,
 	.ndo_get_stats64 = ppp_get_stats64,
 	.ndo_fill_forward_path = ppp_fill_forward_path,
 };
@@ -1744,7 +1744,7 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb)
 		   a four-byte PPP header on each packet */
 		*(u8 *)skb_push(skb, 2) = 1;
 		if (ppp->pass_filter &&
-		    BPF_PROG_RUN(ppp->pass_filter, skb) == 0) {
+		    bpf_prog_run(ppp->pass_filter, skb) == 0) {
 			if (ppp->debug & 1)
 				netdev_printk(KERN_DEBUG, ppp->dev,
 					      "PPP: outbound frame "
@@ -1754,7 +1754,7 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb)
 		}
 		/* if this packet passes the active filter, record the time */
 		if (!(ppp->active_filter &&
-		      BPF_PROG_RUN(ppp->active_filter, skb) == 0))
+		      bpf_prog_run(ppp->active_filter, skb) == 0))
 			ppp->last_xmit = jiffies;
 		skb_pull(skb, 2);
 #else
@@ -2468,7 +2468,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb)
 
 			*(u8 *)skb_push(skb, 2) = 0;
 			if (ppp->pass_filter &&
-			    BPF_PROG_RUN(ppp->pass_filter, skb) == 0) {
+			    bpf_prog_run(ppp->pass_filter, skb) == 0) {
 				if (ppp->debug & 1)
 					netdev_printk(KERN_DEBUG, ppp->dev,
 						      "PPP: inbound frame "
@@ -2477,7 +2477,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb)
 				return;
 			}
 			if (!(ppp->active_filter &&
-			      BPF_PROG_RUN(ppp->active_filter, skb) == 0))
+			      bpf_prog_run(ppp->active_filter, skb) == 0))
 				ppp->last_recv = jiffies;
 			__skb_pull(skb, 2);
 		} else
diff --git a/drivers/net/sb1000.c b/drivers/net/sb1000.c
index e88af978f63c..f01c9db01b16 100644
--- a/drivers/net/sb1000.c
+++ b/drivers/net/sb1000.c
@@ -78,7 +78,8 @@ struct sb1000_private {
 /* prototypes for Linux interface */
 extern int sb1000_probe(struct net_device *dev);
 static int sb1000_open(struct net_device *dev);
-static int sb1000_dev_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd);
+static int sb1000_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+				 void __user *data, int cmd);
 static netdev_tx_t sb1000_start_xmit(struct sk_buff *skb,
 				     struct net_device *dev);
 static irqreturn_t sb1000_interrupt(int irq, void *dev_id);
@@ -135,7 +136,7 @@ MODULE_DEVICE_TABLE(pnp, sb1000_pnp_ids);
 static const struct net_device_ops sb1000_netdev_ops = {
 	.ndo_open		= sb1000_open,
 	.ndo_start_xmit		= sb1000_start_xmit,
-	.ndo_do_ioctl		= sb1000_dev_ioctl,
+	.ndo_siocdevprivate	= sb1000_siocdevprivate,
 	.ndo_stop		= sb1000_close,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
@@ -987,7 +988,8 @@ sb1000_open(struct net_device *dev)
 	return 0;					/* Always succeed */
 }
 
-static int sb1000_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int sb1000_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+				 void __user *data, int cmd)
 {
 	char* name;
 	unsigned char version[2];
@@ -1011,7 +1013,7 @@ static int sb1000_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		stats[2] = dev->stats.rx_packets;
 		stats[3] = dev->stats.rx_errors;
 		stats[4] = dev->stats.rx_dropped;
-		if(copy_to_user(ifr->ifr_data, stats, sizeof(stats)))
+		if (copy_to_user(data, stats, sizeof(stats)))
 			return -EFAULT;
 		status = 0;
 		break;
@@ -1019,21 +1021,21 @@ static int sb1000_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCGCMFIRMWARE:		/* get firmware version */
 		if ((status = sb1000_get_firmware_version(ioaddr, name, version, 1)))
 			return status;
-		if(copy_to_user(ifr->ifr_data, version, sizeof(version)))
+		if (copy_to_user(data, version, sizeof(version)))
 			return -EFAULT;
 		break;
 
 	case SIOCGCMFREQUENCY:		/* get frequency */
 		if ((status = sb1000_get_frequency(ioaddr, name, &frequency)))
 			return status;
-		if(put_user(frequency, (int __user *) ifr->ifr_data))
+		if (put_user(frequency, (int __user *)data))
 			return -EFAULT;
 		break;
 
 	case SIOCSCMFREQUENCY:		/* set frequency */
 		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
-		if(get_user(frequency, (int __user *) ifr->ifr_data))
+		if (get_user(frequency, (int __user *)data))
 			return -EFAULT;
 		if ((status = sb1000_set_frequency(ioaddr, name, frequency)))
 			return status;
@@ -1042,14 +1044,14 @@ static int sb1000_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCGCMPIDS:			/* get PIDs */
 		if ((status = sb1000_get_PIDs(ioaddr, name, PID)))
 			return status;
-		if(copy_to_user(ifr->ifr_data, PID, sizeof(PID)))
+		if (copy_to_user(data, PID, sizeof(PID)))
 			return -EFAULT;
 		break;
 
 	case SIOCSCMPIDS:			/* set PIDs */
 		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
-		if(copy_from_user(PID, ifr->ifr_data, sizeof(PID)))
+		if (copy_from_user(PID, data, sizeof(PID)))
 			return -EFAULT;
 		if ((status = sb1000_set_PIDs(ioaddr, name, PID)))
 			return status;
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index dc84cb844319..5435b5689ce6 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -62,6 +62,7 @@
  */
 
 #define SL_CHECK_TRANSMIT
+#include <linux/compat.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 
@@ -108,7 +109,7 @@ static void slip_unesc6(struct slip *sl, unsigned char c);
 #ifdef CONFIG_SLIP_SMART
 static void sl_keepalive(struct timer_list *t);
 static void sl_outfill(struct timer_list *t);
-static int sl_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
+static int sl_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *data, int cmd);
 #endif
 
 /********************************
@@ -647,7 +648,7 @@ static const struct net_device_ops sl_netdev_ops = {
 	.ndo_change_mtu		= sl_change_mtu,
 	.ndo_tx_timeout		= sl_tx_timeout,
 #ifdef CONFIG_SLIP_SMART
-	.ndo_do_ioctl		= sl_ioctl,
+	.ndo_siocdevprivate	= sl_siocdevprivate,
 #endif
 };
 
@@ -1179,11 +1180,12 @@ static int slip_ioctl(struct tty_struct *tty, struct file *file,
 
 /* VSV changes start here */
 #ifdef CONFIG_SLIP_SMART
-/* function do_ioctl called from net/core/dev.c
+/* function sl_siocdevprivate called from net/core/dev.c
    to allow get/set outfill/keepalive parameter
    by ifconfig                                 */
 
-static int sl_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+static int sl_siocdevprivate(struct net_device *dev, struct ifreq *rq,
+			     void __user *data, int cmd)
 {
 	struct slip *sl = netdev_priv(dev);
 	unsigned long *p = (unsigned long *)&rq->ifr_ifru;
@@ -1191,6 +1193,9 @@ static int sl_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	if (sl == NULL)		/* Allocation failed ?? */
 		return -ENODEV;
 
+	if (in_compat_syscall())
+		return -EOPNOTSUPP;
+
 	spin_lock_bh(&sl->lock);
 
 	if (!sl->tty) {
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index 32aef8ac4a14..b095a4b4957b 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -197,7 +197,7 @@ static unsigned int lb_get_skb_hash(struct lb_priv *lb_priv,
 	fp = rcu_dereference_bh(lb_priv->fp);
 	if (unlikely(!fp))
 		return 0;
-	lhash = BPF_PROG_RUN(fp, skb);
+	lhash = bpf_prog_run(fp, skb);
 	c = (char *) &lhash;
 	return c[0] ^ c[1] ^ c[2] ^ c[3];
 }
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 2ced021f4faf..fecc9a1d293a 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -3510,7 +3510,9 @@ static void tun_set_msglevel(struct net_device *dev, u32 value)
 }
 
 static int tun_get_coalesce(struct net_device *dev,
-			    struct ethtool_coalesce *ec)
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct tun_struct *tun = netdev_priv(dev);
 
@@ -3520,7 +3522,9 @@ static int tun_get_coalesce(struct net_device *dev,
 }
 
 static int tun_set_coalesce(struct net_device *dev,
-			    struct ethtool_coalesce *ec)
+			    struct ethtool_coalesce *ec,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct tun_struct *tun = netdev_priv(dev);
 
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index dc87e8caf954..30821f6a6d7a 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -197,7 +197,7 @@ static const struct net_device_ops ax88172_netdev_ops = {
 	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= asix_ioctl,
+	.ndo_eth_ioctl		= asix_ioctl,
 	.ndo_set_rx_mode	= ax88172_set_multicast,
 };
 
@@ -587,7 +587,7 @@ static const struct net_device_ops ax88772_netdev_ops = {
 	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address 	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_set_rx_mode        = asix_set_multicast,
 };
 
@@ -706,7 +706,6 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
 	u8 buf[ETH_ALEN] = {0}, chipcode = 0;
 	struct asix_common_private *priv;
 	int ret, i;
-	u32 phyid;
 
 	priv = devm_kzalloc(&dev->udev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -767,10 +766,6 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
 		return ret;
 	}
 
-	/* Read PHYID register *AFTER* the PHY was reset properly */
-	phyid = asix_get_phyid(dev);
-	netdev_dbg(dev->net, "PHYID=0x%08x\n", phyid);
-
 	/* Asix framing packs multiple eth frames into a 2K usb bulk transfer */
 	if (dev->driver_info->flags & FLAG_FRAMING_AX) {
 		/* hard_mtu  is still the default - the device does not support
@@ -1105,7 +1100,7 @@ static const struct net_device_ops ax88178_netdev_ops = {
 	.ndo_set_mac_address 	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= asix_set_multicast,
-	.ndo_do_ioctl 		= asix_ioctl,
+	.ndo_eth_ioctl		= asix_ioctl,
 	.ndo_change_mtu 	= ax88178_change_mtu,
 };
 
@@ -1220,6 +1215,7 @@ static const struct driver_info ax88772b_info = {
 	.unbind = ax88772_unbind,
 	.status = asix_status,
 	.reset = ax88772_reset,
+	.stop = ax88772_stop,
 	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
 	         FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index 530947d7477b..d9777d9a7c5d 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -109,7 +109,7 @@ static const struct net_device_ops ax88172a_netdev_ops = {
 	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_set_rx_mode        = asix_set_multicast,
 };
 
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index c1316718304d..f25448a08870 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1035,7 +1035,7 @@ static const struct net_device_ops ax88179_netdev_ops = {
 	.ndo_change_mtu		= ax88179_change_mtu,
 	.ndo_set_mac_address	= ax88179_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= ax88179_ioctl,
+	.ndo_eth_ioctl		= ax88179_ioctl,
 	.ndo_set_rx_mode	= ax88179_set_multicast,
 	.ndo_set_features	= ax88179_set_features,
 };
diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c
index 8d1f69dad603..e1da9102a540 100644
--- a/drivers/net/usb/cdc-phonet.c
+++ b/drivers/net/usb/cdc-phonet.c
@@ -253,7 +253,8 @@ static int usbpn_close(struct net_device *dev)
 	return usb_set_interface(pnd->usb, num, !pnd->active_setting);
 }
 
-static int usbpn_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int usbpn_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+				void __user *data, int cmd)
 {
 	struct if_phonet_req *req = (struct if_phonet_req *)ifr;
 
@@ -269,7 +270,7 @@ static const struct net_device_ops usbpn_ops = {
 	.ndo_open	= usbpn_open,
 	.ndo_stop	= usbpn_close,
 	.ndo_start_xmit = usbpn_xmit,
-	.ndo_do_ioctl	= usbpn_ioctl,
+	.ndo_siocdevprivate = usbpn_siocdevprivate,
 };
 
 static void usbpn_setup(struct net_device *dev)
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 89cc61d7a675..907f98b1eefe 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -345,7 +345,7 @@ static const struct net_device_ops dm9601_netdev_ops = {
 	.ndo_change_mtu		= usbnet_change_mtu,
 	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl 		= dm9601_ioctl,
+	.ndo_eth_ioctl		= dm9601_ioctl,
 	.ndo_set_rx_mode	= dm9601_set_multicast,
 	.ndo_set_mac_address	= dm9601_set_mac_address,
 };
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index dec96e8ab567..24bc1e678b7b 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -1079,8 +1079,7 @@ static void hso_init_termios(struct ktermios *termios)
 	tty_termios_encode_baud_rate(termios, 115200, 115200);
 }
 
-static void _hso_serial_set_termios(struct tty_struct *tty,
-				    struct ktermios *old)
+static void _hso_serial_set_termios(struct tty_struct *tty)
 {
 	struct hso_serial *serial = tty->driver_data;
 
@@ -1262,7 +1261,7 @@ static int hso_serial_open(struct tty_struct *tty, struct file *filp)
 	if (serial->port.count == 1) {
 		serial->rx_state = RX_IDLE;
 		/* Force default termio settings */
-		_hso_serial_set_termios(tty, NULL);
+		_hso_serial_set_termios(tty);
 		tasklet_setup(&serial->unthrottle_tasklet,
 			      hso_unthrottle_tasklet);
 		result = hso_start_serial_device(serial->parent, GFP_KERNEL);
@@ -1394,7 +1393,7 @@ static void hso_serial_set_termios(struct tty_struct *tty, struct ktermios *old)
 	/* the actual setup */
 	spin_lock_irqsave(&serial->serial_lock, flags);
 	if (serial->port.count)
-		_hso_serial_set_termios(tty, old);
+		_hso_serial_set_termios(tty);
 	else
 		tty->termios = *old;
 	spin_unlock_irqrestore(&serial->serial_lock, flags);
@@ -2353,7 +2352,7 @@ static int remove_net_device(struct hso_device *hso_dev)
 }
 
 /* Frees our network device */
-static void hso_free_net_device(struct hso_device *hso_dev, bool bailout)
+static void hso_free_net_device(struct hso_device *hso_dev)
 {
 	int i;
 	struct hso_net *hso_net = dev2net(hso_dev);
@@ -2376,7 +2375,7 @@ static void hso_free_net_device(struct hso_device *hso_dev, bool bailout)
 	kfree(hso_net->mux_bulk_tx_buf);
 	hso_net->mux_bulk_tx_buf = NULL;
 
-	if (hso_net->net && !bailout)
+	if (hso_net->net)
 		free_netdev(hso_net->net);
 
 	kfree(hso_dev);
@@ -3133,7 +3132,7 @@ static void hso_free_interface(struct usb_interface *interface)
 				rfkill_unregister(rfk);
 				rfkill_destroy(rfk);
 			}
-			hso_free_net_device(network_table[i], false);
+			hso_free_net_device(network_table[i]);
 		}
 	}
 }
diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index 207e59e74935..06e2181e5810 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -443,7 +443,7 @@ static int ipheth_probe(struct usb_interface *intf,
 
 	netdev->netdev_ops = &ipheth_netdev_ops;
 	netdev->watchdog_timeo = IPHETH_TX_TIMEOUT;
-	strcpy(netdev->name, "eth%d");
+	strscpy(netdev->name, "eth%d", sizeof(netdev->name));
 
 	dev = netdev_priv(netdev);
 	dev->udev = udev;
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 6d092d78e0cb..793f8fbe0069 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -46,6 +46,19 @@
 
 #define MAX_RX_FIFO_SIZE		(12 * 1024)
 #define MAX_TX_FIFO_SIZE		(12 * 1024)
+
+#define FLOW_THRESHOLD(n)		((((n) + 511) / 512) & 0x7F)
+#define FLOW_CTRL_THRESHOLD(on, off)	((FLOW_THRESHOLD(on)  << 0) | \
+					 (FLOW_THRESHOLD(off) << 8))
+
+/* Flow control turned on when Rx FIFO level rises above this level (bytes) */
+#define FLOW_ON_SS			9216
+#define FLOW_ON_HS			8704
+
+/* Flow control turned off when Rx FIFO level falls below this level (bytes) */
+#define FLOW_OFF_SS			4096
+#define FLOW_OFF_HS			1024
+
 #define DEFAULT_BURST_CAP_SIZE		(MAX_TX_FIFO_SIZE)
 #define DEFAULT_BULK_IN_DELAY		(0x0800)
 #define MAX_SINGLE_PACKET_SIZE		(9000)
@@ -87,6 +100,12 @@
 /* statistic update interval (mSec) */
 #define STAT_UPDATE_TIMER		(1 * 1000)
 
+/* time to wait for MAC or FCT to stop (jiffies) */
+#define HW_DISABLE_TIMEOUT		(HZ / 10)
+
+/* time to wait between polling MAC or FCT state (ms) */
+#define HW_DISABLE_DELAY_MS		1
+
 /* defines interrupts from interrupt EP */
 #define MAX_INT_EP			(32)
 #define INT_EP_INTEP			(31)
@@ -341,6 +360,7 @@ struct usb_context {
 #define EVENT_DEV_ASLEEP		7
 #define EVENT_DEV_OPEN			8
 #define EVENT_STAT_UPDATE		9
+#define EVENT_DEV_DISCONNECT		10
 
 struct statstage {
 	struct mutex			access_lock;	/* for stats access */
@@ -370,7 +390,6 @@ struct lan78xx_net {
 	struct sk_buff_head	rxq;
 	struct sk_buff_head	txq;
 	struct sk_buff_head	done;
-	struct sk_buff_head	rxq_pause;
 	struct sk_buff_head	txq_pend;
 
 	struct tasklet_struct	bh;
@@ -381,8 +400,9 @@ struct lan78xx_net {
 	struct urb		*urb_intr;
 	struct usb_anchor	deferred;
 
+	struct mutex		dev_mutex; /* serialise open/stop wrt suspend/resume */
 	struct mutex		phy_mutex; /* for phy access */
-	unsigned		pipe_in, pipe_out, pipe_intr;
+	unsigned int		pipe_in, pipe_out, pipe_intr;
 
 	u32			hard_mtu;	/* count any extra framing */
 	size_t			rx_urb_size;	/* size for rx urbs */
@@ -392,8 +412,7 @@ struct lan78xx_net {
 	wait_queue_head_t	*wait;
 	unsigned char		suspend_count;
 
-	unsigned		maxpacket;
-	struct timer_list	delay;
+	unsigned int		maxpacket;
 	struct timer_list	stat_monitor;
 
 	unsigned long		data[5];
@@ -426,9 +445,13 @@ MODULE_PARM_DESC(msg_level, "Override default message level");
 
 static int lan78xx_read_reg(struct lan78xx_net *dev, u32 index, u32 *data)
 {
-	u32 *buf = kmalloc(sizeof(u32), GFP_KERNEL);
+	u32 *buf;
 	int ret;
 
+	if (test_bit(EVENT_DEV_DISCONNECT, &dev->flags))
+		return -ENODEV;
+
+	buf = kmalloc(sizeof(u32), GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -439,7 +462,7 @@ static int lan78xx_read_reg(struct lan78xx_net *dev, u32 index, u32 *data)
 	if (likely(ret >= 0)) {
 		le32_to_cpus(buf);
 		*data = *buf;
-	} else {
+	} else if (net_ratelimit()) {
 		netdev_warn(dev->net,
 			    "Failed to read register index 0x%08x. ret = %d",
 			    index, ret);
@@ -452,9 +475,13 @@ static int lan78xx_read_reg(struct lan78xx_net *dev, u32 index, u32 *data)
 
 static int lan78xx_write_reg(struct lan78xx_net *dev, u32 index, u32 data)
 {
-	u32 *buf = kmalloc(sizeof(u32), GFP_KERNEL);
+	u32 *buf;
 	int ret;
 
+	if (test_bit(EVENT_DEV_DISCONNECT, &dev->flags))
+		return -ENODEV;
+
+	buf = kmalloc(sizeof(u32), GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -465,7 +492,8 @@ static int lan78xx_write_reg(struct lan78xx_net *dev, u32 index, u32 data)
 			      USB_VENDOR_REQUEST_WRITE_REGISTER,
 			      USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
 			      0, index, buf, 4, USB_CTRL_SET_TIMEOUT);
-	if (unlikely(ret < 0)) {
+	if (unlikely(ret < 0) &&
+	    net_ratelimit()) {
 		netdev_warn(dev->net,
 			    "Failed to write register index 0x%08x. ret = %d",
 			    index, ret);
@@ -476,6 +504,26 @@ static int lan78xx_write_reg(struct lan78xx_net *dev, u32 index, u32 data)
 	return ret;
 }
 
+static int lan78xx_update_reg(struct lan78xx_net *dev, u32 reg, u32 mask,
+			      u32 data)
+{
+	int ret;
+	u32 buf;
+
+	ret = lan78xx_read_reg(dev, reg, &buf);
+	if (ret < 0)
+		return ret;
+
+	buf &= ~mask;
+	buf |= (mask & data);
+
+	ret = lan78xx_write_reg(dev, reg, buf);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 static int lan78xx_read_stats(struct lan78xx_net *dev,
 			      struct lan78xx_statstage *data)
 {
@@ -501,7 +549,7 @@ static int lan78xx_read_stats(struct lan78xx_net *dev,
 	if (likely(ret >= 0)) {
 		src = (u32 *)stats;
 		dst = (u32 *)data;
-		for (i = 0; i < sizeof(*stats)/sizeof(u32); i++) {
+		for (i = 0; i < sizeof(*stats) / sizeof(u32); i++) {
 			le32_to_cpus(&src[i]);
 			dst[i] = src[i];
 		}
@@ -515,10 +563,11 @@ static int lan78xx_read_stats(struct lan78xx_net *dev,
 	return ret;
 }
 
-#define check_counter_rollover(struct1, dev_stats, member) {	\
-	if (struct1->member < dev_stats.saved.member)		\
-		dev_stats.rollover_count.member++;		\
-	}
+#define check_counter_rollover(struct1, dev_stats, member)		\
+	do {								\
+		if ((struct1)->member < (dev_stats).saved.member)	\
+			(dev_stats).rollover_count.member++;		\
+	} while (0)
 
 static void lan78xx_check_stat_rollover(struct lan78xx_net *dev,
 					struct lan78xx_statstage *stats)
@@ -844,9 +893,9 @@ static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset,
 
 	for (i = 0; i < length; i++) {
 		lan78xx_write_reg(dev, OTP_ADDR1,
-					((offset + i) >> 8) & OTP_ADDR1_15_11);
+				  ((offset + i) >> 8) & OTP_ADDR1_15_11);
 		lan78xx_write_reg(dev, OTP_ADDR2,
-					((offset + i) & OTP_ADDR2_10_3));
+				  ((offset + i) & OTP_ADDR2_10_3));
 
 		lan78xx_write_reg(dev, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_);
 		lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_);
@@ -900,9 +949,9 @@ static int lan78xx_write_raw_otp(struct lan78xx_net *dev, u32 offset,
 
 	for (i = 0; i < length; i++) {
 		lan78xx_write_reg(dev, OTP_ADDR1,
-					((offset + i) >> 8) & OTP_ADDR1_15_11);
+				  ((offset + i) >> 8) & OTP_ADDR1_15_11);
 		lan78xx_write_reg(dev, OTP_ADDR2,
-					((offset + i) & OTP_ADDR2_10_3));
+				  ((offset + i) & OTP_ADDR2_10_3));
 		lan78xx_write_reg(dev, OTP_PRGM_DATA, data[i]);
 		lan78xx_write_reg(dev, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_);
 		lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_);
@@ -959,7 +1008,7 @@ static int lan78xx_dataport_wait_not_busy(struct lan78xx_net *dev)
 		usleep_range(40, 100);
 	}
 
-	netdev_warn(dev->net, "lan78xx_dataport_wait_not_busy timed out");
+	netdev_warn(dev->net, "%s timed out", __func__);
 
 	return -EIO;
 }
@@ -972,7 +1021,7 @@ static int lan78xx_dataport_write(struct lan78xx_net *dev, u32 ram_select,
 	int i, ret;
 
 	if (usb_autopm_get_interface(dev->intf) < 0)
-			return 0;
+		return 0;
 
 	mutex_lock(&pdata->dataport_mutex);
 
@@ -1045,9 +1094,9 @@ static void lan78xx_deferred_multicast_write(struct work_struct *param)
 	for (i = 1; i < NUM_OF_MAF; i++) {
 		lan78xx_write_reg(dev, MAF_HI(i), 0);
 		lan78xx_write_reg(dev, MAF_LO(i),
-					pdata->pfilter_table[i][1]);
+				  pdata->pfilter_table[i][1]);
 		lan78xx_write_reg(dev, MAF_HI(i),
-					pdata->pfilter_table[i][0]);
+				  pdata->pfilter_table[i][0]);
 	}
 
 	lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl);
@@ -1066,11 +1115,12 @@ static void lan78xx_set_multicast(struct net_device *netdev)
 			    RFE_CTL_DA_PERFECT_ | RFE_CTL_MCAST_HASH_);
 
 	for (i = 0; i < DP_SEL_VHF_HASH_LEN; i++)
-			pdata->mchash_table[i] = 0;
+		pdata->mchash_table[i] = 0;
+
 	/* pfilter_table[0] has own HW address */
 	for (i = 1; i < NUM_OF_MAF; i++) {
-			pdata->pfilter_table[i][0] =
-			pdata->pfilter_table[i][1] = 0;
+		pdata->pfilter_table[i][0] = 0;
+		pdata->pfilter_table[i][1] = 0;
 	}
 
 	pdata->rfe_ctl |= RFE_CTL_BCAST_EN_;
@@ -1134,9 +1184,9 @@ static int lan78xx_update_flowcontrol(struct lan78xx_net *dev, u8 duplex,
 		flow |= FLOW_CR_RX_FCEN_;
 
 	if (dev->udev->speed == USB_SPEED_SUPER)
-		fct_flow = 0x817;
+		fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_SS, FLOW_OFF_SS);
 	else if (dev->udev->speed == USB_SPEED_HIGH)
-		fct_flow = 0x211;
+		fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_HS, FLOW_OFF_HS);
 
 	netif_dbg(dev, link, dev->net, "rx pause %s, tx pause %s",
 		  (cap & FLOW_CTRL_RX ? "enabled" : "disabled"),
@@ -1150,6 +1200,52 @@ static int lan78xx_update_flowcontrol(struct lan78xx_net *dev, u8 duplex,
 	return 0;
 }
 
+static int lan78xx_mac_reset(struct lan78xx_net *dev)
+{
+	unsigned long start_time = jiffies;
+	u32 val;
+	int ret;
+
+	mutex_lock(&dev->phy_mutex);
+
+	/* Resetting the device while there is activity on the MDIO
+	 * bus can result in the MAC interface locking up and not
+	 * completing register access transactions.
+	 */
+	ret = lan78xx_phy_wait_not_busy(dev);
+	if (ret < 0)
+		goto done;
+
+	ret = lan78xx_read_reg(dev, MAC_CR, &val);
+	if (ret < 0)
+		goto done;
+
+	val |= MAC_CR_RST_;
+	ret = lan78xx_write_reg(dev, MAC_CR, val);
+	if (ret < 0)
+		goto done;
+
+	/* Wait for the reset to complete before allowing any further
+	 * MAC register accesses otherwise the MAC may lock up.
+	 */
+	do {
+		ret = lan78xx_read_reg(dev, MAC_CR, &val);
+		if (ret < 0)
+			goto done;
+
+		if (!(val & MAC_CR_RST_)) {
+			ret = 0;
+			goto done;
+		}
+	} while (!time_after(jiffies, start_time + HZ));
+
+	ret = -ETIMEDOUT;
+done:
+	mutex_unlock(&dev->phy_mutex);
+
+	return ret;
+}
+
 static int lan78xx_link_reset(struct lan78xx_net *dev)
 {
 	struct phy_device *phydev = dev->net->phydev;
@@ -1160,7 +1256,7 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
 	/* clear LAN78xx interrupt status */
 	ret = lan78xx_write_reg(dev, INT_STS, INT_STS_PHY_INT_);
 	if (unlikely(ret < 0))
-		return -EIO;
+		return ret;
 
 	mutex_lock(&phydev->lock);
 	phy_read_status(phydev);
@@ -1171,13 +1267,9 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
 		dev->link_on = false;
 
 		/* reset MAC */
-		ret = lan78xx_read_reg(dev, MAC_CR, &buf);
-		if (unlikely(ret < 0))
-			return -EIO;
-		buf |= MAC_CR_RST_;
-		ret = lan78xx_write_reg(dev, MAC_CR, buf);
-		if (unlikely(ret < 0))
-			return -EIO;
+		ret = lan78xx_mac_reset(dev);
+		if (ret < 0)
+			return ret;
 
 		del_timer(&dev->stat_monitor);
 	} else if (link && !dev->link_on) {
@@ -1189,18 +1281,30 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
 			if (ecmd.base.speed == 1000) {
 				/* disable U2 */
 				ret = lan78xx_read_reg(dev, USB_CFG1, &buf);
+				if (ret < 0)
+					return ret;
 				buf &= ~USB_CFG1_DEV_U2_INIT_EN_;
 				ret = lan78xx_write_reg(dev, USB_CFG1, buf);
+				if (ret < 0)
+					return ret;
 				/* enable U1 */
 				ret = lan78xx_read_reg(dev, USB_CFG1, &buf);
+				if (ret < 0)
+					return ret;
 				buf |= USB_CFG1_DEV_U1_INIT_EN_;
 				ret = lan78xx_write_reg(dev, USB_CFG1, buf);
+				if (ret < 0)
+					return ret;
 			} else {
 				/* enable U1 & U2 */
 				ret = lan78xx_read_reg(dev, USB_CFG1, &buf);
+				if (ret < 0)
+					return ret;
 				buf |= USB_CFG1_DEV_U2_INIT_EN_;
 				buf |= USB_CFG1_DEV_U1_INIT_EN_;
 				ret = lan78xx_write_reg(dev, USB_CFG1, buf);
+				if (ret < 0)
+					return ret;
 			}
 		}
 
@@ -1218,6 +1322,8 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
 
 		ret = lan78xx_update_flowcontrol(dev, ecmd.base.duplex, ladv,
 						 radv);
+		if (ret < 0)
+			return ret;
 
 		if (!timer_pending(&dev->stat_monitor)) {
 			dev->delta = 1;
@@ -1228,7 +1334,7 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
 		tasklet_schedule(&dev->bh);
 	}
 
-	return ret;
+	return 0;
 }
 
 /* some work can't be done in tasklets, so we use keventd
@@ -1264,9 +1370,10 @@ static void lan78xx_status(struct lan78xx_net *dev, struct urb *urb)
 			generic_handle_irq(dev->domain_data.phyirq);
 			local_irq_enable();
 		}
-	} else
+	} else {
 		netdev_warn(dev->net,
 			    "unexpected interrupt: 0x%08x\n", intdata);
+	}
 }
 
 static int lan78xx_ethtool_get_eeprom_len(struct net_device *netdev)
@@ -1355,7 +1462,7 @@ static void lan78xx_get_wol(struct net_device *netdev,
 	struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]);
 
 	if (usb_autopm_get_interface(dev->intf) < 0)
-			return;
+		return;
 
 	ret = lan78xx_read_reg(dev, USB_CFG0, &buf);
 	if (unlikely(ret < 0)) {
@@ -2003,7 +2110,7 @@ static int lan8835_fixup(struct phy_device *phydev)
 
 	/* RGMII MAC TXC Delay Enable */
 	lan78xx_write_reg(dev, MAC_RGMII_ID,
-				MAC_RGMII_ID_TXC_DELAY_EN_);
+			  MAC_RGMII_ID_TXC_DELAY_EN_);
 
 	/* RGMII TX DLL Tune Adjust */
 	lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00);
@@ -2267,11 +2374,16 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu)
 	int ll_mtu = new_mtu + netdev->hard_header_len;
 	int old_hard_mtu = dev->hard_mtu;
 	int old_rx_urb_size = dev->rx_urb_size;
+	int ret;
 
 	/* no second zero-length packet read wanted after mtu-sized packets */
 	if ((ll_mtu % dev->maxpacket) == 0)
 		return -EDOM;
 
+	ret = usb_autopm_get_interface(dev->intf);
+	if (ret < 0)
+		return ret;
+
 	lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN);
 
 	netdev->mtu = new_mtu;
@@ -2287,6 +2399,8 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu)
 		}
 	}
 
+	usb_autopm_put_interface(dev->intf);
+
 	return 0;
 }
 
@@ -2443,26 +2557,186 @@ static void lan78xx_init_ltm(struct lan78xx_net *dev)
 	lan78xx_write_reg(dev, LTM_INACTIVE1, regs[5]);
 }
 
+static int lan78xx_start_hw(struct lan78xx_net *dev, u32 reg, u32 hw_enable)
+{
+	return lan78xx_update_reg(dev, reg, hw_enable, hw_enable);
+}
+
+static int lan78xx_stop_hw(struct lan78xx_net *dev, u32 reg, u32 hw_enabled,
+			   u32 hw_disabled)
+{
+	unsigned long timeout;
+	bool stopped = true;
+	int ret;
+	u32 buf;
+
+	/* Stop the h/w block (if not already stopped) */
+
+	ret = lan78xx_read_reg(dev, reg, &buf);
+	if (ret < 0)
+		return ret;
+
+	if (buf & hw_enabled) {
+		buf &= ~hw_enabled;
+
+		ret = lan78xx_write_reg(dev, reg, buf);
+		if (ret < 0)
+			return ret;
+
+		stopped = false;
+		timeout = jiffies + HW_DISABLE_TIMEOUT;
+		do  {
+			ret = lan78xx_read_reg(dev, reg, &buf);
+			if (ret < 0)
+				return ret;
+
+			if (buf & hw_disabled)
+				stopped = true;
+			else
+				msleep(HW_DISABLE_DELAY_MS);
+		} while (!stopped && !time_after(jiffies, timeout));
+	}
+
+	ret = stopped ? 0 : -ETIME;
+
+	return ret;
+}
+
+static int lan78xx_flush_fifo(struct lan78xx_net *dev, u32 reg, u32 fifo_flush)
+{
+	return lan78xx_update_reg(dev, reg, fifo_flush, fifo_flush);
+}
+
+static int lan78xx_start_tx_path(struct lan78xx_net *dev)
+{
+	int ret;
+
+	netif_dbg(dev, drv, dev->net, "start tx path");
+
+	/* Start the MAC transmitter */
+
+	ret = lan78xx_start_hw(dev, MAC_TX, MAC_TX_TXEN_);
+	if (ret < 0)
+		return ret;
+
+	/* Start the Tx FIFO */
+
+	ret = lan78xx_start_hw(dev, FCT_TX_CTL, FCT_TX_CTL_EN_);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int lan78xx_stop_tx_path(struct lan78xx_net *dev)
+{
+	int ret;
+
+	netif_dbg(dev, drv, dev->net, "stop tx path");
+
+	/* Stop the Tx FIFO */
+
+	ret = lan78xx_stop_hw(dev, FCT_TX_CTL, FCT_TX_CTL_EN_, FCT_TX_CTL_DIS_);
+	if (ret < 0)
+		return ret;
+
+	/* Stop the MAC transmitter */
+
+	ret = lan78xx_stop_hw(dev, MAC_TX, MAC_TX_TXEN_, MAC_TX_TXD_);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+/* The caller must ensure the Tx path is stopped before calling
+ * lan78xx_flush_tx_fifo().
+ */
+static int lan78xx_flush_tx_fifo(struct lan78xx_net *dev)
+{
+	return lan78xx_flush_fifo(dev, FCT_TX_CTL, FCT_TX_CTL_RST_);
+}
+
+static int lan78xx_start_rx_path(struct lan78xx_net *dev)
+{
+	int ret;
+
+	netif_dbg(dev, drv, dev->net, "start rx path");
+
+	/* Start the Rx FIFO */
+
+	ret = lan78xx_start_hw(dev, FCT_RX_CTL, FCT_RX_CTL_EN_);
+	if (ret < 0)
+		return ret;
+
+	/* Start the MAC receiver*/
+
+	ret = lan78xx_start_hw(dev, MAC_RX, MAC_RX_RXEN_);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int lan78xx_stop_rx_path(struct lan78xx_net *dev)
+{
+	int ret;
+
+	netif_dbg(dev, drv, dev->net, "stop rx path");
+
+	/* Stop the MAC receiver */
+
+	ret = lan78xx_stop_hw(dev, MAC_RX, MAC_RX_RXEN_, MAC_RX_RXD_);
+	if (ret < 0)
+		return ret;
+
+	/* Stop the Rx FIFO */
+
+	ret = lan78xx_stop_hw(dev, FCT_RX_CTL, FCT_RX_CTL_EN_, FCT_RX_CTL_DIS_);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+/* The caller must ensure the Rx path is stopped before calling
+ * lan78xx_flush_rx_fifo().
+ */
+static int lan78xx_flush_rx_fifo(struct lan78xx_net *dev)
+{
+	return lan78xx_flush_fifo(dev, FCT_RX_CTL, FCT_RX_CTL_RST_);
+}
+
 static int lan78xx_reset(struct lan78xx_net *dev)
 {
 	struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]);
-	u32 buf;
-	int ret = 0;
 	unsigned long timeout;
+	int ret;
+	u32 buf;
 	u8 sig;
 
 	ret = lan78xx_read_reg(dev, HW_CFG, &buf);
+	if (ret < 0)
+		return ret;
+
 	buf |= HW_CFG_LRST_;
+
 	ret = lan78xx_write_reg(dev, HW_CFG, buf);
+	if (ret < 0)
+		return ret;
 
 	timeout = jiffies + HZ;
 	do {
 		mdelay(1);
 		ret = lan78xx_read_reg(dev, HW_CFG, &buf);
+		if (ret < 0)
+			return ret;
+
 		if (time_after(jiffies, timeout)) {
 			netdev_warn(dev->net,
 				    "timeout on completion of LiteReset");
-			return -EIO;
+			ret = -ETIMEDOUT;
+			return ret;
 		}
 	} while (buf & HW_CFG_LRST_);
 
@@ -2470,13 +2744,22 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 
 	/* save DEVID for later usage */
 	ret = lan78xx_read_reg(dev, ID_REV, &buf);
+	if (ret < 0)
+		return ret;
+
 	dev->chipid = (buf & ID_REV_CHIP_ID_MASK_) >> 16;
 	dev->chiprev = buf & ID_REV_CHIP_REV_MASK_;
 
 	/* Respond to the IN token with a NAK */
 	ret = lan78xx_read_reg(dev, USB_CFG0, &buf);
+	if (ret < 0)
+		return ret;
+
 	buf |= USB_CFG_BIR_;
+
 	ret = lan78xx_write_reg(dev, USB_CFG0, buf);
+	if (ret < 0)
+		return ret;
 
 	/* Init LTM */
 	lan78xx_init_ltm(dev);
@@ -2499,53 +2782,105 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 	}
 
 	ret = lan78xx_write_reg(dev, BURST_CAP, buf);
+	if (ret < 0)
+		return ret;
+
 	ret = lan78xx_write_reg(dev, BULK_IN_DLY, DEFAULT_BULK_IN_DELAY);
+	if (ret < 0)
+		return ret;
 
 	ret = lan78xx_read_reg(dev, HW_CFG, &buf);
+	if (ret < 0)
+		return ret;
+
 	buf |= HW_CFG_MEF_;
+
 	ret = lan78xx_write_reg(dev, HW_CFG, buf);
+	if (ret < 0)
+		return ret;
 
 	ret = lan78xx_read_reg(dev, USB_CFG0, &buf);
+	if (ret < 0)
+		return ret;
+
 	buf |= USB_CFG_BCE_;
+
 	ret = lan78xx_write_reg(dev, USB_CFG0, buf);
+	if (ret < 0)
+		return ret;
 
 	/* set FIFO sizes */
 	buf = (MAX_RX_FIFO_SIZE - 512) / 512;
+
 	ret = lan78xx_write_reg(dev, FCT_RX_FIFO_END, buf);
+	if (ret < 0)
+		return ret;
 
 	buf = (MAX_TX_FIFO_SIZE - 512) / 512;
+
 	ret = lan78xx_write_reg(dev, FCT_TX_FIFO_END, buf);
+	if (ret < 0)
+		return ret;
 
 	ret = lan78xx_write_reg(dev, INT_STS, INT_STS_CLEAR_ALL_);
+	if (ret < 0)
+		return ret;
+
 	ret = lan78xx_write_reg(dev, FLOW, 0);
+	if (ret < 0)
+		return ret;
+
 	ret = lan78xx_write_reg(dev, FCT_FLOW, 0);
+	if (ret < 0)
+		return ret;
 
 	/* Don't need rfe_ctl_lock during initialisation */
 	ret = lan78xx_read_reg(dev, RFE_CTL, &pdata->rfe_ctl);
+	if (ret < 0)
+		return ret;
+
 	pdata->rfe_ctl |= RFE_CTL_BCAST_EN_ | RFE_CTL_DA_PERFECT_;
+
 	ret = lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl);
+	if (ret < 0)
+		return ret;
 
 	/* Enable or disable checksum offload engines */
-	lan78xx_set_features(dev->net, dev->net->features);
+	ret = lan78xx_set_features(dev->net, dev->net->features);
+	if (ret < 0)
+		return ret;
 
 	lan78xx_set_multicast(dev->net);
 
 	/* reset PHY */
 	ret = lan78xx_read_reg(dev, PMT_CTL, &buf);
+	if (ret < 0)
+		return ret;
+
 	buf |= PMT_CTL_PHY_RST_;
+
 	ret = lan78xx_write_reg(dev, PMT_CTL, buf);
+	if (ret < 0)
+		return ret;
 
 	timeout = jiffies + HZ;
 	do {
 		mdelay(1);
 		ret = lan78xx_read_reg(dev, PMT_CTL, &buf);
+		if (ret < 0)
+			return ret;
+
 		if (time_after(jiffies, timeout)) {
 			netdev_warn(dev->net, "timeout waiting for PHY Reset");
-			return -EIO;
+			ret = -ETIMEDOUT;
+			return ret;
 		}
 	} while ((buf & PMT_CTL_PHY_RST_) || !(buf & PMT_CTL_READY_));
 
 	ret = lan78xx_read_reg(dev, MAC_CR, &buf);
+	if (ret < 0)
+		return ret;
+
 	/* LAN7801 only has RGMII mode */
 	if (dev->chipid == ID_REV_CHIP_ID_7801_)
 		buf &= ~MAC_CR_GMII_EN_;
@@ -2559,27 +2894,13 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 		}
 	}
 	ret = lan78xx_write_reg(dev, MAC_CR, buf);
-
-	ret = lan78xx_read_reg(dev, MAC_TX, &buf);
-	buf |= MAC_TX_TXEN_;
-	ret = lan78xx_write_reg(dev, MAC_TX, buf);
-
-	ret = lan78xx_read_reg(dev, FCT_TX_CTL, &buf);
-	buf |= FCT_TX_CTL_EN_;
-	ret = lan78xx_write_reg(dev, FCT_TX_CTL, buf);
+	if (ret < 0)
+		return ret;
 
 	ret = lan78xx_set_rx_max_frame_length(dev,
 					      dev->net->mtu + VLAN_ETH_HLEN);
 
-	ret = lan78xx_read_reg(dev, MAC_RX, &buf);
-	buf |= MAC_RX_RXEN_;
-	ret = lan78xx_write_reg(dev, MAC_RX, buf);
-
-	ret = lan78xx_read_reg(dev, FCT_RX_CTL, &buf);
-	buf |= FCT_RX_CTL_EN_;
-	ret = lan78xx_write_reg(dev, FCT_RX_CTL, buf);
-
-	return 0;
+	return ret;
 }
 
 static void lan78xx_init_stats(struct lan78xx_net *dev)
@@ -2613,9 +2934,13 @@ static int lan78xx_open(struct net_device *net)
 	struct lan78xx_net *dev = netdev_priv(net);
 	int ret;
 
+	netif_dbg(dev, ifup, dev->net, "open device");
+
 	ret = usb_autopm_get_interface(dev->intf);
 	if (ret < 0)
-		goto out;
+		return ret;
+
+	mutex_lock(&dev->dev_mutex);
 
 	phy_start(net->phydev);
 
@@ -2631,6 +2956,20 @@ static int lan78xx_open(struct net_device *net)
 		}
 	}
 
+	ret = lan78xx_flush_rx_fifo(dev);
+	if (ret < 0)
+		goto done;
+	ret = lan78xx_flush_tx_fifo(dev);
+	if (ret < 0)
+		goto done;
+
+	ret = lan78xx_start_tx_path(dev);
+	if (ret < 0)
+		goto done;
+	ret = lan78xx_start_rx_path(dev);
+	if (ret < 0)
+		goto done;
+
 	lan78xx_init_stats(dev);
 
 	set_bit(EVENT_DEV_OPEN, &dev->flags);
@@ -2641,9 +2980,10 @@ static int lan78xx_open(struct net_device *net)
 
 	lan78xx_defer_kevent(dev, EVENT_LINK_RESET);
 done:
+	mutex_unlock(&dev->dev_mutex);
+
 	usb_autopm_put_interface(dev->intf);
 
-out:
 	return ret;
 }
 
@@ -2660,53 +3000,74 @@ static void lan78xx_terminate_urbs(struct lan78xx_net *dev)
 	temp = unlink_urbs(dev, &dev->txq) + unlink_urbs(dev, &dev->rxq);
 
 	/* maybe wait for deletions to finish. */
-	while (!skb_queue_empty(&dev->rxq) &&
-	       !skb_queue_empty(&dev->txq) &&
-	       !skb_queue_empty(&dev->done)) {
+	while (!skb_queue_empty(&dev->rxq) ||
+	       !skb_queue_empty(&dev->txq)) {
 		schedule_timeout(msecs_to_jiffies(UNLINK_TIMEOUT_MS));
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		netif_dbg(dev, ifdown, dev->net,
-			  "waited for %d urb completions\n", temp);
+			  "waited for %d urb completions", temp);
 	}
 	set_current_state(TASK_RUNNING);
 	dev->wait = NULL;
 	remove_wait_queue(&unlink_wakeup, &wait);
+
+	while (!skb_queue_empty(&dev->done)) {
+		struct skb_data *entry;
+		struct sk_buff *skb;
+
+		skb = skb_dequeue(&dev->done);
+		entry = (struct skb_data *)(skb->cb);
+		usb_free_urb(entry->urb);
+		dev_kfree_skb(skb);
+	}
 }
 
 static int lan78xx_stop(struct net_device *net)
 {
 	struct lan78xx_net *dev = netdev_priv(net);
 
+	netif_dbg(dev, ifup, dev->net, "stop device");
+
+	mutex_lock(&dev->dev_mutex);
+
 	if (timer_pending(&dev->stat_monitor))
 		del_timer_sync(&dev->stat_monitor);
 
-	if (net->phydev)
-		phy_stop(net->phydev);
-
 	clear_bit(EVENT_DEV_OPEN, &dev->flags);
 	netif_stop_queue(net);
+	tasklet_kill(&dev->bh);
+
+	lan78xx_terminate_urbs(dev);
 
 	netif_info(dev, ifdown, dev->net,
 		   "stop stats: rx/tx %lu/%lu, errs %lu/%lu\n",
 		   net->stats.rx_packets, net->stats.tx_packets,
 		   net->stats.rx_errors, net->stats.tx_errors);
 
-	lan78xx_terminate_urbs(dev);
+	/* ignore errors that occur stopping the Tx and Rx data paths */
+	lan78xx_stop_tx_path(dev);
+	lan78xx_stop_rx_path(dev);
 
-	usb_kill_urb(dev->urb_intr);
+	if (net->phydev)
+		phy_stop(net->phydev);
 
-	skb_queue_purge(&dev->rxq_pause);
+	usb_kill_urb(dev->urb_intr);
 
 	/* deferred work (task, timer, softirq) must also stop.
 	 * can't flush_scheduled_work() until we drop rtnl (later),
 	 * else workers could deadlock; so make workers a NOP.
 	 */
-	dev->flags = 0;
+	clear_bit(EVENT_TX_HALT, &dev->flags);
+	clear_bit(EVENT_RX_HALT, &dev->flags);
+	clear_bit(EVENT_LINK_RESET, &dev->flags);
+	clear_bit(EVENT_STAT_UPDATE, &dev->flags);
+
 	cancel_delayed_work_sync(&dev->wq);
-	tasklet_kill(&dev->bh);
 
 	usb_autopm_put_interface(dev->intf);
 
+	mutex_unlock(&dev->dev_mutex);
+
 	return 0;
 }
 
@@ -2795,16 +3156,23 @@ static void tx_complete(struct urb *urb)
 		/* software-driven interface shutdown */
 		case -ECONNRESET:
 		case -ESHUTDOWN:
+			netif_dbg(dev, tx_err, dev->net,
+				  "tx err interface gone %d\n",
+				  entry->urb->status);
 			break;
 
 		case -EPROTO:
 		case -ETIME:
 		case -EILSEQ:
 			netif_stop_queue(dev->net);
+			netif_dbg(dev, tx_err, dev->net,
+				  "tx err queue stopped %d\n",
+				  entry->urb->status);
 			break;
 		default:
 			netif_dbg(dev, tx_err, dev->net,
-				  "tx err %d\n", entry->urb->status);
+				  "unknown tx err %d\n",
+				  entry->urb->status);
 			break;
 		}
 	}
@@ -2829,6 +3197,9 @@ lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net)
 	struct lan78xx_net *dev = netdev_priv(net);
 	struct sk_buff *skb2 = NULL;
 
+	if (test_bit(EVENT_DEV_ASLEEP, &dev->flags))
+		schedule_delayed_work(&dev->wq, 0);
+
 	if (skb) {
 		skb_tx_timestamp(skb);
 		skb2 = lan78xx_tx_prep(dev, skb, GFP_ATOMIC);
@@ -2988,11 +3359,6 @@ static void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb)
 {
 	int status;
 
-	if (test_bit(EVENT_RX_PAUSED, &dev->flags)) {
-		skb_queue_tail(&dev->rxq_pause, skb);
-		return;
-	}
-
 	dev->net->stats.rx_packets++;
 	dev->net->stats.rx_bytes += skb->len;
 
@@ -3140,6 +3506,7 @@ static int rx_submit(struct lan78xx_net *dev, struct urb *urb, gfp_t flags)
 			lan78xx_defer_kevent(dev, EVENT_RX_HALT);
 			break;
 		case -ENODEV:
+		case -ENOENT:
 			netif_dbg(dev, ifdown, dev->net, "device gone\n");
 			netif_device_detach(dev->net);
 			break;
@@ -3340,6 +3707,12 @@ gso_skb:
 		lan78xx_defer_kevent(dev, EVENT_TX_HALT);
 		usb_autopm_put_interface_async(dev->intf);
 		break;
+	case -ENODEV:
+	case -ENOENT:
+		netif_dbg(dev, tx_err, dev->net,
+			  "tx: submit urb err %d (disconnected?)", ret);
+		netif_device_detach(dev->net);
+		break;
 	default:
 		usb_autopm_put_interface_async(dev->intf);
 		netif_dbg(dev, tx_err, dev->net,
@@ -3356,9 +3729,10 @@ drop:
 		if (skb)
 			dev_kfree_skb_any(skb);
 		usb_free_urb(urb);
-	} else
+	} else {
 		netif_dbg(dev, tx_queued, dev->net,
 			  "> tx, len %d, type 0x%x\n", length, skb->protocol);
+	}
 }
 
 static void lan78xx_rx_bh(struct lan78xx_net *dev)
@@ -3421,8 +3795,7 @@ static void lan78xx_bh(struct tasklet_struct *t)
 		if (!skb_queue_empty(&dev->txq_pend))
 			lan78xx_tx_bh(dev);
 
-		if (!timer_pending(&dev->delay) &&
-		    !test_bit(EVENT_RX_HALT, &dev->flags))
+		if (!test_bit(EVENT_RX_HALT, &dev->flags))
 			lan78xx_rx_bh(dev);
 	}
 }
@@ -3434,18 +3807,20 @@ static void lan78xx_delayedwork(struct work_struct *work)
 
 	dev = container_of(work, struct lan78xx_net, wq.work);
 
+	if (test_bit(EVENT_DEV_DISCONNECT, &dev->flags))
+		return;
+
+	if (usb_autopm_get_interface(dev->intf) < 0)
+		return;
+
 	if (test_bit(EVENT_TX_HALT, &dev->flags)) {
 		unlink_urbs(dev, &dev->txq);
-		status = usb_autopm_get_interface(dev->intf);
-		if (status < 0)
-			goto fail_pipe;
+
 		status = usb_clear_halt(dev->udev, dev->pipe_out);
-		usb_autopm_put_interface(dev->intf);
 		if (status < 0 &&
 		    status != -EPIPE &&
 		    status != -ESHUTDOWN) {
 			if (netif_msg_tx_err(dev))
-fail_pipe:
 				netdev_err(dev->net,
 					   "can't clear tx halt, status %d\n",
 					   status);
@@ -3455,18 +3830,14 @@ fail_pipe:
 				netif_wake_queue(dev->net);
 		}
 	}
+
 	if (test_bit(EVENT_RX_HALT, &dev->flags)) {
 		unlink_urbs(dev, &dev->rxq);
-		status = usb_autopm_get_interface(dev->intf);
-		if (status < 0)
-				goto fail_halt;
 		status = usb_clear_halt(dev->udev, dev->pipe_in);
-		usb_autopm_put_interface(dev->intf);
 		if (status < 0 &&
 		    status != -EPIPE &&
 		    status != -ESHUTDOWN) {
 			if (netif_msg_rx_err(dev))
-fail_halt:
 				netdev_err(dev->net,
 					   "can't clear rx halt, status %d\n",
 					   status);
@@ -3480,16 +3851,9 @@ fail_halt:
 		int ret = 0;
 
 		clear_bit(EVENT_LINK_RESET, &dev->flags);
-		status = usb_autopm_get_interface(dev->intf);
-		if (status < 0)
-			goto skip_reset;
 		if (lan78xx_link_reset(dev) < 0) {
-			usb_autopm_put_interface(dev->intf);
-skip_reset:
 			netdev_info(dev->net, "link reset failed (%d)\n",
 				    ret);
-		} else {
-			usb_autopm_put_interface(dev->intf);
 		}
 	}
 
@@ -3503,6 +3867,8 @@ skip_reset:
 
 		dev->delta = min((dev->delta * 2), 50);
 	}
+
+	usb_autopm_put_interface(dev->intf);
 }
 
 static void intr_complete(struct urb *urb)
@@ -3518,6 +3884,7 @@ static void intr_complete(struct urb *urb)
 
 	/* software-driven interface shutdown */
 	case -ENOENT:			/* urb killed */
+	case -ENODEV:			/* hardware gone */
 	case -ESHUTDOWN:		/* hardware gone */
 		netif_dbg(dev, ifdown, dev->net,
 			  "intr shutdown, code %d\n", status);
@@ -3531,14 +3898,29 @@ static void intr_complete(struct urb *urb)
 		break;
 	}
 
-	if (!netif_running(dev->net))
+	if (!netif_device_present(dev->net) ||
+	    !netif_running(dev->net)) {
+		netdev_warn(dev->net, "not submitting new status URB");
 		return;
+	}
 
 	memset(urb->transfer_buffer, 0, urb->transfer_buffer_length);
 	status = usb_submit_urb(urb, GFP_ATOMIC);
-	if (status != 0)
+
+	switch (status) {
+	case  0:
+		break;
+	case -ENODEV:
+	case -ENOENT:
+		netif_dbg(dev, timer, dev->net,
+			  "intr resubmit %d (disconnect?)", status);
+		netif_device_detach(dev->net);
+		break;
+	default:
 		netif_err(dev, timer, dev->net,
 			  "intr resubmit --> %d\n", status);
+		break;
+	}
 }
 
 static void lan78xx_disconnect(struct usb_interface *intf)
@@ -3553,8 +3935,15 @@ static void lan78xx_disconnect(struct usb_interface *intf)
 	if (!dev)
 		return;
 
+	set_bit(EVENT_DEV_DISCONNECT, &dev->flags);
+
 	udev = interface_to_usbdev(intf);
 	net = dev->net;
+
+	unregister_netdev(net);
+
+	cancel_delayed_work_sync(&dev->wq);
+
 	phydev = net->phydev;
 
 	phy_unregister_fixup_for_uid(PHY_KSZ9031RNX, 0xfffffff0);
@@ -3565,12 +3954,11 @@ static void lan78xx_disconnect(struct usb_interface *intf)
 	if (phy_is_pseudo_fixed_link(phydev))
 		fixed_phy_unregister(phydev);
 
-	unregister_netdev(net);
-
-	cancel_delayed_work_sync(&dev->wq);
-
 	usb_scuttle_anchored_urbs(&dev->deferred);
 
+	if (timer_pending(&dev->stat_monitor))
+		del_timer_sync(&dev->stat_monitor);
+
 	lan78xx_unbind(dev, intf);
 
 	usb_kill_urb(dev->urb_intr);
@@ -3609,7 +3997,7 @@ static const struct net_device_ops lan78xx_netdev_ops = {
 	.ndo_change_mtu		= lan78xx_change_mtu,
 	.ndo_set_mac_address	= lan78xx_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_set_rx_mode	= lan78xx_set_multicast,
 	.ndo_set_features	= lan78xx_set_features,
 	.ndo_vlan_rx_add_vid	= lan78xx_vlan_rx_add_vid,
@@ -3632,8 +4020,8 @@ static int lan78xx_probe(struct usb_interface *intf,
 	struct net_device *netdev;
 	struct usb_device *udev;
 	int ret;
-	unsigned maxp;
-	unsigned period;
+	unsigned int maxp;
+	unsigned int period;
 	u8 *buf = NULL;
 
 	udev = interface_to_usbdev(intf);
@@ -3659,9 +4047,9 @@ static int lan78xx_probe(struct usb_interface *intf,
 	skb_queue_head_init(&dev->rxq);
 	skb_queue_head_init(&dev->txq);
 	skb_queue_head_init(&dev->done);
-	skb_queue_head_init(&dev->rxq_pause);
 	skb_queue_head_init(&dev->txq_pend);
 	mutex_init(&dev->phy_mutex);
+	mutex_init(&dev->dev_mutex);
 
 	tasklet_setup(&dev->bh, lan78xx_bh);
 	INIT_DELAYED_WORK(&dev->wq, lan78xx_delayedwork);
@@ -3798,37 +4186,119 @@ static u16 lan78xx_wakeframe_crc16(const u8 *buf, int len)
 	return crc;
 }
 
-static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol)
+static int lan78xx_set_auto_suspend(struct lan78xx_net *dev)
 {
 	u32 buf;
-	int mask_index;
-	u16 crc;
-	u32 temp_wucsr;
-	u32 temp_pmt_ctl;
+	int ret;
+
+	ret = lan78xx_stop_tx_path(dev);
+	if (ret < 0)
+		return ret;
+
+	ret = lan78xx_stop_rx_path(dev);
+	if (ret < 0)
+		return ret;
+
+	/* auto suspend (selective suspend) */
+
+	ret = lan78xx_write_reg(dev, WUCSR, 0);
+	if (ret < 0)
+		return ret;
+	ret = lan78xx_write_reg(dev, WUCSR2, 0);
+	if (ret < 0)
+		return ret;
+	ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL);
+	if (ret < 0)
+		return ret;
+
+	/* set goodframe wakeup */
+
+	ret = lan78xx_read_reg(dev, WUCSR, &buf);
+	if (ret < 0)
+		return ret;
+
+	buf |= WUCSR_RFE_WAKE_EN_;
+	buf |= WUCSR_STORE_WAKE_;
+
+	ret = lan78xx_write_reg(dev, WUCSR, buf);
+	if (ret < 0)
+		return ret;
+
+	ret = lan78xx_read_reg(dev, PMT_CTL, &buf);
+	if (ret < 0)
+		return ret;
+
+	buf &= ~PMT_CTL_RES_CLR_WKP_EN_;
+	buf |= PMT_CTL_RES_CLR_WKP_STS_;
+	buf |= PMT_CTL_PHY_WAKE_EN_;
+	buf |= PMT_CTL_WOL_EN_;
+	buf &= ~PMT_CTL_SUS_MODE_MASK_;
+	buf |= PMT_CTL_SUS_MODE_3_;
+
+	ret = lan78xx_write_reg(dev, PMT_CTL, buf);
+	if (ret < 0)
+		return ret;
+
+	ret = lan78xx_read_reg(dev, PMT_CTL, &buf);
+	if (ret < 0)
+		return ret;
+
+	buf |= PMT_CTL_WUPS_MASK_;
+
+	ret = lan78xx_write_reg(dev, PMT_CTL, buf);
+	if (ret < 0)
+		return ret;
+
+	ret = lan78xx_start_rx_path(dev);
+
+	return ret;
+}
+
+static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol)
+{
 	const u8 ipv4_multicast[3] = { 0x01, 0x00, 0x5E };
 	const u8 ipv6_multicast[3] = { 0x33, 0x33 };
 	const u8 arp_type[2] = { 0x08, 0x06 };
+	u32 temp_pmt_ctl;
+	int mask_index;
+	u32 temp_wucsr;
+	u32 buf;
+	u16 crc;
+	int ret;
 
-	lan78xx_read_reg(dev, MAC_TX, &buf);
-	buf &= ~MAC_TX_TXEN_;
-	lan78xx_write_reg(dev, MAC_TX, buf);
-	lan78xx_read_reg(dev, MAC_RX, &buf);
-	buf &= ~MAC_RX_RXEN_;
-	lan78xx_write_reg(dev, MAC_RX, buf);
+	ret = lan78xx_stop_tx_path(dev);
+	if (ret < 0)
+		return ret;
+	ret = lan78xx_stop_rx_path(dev);
+	if (ret < 0)
+		return ret;
 
-	lan78xx_write_reg(dev, WUCSR, 0);
-	lan78xx_write_reg(dev, WUCSR2, 0);
-	lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL);
+	ret = lan78xx_write_reg(dev, WUCSR, 0);
+	if (ret < 0)
+		return ret;
+	ret = lan78xx_write_reg(dev, WUCSR2, 0);
+	if (ret < 0)
+		return ret;
+	ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL);
+	if (ret < 0)
+		return ret;
 
 	temp_wucsr = 0;
 
 	temp_pmt_ctl = 0;
-	lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl);
+
+	ret = lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl);
+	if (ret < 0)
+		return ret;
+
 	temp_pmt_ctl &= ~PMT_CTL_RES_CLR_WKP_EN_;
 	temp_pmt_ctl |= PMT_CTL_RES_CLR_WKP_STS_;
 
-	for (mask_index = 0; mask_index < NUM_OF_WUF_CFG; mask_index++)
-		lan78xx_write_reg(dev, WUF_CFG(mask_index), 0);
+	for (mask_index = 0; mask_index < NUM_OF_WUF_CFG; mask_index++) {
+		ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), 0);
+		if (ret < 0)
+			return ret;
+	}
 
 	mask_index = 0;
 	if (wol & WAKE_PHY) {
@@ -3857,30 +4327,52 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol)
 
 		/* set WUF_CFG & WUF_MASK for IPv4 Multicast */
 		crc = lan78xx_wakeframe_crc16(ipv4_multicast, 3);
-		lan78xx_write_reg(dev, WUF_CFG(mask_index),
+		ret = lan78xx_write_reg(dev, WUF_CFG(mask_index),
 					WUF_CFGX_EN_ |
 					WUF_CFGX_TYPE_MCAST_ |
 					(0 << WUF_CFGX_OFFSET_SHIFT_) |
 					(crc & WUF_CFGX_CRC16_MASK_));
+		if (ret < 0)
+			return ret;
+
+		ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7);
+		if (ret < 0)
+			return ret;
+		ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0);
+		if (ret < 0)
+			return ret;
+		ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0);
+		if (ret < 0)
+			return ret;
+		ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0);
+		if (ret < 0)
+			return ret;
 
-		lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7);
-		lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0);
-		lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0);
-		lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0);
 		mask_index++;
 
 		/* for IPv6 Multicast */
 		crc = lan78xx_wakeframe_crc16(ipv6_multicast, 2);
-		lan78xx_write_reg(dev, WUF_CFG(mask_index),
+		ret = lan78xx_write_reg(dev, WUF_CFG(mask_index),
 					WUF_CFGX_EN_ |
 					WUF_CFGX_TYPE_MCAST_ |
 					(0 << WUF_CFGX_OFFSET_SHIFT_) |
 					(crc & WUF_CFGX_CRC16_MASK_));
+		if (ret < 0)
+			return ret;
+
+		ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3);
+		if (ret < 0)
+			return ret;
+		ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0);
+		if (ret < 0)
+			return ret;
+		ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0);
+		if (ret < 0)
+			return ret;
+		ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0);
+		if (ret < 0)
+			return ret;
 
-		lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3);
-		lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0);
-		lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0);
-		lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0);
 		mask_index++;
 
 		temp_pmt_ctl |= PMT_CTL_WOL_EN_;
@@ -3901,16 +4393,27 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol)
 		 * for packettype (offset 12,13) = ARP (0x0806)
 		 */
 		crc = lan78xx_wakeframe_crc16(arp_type, 2);
-		lan78xx_write_reg(dev, WUF_CFG(mask_index),
+		ret = lan78xx_write_reg(dev, WUF_CFG(mask_index),
 					WUF_CFGX_EN_ |
 					WUF_CFGX_TYPE_ALL_ |
 					(0 << WUF_CFGX_OFFSET_SHIFT_) |
 					(crc & WUF_CFGX_CRC16_MASK_));
+		if (ret < 0)
+			return ret;
+
+		ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000);
+		if (ret < 0)
+			return ret;
+		ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0);
+		if (ret < 0)
+			return ret;
+		ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0);
+		if (ret < 0)
+			return ret;
+		ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0);
+		if (ret < 0)
+			return ret;
 
-		lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000);
-		lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0);
-		lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0);
-		lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0);
 		mask_index++;
 
 		temp_pmt_ctl |= PMT_CTL_WOL_EN_;
@@ -3918,7 +4421,9 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol)
 		temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_;
 	}
 
-	lan78xx_write_reg(dev, WUCSR, temp_wucsr);
+	ret = lan78xx_write_reg(dev, WUCSR, temp_wucsr);
+	if (ret < 0)
+		return ret;
 
 	/* when multiple WOL bits are set */
 	if (hweight_long((unsigned long)wol) > 1) {
@@ -3926,33 +4431,45 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol)
 		temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_;
 		temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_;
 	}
-	lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl);
+	ret = lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl);
+	if (ret < 0)
+		return ret;
 
 	/* clear WUPS */
-	lan78xx_read_reg(dev, PMT_CTL, &buf);
+	ret = lan78xx_read_reg(dev, PMT_CTL, &buf);
+	if (ret < 0)
+		return ret;
+
 	buf |= PMT_CTL_WUPS_MASK_;
-	lan78xx_write_reg(dev, PMT_CTL, buf);
 
-	lan78xx_read_reg(dev, MAC_RX, &buf);
-	buf |= MAC_RX_RXEN_;
-	lan78xx_write_reg(dev, MAC_RX, buf);
+	ret = lan78xx_write_reg(dev, PMT_CTL, buf);
+	if (ret < 0)
+		return ret;
 
-	return 0;
+	ret = lan78xx_start_rx_path(dev);
+
+	return ret;
 }
 
 static int lan78xx_suspend(struct usb_interface *intf, pm_message_t message)
 {
 	struct lan78xx_net *dev = usb_get_intfdata(intf);
-	struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]);
-	u32 buf;
+	bool dev_open;
 	int ret;
 
-	if (!dev->suspend_count++) {
+	mutex_lock(&dev->dev_mutex);
+
+	netif_dbg(dev, ifdown, dev->net,
+		  "suspending: pm event %#x", message.event);
+
+	dev_open = test_bit(EVENT_DEV_OPEN, &dev->flags);
+
+	if (dev_open) {
 		spin_lock_irq(&dev->txq.lock);
 		/* don't autosuspend while transmitting */
 		if ((skb_queue_len(&dev->txq) ||
 		     skb_queue_len(&dev->txq_pend)) &&
-			PMSG_IS_AUTO(message)) {
+		    PMSG_IS_AUTO(message)) {
 			spin_unlock_irq(&dev->txq.lock);
 			ret = -EBUSY;
 			goto out;
@@ -3961,129 +4478,207 @@ static int lan78xx_suspend(struct usb_interface *intf, pm_message_t message)
 			spin_unlock_irq(&dev->txq.lock);
 		}
 
-		/* stop TX & RX */
-		ret = lan78xx_read_reg(dev, MAC_TX, &buf);
-		buf &= ~MAC_TX_TXEN_;
-		ret = lan78xx_write_reg(dev, MAC_TX, buf);
-		ret = lan78xx_read_reg(dev, MAC_RX, &buf);
-		buf &= ~MAC_RX_RXEN_;
-		ret = lan78xx_write_reg(dev, MAC_RX, buf);
+		/* stop RX */
+		ret = lan78xx_stop_rx_path(dev);
+		if (ret < 0)
+			goto out;
+
+		ret = lan78xx_flush_rx_fifo(dev);
+		if (ret < 0)
+			goto out;
+
+		/* stop Tx */
+		ret = lan78xx_stop_tx_path(dev);
+		if (ret < 0)
+			goto out;
 
-		/* empty out the rx and queues */
+		/* empty out the Rx and Tx queues */
 		netif_device_detach(dev->net);
 		lan78xx_terminate_urbs(dev);
 		usb_kill_urb(dev->urb_intr);
 
 		/* reattach */
 		netif_device_attach(dev->net);
-	}
 
-	if (test_bit(EVENT_DEV_ASLEEP, &dev->flags)) {
 		del_timer(&dev->stat_monitor);
 
 		if (PMSG_IS_AUTO(message)) {
-			/* auto suspend (selective suspend) */
-			ret = lan78xx_read_reg(dev, MAC_TX, &buf);
-			buf &= ~MAC_TX_TXEN_;
-			ret = lan78xx_write_reg(dev, MAC_TX, buf);
-			ret = lan78xx_read_reg(dev, MAC_RX, &buf);
-			buf &= ~MAC_RX_RXEN_;
-			ret = lan78xx_write_reg(dev, MAC_RX, buf);
+			ret = lan78xx_set_auto_suspend(dev);
+			if (ret < 0)
+				goto out;
+		} else {
+			struct lan78xx_priv *pdata;
 
-			ret = lan78xx_write_reg(dev, WUCSR, 0);
-			ret = lan78xx_write_reg(dev, WUCSR2, 0);
-			ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL);
+			pdata = (struct lan78xx_priv *)(dev->data[0]);
+			netif_carrier_off(dev->net);
+			ret = lan78xx_set_suspend(dev, pdata->wol);
+			if (ret < 0)
+				goto out;
+		}
+	} else {
+		/* Interface is down; don't allow WOL and PHY
+		 * events to wake up the host
+		 */
+		u32 buf;
 
-			/* set goodframe wakeup */
-			ret = lan78xx_read_reg(dev, WUCSR, &buf);
+		set_bit(EVENT_DEV_ASLEEP, &dev->flags);
 
-			buf |= WUCSR_RFE_WAKE_EN_;
-			buf |= WUCSR_STORE_WAKE_;
+		ret = lan78xx_write_reg(dev, WUCSR, 0);
+		if (ret < 0)
+			goto out;
+		ret = lan78xx_write_reg(dev, WUCSR2, 0);
+		if (ret < 0)
+			goto out;
 
-			ret = lan78xx_write_reg(dev, WUCSR, buf);
+		ret = lan78xx_read_reg(dev, PMT_CTL, &buf);
+		if (ret < 0)
+			goto out;
+
+		buf &= ~PMT_CTL_RES_CLR_WKP_EN_;
+		buf |= PMT_CTL_RES_CLR_WKP_STS_;
+		buf &= ~PMT_CTL_SUS_MODE_MASK_;
+		buf |= PMT_CTL_SUS_MODE_3_;
+
+		ret = lan78xx_write_reg(dev, PMT_CTL, buf);
+		if (ret < 0)
+			goto out;
 
-			ret = lan78xx_read_reg(dev, PMT_CTL, &buf);
+		ret = lan78xx_read_reg(dev, PMT_CTL, &buf);
+		if (ret < 0)
+			goto out;
+
+		buf |= PMT_CTL_WUPS_MASK_;
+
+		ret = lan78xx_write_reg(dev, PMT_CTL, buf);
+		if (ret < 0)
+			goto out;
+	}
 
-			buf &= ~PMT_CTL_RES_CLR_WKP_EN_;
-			buf |= PMT_CTL_RES_CLR_WKP_STS_;
+	ret = 0;
+out:
+	mutex_unlock(&dev->dev_mutex);
 
-			buf |= PMT_CTL_PHY_WAKE_EN_;
-			buf |= PMT_CTL_WOL_EN_;
-			buf &= ~PMT_CTL_SUS_MODE_MASK_;
-			buf |= PMT_CTL_SUS_MODE_3_;
+	return ret;
+}
 
-			ret = lan78xx_write_reg(dev, PMT_CTL, buf);
+static bool lan78xx_submit_deferred_urbs(struct lan78xx_net *dev)
+{
+	bool pipe_halted = false;
+	struct urb *urb;
 
-			ret = lan78xx_read_reg(dev, PMT_CTL, &buf);
+	while ((urb = usb_get_from_anchor(&dev->deferred))) {
+		struct sk_buff *skb = urb->context;
+		int ret;
 
-			buf |= PMT_CTL_WUPS_MASK_;
+		if (!netif_device_present(dev->net) ||
+		    !netif_carrier_ok(dev->net) ||
+		    pipe_halted) {
+			usb_free_urb(urb);
+			dev_kfree_skb(skb);
+			continue;
+		}
 
-			ret = lan78xx_write_reg(dev, PMT_CTL, buf);
+		ret = usb_submit_urb(urb, GFP_ATOMIC);
 
-			ret = lan78xx_read_reg(dev, MAC_RX, &buf);
-			buf |= MAC_RX_RXEN_;
-			ret = lan78xx_write_reg(dev, MAC_RX, buf);
+		if (ret == 0) {
+			netif_trans_update(dev->net);
+			lan78xx_queue_skb(&dev->txq, skb, tx_start);
 		} else {
-			lan78xx_set_suspend(dev, pdata->wol);
+			usb_free_urb(urb);
+			dev_kfree_skb(skb);
+
+			if (ret == -EPIPE) {
+				netif_stop_queue(dev->net);
+				pipe_halted = true;
+			} else if (ret == -ENODEV) {
+				netif_device_detach(dev->net);
+			}
 		}
 	}
 
-	ret = 0;
-out:
-	return ret;
+	return pipe_halted;
 }
 
 static int lan78xx_resume(struct usb_interface *intf)
 {
 	struct lan78xx_net *dev = usb_get_intfdata(intf);
-	struct sk_buff *skb;
-	struct urb *res;
+	bool dev_open;
 	int ret;
-	u32 buf;
 
-	if (!timer_pending(&dev->stat_monitor)) {
-		dev->delta = 1;
-		mod_timer(&dev->stat_monitor,
-			  jiffies + STAT_UPDATE_TIMER);
-	}
+	mutex_lock(&dev->dev_mutex);
 
-	if (!--dev->suspend_count) {
-		/* resume interrupt URBs */
-		if (dev->urb_intr && test_bit(EVENT_DEV_OPEN, &dev->flags))
-				usb_submit_urb(dev->urb_intr, GFP_NOIO);
+	netif_dbg(dev, ifup, dev->net, "resuming device");
+
+	dev_open = test_bit(EVENT_DEV_OPEN, &dev->flags);
+
+	if (dev_open) {
+		bool pipe_halted = false;
+
+		ret = lan78xx_flush_tx_fifo(dev);
+		if (ret < 0)
+			goto out;
+
+		if (dev->urb_intr) {
+			int ret = usb_submit_urb(dev->urb_intr, GFP_KERNEL);
 
-		spin_lock_irq(&dev->txq.lock);
-		while ((res = usb_get_from_anchor(&dev->deferred))) {
-			skb = (struct sk_buff *)res->context;
-			ret = usb_submit_urb(res, GFP_ATOMIC);
 			if (ret < 0) {
-				dev_kfree_skb_any(skb);
-				usb_free_urb(res);
-				usb_autopm_put_interface_async(dev->intf);
-			} else {
-				netif_trans_update(dev->net);
-				lan78xx_queue_skb(&dev->txq, skb, tx_start);
+				if (ret == -ENODEV)
+					netif_device_detach(dev->net);
+
+			netdev_warn(dev->net, "Failed to submit intr URB");
 			}
 		}
 
+		spin_lock_irq(&dev->txq.lock);
+
+		if (netif_device_present(dev->net)) {
+			pipe_halted = lan78xx_submit_deferred_urbs(dev);
+
+			if (pipe_halted)
+				lan78xx_defer_kevent(dev, EVENT_TX_HALT);
+		}
+
 		clear_bit(EVENT_DEV_ASLEEP, &dev->flags);
+
 		spin_unlock_irq(&dev->txq.lock);
 
-		if (test_bit(EVENT_DEV_OPEN, &dev->flags)) {
-			if (!(skb_queue_len(&dev->txq) >= dev->tx_qlen))
-				netif_start_queue(dev->net);
-			tasklet_schedule(&dev->bh);
+		if (!pipe_halted &&
+		    netif_device_present(dev->net) &&
+		    (skb_queue_len(&dev->txq) < dev->tx_qlen))
+			netif_start_queue(dev->net);
+
+		ret = lan78xx_start_tx_path(dev);
+		if (ret < 0)
+			goto out;
+
+		tasklet_schedule(&dev->bh);
+
+		if (!timer_pending(&dev->stat_monitor)) {
+			dev->delta = 1;
+			mod_timer(&dev->stat_monitor,
+				  jiffies + STAT_UPDATE_TIMER);
 		}
+
+	} else {
+		clear_bit(EVENT_DEV_ASLEEP, &dev->flags);
 	}
 
 	ret = lan78xx_write_reg(dev, WUCSR2, 0);
+	if (ret < 0)
+		goto out;
 	ret = lan78xx_write_reg(dev, WUCSR, 0);
+	if (ret < 0)
+		goto out;
 	ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL);
+	if (ret < 0)
+		goto out;
 
 	ret = lan78xx_write_reg(dev, WUCSR2, WUCSR2_NS_RCD_ |
 					     WUCSR2_ARP_RCD_ |
 					     WUCSR2_IPV6_TCPSYN_RCD_ |
 					     WUCSR2_IPV4_TCPSYN_RCD_);
+	if (ret < 0)
+		goto out;
 
 	ret = lan78xx_write_reg(dev, WUCSR, WUCSR_EEE_TX_WAKE_ |
 					    WUCSR_EEE_RX_WAKE_ |
@@ -4092,23 +4687,32 @@ static int lan78xx_resume(struct usb_interface *intf)
 					    WUCSR_WUFR_ |
 					    WUCSR_MPR_ |
 					    WUCSR_BCST_FR_);
+	if (ret < 0)
+		goto out;
 
-	ret = lan78xx_read_reg(dev, MAC_TX, &buf);
-	buf |= MAC_TX_TXEN_;
-	ret = lan78xx_write_reg(dev, MAC_TX, buf);
+	ret = 0;
+out:
+	mutex_unlock(&dev->dev_mutex);
 
-	return 0;
+	return ret;
 }
 
 static int lan78xx_reset_resume(struct usb_interface *intf)
 {
 	struct lan78xx_net *dev = usb_get_intfdata(intf);
+	int ret;
 
-	lan78xx_reset(dev);
+	netif_dbg(dev, ifup, dev->net, "(reset) resuming device");
+
+	ret = lan78xx_reset(dev);
+	if (ret < 0)
+		return ret;
 
 	phy_start(dev->net->phydev);
 
-	return lan78xx_resume(intf);
+	ret = lan78xx_resume(intf);
+
+	return ret;
 }
 
 static const struct usb_device_id products[] = {
diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c
index 2469bdcb1a04..66866bef25df 100644
--- a/drivers/net/usb/mcs7830.c
+++ b/drivers/net/usb/mcs7830.c
@@ -464,7 +464,7 @@ static const struct net_device_ops mcs7830_netdev_ops = {
 	.ndo_change_mtu		= usbnet_change_mtu,
 	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl 		= mcs7830_ioctl,
+	.ndo_eth_ioctl		= mcs7830_ioctl,
 	.ndo_set_rx_mode	= mcs7830_set_multicast,
 	.ndo_set_mac_address	= mcs7830_set_mac_address,
 };
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 9f9dd0de33cb..6a92a3fef75e 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -1001,7 +1001,8 @@ static const struct ethtool_ops ops = {
 	.set_link_ksettings = pegasus_set_link_ksettings,
 };
 
-static int pegasus_ioctl(struct net_device *net, struct ifreq *rq, int cmd)
+static int pegasus_siocdevprivate(struct net_device *net, struct ifreq *rq,
+				  void __user *udata, int cmd)
 {
 	__u16 *data = (__u16 *) &rq->ifr_ifru;
 	pegasus_t *pegasus = netdev_priv(net);
@@ -1269,7 +1270,7 @@ static int pegasus_resume(struct usb_interface *intf)
 static const struct net_device_ops pegasus_netdev_ops = {
 	.ndo_open =			pegasus_open,
 	.ndo_stop =			pegasus_close,
-	.ndo_do_ioctl =			pegasus_ioctl,
+	.ndo_siocdevprivate =		pegasus_siocdevprivate,
 	.ndo_start_xmit =		pegasus_start_xmit,
 	.ndo_set_rx_mode =		pegasus_set_multicast,
 	.ndo_tx_timeout =		pegasus_tx_timeout,
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 79832374f78d..60ba9b734055 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -8848,7 +8848,9 @@ out:
 }
 
 static int rtl8152_get_coalesce(struct net_device *netdev,
-				struct ethtool_coalesce *coalesce)
+				struct ethtool_coalesce *coalesce,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	struct r8152 *tp = netdev_priv(netdev);
 
@@ -8867,7 +8869,9 @@ static int rtl8152_get_coalesce(struct net_device *netdev,
 }
 
 static int rtl8152_set_coalesce(struct net_device *netdev,
-				struct ethtool_coalesce *coalesce)
+				struct ethtool_coalesce *coalesce,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	struct r8152 *tp = netdev_priv(netdev);
 	int ret;
@@ -9190,7 +9194,7 @@ static int rtl8152_change_mtu(struct net_device *dev, int new_mtu)
 static const struct net_device_ops rtl8152_netdev_ops = {
 	.ndo_open		= rtl8152_open,
 	.ndo_stop		= rtl8152_close,
-	.ndo_do_ioctl		= rtl8152_ioctl,
+	.ndo_eth_ioctl		= rtl8152_ioctl,
 	.ndo_start_xmit		= rtl8152_start_xmit,
 	.ndo_tx_timeout		= rtl8152_tx_timeout,
 	.ndo_set_features	= rtl8152_set_features,
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 7656f2a3afd9..4a1b0e0fc3a3 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -822,7 +822,8 @@ static const struct ethtool_ops ops = {
 	.get_link_ksettings = rtl8150_get_link_ksettings,
 };
 
-static int rtl8150_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
+static int rtl8150_siocdevprivate(struct net_device *netdev, struct ifreq *rq,
+				  void __user *udata, int cmd)
 {
 	rtl8150_t *dev = netdev_priv(netdev);
 	u16 *data = (u16 *) & rq->ifr_ifru;
@@ -850,7 +851,7 @@ static int rtl8150_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
 static const struct net_device_ops rtl8150_netdev_ops = {
 	.ndo_open		= rtl8150_open,
 	.ndo_stop		= rtl8150_close,
-	.ndo_do_ioctl		= rtl8150_ioctl,
+	.ndo_siocdevprivate	= rtl8150_siocdevprivate,
 	.ndo_start_xmit		= rtl8150_start_xmit,
 	.ndo_tx_timeout		= rtl8150_tx_timeout,
 	.ndo_set_rx_mode	= rtl8150_set_multicast,
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 13141dbfa3a8..76f7af161313 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -1439,7 +1439,7 @@ static const struct net_device_ops smsc75xx_netdev_ops = {
 	.ndo_change_mtu		= smsc75xx_change_mtu,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl 		= smsc75xx_ioctl,
+	.ndo_eth_ioctl		= smsc75xx_ioctl,
 	.ndo_set_rx_mode	= smsc75xx_set_multicast,
 	.ndo_set_features	= smsc75xx_set_features,
 };
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 4c8ee1cff4d4..7d953974eb9b 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1044,7 +1044,7 @@ static const struct net_device_ops smsc95xx_netdev_ops = {
 	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl 		= smsc95xx_ioctl,
+	.ndo_eth_ioctl		= smsc95xx_ioctl,
 	.ndo_set_rx_mode	= smsc95xx_set_multicast,
 	.ndo_set_features	= smsc95xx_set_features,
 };
diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index ce29261263cd..6516a37893e2 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -310,7 +310,7 @@ static const struct net_device_ops sr9700_netdev_ops = {
 	.ndo_change_mtu		= usbnet_change_mtu,
 	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= sr9700_ioctl,
+	.ndo_eth_ioctl		= sr9700_ioctl,
 	.ndo_set_rx_mode	= sr9700_set_multicast,
 	.ndo_set_mac_address	= sr9700_set_mac_address,
 };
diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c
index a822d81310d5..576401c8b1be 100644
--- a/drivers/net/usb/sr9800.c
+++ b/drivers/net/usb/sr9800.c
@@ -684,7 +684,7 @@ static const struct net_device_ops sr9800_netdev_ops = {
 	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address	= sr_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= sr_ioctl,
+	.ndo_eth_ioctl		= sr_ioctl,
 	.ndo_set_rx_mode        = sr_set_multicast,
 };
 
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 470e1c1e6353..840c1c2ab16a 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1725,7 +1725,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 	dev->interrupt_count = 0;
 
 	dev->net = net;
-	strcpy (net->name, "usb%d");
+	strscpy(net->name, "usb%d", sizeof(net->name));
 	memcpy (net->dev_addr, node_id, sizeof node_id);
 
 	/* rx and tx sides can use different message sizes;
@@ -1752,13 +1752,13 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 		if ((dev->driver_info->flags & FLAG_ETHER) != 0 &&
 		    ((dev->driver_info->flags & FLAG_POINTTOPOINT) == 0 ||
 		     (net->dev_addr [0] & 0x02) == 0))
-			strcpy (net->name, "eth%d");
+			strscpy(net->name, "eth%d", sizeof(net->name));
 		/* WLAN devices should always be named "wlan%d" */
 		if ((dev->driver_info->flags & FLAG_WLAN) != 0)
-			strcpy(net->name, "wlan%d");
+			strscpy(net->name, "wlan%d", sizeof(net->name));
 		/* WWAN devices should always be named "wwan%d" */
 		if ((dev->driver_info->flags & FLAG_WWAN) != 0)
-			strcpy(net->name, "wwan%d");
+			strscpy(net->name, "wwan%d", sizeof(net->name));
 
 		/* devices that cannot do ARP */
 		if ((dev->driver_info->flags & FLAG_NOARP) != 0)
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index bdb7ce3cb054..50eb43e5bf45 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -224,12 +224,13 @@ static void veth_get_channels(struct net_device *dev,
 {
 	channels->tx_count = dev->real_num_tx_queues;
 	channels->rx_count = dev->real_num_rx_queues;
-	channels->max_tx = dev->real_num_tx_queues;
-	channels->max_rx = dev->real_num_rx_queues;
-	channels->combined_count = min(dev->real_num_rx_queues, dev->real_num_tx_queues);
-	channels->max_combined = min(dev->real_num_rx_queues, dev->real_num_tx_queues);
+	channels->max_tx = dev->num_tx_queues;
+	channels->max_rx = dev->num_rx_queues;
 }
 
+static int veth_set_channels(struct net_device *dev,
+			     struct ethtool_channels *ch);
+
 static const struct ethtool_ops veth_ethtool_ops = {
 	.get_drvinfo		= veth_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
@@ -239,6 +240,7 @@ static const struct ethtool_ops veth_ethtool_ops = {
 	.get_link_ksettings	= veth_get_link_ksettings,
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.get_channels		= veth_get_channels,
+	.set_channels		= veth_set_channels,
 };
 
 /* general routines */
@@ -711,7 +713,7 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
 	int mac_len, delta, off;
 	struct xdp_buff xdp;
 
-	skb_orphan_partial(skb);
+	skb_prepare_for_gro(skb);
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -928,12 +930,12 @@ static int veth_poll(struct napi_struct *napi, int budget)
 	return done;
 }
 
-static int __veth_napi_enable(struct net_device *dev)
+static int __veth_napi_enable_range(struct net_device *dev, int start, int end)
 {
 	struct veth_priv *priv = netdev_priv(dev);
 	int err, i;
 
-	for (i = 0; i < dev->real_num_rx_queues; i++) {
+	for (i = start; i < end; i++) {
 		struct veth_rq *rq = &priv->rq[i];
 
 		err = ptr_ring_init(&rq->xdp_ring, VETH_RING_SIZE, GFP_KERNEL);
@@ -941,7 +943,7 @@ static int __veth_napi_enable(struct net_device *dev)
 			goto err_xdp_ring;
 	}
 
-	for (i = 0; i < dev->real_num_rx_queues; i++) {
+	for (i = start; i < end; i++) {
 		struct veth_rq *rq = &priv->rq[i];
 
 		napi_enable(&rq->xdp_napi);
@@ -949,19 +951,25 @@ static int __veth_napi_enable(struct net_device *dev)
 	}
 
 	return 0;
+
 err_xdp_ring:
-	for (i--; i >= 0; i--)
+	for (i--; i >= start; i--)
 		ptr_ring_cleanup(&priv->rq[i].xdp_ring, veth_ptr_free);
 
 	return err;
 }
 
-static void veth_napi_del(struct net_device *dev)
+static int __veth_napi_enable(struct net_device *dev)
+{
+	return __veth_napi_enable_range(dev, 0, dev->real_num_rx_queues);
+}
+
+static void veth_napi_del_range(struct net_device *dev, int start, int end)
 {
 	struct veth_priv *priv = netdev_priv(dev);
 	int i;
 
-	for (i = 0; i < dev->real_num_rx_queues; i++) {
+	for (i = start; i < end; i++) {
 		struct veth_rq *rq = &priv->rq[i];
 
 		rcu_assign_pointer(priv->rq[i].napi, NULL);
@@ -970,7 +978,7 @@ static void veth_napi_del(struct net_device *dev)
 	}
 	synchronize_net();
 
-	for (i = 0; i < dev->real_num_rx_queues; i++) {
+	for (i = start; i < end; i++) {
 		struct veth_rq *rq = &priv->rq[i];
 
 		rq->rx_notify_masked = false;
@@ -978,41 +986,90 @@ static void veth_napi_del(struct net_device *dev)
 	}
 }
 
+static void veth_napi_del(struct net_device *dev)
+{
+	veth_napi_del_range(dev, 0, dev->real_num_rx_queues);
+}
+
 static bool veth_gro_requested(const struct net_device *dev)
 {
 	return !!(dev->wanted_features & NETIF_F_GRO);
 }
 
-static int veth_enable_xdp(struct net_device *dev)
+static int veth_enable_xdp_range(struct net_device *dev, int start, int end,
+				 bool napi_already_on)
 {
-	bool napi_already_on = veth_gro_requested(dev) && (dev->flags & IFF_UP);
 	struct veth_priv *priv = netdev_priv(dev);
 	int err, i;
 
-	if (!xdp_rxq_info_is_reg(&priv->rq[0].xdp_rxq)) {
-		for (i = 0; i < dev->real_num_rx_queues; i++) {
-			struct veth_rq *rq = &priv->rq[i];
+	for (i = start; i < end; i++) {
+		struct veth_rq *rq = &priv->rq[i];
 
-			if (!napi_already_on)
-				netif_napi_add(dev, &rq->xdp_napi, veth_poll, NAPI_POLL_WEIGHT);
-			err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i, rq->xdp_napi.napi_id);
-			if (err < 0)
-				goto err_rxq_reg;
+		if (!napi_already_on)
+			netif_napi_add(dev, &rq->xdp_napi, veth_poll, NAPI_POLL_WEIGHT);
+		err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i, rq->xdp_napi.napi_id);
+		if (err < 0)
+			goto err_rxq_reg;
 
-			err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
-							 MEM_TYPE_PAGE_SHARED,
-							 NULL);
-			if (err < 0)
-				goto err_reg_mem;
+		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
+						 MEM_TYPE_PAGE_SHARED,
+						 NULL);
+		if (err < 0)
+			goto err_reg_mem;
 
-			/* Save original mem info as it can be overwritten */
-			rq->xdp_mem = rq->xdp_rxq.mem;
-		}
+		/* Save original mem info as it can be overwritten */
+		rq->xdp_mem = rq->xdp_rxq.mem;
+	}
+	return 0;
+
+err_reg_mem:
+	xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
+err_rxq_reg:
+	for (i--; i >= start; i--) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		xdp_rxq_info_unreg(&rq->xdp_rxq);
+		if (!napi_already_on)
+			netif_napi_del(&rq->xdp_napi);
+	}
+
+	return err;
+}
+
+static void veth_disable_xdp_range(struct net_device *dev, int start, int end,
+				   bool delete_napi)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int i;
+
+	for (i = start; i < end; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		rq->xdp_rxq.mem = rq->xdp_mem;
+		xdp_rxq_info_unreg(&rq->xdp_rxq);
+
+		if (delete_napi)
+			netif_napi_del(&rq->xdp_napi);
+	}
+}
+
+static int veth_enable_xdp(struct net_device *dev)
+{
+	bool napi_already_on = veth_gro_requested(dev) && (dev->flags & IFF_UP);
+	struct veth_priv *priv = netdev_priv(dev);
+	int err, i;
+
+	if (!xdp_rxq_info_is_reg(&priv->rq[0].xdp_rxq)) {
+		err = veth_enable_xdp_range(dev, 0, dev->real_num_rx_queues, napi_already_on);
+		if (err)
+			return err;
 
 		if (!napi_already_on) {
 			err = __veth_napi_enable(dev);
-			if (err)
-				goto err_rxq_reg;
+			if (err) {
+				veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, true);
+				return err;
+			}
 
 			if (!veth_gro_requested(dev)) {
 				/* user-space did not require GRO, but adding XDP
@@ -1030,18 +1087,6 @@ static int veth_enable_xdp(struct net_device *dev)
 	}
 
 	return 0;
-err_reg_mem:
-	xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
-err_rxq_reg:
-	for (i--; i >= 0; i--) {
-		struct veth_rq *rq = &priv->rq[i];
-
-		xdp_rxq_info_unreg(&rq->xdp_rxq);
-		if (!napi_already_on)
-			netif_napi_del(&rq->xdp_napi);
-	}
-
-	return err;
 }
 
 static void veth_disable_xdp(struct net_device *dev)
@@ -1064,28 +1109,23 @@ static void veth_disable_xdp(struct net_device *dev)
 		}
 	}
 
-	for (i = 0; i < dev->real_num_rx_queues; i++) {
-		struct veth_rq *rq = &priv->rq[i];
-
-		rq->xdp_rxq.mem = rq->xdp_mem;
-		xdp_rxq_info_unreg(&rq->xdp_rxq);
-	}
+	veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, false);
 }
 
-static int veth_napi_enable(struct net_device *dev)
+static int veth_napi_enable_range(struct net_device *dev, int start, int end)
 {
 	struct veth_priv *priv = netdev_priv(dev);
 	int err, i;
 
-	for (i = 0; i < dev->real_num_rx_queues; i++) {
+	for (i = start; i < end; i++) {
 		struct veth_rq *rq = &priv->rq[i];
 
 		netif_napi_add(dev, &rq->xdp_napi, veth_poll, NAPI_POLL_WEIGHT);
 	}
 
-	err = __veth_napi_enable(dev);
+	err = __veth_napi_enable_range(dev, start, end);
 	if (err) {
-		for (i = 0; i < dev->real_num_rx_queues; i++) {
+		for (i = start; i < end; i++) {
 			struct veth_rq *rq = &priv->rq[i];
 
 			netif_napi_del(&rq->xdp_napi);
@@ -1095,6 +1135,128 @@ static int veth_napi_enable(struct net_device *dev)
 	return err;
 }
 
+static int veth_napi_enable(struct net_device *dev)
+{
+	return veth_napi_enable_range(dev, 0, dev->real_num_rx_queues);
+}
+
+static void veth_disable_range_safe(struct net_device *dev, int start, int end)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	if (start >= end)
+		return;
+
+	if (priv->_xdp_prog) {
+		veth_napi_del_range(dev, start, end);
+		veth_disable_xdp_range(dev, start, end, false);
+	} else if (veth_gro_requested(dev)) {
+		veth_napi_del_range(dev, start, end);
+	}
+}
+
+static int veth_enable_range_safe(struct net_device *dev, int start, int end)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int err;
+
+	if (start >= end)
+		return 0;
+
+	if (priv->_xdp_prog) {
+		/* these channels are freshly initialized, napi is not on there even
+		 * when GRO is requeste
+		 */
+		err = veth_enable_xdp_range(dev, start, end, false);
+		if (err)
+			return err;
+
+		err = __veth_napi_enable_range(dev, start, end);
+		if (err) {
+			/* on error always delete the newly added napis */
+			veth_disable_xdp_range(dev, start, end, true);
+			return err;
+		}
+	} else if (veth_gro_requested(dev)) {
+		return veth_napi_enable_range(dev, start, end);
+	}
+	return 0;
+}
+
+static int veth_set_channels(struct net_device *dev,
+			     struct ethtool_channels *ch)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	unsigned int old_rx_count, new_rx_count;
+	struct veth_priv *peer_priv;
+	struct net_device *peer;
+	int err;
+
+	/* sanity check. Upper bounds are already enforced by the caller */
+	if (!ch->rx_count || !ch->tx_count)
+		return -EINVAL;
+
+	/* avoid braking XDP, if that is enabled */
+	peer = rtnl_dereference(priv->peer);
+	peer_priv = peer ? netdev_priv(peer) : NULL;
+	if (priv->_xdp_prog && peer && ch->rx_count < peer->real_num_tx_queues)
+		return -EINVAL;
+
+	if (peer && peer_priv && peer_priv->_xdp_prog && ch->tx_count > peer->real_num_rx_queues)
+		return -EINVAL;
+
+	old_rx_count = dev->real_num_rx_queues;
+	new_rx_count = ch->rx_count;
+	if (netif_running(dev)) {
+		/* turn device off */
+		netif_carrier_off(dev);
+		if (peer)
+			netif_carrier_off(peer);
+
+		/* try to allocate new resurces, as needed*/
+		err = veth_enable_range_safe(dev, old_rx_count, new_rx_count);
+		if (err)
+			goto out;
+	}
+
+	err = netif_set_real_num_rx_queues(dev, ch->rx_count);
+	if (err)
+		goto revert;
+
+	err = netif_set_real_num_tx_queues(dev, ch->tx_count);
+	if (err) {
+		int err2 = netif_set_real_num_rx_queues(dev, old_rx_count);
+
+		/* this error condition could happen only if rx and tx change
+		 * in opposite directions (e.g. tx nr raises, rx nr decreases)
+		 * and we can't do anything to fully restore the original
+		 * status
+		 */
+		if (err2)
+			pr_warn("Can't restore rx queues config %d -> %d %d",
+				new_rx_count, old_rx_count, err2);
+		else
+			goto revert;
+	}
+
+out:
+	if (netif_running(dev)) {
+		/* note that we need to swap the arguments WRT the enable part
+		 * to identify the range we have to disable
+		 */
+		veth_disable_range_safe(dev, new_rx_count, old_rx_count);
+		netif_carrier_on(dev);
+		if (peer)
+			netif_carrier_on(peer);
+	}
+	return err;
+
+revert:
+	new_rx_count = old_rx_count;
+	old_rx_count = ch->rx_count;
+	goto out;
+}
+
 static int veth_open(struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
@@ -1447,6 +1609,23 @@ static void veth_disable_gro(struct net_device *dev)
 	netdev_update_features(dev);
 }
 
+static int veth_init_queues(struct net_device *dev, struct nlattr *tb[])
+{
+	int err;
+
+	if (!tb[IFLA_NUM_TX_QUEUES] && dev->num_tx_queues > 1) {
+		err = netif_set_real_num_tx_queues(dev, 1);
+		if (err)
+			return err;
+	}
+	if (!tb[IFLA_NUM_RX_QUEUES] && dev->num_rx_queues > 1) {
+		err = netif_set_real_num_rx_queues(dev, 1);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
 static int veth_newlink(struct net *src_net, struct net_device *dev,
 			struct nlattr *tb[], struct nlattr *data[],
 			struct netlink_ext_ack *extack)
@@ -1556,13 +1735,21 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 
 	priv = netdev_priv(dev);
 	rcu_assign_pointer(priv->peer, peer);
+	err = veth_init_queues(dev, tb);
+	if (err)
+		goto err_queues;
 
 	priv = netdev_priv(peer);
 	rcu_assign_pointer(priv->peer, dev);
+	err = veth_init_queues(peer, tb);
+	if (err)
+		goto err_queues;
 
 	veth_disable_gro(dev);
 	return 0;
 
+err_queues:
+	unregister_netdevice(dev);
 err_register_dev:
 	/* nothing to do */
 err_configure_peer:
@@ -1608,6 +1795,16 @@ static struct net *veth_get_link_net(const struct net_device *dev)
 	return peer ? dev_net(peer) : dev_net(dev);
 }
 
+static unsigned int veth_get_num_queues(void)
+{
+	/* enforce the same queue limit as rtnl_create_link */
+	int queues = num_possible_cpus();
+
+	if (queues > 4096)
+		queues = 4096;
+	return queues;
+}
+
 static struct rtnl_link_ops veth_link_ops = {
 	.kind		= DRV_NAME,
 	.priv_size	= sizeof(struct veth_priv),
@@ -1618,6 +1815,8 @@ static struct rtnl_link_ops veth_link_ops = {
 	.policy		= veth_policy,
 	.maxtype	= VETH_INFO_MAX,
 	.get_link_net	= veth_get_link_net,
+	.get_num_tx_queues	= veth_get_num_queues,
+	.get_num_rx_queues	= veth_get_num_queues,
 };
 
 /*
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index eee493685aad..271d38c1d9f8 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -380,7 +380,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 				   struct page *page, unsigned int offset,
 				   unsigned int len, unsigned int truesize,
 				   bool hdr_valid, unsigned int metasize,
-				   bool whole_page)
+				   unsigned int headroom)
 {
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
@@ -398,28 +398,16 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	else
 		hdr_padded_len = sizeof(struct padded_vnet_hdr);
 
-	/* If whole_page, there is an offset between the beginning of the
+	/* If headroom is not 0, there is an offset between the beginning of the
 	 * data and the allocated space, otherwise the data and the allocated
 	 * space are aligned.
 	 *
 	 * Buffers with headroom use PAGE_SIZE as alloc size, see
 	 * add_recvbuf_mergeable() + get_mergeable_buf_len()
 	 */
-	if (whole_page) {
-		/* Buffers with whole_page use PAGE_SIZE as alloc size,
-		 * see add_recvbuf_mergeable() + get_mergeable_buf_len()
-		 */
-		truesize = PAGE_SIZE;
-
-		/* page maybe head page, so we should get the buf by p, not the
-		 * page
-		 */
-		tailroom = truesize - len - offset_in_page(p);
-		buf = (char *)((unsigned long)p & PAGE_MASK);
-	} else {
-		tailroom = truesize - len;
-		buf = p;
-	}
+	truesize = headroom ? PAGE_SIZE : truesize;
+	tailroom = truesize - len - headroom;
+	buf = p - headroom;
 
 	len -= hdr_len;
 	offset += hdr_padded_len;
@@ -540,19 +528,20 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
  * functions to perfectly solve these three problems at the same time.
  */
 #define virtnet_xdp_get_sq(vi) ({                                       \
+	int cpu = smp_processor_id();                                   \
 	struct netdev_queue *txq;                                       \
 	typeof(vi) v = (vi);                                            \
 	unsigned int qp;                                                \
 									\
 	if (v->curr_queue_pairs > nr_cpu_ids) {                         \
 		qp = v->curr_queue_pairs - v->xdp_queue_pairs;          \
-		qp += smp_processor_id();                               \
+		qp += cpu;                                              \
 		txq = netdev_get_tx_queue(v->dev, qp);                  \
 		__netif_tx_acquire(txq);                                \
 	} else {                                                        \
-		qp = smp_processor_id() % v->curr_queue_pairs;          \
+		qp = cpu % v->curr_queue_pairs;                         \
 		txq = netdev_get_tx_queue(v->dev, qp);                  \
-		__netif_tx_lock(txq, raw_smp_processor_id());           \
+		__netif_tx_lock(txq, cpu);                              \
 	}                                                               \
 	v->sq + qp;                                                     \
 })
@@ -978,7 +967,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 				put_page(page);
 				head_skb = page_to_skb(vi, rq, xdp_page, offset,
 						       len, PAGE_SIZE, false,
-						       metasize, true);
+						       metasize,
+						       VIRTIO_XDP_HEADROOM);
 				return head_skb;
 			}
 			break;
@@ -1029,7 +1019,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	rcu_read_unlock();
 
 	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog,
-			       metasize, !!headroom);
+			       metasize, headroom);
 	curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
@@ -2208,14 +2198,14 @@ static int virtnet_set_channels(struct net_device *dev,
 	if (vi->rq[0].xdp_prog)
 		return -EINVAL;
 
-	get_online_cpus();
+	cpus_read_lock();
 	err = _virtnet_set_queues(vi, queue_pairs);
 	if (err) {
-		put_online_cpus();
+		cpus_read_unlock();
 		goto err;
 	}
 	virtnet_set_affinity(vi);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	netif_set_real_num_tx_queues(dev, queue_pairs);
 	netif_set_real_num_rx_queues(dev, queue_pairs);
@@ -2331,7 +2321,9 @@ static int virtnet_get_link_ksettings(struct net_device *dev,
 }
 
 static int virtnet_set_coalesce(struct net_device *dev,
-				struct ethtool_coalesce *ec)
+				struct ethtool_coalesce *ec,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i, napi_weight;
@@ -2352,7 +2344,9 @@ static int virtnet_set_coalesce(struct net_device *dev,
 }
 
 static int virtnet_get_coalesce(struct net_device *dev,
-				struct ethtool_coalesce *ec)
+				struct ethtool_coalesce *ec,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	struct ethtool_coalesce ec_default = {
 		.cmd = ETHTOOL_GCOALESCE,
@@ -2970,9 +2964,9 @@ static int init_vqs(struct virtnet_info *vi)
 	if (ret)
 		goto err_free;
 
-	get_online_cpus();
+	cpus_read_lock();
 	virtnet_set_affinity(vi);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 
diff --git a/drivers/net/vmxnet3/Makefile b/drivers/net/vmxnet3/Makefile
index c5a167a1c85c..7a38925f4165 100644
--- a/drivers/net/vmxnet3/Makefile
+++ b/drivers/net/vmxnet3/Makefile
@@ -2,7 +2,7 @@
 #
 # Linux driver for VMware's vmxnet3 ethernet NIC.
 #
-# Copyright (C) 2007-2020, VMware, Inc. All Rights Reserved.
+# Copyright (C) 2007-2021, VMware, Inc. All Rights Reserved.
 #
 # This program is free software; you can redistribute it and/or modify it
 # under the terms of the GNU General Public License as published by the
diff --git a/drivers/net/vmxnet3/upt1_defs.h b/drivers/net/vmxnet3/upt1_defs.h
index 8c014c98471c..f9f3a23d1698 100644
--- a/drivers/net/vmxnet3/upt1_defs.h
+++ b/drivers/net/vmxnet3/upt1_defs.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2020, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h
index a8d5ebd47c71..74d4e8bc4abc 100644
--- a/drivers/net/vmxnet3/vmxnet3_defs.h
+++ b/drivers/net/vmxnet3/vmxnet3_defs.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2020, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -98,6 +98,9 @@ enum {
 	VMXNET3_CMD_GET_TXDATA_DESC_SIZE,
 	VMXNET3_CMD_GET_COALESCE,
 	VMXNET3_CMD_GET_RSS_FIELDS,
+	VMXNET3_CMD_GET_RESERVED2,
+	VMXNET3_CMD_GET_RESERVED3,
+	VMXNET3_CMD_GET_MAX_QUEUES_CONF,
 };
 
 /*
@@ -341,13 +344,15 @@ struct Vmxnet3_RxCompDescExt {
 #define VMXNET3_TXD_EOP_SIZE 1
 
 /* value of RxCompDesc.rssType */
-enum {
-	VMXNET3_RCD_RSS_TYPE_NONE     = 0,
-	VMXNET3_RCD_RSS_TYPE_IPV4     = 1,
-	VMXNET3_RCD_RSS_TYPE_TCPIPV4  = 2,
-	VMXNET3_RCD_RSS_TYPE_IPV6     = 3,
-	VMXNET3_RCD_RSS_TYPE_TCPIPV6  = 4,
-};
+#define VMXNET3_RCD_RSS_TYPE_NONE     0
+#define VMXNET3_RCD_RSS_TYPE_IPV4     1
+#define VMXNET3_RCD_RSS_TYPE_TCPIPV4  2
+#define VMXNET3_RCD_RSS_TYPE_IPV6     3
+#define VMXNET3_RCD_RSS_TYPE_TCPIPV6  4
+#define VMXNET3_RCD_RSS_TYPE_UDPIPV4  5
+#define VMXNET3_RCD_RSS_TYPE_UDPIPV6  6
+#define VMXNET3_RCD_RSS_TYPE_ESPIPV4  7
+#define VMXNET3_RCD_RSS_TYPE_ESPIPV6  8
 
 
 /* a union for accessing all cmd/completion descriptors */
@@ -533,6 +538,13 @@ enum vmxnet3_intr_type {
 /* addition 1 for events */
 #define VMXNET3_MAX_INTRS      25
 
+/* Version 6 and later will use below macros */
+#define VMXNET3_EXT_MAX_TX_QUEUES  32
+#define VMXNET3_EXT_MAX_RX_QUEUES  32
+/* addition 1 for events */
+#define VMXNET3_EXT_MAX_INTRS      65
+#define VMXNET3_FIRST_SET_INTRS    64
+
 /* value of intrCtrl */
 #define VMXNET3_IC_DISABLE_ALL  0x1   /* bit 0 */
 
@@ -547,6 +559,19 @@ struct Vmxnet3_IntrConf {
 	__le32		reserved[2];
 };
 
+struct Vmxnet3_IntrConfExt {
+	u8              autoMask;
+	u8              numIntrs;      /* # of interrupts */
+	u8              eventIntrIdx;
+	u8              reserved;
+	__le32          intrCtrl;
+	__le32          reserved1;
+	u8              modLevels[VMXNET3_EXT_MAX_INTRS]; /* moderation level for
+							   * each intr
+							   */
+	u8              reserved2[3];
+};
+
 /* one bit per VLAN ID, the size is in the units of u32	*/
 #define VMXNET3_VFT_SIZE  (4096 / (sizeof(u32) * 8))
 
@@ -719,11 +744,16 @@ struct Vmxnet3_DSDevRead {
 	struct Vmxnet3_VariableLenConfDesc	pluginConfDesc;
 };
 
+struct Vmxnet3_DSDevReadExt {
+	/* read-only region for device, read by dev in response to a SET cmd */
+	struct Vmxnet3_IntrConfExt              intrConfExt;
+};
+
 /* All structures in DriverShared are padded to multiples of 8 bytes */
 struct Vmxnet3_DriverShared {
 	__le32				magic;
 	/* make devRead start at 64bit boundaries */
-	__le32				pad;
+	__le32                          size; /* size of DriverShared */
 	struct Vmxnet3_DSDevRead	devRead;
 	__le32				ecr;
 	__le32				reserved;
@@ -734,6 +764,7 @@ struct Vmxnet3_DriverShared {
 						  * command
 						  */
 	} cu;
+	struct Vmxnet3_DSDevReadExt     devReadExt;
 };
 
 
@@ -764,6 +795,7 @@ struct Vmxnet3_DriverShared {
 	((vfTable[vid >> 5] & (1 << (vid & 31))) != 0)
 
 #define VMXNET3_MAX_MTU     9000
+#define VMXNET3_V6_MAX_MTU  9190
 #define VMXNET3_MIN_MTU     60
 
 #define VMXNET3_LINK_UP         (10000 << 16 | 1)    /* 10 Gbps, up */
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 6e87f1fc4874..142f70670f5c 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2020, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -314,10 +314,10 @@ vmxnet3_unmap_tx_buf(struct vmxnet3_tx_buf_info *tbi,
 {
 	if (tbi->map_type == VMXNET3_MAP_SINGLE)
 		dma_unmap_single(&pdev->dev, tbi->dma_addr, tbi->len,
-				 PCI_DMA_TODEVICE);
+				 DMA_TO_DEVICE);
 	else if (tbi->map_type == VMXNET3_MAP_PAGE)
 		dma_unmap_page(&pdev->dev, tbi->dma_addr, tbi->len,
-			       PCI_DMA_TODEVICE);
+			       DMA_TO_DEVICE);
 	else
 		BUG_ON(tbi->map_type != VMXNET3_MAP_NONE);
 
@@ -585,7 +585,7 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
 				rbi->dma_addr = dma_map_single(
 						&adapter->pdev->dev,
 						rbi->skb->data, rbi->len,
-						PCI_DMA_FROMDEVICE);
+						DMA_FROM_DEVICE);
 				if (dma_mapping_error(&adapter->pdev->dev,
 						      rbi->dma_addr)) {
 					dev_kfree_skb_any(rbi->skb);
@@ -609,7 +609,7 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
 				rbi->dma_addr = dma_map_page(
 						&adapter->pdev->dev,
 						rbi->page, 0, PAGE_SIZE,
-						PCI_DMA_FROMDEVICE);
+						DMA_FROM_DEVICE);
 				if (dma_mapping_error(&adapter->pdev->dev,
 						      rbi->dma_addr)) {
 					put_page(rbi->page);
@@ -723,7 +723,7 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 		tbi->map_type = VMXNET3_MAP_SINGLE;
 		tbi->dma_addr = dma_map_single(&adapter->pdev->dev,
 				skb->data + buf_offset, buf_size,
-				PCI_DMA_TODEVICE);
+				DMA_TO_DEVICE);
 		if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
 			return -EFAULT;
 
@@ -1449,7 +1449,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 				new_dma_addr =
 					dma_map_single(&adapter->pdev->dev,
 						       new_skb->data, rbi->len,
-						       PCI_DMA_FROMDEVICE);
+						       DMA_FROM_DEVICE);
 				if (dma_mapping_error(&adapter->pdev->dev,
 						      new_dma_addr)) {
 					dev_kfree_skb(new_skb);
@@ -1467,7 +1467,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 				dma_unmap_single(&adapter->pdev->dev,
 						 rbi->dma_addr,
 						 rbi->len,
-						 PCI_DMA_FROMDEVICE);
+						 DMA_FROM_DEVICE);
 
 				/* Immediate refill */
 				rbi->skb = new_skb;
@@ -1478,10 +1478,28 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 
 #ifdef VMXNET3_RSS
 			if (rcd->rssType != VMXNET3_RCD_RSS_TYPE_NONE &&
-			    (adapter->netdev->features & NETIF_F_RXHASH))
+			    (adapter->netdev->features & NETIF_F_RXHASH)) {
+				enum pkt_hash_types hash_type;
+
+				switch (rcd->rssType) {
+				case VMXNET3_RCD_RSS_TYPE_IPV4:
+				case VMXNET3_RCD_RSS_TYPE_IPV6:
+					hash_type = PKT_HASH_TYPE_L3;
+					break;
+				case VMXNET3_RCD_RSS_TYPE_TCPIPV4:
+				case VMXNET3_RCD_RSS_TYPE_TCPIPV6:
+				case VMXNET3_RCD_RSS_TYPE_UDPIPV4:
+				case VMXNET3_RCD_RSS_TYPE_UDPIPV6:
+					hash_type = PKT_HASH_TYPE_L4;
+					break;
+				default:
+					hash_type = PKT_HASH_TYPE_L3;
+					break;
+				}
 				skb_set_hash(ctx->skb,
 					     le32_to_cpu(rcd->rssHash),
-					     PKT_HASH_TYPE_L3);
+					     hash_type);
+			}
 #endif
 			skb_put(ctx->skb, rcd->len);
 
@@ -1528,7 +1546,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 				new_dma_addr = dma_map_page(&adapter->pdev->dev,
 							    new_page,
 							    0, PAGE_SIZE,
-							    PCI_DMA_FROMDEVICE);
+							    DMA_FROM_DEVICE);
 				if (dma_mapping_error(&adapter->pdev->dev,
 						      new_dma_addr)) {
 					put_page(new_page);
@@ -1541,7 +1559,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 
 				dma_unmap_page(&adapter->pdev->dev,
 					       rbi->dma_addr, rbi->len,
-					       PCI_DMA_FROMDEVICE);
+					       DMA_FROM_DEVICE);
 
 				vmxnet3_append_frag(ctx->skb, rcd, rbi);
 
@@ -1659,13 +1677,13 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq,
 			if (rxd->btype == VMXNET3_RXD_BTYPE_HEAD &&
 					rq->buf_info[ring_idx][i].skb) {
 				dma_unmap_single(&adapter->pdev->dev, rxd->addr,
-						 rxd->len, PCI_DMA_FROMDEVICE);
+						 rxd->len, DMA_FROM_DEVICE);
 				dev_kfree_skb(rq->buf_info[ring_idx][i].skb);
 				rq->buf_info[ring_idx][i].skb = NULL;
 			} else if (rxd->btype == VMXNET3_RXD_BTYPE_BODY &&
 					rq->buf_info[ring_idx][i].page) {
 				dma_unmap_page(&adapter->pdev->dev, rxd->addr,
-					       rxd->len, PCI_DMA_FROMDEVICE);
+					       rxd->len, DMA_FROM_DEVICE);
 				put_page(rq->buf_info[ring_idx][i].page);
 				rq->buf_info[ring_idx][i].page = NULL;
 			}
@@ -2401,7 +2419,7 @@ vmxnet3_set_mc(struct net_device *netdev)
 							&adapter->pdev->dev,
 							new_table,
 							sz,
-							PCI_DMA_TODEVICE);
+							DMA_TO_DEVICE);
 				if (!dma_mapping_error(&adapter->pdev->dev,
 						       new_table_pa)) {
 					new_mode |= VMXNET3_RXM_MCAST;
@@ -2437,7 +2455,7 @@ vmxnet3_set_mc(struct net_device *netdev)
 
 	if (new_table_pa_valid)
 		dma_unmap_single(&adapter->pdev->dev, new_table_pa,
-				 rxConf->mfTableLen, PCI_DMA_TODEVICE);
+				 rxConf->mfTableLen, DMA_TO_DEVICE);
 	kfree(new_table);
 }
 
@@ -2460,6 +2478,7 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 {
 	struct Vmxnet3_DriverShared *shared = adapter->shared;
 	struct Vmxnet3_DSDevRead *devRead = &shared->devRead;
+	struct Vmxnet3_DSDevReadExt *devReadExt = &shared->devReadExt;
 	struct Vmxnet3_TxQueueConf *tqc;
 	struct Vmxnet3_RxQueueConf *rqc;
 	int i;
@@ -2572,14 +2591,26 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 #endif /* VMXNET3_RSS */
 
 	/* intr settings */
-	devRead->intrConf.autoMask = adapter->intr.mask_mode ==
-				     VMXNET3_IMM_AUTO;
-	devRead->intrConf.numIntrs = adapter->intr.num_intrs;
-	for (i = 0; i < adapter->intr.num_intrs; i++)
-		devRead->intrConf.modLevels[i] = adapter->intr.mod_levels[i];
+	if (!VMXNET3_VERSION_GE_6(adapter) ||
+	    !adapter->queuesExtEnabled) {
+		devRead->intrConf.autoMask = adapter->intr.mask_mode ==
+					     VMXNET3_IMM_AUTO;
+		devRead->intrConf.numIntrs = adapter->intr.num_intrs;
+		for (i = 0; i < adapter->intr.num_intrs; i++)
+			devRead->intrConf.modLevels[i] = adapter->intr.mod_levels[i];
+
+		devRead->intrConf.eventIntrIdx = adapter->intr.event_intr_idx;
+		devRead->intrConf.intrCtrl |= cpu_to_le32(VMXNET3_IC_DISABLE_ALL);
+	} else {
+		devReadExt->intrConfExt.autoMask = adapter->intr.mask_mode ==
+						   VMXNET3_IMM_AUTO;
+		devReadExt->intrConfExt.numIntrs = adapter->intr.num_intrs;
+		for (i = 0; i < adapter->intr.num_intrs; i++)
+			devReadExt->intrConfExt.modLevels[i] = adapter->intr.mod_levels[i];
 
-	devRead->intrConf.eventIntrIdx = adapter->intr.event_intr_idx;
-	devRead->intrConf.intrCtrl |= cpu_to_le32(VMXNET3_IC_DISABLE_ALL);
+		devReadExt->intrConfExt.eventIntrIdx = adapter->intr.event_intr_idx;
+		devReadExt->intrConfExt.intrCtrl |= cpu_to_le32(VMXNET3_IC_DISABLE_ALL);
+	}
 
 	/* rx filter settings */
 	devRead->rxFilterConf.rxMode = 0;
@@ -2717,6 +2748,7 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
 	 * tx queue if the link is up.
 	 */
 	vmxnet3_check_link(adapter, true);
+	netif_tx_wake_all_queues(adapter->netdev);
 	for (i = 0; i < adapter->num_rx_queues; i++)
 		napi_enable(&adapter->rx_queue[i].napi);
 	vmxnet3_enable_all_intrs(adapter);
@@ -3372,6 +3404,8 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	int size;
 	int num_tx_queues;
 	int num_rx_queues;
+	int queues;
+	unsigned long flags;
 
 	if (!pci_msi_enabled())
 		enable_mq = 0;
@@ -3383,7 +3417,6 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	else
 #endif
 		num_rx_queues = 1;
-	num_rx_queues = rounddown_pow_of_two(num_rx_queues);
 
 	if (enable_mq)
 		num_tx_queues = min(VMXNET3_DEVICE_MAX_TX_QUEUES,
@@ -3391,13 +3424,8 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	else
 		num_tx_queues = 1;
 
-	num_tx_queues = rounddown_pow_of_two(num_tx_queues);
 	netdev = alloc_etherdev_mq(sizeof(struct vmxnet3_adapter),
 				   max(num_tx_queues, num_rx_queues));
-	dev_info(&pdev->dev,
-		 "# of Tx queues : %d, # of Rx queues : %d\n",
-		 num_tx_queues, num_rx_queues);
-
 	if (!netdev)
 		return -ENOMEM;
 
@@ -3410,19 +3438,12 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	adapter->rx_ring_size = VMXNET3_DEF_RX_RING_SIZE;
 	adapter->rx_ring2_size = VMXNET3_DEF_RX_RING2_SIZE;
 
-	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) {
-		if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) {
-			dev_err(&pdev->dev,
-				"pci_set_consistent_dma_mask failed\n");
-			err = -EIO;
-			goto err_set_mask;
-		}
+	if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) == 0) {
 		dma64 = true;
 	} else {
-		if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) {
-			dev_err(&pdev->dev,
-				"pci_set_dma_mask failed\n");
-			err = -EIO;
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+		if (err) {
+			dev_err(&pdev->dev, "dma_set_mask failed\n");
 			goto err_set_mask;
 		}
 		dma64 = false;
@@ -3431,7 +3452,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	spin_lock_init(&adapter->cmd_lock);
 	adapter->adapter_pa = dma_map_single(&adapter->pdev->dev, adapter,
 					     sizeof(struct vmxnet3_adapter),
-					     PCI_DMA_TODEVICE);
+					     DMA_TO_DEVICE);
 	if (dma_mapping_error(&adapter->pdev->dev, adapter->adapter_pa)) {
 		dev_err(&pdev->dev, "Failed to map dma\n");
 		err = -EFAULT;
@@ -3447,51 +3468,22 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 		goto err_alloc_shared;
 	}
 
-	adapter->num_rx_queues = num_rx_queues;
-	adapter->num_tx_queues = num_tx_queues;
-	adapter->rx_buf_per_pkt = 1;
-
-	size = sizeof(struct Vmxnet3_TxQueueDesc) * adapter->num_tx_queues;
-	size += sizeof(struct Vmxnet3_RxQueueDesc) * adapter->num_rx_queues;
-	adapter->tqd_start = dma_alloc_coherent(&adapter->pdev->dev, size,
-						&adapter->queue_desc_pa,
-						GFP_KERNEL);
-
-	if (!adapter->tqd_start) {
-		dev_err(&pdev->dev, "Failed to allocate memory\n");
-		err = -ENOMEM;
-		goto err_alloc_queue_desc;
-	}
-	adapter->rqd_start = (struct Vmxnet3_RxQueueDesc *)(adapter->tqd_start +
-							    adapter->num_tx_queues);
-
-	adapter->pm_conf = dma_alloc_coherent(&adapter->pdev->dev,
-					      sizeof(struct Vmxnet3_PMConf),
-					      &adapter->pm_conf_pa,
-					      GFP_KERNEL);
-	if (adapter->pm_conf == NULL) {
-		err = -ENOMEM;
-		goto err_alloc_pm;
-	}
-
-#ifdef VMXNET3_RSS
-
-	adapter->rss_conf = dma_alloc_coherent(&adapter->pdev->dev,
-					       sizeof(struct UPT1_RSSConf),
-					       &adapter->rss_conf_pa,
-					       GFP_KERNEL);
-	if (adapter->rss_conf == NULL) {
-		err = -ENOMEM;
-		goto err_alloc_rss;
-	}
-#endif /* VMXNET3_RSS */
-
 	err = vmxnet3_alloc_pci_resources(adapter);
 	if (err < 0)
 		goto err_alloc_pci;
 
 	ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS);
-	if (ver & (1 << VMXNET3_REV_4)) {
+	if (ver & (1 << VMXNET3_REV_6)) {
+		VMXNET3_WRITE_BAR1_REG(adapter,
+				       VMXNET3_REG_VRRS,
+				       1 << VMXNET3_REV_6);
+		adapter->version = VMXNET3_REV_6 + 1;
+	} else if (ver & (1 << VMXNET3_REV_5)) {
+		VMXNET3_WRITE_BAR1_REG(adapter,
+				       VMXNET3_REG_VRRS,
+				       1 << VMXNET3_REV_5);
+		adapter->version = VMXNET3_REV_5 + 1;
+	} else if (ver & (1 << VMXNET3_REV_4)) {
 		VMXNET3_WRITE_BAR1_REG(adapter,
 				       VMXNET3_REG_VRRS,
 				       1 << VMXNET3_REV_4);
@@ -3529,6 +3521,77 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 		goto err_ver;
 	}
 
+	if (VMXNET3_VERSION_GE_6(adapter)) {
+		spin_lock_irqsave(&adapter->cmd_lock, flags);
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_MAX_QUEUES_CONF);
+		queues = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
+		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+		if (queues > 0) {
+			adapter->num_rx_queues = min(num_rx_queues, ((queues >> 8) & 0xff));
+			adapter->num_tx_queues = min(num_tx_queues, (queues & 0xff));
+		} else {
+			adapter->num_rx_queues = min(num_rx_queues,
+						     VMXNET3_DEVICE_DEFAULT_RX_QUEUES);
+			adapter->num_tx_queues = min(num_tx_queues,
+						     VMXNET3_DEVICE_DEFAULT_TX_QUEUES);
+		}
+		if (adapter->num_rx_queues > VMXNET3_MAX_RX_QUEUES ||
+		    adapter->num_tx_queues > VMXNET3_MAX_TX_QUEUES) {
+			adapter->queuesExtEnabled = true;
+		} else {
+			adapter->queuesExtEnabled = false;
+		}
+	} else {
+		adapter->queuesExtEnabled = false;
+		num_rx_queues = rounddown_pow_of_two(num_rx_queues);
+		num_tx_queues = rounddown_pow_of_two(num_tx_queues);
+		adapter->num_rx_queues = min(num_rx_queues,
+					     VMXNET3_DEVICE_DEFAULT_RX_QUEUES);
+		adapter->num_tx_queues = min(num_tx_queues,
+					     VMXNET3_DEVICE_DEFAULT_TX_QUEUES);
+	}
+	dev_info(&pdev->dev,
+		 "# of Tx queues : %d, # of Rx queues : %d\n",
+		 adapter->num_tx_queues, adapter->num_rx_queues);
+
+	adapter->rx_buf_per_pkt = 1;
+
+	size = sizeof(struct Vmxnet3_TxQueueDesc) * adapter->num_tx_queues;
+	size += sizeof(struct Vmxnet3_RxQueueDesc) * adapter->num_rx_queues;
+	adapter->tqd_start = dma_alloc_coherent(&adapter->pdev->dev, size,
+						&adapter->queue_desc_pa,
+						GFP_KERNEL);
+
+	if (!adapter->tqd_start) {
+		dev_err(&pdev->dev, "Failed to allocate memory\n");
+		err = -ENOMEM;
+		goto err_ver;
+	}
+	adapter->rqd_start = (struct Vmxnet3_RxQueueDesc *)(adapter->tqd_start +
+							    adapter->num_tx_queues);
+
+	adapter->pm_conf = dma_alloc_coherent(&adapter->pdev->dev,
+					      sizeof(struct Vmxnet3_PMConf),
+					      &adapter->pm_conf_pa,
+					      GFP_KERNEL);
+	if (adapter->pm_conf == NULL) {
+		err = -ENOMEM;
+		goto err_alloc_pm;
+	}
+
+#ifdef VMXNET3_RSS
+
+	adapter->rss_conf = dma_alloc_coherent(&adapter->pdev->dev,
+					       sizeof(struct UPT1_RSSConf),
+					       &adapter->rss_conf_pa,
+					       GFP_KERNEL);
+	if (adapter->rss_conf == NULL) {
+		err = -ENOMEM;
+		goto err_alloc_rss;
+	}
+#endif /* VMXNET3_RSS */
+
 	if (VMXNET3_VERSION_GE_3(adapter)) {
 		adapter->coal_conf =
 			dma_alloc_coherent(&adapter->pdev->dev,
@@ -3538,7 +3601,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 					   GFP_KERNEL);
 		if (!adapter->coal_conf) {
 			err = -ENOMEM;
-			goto err_ver;
+			goto err_coal_conf;
 		}
 		adapter->coal_conf->coalMode = VMXNET3_COALESCE_DISABLED;
 		adapter->default_coal_mode = true;
@@ -3581,9 +3644,12 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	vmxnet3_set_ethtool_ops(netdev);
 	netdev->watchdog_timeo = 5 * HZ;
 
-	/* MTU range: 60 - 9000 */
+	/* MTU range: 60 - 9190 */
 	netdev->min_mtu = VMXNET3_MIN_MTU;
-	netdev->max_mtu = VMXNET3_MAX_MTU;
+	if (VMXNET3_VERSION_GE_6(adapter))
+		netdev->max_mtu = VMXNET3_V6_MAX_MTU;
+	else
+		netdev->max_mtu = VMXNET3_MAX_MTU;
 
 	INIT_WORK(&adapter->work, vmxnet3_reset_work);
 	set_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state);
@@ -3621,9 +3687,7 @@ err_register:
 				  adapter->coal_conf, adapter->coal_conf_pa);
 	}
 	vmxnet3_free_intr_resources(adapter);
-err_ver:
-	vmxnet3_free_pci_resources(adapter);
-err_alloc_pci:
+err_coal_conf:
 #ifdef VMXNET3_RSS
 	dma_free_coherent(&adapter->pdev->dev, sizeof(struct UPT1_RSSConf),
 			  adapter->rss_conf, adapter->rss_conf_pa);
@@ -3634,13 +3698,15 @@ err_alloc_rss:
 err_alloc_pm:
 	dma_free_coherent(&adapter->pdev->dev, size, adapter->tqd_start,
 			  adapter->queue_desc_pa);
-err_alloc_queue_desc:
+err_ver:
+	vmxnet3_free_pci_resources(adapter);
+err_alloc_pci:
 	dma_free_coherent(&adapter->pdev->dev,
 			  sizeof(struct Vmxnet3_DriverShared),
 			  adapter->shared, adapter->shared_pa);
 err_alloc_shared:
 	dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa,
-			 sizeof(struct vmxnet3_adapter), PCI_DMA_TODEVICE);
+			 sizeof(struct vmxnet3_adapter), DMA_TO_DEVICE);
 err_set_mask:
 	free_netdev(netdev);
 	return err;
@@ -3653,7 +3719,8 @@ vmxnet3_remove_device(struct pci_dev *pdev)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	int size = 0;
-	int num_rx_queues;
+	int num_rx_queues, rx_queues;
+	unsigned long flags;
 
 #ifdef VMXNET3_RSS
 	if (enable_mq)
@@ -3662,7 +3729,24 @@ vmxnet3_remove_device(struct pci_dev *pdev)
 	else
 #endif
 		num_rx_queues = 1;
-	num_rx_queues = rounddown_pow_of_two(num_rx_queues);
+	if (!VMXNET3_VERSION_GE_6(adapter)) {
+		num_rx_queues = rounddown_pow_of_two(num_rx_queues);
+	}
+	if (VMXNET3_VERSION_GE_6(adapter)) {
+		spin_lock_irqsave(&adapter->cmd_lock, flags);
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_MAX_QUEUES_CONF);
+		rx_queues = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
+		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+		if (rx_queues > 0)
+			rx_queues = (rx_queues >> 8) & 0xff;
+		else
+			rx_queues = min(num_rx_queues, VMXNET3_DEVICE_DEFAULT_RX_QUEUES);
+		num_rx_queues = min(num_rx_queues, rx_queues);
+	} else {
+		num_rx_queues = min(num_rx_queues,
+				    VMXNET3_DEVICE_DEFAULT_RX_QUEUES);
+	}
 
 	cancel_work_sync(&adapter->work);
 
@@ -3690,7 +3774,7 @@ vmxnet3_remove_device(struct pci_dev *pdev)
 			  sizeof(struct Vmxnet3_DriverShared),
 			  adapter->shared, adapter->shared_pa);
 	dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa,
-			 sizeof(struct vmxnet3_adapter), PCI_DMA_TODEVICE);
+			 sizeof(struct vmxnet3_adapter), DMA_TO_DEVICE);
 	free_netdev(netdev);
 }
 
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 1b483cf2b1ca..5dd8360b21a0 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -787,6 +787,10 @@ vmxnet3_get_rss_hash_opts(struct vmxnet3_adapter *adapter,
 	case AH_ESP_V6_FLOW:
 	case AH_V6_FLOW:
 	case ESP_V6_FLOW:
+		if (VMXNET3_VERSION_GE_6(adapter) &&
+		    (rss_fields & VMXNET3_RSS_FIELDS_ESPIP6))
+			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		fallthrough;
 	case SCTP_V6_FLOW:
 	case IPV6_FLOW:
 		info->data |= RXH_IP_SRC | RXH_IP_DST;
@@ -871,6 +875,22 @@ vmxnet3_set_rss_hash_opt(struct net_device *netdev,
 	case ESP_V6_FLOW:
 	case AH_V6_FLOW:
 	case AH_ESP_V6_FLOW:
+		if (!VMXNET3_VERSION_GE_6(adapter))
+			return -EOPNOTSUPP;
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST))
+			return -EINVAL;
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			rss_fields &= ~VMXNET3_RSS_FIELDS_ESPIP6;
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			rss_fields |= VMXNET3_RSS_FIELDS_ESPIP6;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
 	case SCTP_V4_FLOW:
 	case SCTP_V6_FLOW:
 		if (!(nfc->data & RXH_IP_SRC) ||
@@ -1033,8 +1053,10 @@ vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key,
 }
 #endif
 
-static int
-vmxnet3_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+static int vmxnet3_get_coalesce(struct net_device *netdev,
+				struct ethtool_coalesce *ec,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 
@@ -1068,8 +1090,10 @@ vmxnet3_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
 	return 0;
 }
 
-static int
-vmxnet3_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+static int vmxnet3_set_coalesce(struct net_device *netdev,
+				struct ethtool_coalesce *ec,
+				struct kernel_ethtool_coalesce *kernel_coal,
+				struct netlink_ext_ack *extack)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	struct Vmxnet3_DriverShared *shared = adapter->shared;
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index e910596b79cf..7027ff483fa5 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2020, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -69,18 +69,20 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.5.0.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.6.0.0-k"
 
 /* Each byte of this 32-bit integer encodes a version number in
  * VMXNET3_DRIVER_VERSION_STRING.
  */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01050000
+#define VMXNET3_DRIVER_VERSION_NUM      0x01060000
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */
 	#define VMXNET3_RSS
 #endif
 
+#define VMXNET3_REV_6		5	/* Vmxnet3 Rev. 6 */
+#define VMXNET3_REV_5		4	/* Vmxnet3 Rev. 5 */
 #define VMXNET3_REV_4		3	/* Vmxnet3 Rev. 4 */
 #define VMXNET3_REV_3		2	/* Vmxnet3 Rev. 3 */
 #define VMXNET3_REV_2		1	/* Vmxnet3 Rev. 2 */
@@ -301,15 +303,18 @@ struct vmxnet3_rx_queue {
 	struct vmxnet3_rq_driver_stats  stats;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
-#define VMXNET3_DEVICE_MAX_TX_QUEUES 8
-#define VMXNET3_DEVICE_MAX_RX_QUEUES 8   /* Keep this value as a power of 2 */
+#define VMXNET3_DEVICE_MAX_TX_QUEUES 32
+#define VMXNET3_DEVICE_MAX_RX_QUEUES 32   /* Keep this value as a power of 2 */
+
+#define VMXNET3_DEVICE_DEFAULT_TX_QUEUES 8
+#define VMXNET3_DEVICE_DEFAULT_RX_QUEUES 8   /* Keep this value as a power of 2 */
 
 /* Should be less than UPT1_RSS_MAX_IND_TABLE_SIZE */
 #define VMXNET3_RSS_IND_TABLE_SIZE (VMXNET3_DEVICE_MAX_RX_QUEUES * 4)
 
 #define VMXNET3_LINUX_MAX_MSIX_VECT     (VMXNET3_DEVICE_MAX_TX_QUEUES + \
 					 VMXNET3_DEVICE_MAX_RX_QUEUES + 1)
-#define VMXNET3_LINUX_MIN_MSIX_VECT     2 /* 1 for tx-rx pair and 1 for event */
+#define VMXNET3_LINUX_MIN_MSIX_VECT     3 /* 1 for tx, 1 for rx pair and 1 for event */
 
 
 struct vmxnet3_intr {
@@ -396,6 +401,7 @@ struct vmxnet3_adapter {
 	dma_addr_t adapter_pa;
 	dma_addr_t pm_conf_pa;
 	dma_addr_t rss_conf_pa;
+	bool   queuesExtEnabled;
 };
 
 #define VMXNET3_WRITE_BAR0_REG(adapter, reg, val)  \
@@ -421,6 +427,10 @@ struct vmxnet3_adapter {
 	(adapter->version >= VMXNET3_REV_3 + 1)
 #define VMXNET3_VERSION_GE_4(adapter) \
 	(adapter->version >= VMXNET3_REV_4 + 1)
+#define VMXNET3_VERSION_GE_5(adapter) \
+	(adapter->version >= VMXNET3_REV_5 + 1)
+#define VMXNET3_VERSION_GE_6(adapter) \
+	(adapter->version >= VMXNET3_REV_6 + 1)
 
 /* must be a multiple of VMXNET3_RING_SIZE_ALIGN */
 #define VMXNET3_DEF_TX_RING_SIZE    512
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 8bbe2a7bb141..bf2fac913942 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -857,30 +857,24 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	unsigned int hh_len = LL_RESERVED_SPACE(dev);
 	struct neighbour *neigh;
 	bool is_v6gw = false;
-	int ret = -EINVAL;
 
 	nf_reset_ct(skb);
 
 	/* Be paranoid, rather than too clever. */
 	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
-		struct sk_buff *skb2;
-
-		skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev));
-		if (!skb2) {
-			ret = -ENOMEM;
-			goto err;
+		skb = skb_expand_head(skb, hh_len);
+		if (!skb) {
+			dev->stats.tx_errors++;
+			return -ENOMEM;
 		}
-		if (skb->sk)
-			skb_set_owner_w(skb2, skb->sk);
-
-		consume_skb(skb);
-		skb = skb2;
 	}
 
 	rcu_read_lock_bh();
 
 	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
 	if (!IS_ERR(neigh)) {
+		int ret;
+
 		sock_confirm_neigh(skb, neigh);
 		/* if crossing protocols, can not use the cached header */
 		ret = neigh_output(neigh, skb, is_v6gw);
@@ -889,9 +883,8 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	}
 
 	rcu_read_unlock_bh();
-err:
 	vrf_tx_error(skb->dev, skb);
-	return ret;
+	return -EINVAL;
 }
 
 static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index 473df2505c8e..592a8389fc5a 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -290,30 +290,6 @@ config SLIC_DS26522
 	  To compile this driver as a module, choose M here: the
 	  module will be called slic_ds26522.
 
-config DSCC4_PCISYNC
-	bool "Etinc PCISYNC features"
-	depends on DSCC4
-	help
-	  Due to Etinc's design choice for its PCISYNC cards, some operations
-	  are only allowed on specific ports of the DSCC4. This option is the
-	  only way for the driver to know that it shouldn't return a success
-	  code for these operations.
-
-	  Please say Y if your card is an Etinc's PCISYNC.
-
-config DSCC4_PCI_RST
-	bool "Hard reset support"
-	depends on DSCC4
-	help
-	  Various DSCC4 bugs forbid any reliable software reset of the ASIC.
-	  As a replacement, some vendors provide a way to assert the PCI #RST
-	  pin of DSCC4 through the GPIO port of the card. If you choose Y,
-	  the driver will make use of this feature before module removal
-	  (i.e. rmmod). The feature is known to be available on Commtech's
-	  cards. Contact your manufacturer for details.
-
-	  Say Y if your card supports this feature.
-
 config IXP4XX_HSS
 	tristate "Intel IXP4xx HSS (synchronous serial port) support"
 	depends on HDLC && IXP4XX_NPE && IXP4XX_QMGR
@@ -337,33 +313,6 @@ config LAPBETHER
 	  To compile this driver as a module, choose M here: the
 	  module will be called lapbether.
 
-	  If unsure, say N.
-
-config SBNI
-	tristate "Granch SBNI12 Leased Line adapter support"
-	depends on X86
-	help
-	  Driver for ISA SBNI12-xx cards which are low cost alternatives to
-	  leased line modems.
-
-	  You can find more information and last versions of drivers and
-	  utilities at <http://www.granch.ru/>. If you have any question you
-	  can send email to <sbni@granch.ru>.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called sbni.
-
-	  If unsure, say N.
-
-config SBNI_MULTILINE
-	bool "Multiple line feature support"
-	depends on SBNI
-	help
-	  Schedule traffic for some parallel lines, via SBNI12 adapters.
-
-	  If you have two computers connected with two parallel lines it's
-	  possible to increase transfer rate nearly twice. You should have
-	  a program named 'sbniconfig' to configure adapters.
 
 	  If unsure, say N.
 
diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile
index 081666c36ca2..f6b92efffc94 100644
--- a/drivers/net/wan/Makefile
+++ b/drivers/net/wan/Makefile
@@ -22,7 +22,6 @@ obj-$(CONFIG_FARSYNC)		+= farsync.o
 obj-$(CONFIG_LANMEDIA)		+= lmc/
 
 obj-$(CONFIG_LAPBETHER)		+= lapbether.o
-obj-$(CONFIG_SBNI)		+= sbni.o
 obj-$(CONFIG_N2)		+= n2.o
 obj-$(CONFIG_C101)		+= c101.o
 obj-$(CONFIG_WANXL)		+= wanxl.o
diff --git a/drivers/net/wan/c101.c b/drivers/net/wan/c101.c
index 059c2f7133be..8dd14d916c3a 100644
--- a/drivers/net/wan/c101.c
+++ b/drivers/net/wan/c101.c
@@ -208,14 +208,12 @@ static int c101_close(struct net_device *dev)
 	return 0;
 }
 
-static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int c101_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			       void __user *data, int cmd)
 {
-	const size_t size = sizeof(sync_serial_settings);
-	sync_serial_settings new_line;
-	sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync;
+#ifdef DEBUG_RINGS
 	port_t *port = dev_to_port(dev);
 
-#ifdef DEBUG_RINGS
 	if (cmd == SIOCDEVPRIVATE) {
 		sca_dump_rings(dev);
 		printk(KERN_DEBUG "MSCI1: ST: %02x %02x %02x %02x\n",
@@ -226,14 +224,22 @@ static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		return 0;
 	}
 #endif
-	if (cmd != SIOCWANDEV)
-		return hdlc_ioctl(dev, ifr, cmd);
 
-	switch (ifr->ifr_settings.type) {
+	return -EOPNOTSUPP;
+}
+
+static int c101_ioctl(struct net_device *dev, struct if_settings *ifs)
+{
+	const size_t size = sizeof(sync_serial_settings);
+	sync_serial_settings new_line;
+	sync_serial_settings __user *line = ifs->ifs_ifsu.sync;
+	port_t *port = dev_to_port(dev);
+
+	switch (ifs->type) {
 	case IF_GET_IFACE:
-		ifr->ifr_settings.type = IF_IFACE_SYNC_SERIAL;
-		if (ifr->ifr_settings.size < size) {
-			ifr->ifr_settings.size = size; /* data size wanted */
+		ifs->type = IF_IFACE_SYNC_SERIAL;
+		if (ifs->size < size) {
+			ifs->size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
 		if (copy_to_user(line, &port->settings, size))
@@ -261,7 +267,7 @@ static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		return 0;
 
 	default:
-		return hdlc_ioctl(dev, ifr, cmd);
+		return hdlc_ioctl(dev, ifs);
 	}
 }
 
@@ -286,7 +292,8 @@ static const struct net_device_ops c101_ops = {
 	.ndo_open       = c101_open,
 	.ndo_stop       = c101_close,
 	.ndo_start_xmit = hdlc_start_xmit,
-	.ndo_do_ioctl   = c101_ioctl,
+	.ndo_siocwandev = c101_ioctl,
+	.ndo_siocdevprivate = c101_siocdevprivate,
 };
 
 static int __init c101_run(unsigned long irq, unsigned long winbase)
diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c
index 43caab0b7dee..23d2954d9747 100644
--- a/drivers/net/wan/cosa.c
+++ b/drivers/net/wan/cosa.c
@@ -267,7 +267,6 @@ static netdev_tx_t cosa_net_tx(struct sk_buff *skb, struct net_device *d);
 static char *cosa_net_setup_rx(struct channel_data *channel, int size);
 static int cosa_net_rx_done(struct channel_data *channel);
 static int cosa_net_tx_done(struct channel_data *channel, int size);
-static int cosa_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
 
 /* Character device */
 static char *chrdev_setup_rx(struct channel_data *channel, int size);
@@ -415,7 +414,7 @@ static const struct net_device_ops cosa_ops = {
 	.ndo_open       = cosa_net_open,
 	.ndo_stop       = cosa_net_close,
 	.ndo_start_xmit = hdlc_start_xmit,
-	.ndo_do_ioctl   = cosa_net_ioctl,
+	.ndo_siocwandev = hdlc_ioctl,
 	.ndo_tx_timeout = cosa_net_timeout,
 };
 
@@ -1169,18 +1168,6 @@ static int cosa_ioctl_common(struct cosa_data *cosa,
 	return -ENOIOCTLCMD;
 }
 
-static int cosa_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	int rv;
-	struct channel_data *chan = dev_to_chan(dev);
-
-	rv = cosa_ioctl_common(chan->cosa, chan, cmd,
-			       (unsigned long)ifr->ifr_data);
-	if (rv != -ENOIOCTLCMD)
-		return rv;
-	return hdlc_ioctl(dev, ifr, cmd);
-}
-
 static long cosa_chardev_ioctl(struct file *file, unsigned int cmd,
 			       unsigned long arg)
 {
diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index b3466e084e84..6a212c085435 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -1784,16 +1784,15 @@ gather_conf_info(struct fst_card_info *card, struct fst_port_info *port,
 
 static int
 fst_set_iface(struct fst_card_info *card, struct fst_port_info *port,
-	      struct ifreq *ifr)
+	      struct if_settings *ifs)
 {
 	sync_serial_settings sync;
 	int i;
 
-	if (ifr->ifr_settings.size != sizeof(sync))
+	if (ifs->size != sizeof(sync))
 		return -ENOMEM;
 
-	if (copy_from_user
-	    (&sync, ifr->ifr_settings.ifs_ifsu.sync, sizeof(sync)))
+	if (copy_from_user(&sync, ifs->ifs_ifsu.sync, sizeof(sync)))
 		return -EFAULT;
 
 	if (sync.loopback)
@@ -1801,7 +1800,7 @@ fst_set_iface(struct fst_card_info *card, struct fst_port_info *port,
 
 	i = port->index;
 
-	switch (ifr->ifr_settings.type) {
+	switch (ifs->type) {
 	case IF_IFACE_V35:
 		FST_WRW(card, portConfig[i].lineInterface, V35);
 		port->hwif = V35;
@@ -1857,7 +1856,7 @@ fst_set_iface(struct fst_card_info *card, struct fst_port_info *port,
 
 static int
 fst_get_iface(struct fst_card_info *card, struct fst_port_info *port,
-	      struct ifreq *ifr)
+	      struct if_settings *ifs)
 {
 	sync_serial_settings sync;
 	int i;
@@ -1868,29 +1867,29 @@ fst_get_iface(struct fst_card_info *card, struct fst_port_info *port,
 	 */
 	switch (port->hwif) {
 	case E1:
-		ifr->ifr_settings.type = IF_IFACE_E1;
+		ifs->type = IF_IFACE_E1;
 		break;
 	case T1:
-		ifr->ifr_settings.type = IF_IFACE_T1;
+		ifs->type = IF_IFACE_T1;
 		break;
 	case V35:
-		ifr->ifr_settings.type = IF_IFACE_V35;
+		ifs->type = IF_IFACE_V35;
 		break;
 	case V24:
-		ifr->ifr_settings.type = IF_IFACE_V24;
+		ifs->type = IF_IFACE_V24;
 		break;
 	case X21D:
-		ifr->ifr_settings.type = IF_IFACE_X21D;
+		ifs->type = IF_IFACE_X21D;
 		break;
 	case X21:
 	default:
-		ifr->ifr_settings.type = IF_IFACE_X21;
+		ifs->type = IF_IFACE_X21;
 		break;
 	}
-	if (ifr->ifr_settings.size == 0)
+	if (!ifs->size)
 		return 0;	/* only type requested */
 
-	if (ifr->ifr_settings.size < sizeof(sync))
+	if (ifs->size < sizeof(sync))
 		return -ENOMEM;
 
 	i = port->index;
@@ -1901,15 +1900,15 @@ fst_get_iface(struct fst_card_info *card, struct fst_port_info *port,
 	    INTCLK ? CLOCK_INT : CLOCK_EXT;
 	sync.loopback = 0;
 
-	if (copy_to_user(ifr->ifr_settings.ifs_ifsu.sync, &sync, sizeof(sync)))
+	if (copy_to_user(ifs->ifs_ifsu.sync, &sync, sizeof(sync)))
 		return -EFAULT;
 
-	ifr->ifr_settings.size = sizeof(sync);
+	ifs->size = sizeof(sync);
 	return 0;
 }
 
 static int
-fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+fst_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd)
 {
 	struct fst_card_info *card;
 	struct fst_port_info *port;
@@ -1918,7 +1917,7 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	unsigned long flags;
 	void *buf;
 
-	dbg(DBG_IOCTL, "ioctl: %x, %p\n", cmd, ifr->ifr_data);
+	dbg(DBG_IOCTL, "ioctl: %x, %p\n", cmd, data);
 
 	port = dev_to_port(dev);
 	card = port->card;
@@ -1942,11 +1941,10 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		/* First copy in the header with the length and offset of data
 		 * to write
 		 */
-		if (!ifr->ifr_data)
+		if (!data)
 			return -EINVAL;
 
-		if (copy_from_user(&wrthdr, ifr->ifr_data,
-				   sizeof(struct fstioc_write)))
+		if (copy_from_user(&wrthdr, data, sizeof(struct fstioc_write)))
 			return -EFAULT;
 
 		/* Sanity check the parameters. We don't support partial writes
@@ -1958,7 +1956,7 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 		/* Now copy the data to the card. */
 
-		buf = memdup_user(ifr->ifr_data + sizeof(struct fstioc_write),
+		buf = memdup_user(data + sizeof(struct fstioc_write),
 				  wrthdr.size);
 		if (IS_ERR(buf))
 			return PTR_ERR(buf);
@@ -1991,12 +1989,12 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			}
 		}
 
-		if (!ifr->ifr_data)
+		if (!data)
 			return -EINVAL;
 
 		gather_conf_info(card, port, &info);
 
-		if (copy_to_user(ifr->ifr_data, &info, sizeof(info)))
+		if (copy_to_user(data, &info, sizeof(info)))
 			return -EFAULT;
 
 		return 0;
@@ -2011,46 +2009,58 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			       card->card_no, card->state);
 			return -EIO;
 		}
-		if (copy_from_user(&info, ifr->ifr_data, sizeof(info)))
+		if (copy_from_user(&info, data, sizeof(info)))
 			return -EFAULT;
 
 		return set_conf_from_info(card, port, &info);
+	default:
+		return -EINVAL;
+	}
+}
 
-	case SIOCWANDEV:
-		switch (ifr->ifr_settings.type) {
-		case IF_GET_IFACE:
-			return fst_get_iface(card, port, ifr);
-
-		case IF_IFACE_SYNC_SERIAL:
-		case IF_IFACE_V35:
-		case IF_IFACE_V24:
-		case IF_IFACE_X21:
-		case IF_IFACE_X21D:
-		case IF_IFACE_T1:
-		case IF_IFACE_E1:
-			return fst_set_iface(card, port, ifr);
-
-		case IF_PROTO_RAW:
-			port->mode = FST_RAW;
-			return 0;
+static int
+fst_ioctl(struct net_device *dev, struct if_settings *ifs)
+{
+	struct fst_card_info *card;
+	struct fst_port_info *port;
 
-		case IF_GET_PROTO:
-			if (port->mode == FST_RAW) {
-				ifr->ifr_settings.type = IF_PROTO_RAW;
-				return 0;
-			}
-			return hdlc_ioctl(dev, ifr, cmd);
+	dbg(DBG_IOCTL, "SIOCDEVPRIVATE, %x\n", ifs->type);
 
-		default:
-			port->mode = FST_GEN_HDLC;
-			dbg(DBG_IOCTL, "Passing this type to hdlc %x\n",
-			    ifr->ifr_settings.type);
-			return hdlc_ioctl(dev, ifr, cmd);
+	port = dev_to_port(dev);
+	card = port->card;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	switch (ifs->type) {
+	case IF_GET_IFACE:
+		return fst_get_iface(card, port, ifs);
+
+	case IF_IFACE_SYNC_SERIAL:
+	case IF_IFACE_V35:
+	case IF_IFACE_V24:
+	case IF_IFACE_X21:
+	case IF_IFACE_X21D:
+	case IF_IFACE_T1:
+	case IF_IFACE_E1:
+		return fst_set_iface(card, port, ifs);
+
+	case IF_PROTO_RAW:
+		port->mode = FST_RAW;
+		return 0;
+
+	case IF_GET_PROTO:
+		if (port->mode == FST_RAW) {
+			ifs->type = IF_PROTO_RAW;
+			return 0;
 		}
+		return hdlc_ioctl(dev, ifs);
 
 	default:
-		/* Not one of ours. Pass through to HDLC package */
-		return hdlc_ioctl(dev, ifr, cmd);
+		port->mode = FST_GEN_HDLC;
+		dbg(DBG_IOCTL, "Passing this type to hdlc %x\n",
+		    ifs->type);
+		return hdlc_ioctl(dev, ifs);
 	}
 }
 
@@ -2310,7 +2320,8 @@ static const struct net_device_ops fst_ops = {
 	.ndo_open       = fst_open,
 	.ndo_stop       = fst_close,
 	.ndo_start_xmit = hdlc_start_xmit,
-	.ndo_do_ioctl   = fst_ioctl,
+	.ndo_siocwandev	= fst_ioctl,
+	.ndo_siocdevprivate = fst_siocdevprivate,
 	.ndo_tx_timeout = fst_tx_timeout,
 };
 
diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index 39f05fabbfa4..cda1b4ce6b21 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -674,31 +674,28 @@ static irqreturn_t ucc_hdlc_irq_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int uhdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int uhdlc_ioctl(struct net_device *dev, struct if_settings *ifs)
 {
 	const size_t size = sizeof(te1_settings);
 	te1_settings line;
 	struct ucc_hdlc_private *priv = netdev_priv(dev);
 
-	if (cmd != SIOCWANDEV)
-		return hdlc_ioctl(dev, ifr, cmd);
-
-	switch (ifr->ifr_settings.type) {
+	switch (ifs->type) {
 	case IF_GET_IFACE:
-		ifr->ifr_settings.type = IF_IFACE_E1;
-		if (ifr->ifr_settings.size < size) {
-			ifr->ifr_settings.size = size; /* data size wanted */
+		ifs->type = IF_IFACE_E1;
+		if (ifs->size < size) {
+			ifs->size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
 		memset(&line, 0, sizeof(line));
 		line.clock_type = priv->clocking;
 
-		if (copy_to_user(ifr->ifr_settings.ifs_ifsu.sync, &line, size))
+		if (copy_to_user(ifs->ifs_ifsu.sync, &line, size))
 			return -EFAULT;
 		return 0;
 
 	default:
-		return hdlc_ioctl(dev, ifr, cmd);
+		return hdlc_ioctl(dev, ifs);
 	}
 }
 
@@ -1053,7 +1050,7 @@ static const struct net_device_ops uhdlc_ops = {
 	.ndo_open       = uhdlc_open,
 	.ndo_stop       = uhdlc_close,
 	.ndo_start_xmit = hdlc_start_xmit,
-	.ndo_do_ioctl   = uhdlc_ioctl,
+	.ndo_siocwandev = uhdlc_ioctl,
 	.ndo_tx_timeout	= uhdlc_tx_timeout,
 };
 
diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c
index dd6312b69861..cbed10b1d862 100644
--- a/drivers/net/wan/hdlc.c
+++ b/drivers/net/wan/hdlc.c
@@ -196,16 +196,13 @@ void hdlc_close(struct net_device *dev)
 }
 EXPORT_SYMBOL(hdlc_close);
 
-int hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+int hdlc_ioctl(struct net_device *dev, struct if_settings *ifs)
 {
 	struct hdlc_proto *proto = first_proto;
 	int result;
 
-	if (cmd != SIOCWANDEV)
-		return -EINVAL;
-
 	if (dev_to_hdlc(dev)->proto) {
-		result = dev_to_hdlc(dev)->proto->ioctl(dev, ifr);
+		result = dev_to_hdlc(dev)->proto->ioctl(dev, ifs);
 		if (result != -EINVAL)
 			return result;
 	}
@@ -213,7 +210,7 @@ int hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	/* Not handled by currently attached protocol (if any) */
 
 	while (proto) {
-		result = proto->ioctl(dev, ifr);
+		result = proto->ioctl(dev, ifs);
 		if (result != -EINVAL)
 			return result;
 		proto = proto->next;
diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c
index c54fdae950fb..cdebe65a7e2d 100644
--- a/drivers/net/wan/hdlc_cisco.c
+++ b/drivers/net/wan/hdlc_cisco.c
@@ -56,7 +56,7 @@ struct cisco_state {
 	u32 rxseq; /* RX sequence number */
 };
 
-static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr);
+static int cisco_ioctl(struct net_device *dev, struct if_settings *ifs);
 
 static inline struct cisco_state *state(hdlc_device *hdlc)
 {
@@ -306,21 +306,21 @@ static const struct header_ops cisco_header_ops = {
 	.create = cisco_hard_header,
 };
 
-static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr)
+static int cisco_ioctl(struct net_device *dev, struct if_settings *ifs)
 {
-	cisco_proto __user *cisco_s = ifr->ifr_settings.ifs_ifsu.cisco;
+	cisco_proto __user *cisco_s = ifs->ifs_ifsu.cisco;
 	const size_t size = sizeof(cisco_proto);
 	cisco_proto new_settings;
 	hdlc_device *hdlc = dev_to_hdlc(dev);
 	int result;
 
-	switch (ifr->ifr_settings.type) {
+	switch (ifs->type) {
 	case IF_GET_PROTO:
 		if (dev_to_hdlc(dev)->proto != &proto)
 			return -EINVAL;
-		ifr->ifr_settings.type = IF_PROTO_CISCO;
-		if (ifr->ifr_settings.size < size) {
-			ifr->ifr_settings.size = size; /* data size wanted */
+		ifs->type = IF_PROTO_CISCO;
+		if (ifs->size < size) {
+			ifs->size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
 		if (copy_to_user(cisco_s, &state(hdlc)->settings, size))
diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index 25e3564ce118..7637edce443e 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -146,7 +146,7 @@ struct frad_state {
 	u8 rxseq; /* RX sequence number */
 };
 
-static int fr_ioctl(struct net_device *dev, struct ifreq *ifr);
+static int fr_ioctl(struct net_device *dev, struct if_settings *ifs);
 
 static inline u16 q922_to_dlci(u8 *hdr)
 {
@@ -357,26 +357,26 @@ static int pvc_close(struct net_device *dev)
 	return 0;
 }
 
-static int pvc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int pvc_ioctl(struct net_device *dev, struct if_settings *ifs)
 {
 	struct pvc_device *pvc = dev->ml_priv;
 	fr_proto_pvc_info info;
 
-	if (ifr->ifr_settings.type == IF_GET_PROTO) {
+	if (ifs->type == IF_GET_PROTO) {
 		if (dev->type == ARPHRD_ETHER)
-			ifr->ifr_settings.type = IF_PROTO_FR_ETH_PVC;
+			ifs->type = IF_PROTO_FR_ETH_PVC;
 		else
-			ifr->ifr_settings.type = IF_PROTO_FR_PVC;
+			ifs->type = IF_PROTO_FR_PVC;
 
-		if (ifr->ifr_settings.size < sizeof(info)) {
+		if (ifs->size < sizeof(info)) {
 			/* data size wanted */
-			ifr->ifr_settings.size = sizeof(info);
+			ifs->size = sizeof(info);
 			return -ENOBUFS;
 		}
 
 		info.dlci = pvc->dlci;
 		memcpy(info.master, pvc->frad->name, IFNAMSIZ);
-		if (copy_to_user(ifr->ifr_settings.ifs_ifsu.fr_pvc_info,
+		if (copy_to_user(ifs->ifs_ifsu.fr_pvc_info,
 				 &info, sizeof(info)))
 			return -EFAULT;
 		return 0;
@@ -1056,7 +1056,7 @@ static const struct net_device_ops pvc_ops = {
 	.ndo_open       = pvc_open,
 	.ndo_stop       = pvc_close,
 	.ndo_start_xmit = pvc_xmit,
-	.ndo_do_ioctl   = pvc_ioctl,
+	.ndo_siocwandev = pvc_ioctl,
 };
 
 static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
@@ -1179,22 +1179,22 @@ static struct hdlc_proto proto = {
 	.module		= THIS_MODULE,
 };
 
-static int fr_ioctl(struct net_device *dev, struct ifreq *ifr)
+static int fr_ioctl(struct net_device *dev, struct if_settings *ifs)
 {
-	fr_proto __user *fr_s = ifr->ifr_settings.ifs_ifsu.fr;
+	fr_proto __user *fr_s = ifs->ifs_ifsu.fr;
 	const size_t size = sizeof(fr_proto);
 	fr_proto new_settings;
 	hdlc_device *hdlc = dev_to_hdlc(dev);
 	fr_proto_pvc pvc;
 	int result;
 
-	switch (ifr->ifr_settings.type) {
+	switch (ifs->type) {
 	case IF_GET_PROTO:
 		if (dev_to_hdlc(dev)->proto != &proto) /* Different proto */
 			return -EINVAL;
-		ifr->ifr_settings.type = IF_PROTO_FR;
-		if (ifr->ifr_settings.size < size) {
-			ifr->ifr_settings.size = size; /* data size wanted */
+		ifs->type = IF_PROTO_FR;
+		if (ifs->size < size) {
+			ifs->size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
 		if (copy_to_user(fr_s, &state(hdlc)->settings, size))
@@ -1256,21 +1256,21 @@ static int fr_ioctl(struct net_device *dev, struct ifreq *ifr)
 		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
 
-		if (copy_from_user(&pvc, ifr->ifr_settings.ifs_ifsu.fr_pvc,
+		if (copy_from_user(&pvc, ifs->ifs_ifsu.fr_pvc,
 				   sizeof(fr_proto_pvc)))
 			return -EFAULT;
 
 		if (pvc.dlci <= 0 || pvc.dlci >= 1024)
 			return -EINVAL;	/* Only 10 bits, DLCI 0 reserved */
 
-		if (ifr->ifr_settings.type == IF_PROTO_FR_ADD_ETH_PVC ||
-		    ifr->ifr_settings.type == IF_PROTO_FR_DEL_ETH_PVC)
+		if (ifs->type == IF_PROTO_FR_ADD_ETH_PVC ||
+		    ifs->type == IF_PROTO_FR_DEL_ETH_PVC)
 			result = ARPHRD_ETHER; /* bridged Ethernet device */
 		else
 			result = ARPHRD_DLCI;
 
-		if (ifr->ifr_settings.type == IF_PROTO_FR_ADD_PVC ||
-		    ifr->ifr_settings.type == IF_PROTO_FR_ADD_ETH_PVC)
+		if (ifs->type == IF_PROTO_FR_ADD_PVC ||
+		    ifs->type == IF_PROTO_FR_ADD_ETH_PVC)
 			return fr_add_pvc(dev, pvc.dlci, result);
 		else
 			return fr_del_pvc(hdlc, pvc.dlci, result);
diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index b81ecf432a0c..37a3c989cba1 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -100,7 +100,7 @@ static const char *const event_names[EVENTS] = {
 
 static struct sk_buff_head tx_queue; /* used when holding the spin lock */
 
-static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr);
+static int ppp_ioctl(struct net_device *dev, struct if_settings *ifs);
 
 static inline struct ppp *get_ppp(struct net_device *dev)
 {
@@ -655,17 +655,17 @@ static const struct header_ops ppp_header_ops = {
 	.create = ppp_hard_header,
 };
 
-static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr)
+static int ppp_ioctl(struct net_device *dev, struct if_settings *ifs)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
 	struct ppp *ppp;
 	int result;
 
-	switch (ifr->ifr_settings.type) {
+	switch (ifs->type) {
 	case IF_GET_PROTO:
 		if (dev_to_hdlc(dev)->proto != &proto)
 			return -EINVAL;
-		ifr->ifr_settings.type = IF_PROTO_PPP;
+		ifs->type = IF_PROTO_PPP;
 		return 0; /* return protocol only, no settable parameters */
 
 	case IF_PROTO_PPP:
diff --git a/drivers/net/wan/hdlc_raw.c b/drivers/net/wan/hdlc_raw.c
index 54d28496fefd..4a2f068721bc 100644
--- a/drivers/net/wan/hdlc_raw.c
+++ b/drivers/net/wan/hdlc_raw.c
@@ -19,7 +19,7 @@
 #include <linux/skbuff.h>
 
 
-static int raw_ioctl(struct net_device *dev, struct ifreq *ifr);
+static int raw_ioctl(struct net_device *dev, struct if_settings *ifs);
 
 static __be16 raw_type_trans(struct sk_buff *skb, struct net_device *dev)
 {
@@ -33,21 +33,21 @@ static struct hdlc_proto proto = {
 };
 
 
-static int raw_ioctl(struct net_device *dev, struct ifreq *ifr)
+static int raw_ioctl(struct net_device *dev, struct if_settings *ifs)
 {
-	raw_hdlc_proto __user *raw_s = ifr->ifr_settings.ifs_ifsu.raw_hdlc;
+	raw_hdlc_proto __user *raw_s = ifs->ifs_ifsu.raw_hdlc;
 	const size_t size = sizeof(raw_hdlc_proto);
 	raw_hdlc_proto new_settings;
 	hdlc_device *hdlc = dev_to_hdlc(dev);
 	int result;
 
-	switch (ifr->ifr_settings.type) {
+	switch (ifs->type) {
 	case IF_GET_PROTO:
 		if (dev_to_hdlc(dev)->proto != &proto)
 			return -EINVAL;
-		ifr->ifr_settings.type = IF_PROTO_HDLC;
-		if (ifr->ifr_settings.size < size) {
-			ifr->ifr_settings.size = size; /* data size wanted */
+		ifs->type = IF_PROTO_HDLC;
+		if (ifs->size < size) {
+			ifs->size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
 		if (copy_to_user(raw_s, hdlc->state, size))
diff --git a/drivers/net/wan/hdlc_raw_eth.c b/drivers/net/wan/hdlc_raw_eth.c
index 927596276a07..0a66b7356405 100644
--- a/drivers/net/wan/hdlc_raw_eth.c
+++ b/drivers/net/wan/hdlc_raw_eth.c
@@ -20,7 +20,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/skbuff.h>
 
-static int raw_eth_ioctl(struct net_device *dev, struct ifreq *ifr);
+static int raw_eth_ioctl(struct net_device *dev, struct if_settings *ifs);
 
 static netdev_tx_t eth_tx(struct sk_buff *skb, struct net_device *dev)
 {
@@ -48,22 +48,22 @@ static struct hdlc_proto proto = {
 };
 
 
-static int raw_eth_ioctl(struct net_device *dev, struct ifreq *ifr)
+static int raw_eth_ioctl(struct net_device *dev, struct if_settings *ifs)
 {
-	raw_hdlc_proto __user *raw_s = ifr->ifr_settings.ifs_ifsu.raw_hdlc;
+	raw_hdlc_proto __user *raw_s = ifs->ifs_ifsu.raw_hdlc;
 	const size_t size = sizeof(raw_hdlc_proto);
 	raw_hdlc_proto new_settings;
 	hdlc_device *hdlc = dev_to_hdlc(dev);
 	unsigned int old_qlen;
 	int result;
 
-	switch (ifr->ifr_settings.type) {
+	switch (ifs->type) {
 	case IF_GET_PROTO:
 		if (dev_to_hdlc(dev)->proto != &proto)
 			return -EINVAL;
-		ifr->ifr_settings.type = IF_PROTO_HDLC_ETH;
-		if (ifr->ifr_settings.size < size) {
-			ifr->ifr_settings.size = size; /* data size wanted */
+		ifs->type = IF_PROTO_HDLC_ETH;
+		if (ifs->size < size) {
+			ifs->size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
 		if (copy_to_user(raw_s, hdlc->state, size))
diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c
index 9b7ebf8bd85c..f72c92c24003 100644
--- a/drivers/net/wan/hdlc_x25.c
+++ b/drivers/net/wan/hdlc_x25.c
@@ -29,7 +29,7 @@ struct x25_state {
 	struct tasklet_struct rx_tasklet;
 };
 
-static int x25_ioctl(struct net_device *dev, struct ifreq *ifr);
+static int x25_ioctl(struct net_device *dev, struct if_settings *ifs);
 
 static struct x25_state *state(hdlc_device *hdlc)
 {
@@ -274,21 +274,21 @@ static struct hdlc_proto proto = {
 	.module		= THIS_MODULE,
 };
 
-static int x25_ioctl(struct net_device *dev, struct ifreq *ifr)
+static int x25_ioctl(struct net_device *dev, struct if_settings *ifs)
 {
-	x25_hdlc_proto __user *x25_s = ifr->ifr_settings.ifs_ifsu.x25;
+	x25_hdlc_proto __user *x25_s = ifs->ifs_ifsu.x25;
 	const size_t size = sizeof(x25_hdlc_proto);
 	hdlc_device *hdlc = dev_to_hdlc(dev);
 	x25_hdlc_proto new_settings;
 	int result;
 
-	switch (ifr->ifr_settings.type) {
+	switch (ifs->type) {
 	case IF_GET_PROTO:
 		if (dev_to_hdlc(dev)->proto != &proto)
 			return -EINVAL;
-		ifr->ifr_settings.type = IF_PROTO_X25;
-		if (ifr->ifr_settings.size < size) {
-			ifr->ifr_settings.size = size; /* data size wanted */
+		ifs->type = IF_PROTO_X25;
+		if (ifs->size < size) {
+			ifs->size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
 		if (copy_to_user(x25_s, &state(hdlc)->settings, size))
@@ -303,7 +303,7 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr)
 			return -EBUSY;
 
 		/* backward compatibility */
-		if (ifr->ifr_settings.size == 0) {
+		if (ifs->size == 0) {
 			new_settings.dce = 0;
 			new_settings.modulo = 8;
 			new_settings.window = 7;
diff --git a/drivers/net/wan/hostess_sv11.c b/drivers/net/wan/hostess_sv11.c
index fd61a7cc4fdf..e985e54ba75d 100644
--- a/drivers/net/wan/hostess_sv11.c
+++ b/drivers/net/wan/hostess_sv11.c
@@ -142,11 +142,6 @@ static int hostess_close(struct net_device *d)
 	return 0;
 }
 
-static int hostess_ioctl(struct net_device *d, struct ifreq *ifr, int cmd)
-{
-	return hdlc_ioctl(d, ifr, cmd);
-}
-
 /*	Passed network frames, fire them downwind.
  */
 
@@ -171,7 +166,7 @@ static const struct net_device_ops hostess_ops = {
 	.ndo_open       = hostess_open,
 	.ndo_stop       = hostess_close,
 	.ndo_start_xmit = hdlc_start_xmit,
-	.ndo_do_ioctl   = hostess_ioctl,
+	.ndo_siocwandev = hdlc_ioctl,
 };
 
 static struct z8530_dev *sv11_init(int iobase, int irq)
@@ -324,16 +319,18 @@ MODULE_DESCRIPTION("Modular driver for the Comtrol Hostess SV11");
 
 static struct z8530_dev *sv11_unit;
 
-int init_module(void)
+static int sv11_module_init(void)
 {
 	sv11_unit = sv11_init(io, irq);
 	if (!sv11_unit)
 		return -ENODEV;
 	return 0;
 }
+module_init(sv11_module_init);
 
-void cleanup_module(void)
+static void sv11_module_cleanup(void)
 {
 	if (sv11_unit)
 		sv11_shutdown(sv11_unit);
 }
+module_exit(sv11_module_cleanup);
diff --git a/drivers/net/wan/ixp4xx_hss.c b/drivers/net/wan/ixp4xx_hss.c
index 3c51ab239fb2..88a36a069311 100644
--- a/drivers/net/wan/ixp4xx_hss.c
+++ b/drivers/net/wan/ixp4xx_hss.c
@@ -975,11 +975,10 @@ static int init_hdlc_queues(struct port *port)
 			return -ENOMEM;
 	}
 
-	port->desc_tab = dma_pool_alloc(dma_pool, GFP_KERNEL,
+	port->desc_tab = dma_pool_zalloc(dma_pool, GFP_KERNEL,
 					&port->desc_tab_phys);
 	if (!port->desc_tab)
 		return -ENOMEM;
-	memset(port->desc_tab, 0, POOL_ALLOC_SIZE);
 	memset(port->rx_buff_tab, 0, sizeof(port->rx_buff_tab)); /* tables */
 	memset(port->tx_buff_tab, 0, sizeof(port->tx_buff_tab));
 
@@ -1255,23 +1254,20 @@ static void find_best_clock(u32 timer_freq, u32 rate, u32 *best, u32 *reg)
 	}
 }
 
-static int hss_hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int hss_hdlc_ioctl(struct net_device *dev, struct if_settings *ifs)
 {
 	const size_t size = sizeof(sync_serial_settings);
 	sync_serial_settings new_line;
-	sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync;
+	sync_serial_settings __user *line = ifs->ifs_ifsu.sync;
 	struct port *port = dev_to_port(dev);
 	unsigned long flags;
 	int clk;
 
-	if (cmd != SIOCWANDEV)
-		return hdlc_ioctl(dev, ifr, cmd);
-
-	switch (ifr->ifr_settings.type) {
+	switch (ifs->type) {
 	case IF_GET_IFACE:
-		ifr->ifr_settings.type = IF_IFACE_V35;
-		if (ifr->ifr_settings.size < size) {
-			ifr->ifr_settings.size = size; /* data size wanted */
+		ifs->type = IF_IFACE_V35;
+		if (ifs->size < size) {
+			ifs->size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
 		memset(&new_line, 0, sizeof(new_line));
@@ -1324,7 +1320,7 @@ static int hss_hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		return 0;
 
 	default:
-		return hdlc_ioctl(dev, ifr, cmd);
+		return hdlc_ioctl(dev, ifs);
 	}
 }
 
@@ -1336,7 +1332,7 @@ static const struct net_device_ops hss_hdlc_ops = {
 	.ndo_open       = hss_hdlc_open,
 	.ndo_stop       = hss_hdlc_close,
 	.ndo_start_xmit = hdlc_start_xmit,
-	.ndo_do_ioctl   = hss_hdlc_ioctl,
+	.ndo_siocwandev = hss_hdlc_ioctl,
 };
 
 static int hss_init_one(struct platform_device *pdev)
diff --git a/drivers/net/wan/lmc/lmc.h b/drivers/net/wan/lmc/lmc.h
index 3bd541c868d5..d7d59b4595f9 100644
--- a/drivers/net/wan/lmc/lmc.h
+++ b/drivers/net/wan/lmc/lmc.h
@@ -19,7 +19,7 @@ void lmc_mii_writereg(lmc_softc_t * const, unsigned, unsigned, unsigned);
 void lmc_gpio_mkinput(lmc_softc_t * const sc, u32 bits);
 void lmc_gpio_mkoutput(lmc_softc_t * const sc, u32 bits);
 
-int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
+int lmc_ioctl(struct net_device *dev, struct if_settings *ifs);
 
 extern lmc_media_t lmc_ds3_media;
 extern lmc_media_t lmc_ssi_media;
diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c
index 6c163db52835..ed687bf6ec47 100644
--- a/drivers/net/wan/lmc/lmc_main.c
+++ b/drivers/net/wan/lmc/lmc_main.c
@@ -105,7 +105,8 @@ static void lmc_driver_timeout(struct net_device *dev, unsigned int txqueue);
  * linux reserves 16 device specific IOCTLs.  We call them
  * LMCIOC* to control various bits of our world.
  */
-int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
+static int lmc_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			      void __user *data, int cmd) /*fold00*/
 {
     lmc_softc_t *sc = dev_to_sc(dev);
     lmc_ctl_t ctl;
@@ -124,7 +125,7 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
          * To date internally, just copy this out to the user.
          */
     case LMCIOCGINFO: /*fold01*/
-	if (copy_to_user(ifr->ifr_data, &sc->ictl, sizeof(lmc_ctl_t)))
+	if (copy_to_user(data, &sc->ictl, sizeof(lmc_ctl_t)))
 		ret = -EFAULT;
 	else
 		ret = 0;
@@ -141,7 +142,7 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
             break;
         }
 
-	if (copy_from_user(&ctl, ifr->ifr_data, sizeof(lmc_ctl_t))) {
+	if (copy_from_user(&ctl, data, sizeof(lmc_ctl_t))) {
 		ret = -EFAULT;
 		break;
 	}
@@ -171,7 +172,7 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
 		break;
 	    }
 
-	    if (copy_from_user(&new_type, ifr->ifr_data, sizeof(u16))) {
+	    if (copy_from_user(&new_type, data, sizeof(u16))) {
 		ret = -EFAULT;
 		break;
 	    }
@@ -211,8 +212,7 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
 
         sc->lmc_xinfo.Magic1 = 0xDEADBEEF;
 
-        if (copy_to_user(ifr->ifr_data, &sc->lmc_xinfo,
-			 sizeof(struct lmc_xinfo)))
+	if (copy_to_user(data, &sc->lmc_xinfo, sizeof(struct lmc_xinfo)))
 		ret = -EFAULT;
 	else
 		ret = 0;
@@ -245,9 +245,9 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
 			    regVal & T1FRAMER_SEF_MASK;
 	    }
 	    spin_unlock_irqrestore(&sc->lmc_lock, flags);
-	    if (copy_to_user(ifr->ifr_data, &sc->lmc_device->stats,
+	    if (copy_to_user(data, &sc->lmc_device->stats,
 			     sizeof(sc->lmc_device->stats)) ||
-		copy_to_user(ifr->ifr_data + sizeof(sc->lmc_device->stats),
+		copy_to_user(data + sizeof(sc->lmc_device->stats),
 			     &sc->extra_stats, sizeof(sc->extra_stats)))
 		    ret = -EFAULT;
 	    else
@@ -282,7 +282,7 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
             break;
         }
 
-	if (copy_from_user(&ctl, ifr->ifr_data, sizeof(lmc_ctl_t))) {
+	if (copy_from_user(&ctl, data, sizeof(lmc_ctl_t))) {
 		ret = -EFAULT;
 		break;
 	}
@@ -314,11 +314,11 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
 
 #ifdef DEBUG
     case LMCIOCDUMPEVENTLOG:
-	if (copy_to_user(ifr->ifr_data, &lmcEventLogIndex, sizeof(u32))) {
+	if (copy_to_user(data, &lmcEventLogIndex, sizeof(u32))) {
 		ret = -EFAULT;
 		break;
 	}
-	if (copy_to_user(ifr->ifr_data + sizeof(u32), lmcEventLogBuf,
+	if (copy_to_user(data + sizeof(u32), lmcEventLogBuf,
 			 sizeof(lmcEventLogBuf)))
 		ret = -EFAULT;
 	else
@@ -346,7 +346,7 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
              */
             netif_stop_queue(dev);
 
-	    if (copy_from_user(&xc, ifr->ifr_data, sizeof(struct lmc_xilinx_control))) {
+	    if (copy_from_user(&xc, data, sizeof(struct lmc_xilinx_control))) {
 		ret = -EFAULT;
 		break;
 	    }
@@ -609,10 +609,8 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
 
         }
         break;
-    default: /*fold01*/
-        /* If we don't know what to do, give the protocol a shot. */
-        ret = lmc_proto_ioctl (sc, ifr, cmd);
-        break;
+    default:
+	break;
     }
 
     return ret;
@@ -788,7 +786,8 @@ static const struct net_device_ops lmc_ops = {
 	.ndo_open       = lmc_open,
 	.ndo_stop       = lmc_close,
 	.ndo_start_xmit = hdlc_start_xmit,
-	.ndo_do_ioctl   = lmc_ioctl,
+	.ndo_siocwandev = hdlc_ioctl,
+	.ndo_siocdevprivate = lmc_siocdevprivate,
 	.ndo_tx_timeout = lmc_driver_timeout,
 	.ndo_get_stats  = lmc_get_stats,
 };
diff --git a/drivers/net/wan/lmc/lmc_proto.c b/drivers/net/wan/lmc/lmc_proto.c
index 4e9cc83b615a..e5487616a816 100644
--- a/drivers/net/wan/lmc/lmc_proto.c
+++ b/drivers/net/wan/lmc/lmc_proto.c
@@ -58,13 +58,6 @@ void lmc_proto_attach(lmc_softc_t *sc) /*FOLD00*/
         }
 }
 
-int lmc_proto_ioctl(lmc_softc_t *sc, struct ifreq *ifr, int cmd)
-{
-	if (sc->if_type == LMC_PPP)
-		return hdlc_ioctl(sc->lmc_device, ifr, cmd);
-	return -EOPNOTSUPP;
-}
-
 int lmc_proto_open(lmc_softc_t *sc)
 {
 	int ret = 0;
diff --git a/drivers/net/wan/lmc/lmc_proto.h b/drivers/net/wan/lmc/lmc_proto.h
index bb098e443776..e56e7072de44 100644
--- a/drivers/net/wan/lmc/lmc_proto.h
+++ b/drivers/net/wan/lmc/lmc_proto.h
@@ -5,7 +5,6 @@
 #include <linux/hdlc.h>
 
 void lmc_proto_attach(lmc_softc_t *sc);
-int lmc_proto_ioctl(lmc_softc_t *sc, struct ifreq *ifr, int cmd);
 int lmc_proto_open(lmc_softc_t *sc);
 void lmc_proto_close(lmc_softc_t *sc);
 __be16 lmc_proto_type(lmc_softc_t *sc, struct sk_buff *skb);
diff --git a/drivers/net/wan/n2.c b/drivers/net/wan/n2.c
index bdb6dc2409bc..f3e80722ba1d 100644
--- a/drivers/net/wan/n2.c
+++ b/drivers/net/wan/n2.c
@@ -227,27 +227,30 @@ static int n2_close(struct net_device *dev)
 	return 0;
 }
 
-static int n2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int n2_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			     void __user *data, int cmd)
 {
-	const size_t size = sizeof(sync_serial_settings);
-	sync_serial_settings new_line;
-	sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync;
-	port_t *port = dev_to_port(dev);
-
 #ifdef DEBUG_RINGS
 	if (cmd == SIOCDEVPRIVATE) {
 		sca_dump_rings(dev);
 		return 0;
 	}
 #endif
-	if (cmd != SIOCWANDEV)
-		return hdlc_ioctl(dev, ifr, cmd);
+	return -EOPNOTSUPP;
+}
+
+static int n2_ioctl(struct net_device *dev, struct if_settings *ifs)
+{
+	const size_t size = sizeof(sync_serial_settings);
+	sync_serial_settings new_line;
+	sync_serial_settings __user *line = ifs->ifs_ifsu.sync;
+	port_t *port = dev_to_port(dev);
 
-	switch (ifr->ifr_settings.type) {
+	switch (ifs->type) {
 	case IF_GET_IFACE:
-		ifr->ifr_settings.type = IF_IFACE_SYNC_SERIAL;
-		if (ifr->ifr_settings.size < size) {
-			ifr->ifr_settings.size = size; /* data size wanted */
+		ifs->type = IF_IFACE_SYNC_SERIAL;
+		if (ifs->size < size) {
+			ifs->size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
 		if (copy_to_user(line, &port->settings, size))
@@ -275,7 +278,7 @@ static int n2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		return 0;
 
 	default:
-		return hdlc_ioctl(dev, ifr, cmd);
+		return hdlc_ioctl(dev, ifs);
 	}
 }
 
@@ -311,7 +314,8 @@ static const struct net_device_ops n2_ops = {
 	.ndo_open       = n2_open,
 	.ndo_stop       = n2_close,
 	.ndo_start_xmit = hdlc_start_xmit,
-	.ndo_do_ioctl   = n2_ioctl,
+	.ndo_siocwandev = n2_ioctl,
+	.ndo_siocdevprivate = n2_siocdevprivate,
 };
 
 static int __init n2_run(unsigned long io, unsigned long irq,
diff --git a/drivers/net/wan/pc300too.c b/drivers/net/wan/pc300too.c
index 7b123a771aa6..4766446f0fa0 100644
--- a/drivers/net/wan/pc300too.c
+++ b/drivers/net/wan/pc300too.c
@@ -174,27 +174,30 @@ static int pc300_close(struct net_device *dev)
 	return 0;
 }
 
-static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int pc300_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+				void __user *data, int cmd)
 {
-	const size_t size = sizeof(sync_serial_settings);
-	sync_serial_settings new_line;
-	sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync;
-	int new_type;
-	port_t *port = dev_to_port(dev);
-
 #ifdef DEBUG_RINGS
 	if (cmd == SIOCDEVPRIVATE) {
 		sca_dump_rings(dev);
 		return 0;
 	}
 #endif
-	if (cmd != SIOCWANDEV)
-		return hdlc_ioctl(dev, ifr, cmd);
+	return -EOPNOTSUPP;
+}
+
+static int pc300_ioctl(struct net_device *dev, struct if_settings *ifs)
+{
+	const size_t size = sizeof(sync_serial_settings);
+	sync_serial_settings new_line;
+	sync_serial_settings __user *line = ifs->ifs_ifsu.sync;
+	int new_type;
+	port_t *port = dev_to_port(dev);
 
-	if (ifr->ifr_settings.type == IF_GET_IFACE) {
-		ifr->ifr_settings.type = port->iface;
-		if (ifr->ifr_settings.size < size) {
-			ifr->ifr_settings.size = size; /* data size wanted */
+	if (ifs->type == IF_GET_IFACE) {
+		ifs->type = port->iface;
+		if (ifs->size < size) {
+			ifs->size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
 		if (copy_to_user(line, &port->settings, size))
@@ -203,21 +206,21 @@ static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	}
 
 	if (port->card->type == PC300_X21 &&
-	    (ifr->ifr_settings.type == IF_IFACE_SYNC_SERIAL ||
-	     ifr->ifr_settings.type == IF_IFACE_X21))
+	    (ifs->type == IF_IFACE_SYNC_SERIAL ||
+	     ifs->type == IF_IFACE_X21))
 		new_type = IF_IFACE_X21;
 
 	else if (port->card->type == PC300_RSV &&
-		 (ifr->ifr_settings.type == IF_IFACE_SYNC_SERIAL ||
-		  ifr->ifr_settings.type == IF_IFACE_V35))
+		 (ifs->type == IF_IFACE_SYNC_SERIAL ||
+		  ifs->type == IF_IFACE_V35))
 		new_type = IF_IFACE_V35;
 
 	else if (port->card->type == PC300_RSV &&
-		 ifr->ifr_settings.type == IF_IFACE_V24)
+		 ifs->type == IF_IFACE_V24)
 		new_type = IF_IFACE_V24;
 
 	else
-		return hdlc_ioctl(dev, ifr, cmd);
+		return hdlc_ioctl(dev, ifs);
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -272,7 +275,8 @@ static const struct net_device_ops pc300_ops = {
 	.ndo_open       = pc300_open,
 	.ndo_stop       = pc300_close,
 	.ndo_start_xmit = hdlc_start_xmit,
-	.ndo_do_ioctl   = pc300_ioctl,
+	.ndo_siocwandev = pc300_ioctl,
+	.ndo_siocdevprivate = pc300_siocdevprivate,
 };
 
 static int pc300_pci_init_one(struct pci_dev *pdev,
diff --git a/drivers/net/wan/pci200syn.c b/drivers/net/wan/pci200syn.c
index dee9c4e15eca..ea86c7035653 100644
--- a/drivers/net/wan/pci200syn.c
+++ b/drivers/net/wan/pci200syn.c
@@ -167,27 +167,30 @@ static int pci200_close(struct net_device *dev)
 	return 0;
 }
 
-static int pci200_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int pci200_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+				 void __user *data, int cmd)
 {
-	const size_t size = sizeof(sync_serial_settings);
-	sync_serial_settings new_line;
-	sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync;
-	port_t *port = dev_to_port(dev);
-
 #ifdef DEBUG_RINGS
 	if (cmd == SIOCDEVPRIVATE) {
 		sca_dump_rings(dev);
 		return 0;
 	}
 #endif
-	if (cmd != SIOCWANDEV)
-		return hdlc_ioctl(dev, ifr, cmd);
+	return -EOPNOTSUPP;
+}
+
+static int pci200_ioctl(struct net_device *dev, struct if_settings *ifs)
+{
+	const size_t size = sizeof(sync_serial_settings);
+	sync_serial_settings new_line;
+	sync_serial_settings __user *line = ifs->ifs_ifsu.sync;
+	port_t *port = dev_to_port(dev);
 
-	switch (ifr->ifr_settings.type) {
+	switch (ifs->type) {
 	case IF_GET_IFACE:
-		ifr->ifr_settings.type = IF_IFACE_V35;
-		if (ifr->ifr_settings.size < size) {
-			ifr->ifr_settings.size = size; /* data size wanted */
+		ifs->type = IF_IFACE_V35;
+		if (ifs->size < size) {
+			ifs->size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
 		if (copy_to_user(line, &port->settings, size))
@@ -217,7 +220,7 @@ static int pci200_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		return 0;
 
 	default:
-		return hdlc_ioctl(dev, ifr, cmd);
+		return hdlc_ioctl(dev, ifs);
 	}
 }
 
@@ -253,7 +256,8 @@ static const struct net_device_ops pci200_ops = {
 	.ndo_open       = pci200_open,
 	.ndo_stop       = pci200_close,
 	.ndo_start_xmit = hdlc_start_xmit,
-	.ndo_do_ioctl   = pci200_ioctl,
+	.ndo_siocwandev = pci200_ioctl,
+	.ndo_siocdevprivate = pci200_siocdevprivate,
 };
 
 static int pci200_pci_init_one(struct pci_dev *pdev,
diff --git a/drivers/net/wan/sbni.c b/drivers/net/wan/sbni.c
deleted file mode 100644
index 3092a09d3eaa..000000000000
--- a/drivers/net/wan/sbni.c
+++ /dev/null
@@ -1,1638 +0,0 @@
-/* sbni.c:  Granch SBNI12 leased line adapters driver for linux
- *
- *	Written 2001 by Denis I.Timofeev (timofeev@granch.ru)
- *
- *	Previous versions were written by Yaroslav Polyakov,
- *	Alexey Zverev and Max Khon.
- *
- *	Driver supports SBNI12-02,-04,-05,-10,-11 cards, single and
- *	double-channel, PCI and ISA modifications.
- *	More info and useful utilities to work with SBNI12 cards you can find
- *	at http://www.granch.com (English) or http://www.granch.ru (Russian)
- *
- *	This software may be used and distributed according to the terms
- *	of the GNU General Public License.
- *
- *
- *  5.0.1	Jun 22 2001
- *	  - Fixed bug in probe
- *  5.0.0	Jun 06 2001
- *	  - Driver was completely redesigned by Denis I.Timofeev,
- *	  - now PCI/Dual, ISA/Dual (with single interrupt line) models are
- *	  - supported
- *  3.3.0	Thu Feb 24 21:30:28 NOVT 2000 
- *        - PCI cards support
- *  3.2.0	Mon Dec 13 22:26:53 NOVT 1999
- * 	  - Completely rebuilt all the packet storage system
- * 	  -    to work in Ethernet-like style.
- *  3.1.1	just fixed some bugs (5 aug 1999)
- *  3.1.0	added balancing feature	(26 apr 1999)
- *  3.0.1	just fixed some bugs (14 apr 1999).
- *  3.0.0	Initial Revision, Yaroslav Polyakov (24 Feb 1999)
- *        - added pre-calculation for CRC, fixed bug with "len-2" frames, 
- *        - removed outbound fragmentation (MTU=1000), written CRC-calculation 
- *        - on asm, added work with hard_headers and now we have our own cache 
- *        - for them, optionally supported word-interchange on some chipsets,
- * 
- *	Known problem: this driver wasn't tested on multiprocessor machine.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/ptrace.h>
-#include <linux/fcntl.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/pci.h>
-#include <linux/skbuff.h>
-#include <linux/timer.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-
-#include <net/net_namespace.h>
-#include <net/arp.h>
-#include <net/Space.h>
-
-#include <asm/io.h>
-#include <asm/types.h>
-#include <asm/byteorder.h>
-#include <asm/irq.h>
-#include <linux/uaccess.h>
-
-#include "sbni.h"
-
-/* device private data */
-
-struct net_local {
-	struct timer_list	watchdog;
-	struct net_device	*watchdog_dev;
-
-	spinlock_t	lock;
-	struct sk_buff  *rx_buf_p;		/* receive buffer ptr */
-	struct sk_buff  *tx_buf_p;		/* transmit buffer ptr */
-	
-	unsigned int	framelen;		/* current frame length */
-	unsigned int	maxframe;		/* maximum valid frame length */
-	unsigned int	state;
-	unsigned int	inppos, outpos;		/* positions in rx/tx buffers */
-
-	/* transmitting frame number - from frames qty to 1 */
-	unsigned int	tx_frameno;
-
-	/* expected number of next receiving frame */
-	unsigned int	wait_frameno;
-
-	/* count of failed attempts to frame send - 32 attempts do before
-	   error - while receiver tunes on opposite side of wire */
-	unsigned int	trans_errors;
-
-	/* idle time; send pong when limit exceeded */
-	unsigned int	timer_ticks;
-
-	/* fields used for receive level autoselection */
-	int	delta_rxl;
-	unsigned int	cur_rxl_index, timeout_rxl;
-	unsigned long	cur_rxl_rcvd, prev_rxl_rcvd;
-
-	struct sbni_csr1	csr1;		/* current value of CSR1 */
-	struct sbni_in_stats	in_stats; 	/* internal statistics */ 
-
-	struct net_device		*second;	/* for ISA/dual cards */
-
-#ifdef CONFIG_SBNI_MULTILINE
-	struct net_device		*master;
-	struct net_device		*link;
-#endif
-};
-
-
-static int  sbni_card_probe( unsigned long );
-static int  sbni_pci_probe( struct net_device  * );
-static struct net_device  *sbni_probe1(struct net_device *, unsigned long, int);
-static int  sbni_open( struct net_device * );
-static int  sbni_close( struct net_device * );
-static netdev_tx_t sbni_start_xmit(struct sk_buff *,
-					 struct net_device * );
-static int  sbni_ioctl( struct net_device *, struct ifreq *, int );
-static void  set_multicast_list( struct net_device * );
-
-static irqreturn_t sbni_interrupt( int, void * );
-static void  handle_channel( struct net_device * );
-static int   recv_frame( struct net_device * );
-static void  send_frame( struct net_device * );
-static int   upload_data( struct net_device *,
-			  unsigned, unsigned, unsigned, u32 );
-static void  download_data( struct net_device *, u32 * );
-static void  sbni_watchdog(struct timer_list *);
-static void  interpret_ack( struct net_device *, unsigned );
-static int   append_frame_to_pkt( struct net_device *, unsigned, u32 );
-static void  indicate_pkt( struct net_device * );
-static void  card_start( struct net_device * );
-static void  prepare_to_send( struct sk_buff *, struct net_device * );
-static void  drop_xmit_queue( struct net_device * );
-static void  send_frame_header( struct net_device *, u32 * );
-static int   skip_tail( unsigned int, unsigned int, u32 );
-static int   check_fhdr( u32, u32 *, u32 *, u32 *, u32 *, u32 * );
-static void  change_level( struct net_device * );
-static void  timeout_change_level( struct net_device * );
-static u32   calc_crc32( u32, u8 *, u32 );
-static struct sk_buff *  get_rx_buf( struct net_device * );
-static int  sbni_init( struct net_device * );
-
-#ifdef CONFIG_SBNI_MULTILINE
-static int  enslave( struct net_device *, struct net_device * );
-static int  emancipate( struct net_device * );
-#endif
-
-static const char  version[] =
-	"Granch SBNI12 driver ver 5.0.1  Jun 22 2001  Denis I.Timofeev.\n";
-
-static bool skip_pci_probe	__initdata = false;
-static int  scandone	__initdata = 0;
-static int  num		__initdata = 0;
-
-static unsigned char  rxl_tab[];
-static u32  crc32tab[];
-
-/* A list of all installed devices, for removing the driver module. */
-static struct net_device  *sbni_cards[ SBNI_MAX_NUM_CARDS ];
-
-/* Lists of device's parameters */
-static u32	io[   SBNI_MAX_NUM_CARDS ] __initdata =
-	{ [0 ... SBNI_MAX_NUM_CARDS-1] = -1 };
-static u32	irq[  SBNI_MAX_NUM_CARDS ] __initdata;
-static u32	baud[ SBNI_MAX_NUM_CARDS ] __initdata;
-static u32	rxl[  SBNI_MAX_NUM_CARDS ] __initdata =
-	{ [0 ... SBNI_MAX_NUM_CARDS-1] = -1 };
-static u32	mac[  SBNI_MAX_NUM_CARDS ] __initdata;
-
-#ifndef MODULE
-typedef u32  iarr[];
-static iarr *dest[5] __initdata = { &io, &irq, &baud, &rxl, &mac };
-#endif
-
-/* A zero-terminated list of I/O addresses to be probed on ISA bus */
-static unsigned int  netcard_portlist[ ] __initdata = { 
-	0x210, 0x214, 0x220, 0x224, 0x230, 0x234, 0x240, 0x244, 0x250, 0x254,
-	0x260, 0x264, 0x270, 0x274, 0x280, 0x284, 0x290, 0x294, 0x2a0, 0x2a4,
-	0x2b0, 0x2b4, 0x2c0, 0x2c4, 0x2d0, 0x2d4, 0x2e0, 0x2e4, 0x2f0, 0x2f4,
-	0 };
-
-#define NET_LOCAL_LOCK(dev) (((struct net_local *)netdev_priv(dev))->lock)
-
-/*
- * Look for SBNI card which addr stored in dev->base_addr, if nonzero.
- * Otherwise, look through PCI bus. If none PCI-card was found, scan ISA.
- */
-
-static inline int __init
-sbni_isa_probe( struct net_device  *dev )
-{
-	if( dev->base_addr > 0x1ff &&
-	    request_region( dev->base_addr, SBNI_IO_EXTENT, dev->name ) &&
-	    sbni_probe1( dev, dev->base_addr, dev->irq ) )
-
-		return  0;
-	else {
-		pr_err("base address 0x%lx is busy, or adapter is malfunctional!\n",
-		       dev->base_addr);
-		return  -ENODEV;
-	}
-}
-
-static const struct net_device_ops sbni_netdev_ops = {
-	.ndo_open		= sbni_open,
-	.ndo_stop		= sbni_close,
-	.ndo_start_xmit		= sbni_start_xmit,
-	.ndo_set_rx_mode	= set_multicast_list,
-	.ndo_do_ioctl		= sbni_ioctl,
-	.ndo_set_mac_address 	= eth_mac_addr,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-static void __init sbni_devsetup(struct net_device *dev)
-{
-	ether_setup( dev );
-	dev->netdev_ops = &sbni_netdev_ops;
-}
-
-int __init sbni_probe(int unit)
-{
-	struct net_device *dev;
-	int err;
-
-	dev = alloc_netdev(sizeof(struct net_local), "sbni",
-			   NET_NAME_UNKNOWN, sbni_devsetup);
-	if (!dev)
-		return -ENOMEM;
-
-	dev->netdev_ops = &sbni_netdev_ops;
-
-	sprintf(dev->name, "sbni%d", unit);
-	netdev_boot_setup_check(dev);
-
-	err = sbni_init(dev);
-	if (err) {
-		free_netdev(dev);
-		return err;
-	}
-
-	err = register_netdev(dev);
-	if (err) {
-		release_region( dev->base_addr, SBNI_IO_EXTENT );
-		free_netdev(dev);
-		return err;
-	}
-	pr_info_once("%s", version);
-	return 0;
-}
-
-static int __init sbni_init(struct net_device *dev)
-{
-	int  i;
-	if( dev->base_addr )
-		return  sbni_isa_probe( dev );
-	/* otherwise we have to perform search our adapter */
-
-	if( io[ num ] != -1 ) {
-		dev->base_addr	= io[ num ];
-		dev->irq	= irq[ num ];
-	} else if( scandone  ||  io[ 0 ] != -1 ) {
-		return  -ENODEV;
-	}
-
-	/* if io[ num ] contains non-zero address, then that is on ISA bus */
-	if( dev->base_addr )
-		return  sbni_isa_probe( dev );
-
-	/* ...otherwise - scan PCI first */
-	if( !skip_pci_probe  &&  !sbni_pci_probe( dev ) )
-		return  0;
-
-	if( io[ num ] == -1 ) {
-		/* Auto-scan will be stopped when first ISA card were found */
-		scandone = 1;
-		if( num > 0 )
-			return  -ENODEV;
-	}
-
-	for( i = 0;  netcard_portlist[ i ];  ++i ) {
-		int  ioaddr = netcard_portlist[ i ];
-		if( request_region( ioaddr, SBNI_IO_EXTENT, dev->name ) &&
-		    sbni_probe1( dev, ioaddr, 0 ))
-			return 0;
-	}
-
-	return  -ENODEV;
-}
-
-
-static int __init
-sbni_pci_probe( struct net_device  *dev )
-{
-	struct pci_dev  *pdev = NULL;
-
-	while( (pdev = pci_get_class( PCI_CLASS_NETWORK_OTHER << 8, pdev ))
-	       != NULL ) {
-		int  pci_irq_line;
-		unsigned long  pci_ioaddr;
-
-		if( pdev->vendor != SBNI_PCI_VENDOR &&
-		    pdev->device != SBNI_PCI_DEVICE )
-			continue;
-
-		pci_ioaddr = pci_resource_start( pdev, 0 );
-		pci_irq_line = pdev->irq;
-
-		/* Avoid already found cards from previous calls */
-		if( !request_region( pci_ioaddr, SBNI_IO_EXTENT, dev->name ) ) {
-			if (pdev->subsystem_device != 2)
-				continue;
-
-			/* Dual adapter is present */
-			if (!request_region(pci_ioaddr += 4, SBNI_IO_EXTENT,
-							dev->name ) )
-				continue;
-		}
-
-		if (pci_irq_line <= 0 || pci_irq_line >= nr_irqs)
-			pr_warn(
-"WARNING: The PCI BIOS assigned this PCI card to IRQ %d, which is unlikely to work!.\n"
-"You should use the PCI BIOS setup to assign a valid IRQ line.\n",
-				pci_irq_line );
-
-		/* avoiding re-enable dual adapters */
-		if( (pci_ioaddr & 7) == 0  &&  pci_enable_device( pdev ) ) {
-			release_region( pci_ioaddr, SBNI_IO_EXTENT );
-			pci_dev_put( pdev );
-			return  -EIO;
-		}
-		if( sbni_probe1( dev, pci_ioaddr, pci_irq_line ) ) {
-			SET_NETDEV_DEV(dev, &pdev->dev);
-			/* not the best thing to do, but this is all messed up 
-			   for hotplug systems anyway... */
-			pci_dev_put( pdev );
-			return  0;
-		}
-	}
-	return  -ENODEV;
-}
-
-
-static struct net_device * __init
-sbni_probe1( struct net_device  *dev,  unsigned long  ioaddr,  int  irq )
-{
-	struct net_local  *nl;
-
-	if( sbni_card_probe( ioaddr ) ) {
-		release_region( ioaddr, SBNI_IO_EXTENT );
-		return NULL;
-	}
-
-	outb( 0, ioaddr + CSR0 );
-
-	if( irq < 2 ) {
-		unsigned long irq_mask;
-
-		irq_mask = probe_irq_on();
-		outb( EN_INT | TR_REQ, ioaddr + CSR0 );
-		outb( PR_RES, ioaddr + CSR1 );
-		mdelay(50);
-		irq = probe_irq_off(irq_mask);
-		outb( 0, ioaddr + CSR0 );
-
-		if( !irq ) {
-			pr_err("%s: can't detect device irq!\n", dev->name);
-			release_region( ioaddr, SBNI_IO_EXTENT );
-			return NULL;
-		}
-	} else if( irq == 2 )
-		irq = 9;
-
-	dev->irq = irq;
-	dev->base_addr = ioaddr;
-
-	/* Fill in sbni-specific dev fields. */
-	nl = netdev_priv(dev);
-	if( !nl ) {
-		pr_err("%s: unable to get memory!\n", dev->name);
-		release_region( ioaddr, SBNI_IO_EXTENT );
-		return NULL;
-	}
-
-	memset( nl, 0, sizeof(struct net_local) );
-	spin_lock_init( &nl->lock );
-
-	/* store MAC address (generate if that isn't known) */
-	*(__be16 *)dev->dev_addr = htons( 0x00ff );
-	*(__be32 *)(dev->dev_addr + 2) = htonl( 0x01000000 |
-		((mac[num] ?
-		mac[num] :
-		(u32)((long)netdev_priv(dev))) & 0x00ffffff));
-
-	/* store link settings (speed, receive level ) */
-	nl->maxframe  = DEFAULT_FRAME_LEN;
-	nl->csr1.rate = baud[ num ];
-
-	if( (nl->cur_rxl_index = rxl[ num ]) == -1 ) {
-		/* autotune rxl */
-		nl->cur_rxl_index = DEF_RXL;
-		nl->delta_rxl = DEF_RXL_DELTA;
-	} else {
-		nl->delta_rxl = 0;
-	}
-	nl->csr1.rxl  = rxl_tab[ nl->cur_rxl_index ];
-	if( inb( ioaddr + CSR0 ) & 0x01 )
-		nl->state |= FL_SLOW_MODE;
-
-	pr_notice("%s: ioaddr %#lx, irq %d, MAC: 00:ff:01:%02x:%02x:%02x\n",
-		  dev->name, dev->base_addr, dev->irq,
-		  ((u8 *)dev->dev_addr)[3],
-		  ((u8 *)dev->dev_addr)[4],
-		  ((u8 *)dev->dev_addr)[5]);
-
-	pr_notice("%s: speed %d",
-		  dev->name,
-		  ((nl->state & FL_SLOW_MODE) ? 500000 : 2000000)
-		  / (1 << nl->csr1.rate));
-
-	if( nl->delta_rxl == 0 )
-		pr_cont(", receive level 0x%x (fixed)\n", nl->cur_rxl_index);
-	else
-		pr_cont(", receive level (auto)\n");
-
-#ifdef CONFIG_SBNI_MULTILINE
-	nl->master = dev;
-	nl->link   = NULL;
-#endif
-   
-	sbni_cards[ num++ ] = dev;
-	return  dev;
-}
-
-/* -------------------------------------------------------------------------- */
-
-#ifdef CONFIG_SBNI_MULTILINE
-
-static netdev_tx_t
-sbni_start_xmit( struct sk_buff  *skb,  struct net_device  *dev )
-{
-	struct net_device  *p;
-
-	netif_stop_queue( dev );
-
-	/* Looking for idle device in the list */
-	for( p = dev;  p; ) {
-		struct net_local  *nl = netdev_priv(p);
-		spin_lock( &nl->lock );
-		if( nl->tx_buf_p  ||  (nl->state & FL_LINE_DOWN) ) {
-			p = nl->link;
-			spin_unlock( &nl->lock );
-		} else {
-			/* Idle dev is found */
-			prepare_to_send( skb, p );
-			spin_unlock( &nl->lock );
-			netif_start_queue( dev );
-			return NETDEV_TX_OK;
-		}
-	}
-
-	return NETDEV_TX_BUSY;
-}
-
-#else	/* CONFIG_SBNI_MULTILINE */
-
-static netdev_tx_t
-sbni_start_xmit( struct sk_buff  *skb,  struct net_device  *dev )
-{
-	struct net_local  *nl  = netdev_priv(dev);
-
-	netif_stop_queue( dev );
-	spin_lock( &nl->lock );
-
-	prepare_to_send( skb, dev );
-
-	spin_unlock( &nl->lock );
-	return NETDEV_TX_OK;
-}
-
-#endif	/* CONFIG_SBNI_MULTILINE */
-
-/* -------------------------------------------------------------------------- */
-
-/* interrupt handler */
-
-/*
- * 	SBNI12D-10, -11/ISA boards within "common interrupt" mode could not
- * be looked as two independent single-channel devices. Every channel seems
- * as Ethernet interface but interrupt handler must be common. Really, first
- * channel ("master") driver only registers the handler. In its struct net_local
- * it has got pointer to "slave" channel's struct net_local and handles that's
- * interrupts too.
- *	dev of successfully attached ISA SBNI boards is linked to list.
- * While next board driver is initialized, it scans this list. If one
- * has found dev with same irq and ioaddr different by 4 then it assumes
- * this board to be "master".
- */ 
-
-static irqreturn_t
-sbni_interrupt( int  irq,  void  *dev_id )
-{
-	struct net_device	  *dev = dev_id;
-	struct net_local  *nl  = netdev_priv(dev);
-	int	repeat;
-
-	spin_lock( &nl->lock );
-	if( nl->second )
-		spin_lock(&NET_LOCAL_LOCK(nl->second));
-
-	do {
-		repeat = 0;
-		if( inb( dev->base_addr + CSR0 ) & (RC_RDY | TR_RDY) ) {
-			handle_channel( dev );
-			repeat = 1;
-		}
-		if( nl->second  && 	/* second channel present */
-		    (inb( nl->second->base_addr+CSR0 ) & (RC_RDY | TR_RDY)) ) {
-			handle_channel( nl->second );
-			repeat = 1;
-		}
-	} while( repeat );
-
-	if( nl->second )
-		spin_unlock(&NET_LOCAL_LOCK(nl->second));
-	spin_unlock( &nl->lock );
-	return IRQ_HANDLED;
-}
-
-
-static void
-handle_channel( struct net_device  *dev )
-{
-	struct net_local	*nl    = netdev_priv(dev);
-	unsigned long		ioaddr = dev->base_addr;
-
-	int  req_ans;
-	unsigned char  csr0;
-
-#ifdef CONFIG_SBNI_MULTILINE
-	/* Lock the master device because we going to change its local data */
-	if( nl->state & FL_SLAVE )
-		spin_lock(&NET_LOCAL_LOCK(nl->master));
-#endif
-
-	outb( (inb( ioaddr + CSR0 ) & ~EN_INT) | TR_REQ, ioaddr + CSR0 );
-
-	nl->timer_ticks = CHANGE_LEVEL_START_TICKS;
-	for(;;) {
-		csr0 = inb( ioaddr + CSR0 );
-		if( ( csr0 & (RC_RDY | TR_RDY) ) == 0 )
-			break;
-
-		req_ans = !(nl->state & FL_PREV_OK);
-
-		if( csr0 & RC_RDY )
-			req_ans = recv_frame( dev );
-
-		/*
-		 * TR_RDY always equals 1 here because we have owned the marker,
-		 * and we set TR_REQ when disabled interrupts
-		 */
-		csr0 = inb( ioaddr + CSR0 );
-		if( !(csr0 & TR_RDY)  ||  (csr0 & RC_RDY) )
-			netdev_err(dev, "internal error!\n");
-
-		/* if state & FL_NEED_RESEND != 0 then tx_frameno != 0 */
-		if( req_ans  ||  nl->tx_frameno != 0 )
-			send_frame( dev );
-		else
-			/* send marker without any data */
-			outb( inb( ioaddr + CSR0 ) & ~TR_REQ, ioaddr + CSR0 );
-	}
-
-	outb( inb( ioaddr + CSR0 ) | EN_INT, ioaddr + CSR0 );
-
-#ifdef CONFIG_SBNI_MULTILINE
-	if( nl->state & FL_SLAVE )
-		spin_unlock(&NET_LOCAL_LOCK(nl->master));
-#endif
-}
-
-
-/*
- * Routine returns 1 if it needs to acknowledge received frame.
- * Empty frame received without errors won't be acknowledged.
- */
-
-static int
-recv_frame( struct net_device  *dev )
-{
-	struct net_local  *nl   = netdev_priv(dev);
-	unsigned long  ioaddr	= dev->base_addr;
-
-	u32  crc = CRC32_INITIAL;
-
-	unsigned  framelen = 0, frameno, ack;
-	unsigned  is_first, frame_ok = 0;
-
-	if( check_fhdr( ioaddr, &framelen, &frameno, &ack, &is_first, &crc ) ) {
-		frame_ok = framelen > 4
-			?  upload_data( dev, framelen, frameno, is_first, crc )
-			:  skip_tail( ioaddr, framelen, crc );
-		if( frame_ok )
-			interpret_ack( dev, ack );
-	}
-
-	outb( inb( ioaddr + CSR0 ) ^ CT_ZER, ioaddr + CSR0 );
-	if( frame_ok ) {
-		nl->state |= FL_PREV_OK;
-		if( framelen > 4 )
-			nl->in_stats.all_rx_number++;
-	} else {
-		nl->state &= ~FL_PREV_OK;
-		change_level( dev );
-		nl->in_stats.all_rx_number++;
-		nl->in_stats.bad_rx_number++;
-	}
-
-	return  !frame_ok  ||  framelen > 4;
-}
-
-
-static void
-send_frame( struct net_device  *dev )
-{
-	struct net_local  *nl    = netdev_priv(dev);
-
-	u32  crc = CRC32_INITIAL;
-
-	if( nl->state & FL_NEED_RESEND ) {
-
-		/* if frame was sended but not ACK'ed - resend it */
-		if( nl->trans_errors ) {
-			--nl->trans_errors;
-			if( nl->framelen != 0 )
-				nl->in_stats.resend_tx_number++;
-		} else {
-			/* cannot xmit with many attempts */
-#ifdef CONFIG_SBNI_MULTILINE
-			if( (nl->state & FL_SLAVE)  ||  nl->link )
-#endif
-			nl->state |= FL_LINE_DOWN;
-			drop_xmit_queue( dev );
-			goto  do_send;
-		}
-	} else
-		nl->trans_errors = TR_ERROR_COUNT;
-
-	send_frame_header( dev, &crc );
-	nl->state |= FL_NEED_RESEND;
-	/*
-	 * FL_NEED_RESEND will be cleared after ACK, but if empty
-	 * frame sended then in prepare_to_send next frame
-	 */
-
-
-	if( nl->framelen ) {
-		download_data( dev, &crc );
-		nl->in_stats.all_tx_number++;
-		nl->state |= FL_WAIT_ACK;
-	}
-
-	outsb( dev->base_addr + DAT, (u8 *)&crc, sizeof crc );
-
-do_send:
-	outb( inb( dev->base_addr + CSR0 ) & ~TR_REQ, dev->base_addr + CSR0 );
-
-	if( nl->tx_frameno )
-		/* next frame exists - we request card to send it */
-		outb( inb( dev->base_addr + CSR0 ) | TR_REQ,
-		      dev->base_addr + CSR0 );
-}
-
-
-/*
- * Write the frame data into adapter's buffer memory, and calculate CRC.
- * Do padding if necessary.
- */
-
-static void
-download_data( struct net_device  *dev,  u32  *crc_p )
-{
-	struct net_local  *nl    = netdev_priv(dev);
-	struct sk_buff    *skb	 = nl->tx_buf_p;
-
-	unsigned  len = min_t(unsigned int, skb->len - nl->outpos, nl->framelen);
-
-	outsb( dev->base_addr + DAT, skb->data + nl->outpos, len );
-	*crc_p = calc_crc32( *crc_p, skb->data + nl->outpos, len );
-
-	/* if packet too short we should write some more bytes to pad */
-	for( len = nl->framelen - len;  len--; ) {
-		outb( 0, dev->base_addr + DAT );
-		*crc_p = CRC32( 0, *crc_p );
-	}
-}
-
-
-static int
-upload_data( struct net_device  *dev,  unsigned  framelen,  unsigned  frameno,
-	     unsigned  is_first,  u32  crc )
-{
-	struct net_local  *nl = netdev_priv(dev);
-
-	int  frame_ok;
-
-	if( is_first ) {
-		nl->wait_frameno = frameno;
-		nl->inppos = 0;
-	}
-
-	if( nl->wait_frameno == frameno ) {
-
-		if( nl->inppos + framelen  <=  ETHER_MAX_LEN )
-			frame_ok = append_frame_to_pkt( dev, framelen, crc );
-
-		/*
-		 * if CRC is right but framelen incorrect then transmitter
-		 * error was occurred... drop entire packet
-		 */
-		else if( (frame_ok = skip_tail( dev->base_addr, framelen, crc ))
-			 != 0 ) {
-			nl->wait_frameno = 0;
-			nl->inppos = 0;
-#ifdef CONFIG_SBNI_MULTILINE
-			nl->master->stats.rx_errors++;
-			nl->master->stats.rx_missed_errors++;
-#else
-		        dev->stats.rx_errors++;
-			dev->stats.rx_missed_errors++;
-#endif
-		}
-			/* now skip all frames until is_first != 0 */
-	} else
-		frame_ok = skip_tail( dev->base_addr, framelen, crc );
-
-	if( is_first  &&  !frame_ok ) {
-		/*
-		 * Frame has been broken, but we had already stored
-		 * is_first... Drop entire packet.
-		 */
-		nl->wait_frameno = 0;
-#ifdef CONFIG_SBNI_MULTILINE
-		nl->master->stats.rx_errors++;
-		nl->master->stats.rx_crc_errors++;
-#else
-		dev->stats.rx_errors++;
-		dev->stats.rx_crc_errors++;
-#endif
-	}
-
-	return  frame_ok;
-}
-
-
-static inline void
-send_complete( struct net_device *dev )
-{
-	struct net_local  *nl = netdev_priv(dev);
-
-#ifdef CONFIG_SBNI_MULTILINE
-	nl->master->stats.tx_packets++;
-	nl->master->stats.tx_bytes += nl->tx_buf_p->len;
-#else
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += nl->tx_buf_p->len;
-#endif
-	dev_consume_skb_irq(nl->tx_buf_p);
-
-	nl->tx_buf_p = NULL;
-
-	nl->outpos = 0;
-	nl->state &= ~(FL_WAIT_ACK | FL_NEED_RESEND);
-	nl->framelen   = 0;
-}
-
-
-static void
-interpret_ack( struct net_device  *dev,  unsigned  ack )
-{
-	struct net_local  *nl = netdev_priv(dev);
-
-	if( ack == FRAME_SENT_OK ) {
-		nl->state &= ~FL_NEED_RESEND;
-
-		if( nl->state & FL_WAIT_ACK ) {
-			nl->outpos += nl->framelen;
-
-			if( --nl->tx_frameno ) {
-				nl->framelen = min_t(unsigned int,
-						   nl->maxframe,
-						   nl->tx_buf_p->len - nl->outpos);
-			} else {
-				send_complete( dev );
-#ifdef CONFIG_SBNI_MULTILINE
-				netif_wake_queue( nl->master );
-#else
-				netif_wake_queue( dev );
-#endif
-			}
-		}
-	}
-
-	nl->state &= ~FL_WAIT_ACK;
-}
-
-
-/*
- * Glue received frame with previous fragments of packet.
- * Indicate packet when last frame would be accepted.
- */
-
-static int
-append_frame_to_pkt( struct net_device  *dev,  unsigned  framelen,  u32  crc )
-{
-	struct net_local  *nl = netdev_priv(dev);
-
-	u8  *p;
-
-	if( nl->inppos + framelen  >  ETHER_MAX_LEN )
-		return  0;
-
-	if( !nl->rx_buf_p  &&  !(nl->rx_buf_p = get_rx_buf( dev )) )
-		return  0;
-
-	p = nl->rx_buf_p->data + nl->inppos;
-	insb( dev->base_addr + DAT, p, framelen );
-	if( calc_crc32( crc, p, framelen ) != CRC32_REMAINDER )
-		return  0;
-
-	nl->inppos += framelen - 4;
-	if( --nl->wait_frameno == 0 )		/* last frame received */
-		indicate_pkt( dev );
-
-	return  1;
-}
-
-
-/*
- * Prepare to start output on adapter.
- * Transmitter will be actually activated when marker is accepted.
- */
-
-static void
-prepare_to_send( struct sk_buff  *skb,  struct net_device  *dev )
-{
-	struct net_local  *nl = netdev_priv(dev);
-
-	unsigned int  len;
-
-	/* nl->tx_buf_p == NULL here! */
-	if( nl->tx_buf_p )
-		netdev_err(dev, "memory leak!\n");
-
-	nl->outpos = 0;
-	nl->state &= ~(FL_WAIT_ACK | FL_NEED_RESEND);
-
-	len = skb->len;
-	if( len < SBNI_MIN_LEN )
-		len = SBNI_MIN_LEN;
-
-	nl->tx_buf_p	= skb;
-	nl->tx_frameno	= DIV_ROUND_UP(len, nl->maxframe);
-	nl->framelen	= len < nl->maxframe  ?  len  :  nl->maxframe;
-
-	outb( inb( dev->base_addr + CSR0 ) | TR_REQ,  dev->base_addr + CSR0 );
-#ifdef CONFIG_SBNI_MULTILINE
-	netif_trans_update(nl->master);
-#else
-	netif_trans_update(dev);
-#endif
-}
-
-
-static void
-drop_xmit_queue( struct net_device  *dev )
-{
-	struct net_local  *nl = netdev_priv(dev);
-
-	if( nl->tx_buf_p ) {
-		dev_kfree_skb_any( nl->tx_buf_p );
-		nl->tx_buf_p = NULL;
-#ifdef CONFIG_SBNI_MULTILINE
-		nl->master->stats.tx_errors++;
-		nl->master->stats.tx_carrier_errors++;
-#else
-		dev->stats.tx_errors++;
-		dev->stats.tx_carrier_errors++;
-#endif
-	}
-
-	nl->tx_frameno	= 0;
-	nl->framelen	= 0;
-	nl->outpos	= 0;
-	nl->state &= ~(FL_WAIT_ACK | FL_NEED_RESEND);
-#ifdef CONFIG_SBNI_MULTILINE
-	netif_start_queue( nl->master );
-	netif_trans_update(nl->master);
-#else
-	netif_start_queue( dev );
-	netif_trans_update(dev);
-#endif
-}
-
-
-static void
-send_frame_header( struct net_device  *dev,  u32  *crc_p )
-{
-	struct net_local  *nl  = netdev_priv(dev);
-
-	u32  crc = *crc_p;
-	u32  len_field = nl->framelen + 6;	/* CRC + frameno + reserved */
-	u8   value;
-
-	if( nl->state & FL_NEED_RESEND )
-		len_field |= FRAME_RETRY;	/* non-first attempt... */
-
-	if( nl->outpos == 0 )
-		len_field |= FRAME_FIRST;
-
-	len_field |= (nl->state & FL_PREV_OK) ? FRAME_SENT_OK : FRAME_SENT_BAD;
-	outb( SBNI_SIG, dev->base_addr + DAT );
-
-	value = (u8) len_field;
-	outb( value, dev->base_addr + DAT );
-	crc = CRC32( value, crc );
-	value = (u8) (len_field >> 8);
-	outb( value, dev->base_addr + DAT );
-	crc = CRC32( value, crc );
-
-	outb( nl->tx_frameno, dev->base_addr + DAT );
-	crc = CRC32( nl->tx_frameno, crc );
-	outb( 0, dev->base_addr + DAT );
-	crc = CRC32( 0, crc );
-	*crc_p = crc;
-}
-
-
-/*
- * if frame tail not needed (incorrect number or received twice),
- * it won't store, but CRC will be calculated
- */
-
-static int
-skip_tail( unsigned int  ioaddr,  unsigned int  tail_len,  u32 crc )
-{
-	while( tail_len-- )
-		crc = CRC32( inb( ioaddr + DAT ), crc );
-
-	return  crc == CRC32_REMAINDER;
-}
-
-
-/*
- * Preliminary checks if frame header is correct, calculates its CRC
- * and split it to simple fields
- */
-
-static int
-check_fhdr( u32  ioaddr,  u32  *framelen,  u32  *frameno,  u32  *ack,
-	    u32  *is_first,  u32  *crc_p )
-{
-	u32  crc = *crc_p;
-	u8   value;
-
-	if( inb( ioaddr + DAT ) != SBNI_SIG )
-		return  0;
-
-	value = inb( ioaddr + DAT );
-	*framelen = (u32)value;
-	crc = CRC32( value, crc );
-	value = inb( ioaddr + DAT );
-	*framelen |= ((u32)value) << 8;
-	crc = CRC32( value, crc );
-
-	*ack = *framelen & FRAME_ACK_MASK;
-	*is_first = (*framelen & FRAME_FIRST) != 0;
-
-	if( (*framelen &= FRAME_LEN_MASK) < 6 ||
-	    *framelen > SBNI_MAX_FRAME - 3 )
-		return  0;
-
-	value = inb( ioaddr + DAT );
-	*frameno = (u32)value;
-	crc = CRC32( value, crc );
-
-	crc = CRC32( inb( ioaddr + DAT ), crc );	/* reserved byte */
-	*framelen -= 2;
-
-	*crc_p = crc;
-	return  1;
-}
-
-
-static struct sk_buff *
-get_rx_buf( struct net_device  *dev )
-{
-	/* +2 is to compensate for the alignment fixup below */
-	struct sk_buff  *skb = dev_alloc_skb( ETHER_MAX_LEN + 2 );
-	if( !skb )
-		return  NULL;
-
-	skb_reserve( skb, 2 );		/* Align IP on longword boundaries */
-	return  skb;
-}
-
-
-static void
-indicate_pkt( struct net_device  *dev )
-{
-	struct net_local  *nl  = netdev_priv(dev);
-	struct sk_buff    *skb = nl->rx_buf_p;
-
-	skb_put( skb, nl->inppos );
-
-#ifdef CONFIG_SBNI_MULTILINE
-	skb->protocol = eth_type_trans( skb, nl->master );
-	netif_rx( skb );
-	++nl->master->stats.rx_packets;
-	nl->master->stats.rx_bytes += nl->inppos;
-#else
-	skb->protocol = eth_type_trans( skb, dev );
-	netif_rx( skb );
-	++dev->stats.rx_packets;
-	dev->stats.rx_bytes += nl->inppos;
-#endif
-	nl->rx_buf_p = NULL;	/* protocol driver will clear this sk_buff */
-}
-
-
-/* -------------------------------------------------------------------------- */
-
-/*
- * Routine checks periodically wire activity and regenerates marker if
- * connect was inactive for a long time.
- */
-
-static void
-sbni_watchdog(struct timer_list *t)
-{
-	struct net_local   *nl  = from_timer(nl, t, watchdog);
-	struct net_device  *dev = nl->watchdog_dev;
-	unsigned long	   flags;
-	unsigned char	   csr0;
-
-	spin_lock_irqsave( &nl->lock, flags );
-
-	csr0 = inb( dev->base_addr + CSR0 );
-	if( csr0 & RC_CHK ) {
-
-		if( nl->timer_ticks ) {
-			if( csr0 & (RC_RDY | BU_EMP) )
-				/* receiving not active */
-				nl->timer_ticks--;
-		} else {
-			nl->in_stats.timeout_number++;
-			if( nl->delta_rxl )
-				timeout_change_level( dev );
-
-			outb( *(u_char *)&nl->csr1 | PR_RES,
-			      dev->base_addr + CSR1 );
-			csr0 = inb( dev->base_addr + CSR0 );
-		}
-	} else
-		nl->state &= ~FL_LINE_DOWN;
-
-	outb( csr0 | RC_CHK, dev->base_addr + CSR0 ); 
-
-	mod_timer(t, jiffies + SBNI_TIMEOUT);
-
-	spin_unlock_irqrestore( &nl->lock, flags );
-}
-
-
-static unsigned char  rxl_tab[] = {
-	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x08,
-	0x0a, 0x0c, 0x0f, 0x16, 0x18, 0x1a, 0x1c, 0x1f
-};
-
-#define SIZE_OF_TIMEOUT_RXL_TAB 4
-static unsigned char  timeout_rxl_tab[] = {
-	0x03, 0x05, 0x08, 0x0b
-};
-
-/* -------------------------------------------------------------------------- */
-
-static void
-card_start( struct net_device  *dev )
-{
-	struct net_local  *nl = netdev_priv(dev);
-
-	nl->timer_ticks = CHANGE_LEVEL_START_TICKS;
-	nl->state &= ~(FL_WAIT_ACK | FL_NEED_RESEND);
-	nl->state |= FL_PREV_OK;
-
-	nl->inppos = nl->outpos = 0;
-	nl->wait_frameno = 0;
-	nl->tx_frameno	 = 0;
-	nl->framelen	 = 0;
-
-	outb( *(u_char *)&nl->csr1 | PR_RES, dev->base_addr + CSR1 );
-	outb( EN_INT, dev->base_addr + CSR0 );
-}
-
-/* -------------------------------------------------------------------------- */
-
-/* Receive level auto-selection */
-
-static void
-change_level( struct net_device  *dev )
-{
-	struct net_local  *nl = netdev_priv(dev);
-
-	if( nl->delta_rxl == 0 )	/* do not auto-negotiate RxL */
-		return;
-
-	if( nl->cur_rxl_index == 0 )
-		nl->delta_rxl = 1;
-	else if( nl->cur_rxl_index == 15 )
-		nl->delta_rxl = -1;
-	else if( nl->cur_rxl_rcvd < nl->prev_rxl_rcvd )
-		nl->delta_rxl = -nl->delta_rxl;
-
-	nl->csr1.rxl = rxl_tab[ nl->cur_rxl_index += nl->delta_rxl ];
-	inb( dev->base_addr + CSR0 );	/* needs for PCI cards */
-	outb( *(u8 *)&nl->csr1, dev->base_addr + CSR1 );
-
-	nl->prev_rxl_rcvd = nl->cur_rxl_rcvd;
-	nl->cur_rxl_rcvd  = 0;
-}
-
-
-static void
-timeout_change_level( struct net_device  *dev )
-{
-	struct net_local  *nl = netdev_priv(dev);
-
-	nl->cur_rxl_index = timeout_rxl_tab[ nl->timeout_rxl ];
-	if( ++nl->timeout_rxl >= 4 )
-		nl->timeout_rxl = 0;
-
-	nl->csr1.rxl = rxl_tab[ nl->cur_rxl_index ];
-	inb( dev->base_addr + CSR0 );
-	outb( *(unsigned char *)&nl->csr1, dev->base_addr + CSR1 );
-
-	nl->prev_rxl_rcvd = nl->cur_rxl_rcvd;
-	nl->cur_rxl_rcvd  = 0;
-}
-
-/* -------------------------------------------------------------------------- */
-
-/*
- *	Open/initialize the board. 
- */
-
-static int
-sbni_open( struct net_device  *dev )
-{
-	struct net_local	*nl = netdev_priv(dev);
-	struct timer_list	*w  = &nl->watchdog;
-
-	/*
-	 * For double ISA adapters within "common irq" mode, we have to
-	 * determine whether primary or secondary channel is initialized,
-	 * and set the irq handler only in first case.
-	 */
-	if( dev->base_addr < 0x400 ) {		/* ISA only */
-		struct net_device  **p = sbni_cards;
-		for( ;  *p  &&  p < sbni_cards + SBNI_MAX_NUM_CARDS;  ++p )
-			if( (*p)->irq == dev->irq &&
-			    ((*p)->base_addr == dev->base_addr + 4 ||
-			     (*p)->base_addr == dev->base_addr - 4) &&
-			    (*p)->flags & IFF_UP ) {
-
-				((struct net_local *) (netdev_priv(*p)))
-					->second = dev;
-				netdev_notice(dev, "using shared irq with %s\n",
-					      (*p)->name);
-				nl->state |= FL_SECONDARY;
-				goto  handler_attached;
-			}
-	}
-
-	if( request_irq(dev->irq, sbni_interrupt, IRQF_SHARED, dev->name, dev) ) {
-		netdev_err(dev, "unable to get IRQ %d\n", dev->irq);
-		return  -EAGAIN;
-	}
-
-handler_attached:
-
-	spin_lock( &nl->lock );
-	memset( &dev->stats, 0, sizeof(struct net_device_stats) );
-	memset( &nl->in_stats, 0, sizeof(struct sbni_in_stats) );
-
-	card_start( dev );
-
-	netif_start_queue( dev );
-
-	/* set timer watchdog */
-	nl->watchdog_dev = dev;
-	timer_setup(w, sbni_watchdog, 0);
-	w->expires	= jiffies + SBNI_TIMEOUT;
-	add_timer( w );
-   
-	spin_unlock( &nl->lock );
-	return 0;
-}
-
-
-static int
-sbni_close( struct net_device  *dev )
-{
-	struct net_local  *nl = netdev_priv(dev);
-
-	if( nl->second  &&  nl->second->flags & IFF_UP ) {
-		netdev_notice(dev, "Secondary channel (%s) is active!\n",
-			      nl->second->name);
-		return  -EBUSY;
-	}
-
-#ifdef CONFIG_SBNI_MULTILINE
-	if( nl->state & FL_SLAVE )
-		emancipate( dev );
-	else
-		while( nl->link )	/* it's master device! */
-			emancipate( nl->link );
-#endif
-
-	spin_lock( &nl->lock );
-
-	nl->second = NULL;
-	drop_xmit_queue( dev );	
-	netif_stop_queue( dev );
-   
-	del_timer( &nl->watchdog );
-
-	outb( 0, dev->base_addr + CSR0 );
-
-	if( !(nl->state & FL_SECONDARY) )
-		free_irq( dev->irq, dev );
-	nl->state &= FL_SECONDARY;
-
-	spin_unlock( &nl->lock );
-	return 0;
-}
-
-
-/*
-	Valid combinations in CSR0 (for probing):
-
-	VALID_DECODER	0000,0011,1011,1010
-
-				    	; 0   ; -
-				TR_REQ	; 1   ; +
-			TR_RDY	    	; 2   ; -
-			TR_RDY	TR_REQ	; 3   ; +
-		BU_EMP		    	; 4   ; +
-		BU_EMP	     	TR_REQ	; 5   ; +
-		BU_EMP	TR_RDY	    	; 6   ; -
-		BU_EMP	TR_RDY	TR_REQ	; 7   ; +
-	RC_RDY 		     		; 8   ; +
-	RC_RDY			TR_REQ	; 9   ; +
-	RC_RDY		TR_RDY		; 10  ; -
-	RC_RDY		TR_RDY	TR_REQ	; 11  ; -
-	RC_RDY	BU_EMP			; 12  ; -
-	RC_RDY	BU_EMP		TR_REQ	; 13  ; -
-	RC_RDY	BU_EMP	TR_RDY		; 14  ; -
-	RC_RDY	BU_EMP	TR_RDY	TR_REQ	; 15  ; -
-*/
-
-#define VALID_DECODER (2 + 8 + 0x10 + 0x20 + 0x80 + 0x100 + 0x200)
-
-
-static int
-sbni_card_probe( unsigned long  ioaddr )
-{
-	unsigned char  csr0;
-
-	csr0 = inb( ioaddr + CSR0 );
-	if( csr0 != 0xff  &&  csr0 != 0x00 ) {
-		csr0 &= ~EN_INT;
-		if( csr0 & BU_EMP )
-			csr0 |= EN_INT;
-      
-		if( VALID_DECODER & (1 << (csr0 >> 4)) )
-			return  0;
-	}
-   
-	return  -ENODEV;
-}
-
-/* -------------------------------------------------------------------------- */
-
-static int
-sbni_ioctl( struct net_device  *dev,  struct ifreq  *ifr,  int  cmd )
-{
-	struct net_local  *nl = netdev_priv(dev);
-	struct sbni_flags  flags;
-	int  error = 0;
-
-#ifdef CONFIG_SBNI_MULTILINE
-	struct net_device  *slave_dev;
-	char  slave_name[ 8 ];
-#endif
-  
-	switch( cmd ) {
-	case  SIOCDEVGETINSTATS :
-		if (copy_to_user( ifr->ifr_data, &nl->in_stats,
-					sizeof(struct sbni_in_stats) ))
-			error = -EFAULT;
-		break;
-
-	case  SIOCDEVRESINSTATS :
-		if (!capable(CAP_NET_ADMIN))
-			return  -EPERM;
-		memset( &nl->in_stats, 0, sizeof(struct sbni_in_stats) );
-		break;
-
-	case  SIOCDEVGHWSTATE :
-		flags.mac_addr	= *(u32 *)(dev->dev_addr + 3);
-		flags.rate	= nl->csr1.rate;
-		flags.slow_mode	= (nl->state & FL_SLOW_MODE) != 0;
-		flags.rxl	= nl->cur_rxl_index;
-		flags.fixed_rxl	= nl->delta_rxl == 0;
-
-		if (copy_to_user( ifr->ifr_data, &flags, sizeof flags ))
-			error = -EFAULT;
-		break;
-
-	case  SIOCDEVSHWSTATE :
-		if (!capable(CAP_NET_ADMIN))
-			return  -EPERM;
-
-		spin_lock( &nl->lock );
-		flags = *(struct sbni_flags*) &ifr->ifr_ifru;
-		if( flags.fixed_rxl ) {
-			nl->delta_rxl = 0;
-			nl->cur_rxl_index = flags.rxl;
-		} else {
-			nl->delta_rxl = DEF_RXL_DELTA;
-			nl->cur_rxl_index = DEF_RXL;
-		}
-
-		nl->csr1.rxl = rxl_tab[ nl->cur_rxl_index ];
-		nl->csr1.rate = flags.rate;
-		outb( *(u8 *)&nl->csr1 | PR_RES, dev->base_addr + CSR1 );
-		spin_unlock( &nl->lock );
-		break;
-
-#ifdef CONFIG_SBNI_MULTILINE
-
-	case  SIOCDEVENSLAVE :
-		if (!capable(CAP_NET_ADMIN))
-			return  -EPERM;
-
-		if (copy_from_user( slave_name, ifr->ifr_data, sizeof slave_name ))
-			return -EFAULT;
-		slave_dev = dev_get_by_name(&init_net, slave_name );
-		if( !slave_dev  ||  !(slave_dev->flags & IFF_UP) ) {
-			netdev_err(dev, "trying to enslave non-active device %s\n",
-				   slave_name);
-			if (slave_dev)
-				dev_put(slave_dev);
-			return  -EPERM;
-		}
-
-		return  enslave( dev, slave_dev );
-
-	case  SIOCDEVEMANSIPATE :
-		if (!capable(CAP_NET_ADMIN))
-			return  -EPERM;
-
-		return  emancipate( dev );
-
-#endif	/* CONFIG_SBNI_MULTILINE */
-
-	default :
-		return  -EOPNOTSUPP;
-	}
-
-	return  error;
-}
-
-
-#ifdef CONFIG_SBNI_MULTILINE
-
-static int
-enslave( struct net_device  *dev,  struct net_device  *slave_dev )
-{
-	struct net_local  *nl  = netdev_priv(dev);
-	struct net_local  *snl = netdev_priv(slave_dev);
-
-	if( nl->state & FL_SLAVE )	/* This isn't master or free device */
-		return  -EBUSY;
-
-	if( snl->state & FL_SLAVE )	/* That was already enslaved */
-		return  -EBUSY;
-
-	spin_lock( &nl->lock );
-	spin_lock( &snl->lock );
-
-	/* append to list */
-	snl->link = nl->link;
-	nl->link  = slave_dev;
-	snl->master = dev;
-	snl->state |= FL_SLAVE;
-
-	/* Summary statistics of MultiLine operation will be stored
-	   in master's counters */
-	memset( &slave_dev->stats, 0, sizeof(struct net_device_stats) );
-	netif_stop_queue( slave_dev );
-	netif_wake_queue( dev );	/* Now we are able to transmit */
-
-	spin_unlock( &snl->lock );
-	spin_unlock( &nl->lock );
-	netdev_notice(dev, "slave device (%s) attached\n", slave_dev->name);
-	return  0;
-}
-
-
-static int
-emancipate( struct net_device  *dev )
-{
-	struct net_local   *snl = netdev_priv(dev);
-	struct net_device  *p   = snl->master;
-	struct net_local   *nl  = netdev_priv(p);
-
-	if( !(snl->state & FL_SLAVE) )
-		return  -EINVAL;
-
-	spin_lock( &nl->lock );
-	spin_lock( &snl->lock );
-	drop_xmit_queue( dev );
-
-	/* exclude from list */
-	for(;;) {	/* must be in list */
-		struct net_local  *t = netdev_priv(p);
-		if( t->link == dev ) {
-			t->link = snl->link;
-			break;
-		}
-		p = t->link;
-	}
-
-	snl->link = NULL;
-	snl->master = dev;
-	snl->state &= ~FL_SLAVE;
-
-	netif_start_queue( dev );
-
-	spin_unlock( &snl->lock );
-	spin_unlock( &nl->lock );
-
-	dev_put( dev );
-	return  0;
-}
-
-#endif
-
-static void
-set_multicast_list( struct net_device  *dev )
-{
-	return;		/* sbni always operate in promiscuos mode */
-}
-
-
-#ifdef MODULE
-module_param_hw_array(io, int, ioport, NULL, 0);
-module_param_hw_array(irq, int, irq, NULL, 0);
-module_param_array(baud, int, NULL, 0);
-module_param_array(rxl, int, NULL, 0);
-module_param_array(mac, int, NULL, 0);
-module_param(skip_pci_probe, bool, 0);
-
-MODULE_LICENSE("GPL");
-
-
-int __init init_module( void )
-{
-	struct net_device  *dev;
-	int err;
-
-	while( num < SBNI_MAX_NUM_CARDS ) {
-		dev = alloc_netdev(sizeof(struct net_local), "sbni%d",
-				   NET_NAME_UNKNOWN, sbni_devsetup);
-		if( !dev)
-			break;
-
-		sprintf( dev->name, "sbni%d", num );
-
-		err = sbni_init(dev);
-		if (err) {
-			free_netdev(dev);
-			break;
-		}
-
-		if( register_netdev( dev ) ) {
-			release_region( dev->base_addr, SBNI_IO_EXTENT );
-			free_netdev( dev );
-			break;
-		}
-	}
-
-	return  *sbni_cards  ?  0  :  -ENODEV;
-}
-
-void
-cleanup_module(void)
-{
-	int i;
-
-	for (i = 0;  i < SBNI_MAX_NUM_CARDS;  ++i) {
-		struct net_device *dev = sbni_cards[i];
-		if (dev != NULL) {
-			unregister_netdev(dev);
-			release_region(dev->base_addr, SBNI_IO_EXTENT);
-			free_netdev(dev);
-		}
-	}
-}
-
-#else	/* MODULE */
-
-static int __init
-sbni_setup( char  *p )
-{
-	int  n, parm;
-
-	if( *p++ != '(' )
-		goto  bad_param;
-
-	for( n = 0, parm = 0;  *p  &&  n < 8; ) {
-		(*dest[ parm ])[ n ] = simple_strtoul( p, &p, 0 );
-		if( !*p  ||  *p == ')' )
-			return 1;
-		if( *p == ';' ) {
-			++p;
-			++n;
-			parm = 0;
-		} else if( *p++ != ',' ) {
-			break;
-		} else {
-			if( ++parm >= 5 )
-				break;
-		}
-	}
-bad_param:
-	pr_err("Error in sbni kernel parameter!\n");
-	return 0;
-}
-
-__setup( "sbni=", sbni_setup );
-
-#endif	/* MODULE */
-
-/* -------------------------------------------------------------------------- */
-
-static u32
-calc_crc32( u32  crc,  u8  *p,  u32  len )
-{
-	while( len-- )
-		crc = CRC32( *p++, crc );
-
-	return  crc;
-}
-
-static u32  crc32tab[] __attribute__ ((aligned(8))) = {
-	0xD202EF8D,  0xA505DF1B,  0x3C0C8EA1,  0x4B0BBE37,
-	0xD56F2B94,  0xA2681B02,  0x3B614AB8,  0x4C667A2E,
-	0xDCD967BF,  0xABDE5729,  0x32D70693,  0x45D03605,
-	0xDBB4A3A6,  0xACB39330,  0x35BAC28A,  0x42BDF21C,
-	0xCFB5FFE9,  0xB8B2CF7F,  0x21BB9EC5,  0x56BCAE53,
-	0xC8D83BF0,  0xBFDF0B66,  0x26D65ADC,  0x51D16A4A,
-	0xC16E77DB,  0xB669474D,  0x2F6016F7,  0x58672661,
-	0xC603B3C2,  0xB1048354,  0x280DD2EE,  0x5F0AE278,
-	0xE96CCF45,  0x9E6BFFD3,  0x0762AE69,  0x70659EFF,
-	0xEE010B5C,  0x99063BCA,  0x000F6A70,  0x77085AE6,
-	0xE7B74777,  0x90B077E1,  0x09B9265B,  0x7EBE16CD,
-	0xE0DA836E,  0x97DDB3F8,  0x0ED4E242,  0x79D3D2D4,
-	0xF4DBDF21,  0x83DCEFB7,  0x1AD5BE0D,  0x6DD28E9B,
-	0xF3B61B38,  0x84B12BAE,  0x1DB87A14,  0x6ABF4A82,
-	0xFA005713,  0x8D076785,  0x140E363F,  0x630906A9,
-	0xFD6D930A,  0x8A6AA39C,  0x1363F226,  0x6464C2B0,
-	0xA4DEAE1D,  0xD3D99E8B,  0x4AD0CF31,  0x3DD7FFA7,
-	0xA3B36A04,  0xD4B45A92,  0x4DBD0B28,  0x3ABA3BBE,
-	0xAA05262F,  0xDD0216B9,  0x440B4703,  0x330C7795,
-	0xAD68E236,  0xDA6FD2A0,  0x4366831A,  0x3461B38C,
-	0xB969BE79,  0xCE6E8EEF,  0x5767DF55,  0x2060EFC3,
-	0xBE047A60,  0xC9034AF6,  0x500A1B4C,  0x270D2BDA,
-	0xB7B2364B,  0xC0B506DD,  0x59BC5767,  0x2EBB67F1,
-	0xB0DFF252,  0xC7D8C2C4,  0x5ED1937E,  0x29D6A3E8,
-	0x9FB08ED5,  0xE8B7BE43,  0x71BEEFF9,  0x06B9DF6F,
-	0x98DD4ACC,  0xEFDA7A5A,  0x76D32BE0,  0x01D41B76,
-	0x916B06E7,  0xE66C3671,  0x7F6567CB,  0x0862575D,
-	0x9606C2FE,  0xE101F268,  0x7808A3D2,  0x0F0F9344,
-	0x82079EB1,  0xF500AE27,  0x6C09FF9D,  0x1B0ECF0B,
-	0x856A5AA8,  0xF26D6A3E,  0x6B643B84,  0x1C630B12,
-	0x8CDC1683,  0xFBDB2615,  0x62D277AF,  0x15D54739,
-	0x8BB1D29A,  0xFCB6E20C,  0x65BFB3B6,  0x12B88320,
-	0x3FBA6CAD,  0x48BD5C3B,  0xD1B40D81,  0xA6B33D17,
-	0x38D7A8B4,  0x4FD09822,  0xD6D9C998,  0xA1DEF90E,
-	0x3161E49F,  0x4666D409,  0xDF6F85B3,  0xA868B525,
-	0x360C2086,  0x410B1010,  0xD80241AA,  0xAF05713C,
-	0x220D7CC9,  0x550A4C5F,  0xCC031DE5,  0xBB042D73,
-	0x2560B8D0,  0x52678846,  0xCB6ED9FC,  0xBC69E96A,
-	0x2CD6F4FB,  0x5BD1C46D,  0xC2D895D7,  0xB5DFA541,
-	0x2BBB30E2,  0x5CBC0074,  0xC5B551CE,  0xB2B26158,
-	0x04D44C65,  0x73D37CF3,  0xEADA2D49,  0x9DDD1DDF,
-	0x03B9887C,  0x74BEB8EA,  0xEDB7E950,  0x9AB0D9C6,
-	0x0A0FC457,  0x7D08F4C1,  0xE401A57B,  0x930695ED,
-	0x0D62004E,  0x7A6530D8,  0xE36C6162,  0x946B51F4,
-	0x19635C01,  0x6E646C97,  0xF76D3D2D,  0x806A0DBB,
-	0x1E0E9818,  0x6909A88E,  0xF000F934,  0x8707C9A2,
-	0x17B8D433,  0x60BFE4A5,  0xF9B6B51F,  0x8EB18589,
-	0x10D5102A,  0x67D220BC,  0xFEDB7106,  0x89DC4190,
-	0x49662D3D,  0x3E611DAB,  0xA7684C11,  0xD06F7C87,
-	0x4E0BE924,  0x390CD9B2,  0xA0058808,  0xD702B89E,
-	0x47BDA50F,  0x30BA9599,  0xA9B3C423,  0xDEB4F4B5,
-	0x40D06116,  0x37D75180,  0xAEDE003A,  0xD9D930AC,
-	0x54D13D59,  0x23D60DCF,  0xBADF5C75,  0xCDD86CE3,
-	0x53BCF940,  0x24BBC9D6,  0xBDB2986C,  0xCAB5A8FA,
-	0x5A0AB56B,  0x2D0D85FD,  0xB404D447,  0xC303E4D1,
-	0x5D677172,  0x2A6041E4,  0xB369105E,  0xC46E20C8,
-	0x72080DF5,  0x050F3D63,  0x9C066CD9,  0xEB015C4F,
-	0x7565C9EC,  0x0262F97A,  0x9B6BA8C0,  0xEC6C9856,
-	0x7CD385C7,  0x0BD4B551,  0x92DDE4EB,  0xE5DAD47D,
-	0x7BBE41DE,  0x0CB97148,  0x95B020F2,  0xE2B71064,
-	0x6FBF1D91,  0x18B82D07,  0x81B17CBD,  0xF6B64C2B,
-	0x68D2D988,  0x1FD5E91E,  0x86DCB8A4,  0xF1DB8832,
-	0x616495A3,  0x1663A535,  0x8F6AF48F,  0xF86DC419,
-	0x660951BA,  0x110E612C,  0x88073096,  0xFF000000
-};
-
diff --git a/drivers/net/wan/sbni.h b/drivers/net/wan/sbni.h
deleted file mode 100644
index 84264510a8ed..000000000000
--- a/drivers/net/wan/sbni.h
+++ /dev/null
@@ -1,147 +0,0 @@
-/* sbni.h:  definitions for a Granch SBNI12 driver, version 5.0.0
- * Written 2001 Denis I.Timofeev (timofeev@granch.ru)
- * This file is distributed under the GNU GPL
- */
-
-#ifndef SBNI_H
-#define SBNI_H
-
-#ifdef SBNI_DEBUG
-#define DP( A ) A
-#else
-#define DP( A )
-#endif
-
-
-/* We don't have official vendor id yet... */
-#define SBNI_PCI_VENDOR 	0x55 
-#define SBNI_PCI_DEVICE 	0x9f
-
-#define ISA_MODE 0x00
-#define PCI_MODE 0x01
-
-#define	SBNI_IO_EXTENT	4
-
-enum sbni_reg {
-	CSR0 = 0,
-	CSR1 = 1,
-	DAT  = 2
-};
-
-/* CSR0 mapping */
-enum {
-	BU_EMP = 0x02,
-	RC_CHK = 0x04,
-	CT_ZER = 0x08,
-	TR_REQ = 0x10,
-	TR_RDY = 0x20,
-	EN_INT = 0x40,
-	RC_RDY = 0x80
-};
-
-
-/* CSR1 mapping */
-#define PR_RES 0x80
-
-struct sbni_csr1 {
-#ifdef __LITTLE_ENDIAN_BITFIELD
-	u8 rxl	: 5;
-	u8 rate	: 2;
-	u8 	: 1;
-#else
-	u8 	: 1;
-	u8 rate	: 2;
-	u8 rxl	: 5;
-#endif
-};
-
-/* fields in frame header */
-#define FRAME_ACK_MASK  (unsigned short)0x7000
-#define FRAME_LEN_MASK  (unsigned short)0x03FF
-#define FRAME_FIRST     (unsigned short)0x8000
-#define FRAME_RETRY     (unsigned short)0x0800
-
-#define FRAME_SENT_BAD  (unsigned short)0x4000
-#define FRAME_SENT_OK   (unsigned short)0x3000
-
-
-/* state flags */
-enum {
-	FL_WAIT_ACK    = 0x01,
-	FL_NEED_RESEND = 0x02,
-	FL_PREV_OK     = 0x04,
-	FL_SLOW_MODE   = 0x08,
-	FL_SECONDARY   = 0x10,
-#ifdef CONFIG_SBNI_MULTILINE
-	FL_SLAVE       = 0x20,
-#endif
-	FL_LINE_DOWN   = 0x40
-};
-
-
-enum {
-	DEFAULT_IOBASEADDR = 0x210,
-	DEFAULT_INTERRUPTNUMBER = 5,
-	DEFAULT_RATE = 0,
-	DEFAULT_FRAME_LEN = 1012
-};
-
-#define DEF_RXL_DELTA	-1
-#define DEF_RXL		0xf
-
-#define SBNI_SIG 0x5a
-
-#define	SBNI_MIN_LEN	60	/* Shortest Ethernet frame without FCS */
-#define SBNI_MAX_FRAME	1023
-#define ETHER_MAX_LEN	1518
-
-#define SBNI_TIMEOUT	(HZ/10)
-
-#define TR_ERROR_COUNT	32
-#define CHANGE_LEVEL_START_TICKS 4
-
-#define SBNI_MAX_NUM_CARDS	16
-
-/* internal SBNI-specific statistics */
-struct sbni_in_stats {
-	u32	all_rx_number;
-	u32	bad_rx_number;
-	u32	timeout_number;
-	u32	all_tx_number;
-	u32	resend_tx_number;
-};
-
-/* SBNI ioctl params */
-#define SIOCDEVGETINSTATS 	SIOCDEVPRIVATE
-#define SIOCDEVRESINSTATS 	SIOCDEVPRIVATE+1
-#define SIOCDEVGHWSTATE   	SIOCDEVPRIVATE+2
-#define SIOCDEVSHWSTATE   	SIOCDEVPRIVATE+3
-#define SIOCDEVENSLAVE  	SIOCDEVPRIVATE+4
-#define SIOCDEVEMANSIPATE  	SIOCDEVPRIVATE+5
-
-
-/* data packet for SIOCDEVGHWSTATE/SIOCDEVSHWSTATE ioctl requests */
-struct sbni_flags {
-	u32	rxl		: 4;
-	u32	rate		: 2;
-	u32	fixed_rxl	: 1;
-	u32	slow_mode	: 1;
-	u32	mac_addr	: 24;
-};
-
-/*
- * CRC-32 stuff
- */
-#define CRC32(c,crc) (crc32tab[((size_t)(crc) ^ (c)) & 0xff] ^ (((crc) >> 8) & 0x00FFFFFF))
-      /* CRC generator 0xEDB88320 */
-      /* CRC remainder 0x2144DF1C */
-      /* CRC initial value 0x00000000 */
-#define CRC32_REMAINDER 0x2144DF1C
-#define CRC32_INITIAL 0x00000000
-
-#ifndef __initdata
-#define __initdata
-#endif
-
-#endif
-
diff --git a/drivers/net/wan/sealevel.c b/drivers/net/wan/sealevel.c
index 4403e219ca03..eddd20aab691 100644
--- a/drivers/net/wan/sealevel.c
+++ b/drivers/net/wan/sealevel.c
@@ -124,14 +124,6 @@ static int sealevel_close(struct net_device *d)
 	return 0;
 }
 
-static int sealevel_ioctl(struct net_device *d, struct ifreq *ifr, int cmd)
-{
-	/* struct slvl_device *slvl=dev_to_chan(d);
-	 * z8530_ioctl(d,&slvl->sync.chanA,ifr,cmd)
-	 */
-	return hdlc_ioctl(d, ifr, cmd);
-}
-
 /*	Passed network frames, fire them downwind. */
 
 static netdev_tx_t sealevel_queue_xmit(struct sk_buff *skb,
@@ -152,7 +144,7 @@ static const struct net_device_ops sealevel_ops = {
 	.ndo_open       = sealevel_open,
 	.ndo_stop       = sealevel_close,
 	.ndo_start_xmit = hdlc_start_xmit,
-	.ndo_do_ioctl   = sealevel_ioctl,
+	.ndo_siocwandev = hdlc_ioctl,
 };
 
 static int slvl_setup(struct slvl_device *sv, int iobase, int irq)
diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c
index f22e48415e6f..5a9e262188ef 100644
--- a/drivers/net/wan/wanxl.c
+++ b/drivers/net/wan/wanxl.c
@@ -343,20 +343,17 @@ static int wanxl_attach(struct net_device *dev, unsigned short encoding,
 	return 0;
 }
 
-static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int wanxl_ioctl(struct net_device *dev, struct if_settings *ifs)
 {
 	const size_t size = sizeof(sync_serial_settings);
 	sync_serial_settings line;
 	struct port *port = dev_to_port(dev);
 
-	if (cmd != SIOCWANDEV)
-		return hdlc_ioctl(dev, ifr, cmd);
-
-	switch (ifr->ifr_settings.type) {
+	switch (ifs->type) {
 	case IF_GET_IFACE:
-		ifr->ifr_settings.type = IF_IFACE_SYNC_SERIAL;
-		if (ifr->ifr_settings.size < size) {
-			ifr->ifr_settings.size = size; /* data size wanted */
+		ifs->type = IF_IFACE_SYNC_SERIAL;
+		if (ifs->size < size) {
+			ifs->size = size; /* data size wanted */
 			return -ENOBUFS;
 		}
 		memset(&line, 0, sizeof(line));
@@ -364,7 +361,7 @@ static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		line.clock_rate = 0;
 		line.loopback = 0;
 
-		if (copy_to_user(ifr->ifr_settings.ifs_ifsu.sync, &line, size))
+		if (copy_to_user(ifs->ifs_ifsu.sync, &line, size))
 			return -EFAULT;
 		return 0;
 
@@ -374,7 +371,7 @@ static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		if (dev->flags & IFF_UP)
 			return -EBUSY;
 
-		if (copy_from_user(&line, ifr->ifr_settings.ifs_ifsu.sync,
+		if (copy_from_user(&line, ifs->ifs_ifsu.sync,
 				   size))
 			return -EFAULT;
 
@@ -389,7 +386,7 @@ static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		return 0;
 
 	default:
-		return hdlc_ioctl(dev, ifr, cmd);
+		return hdlc_ioctl(dev, ifs);
 	}
 }
 
@@ -545,7 +542,7 @@ static const struct net_device_ops wanxl_ops = {
 	.ndo_open       = wanxl_open,
 	.ndo_stop       = wanxl_close,
 	.ndo_start_xmit = hdlc_start_xmit,
-	.ndo_do_ioctl   = wanxl_ioctl,
+	.ndo_siocwandev = wanxl_ioctl,
 	.ndo_get_stats  = wanxl_get_stats,
 };
 
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 71878ab35b93..4d4e2f91e15c 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -3393,19 +3393,12 @@ static int ath10k_pci_claim(struct ath10k *ar)
 	}
 
 	/* Target expects 32 bit DMA. Enforce it. */
-	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 	if (ret) {
 		ath10k_err(ar, "failed to set dma mask to 32-bit: %d\n", ret);
 		goto err_region;
 	}
 
-	ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
-	if (ret) {
-		ath10k_err(ar, "failed to set consistent dma mask to 32-bit: %d\n",
-			   ret);
-		goto err_region;
-	}
-
 	pci_set_master(pdev);
 
 	/* Arrange for access to Target SoC registers. */
diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 603d2f93ac18..9a224817630a 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -1406,11 +1406,6 @@ ath11k_update_per_peer_tx_stats(struct ath11k *ar,
 	 * Firmware rate's control to be skipped for this?
 	 */
 
-	if (flags == WMI_RATE_PREAMBLE_HE && mcs > 11) {
-		ath11k_warn(ab, "Invalid HE mcs %d peer stats",  mcs);
-		return;
-	}
-
 	if (flags == WMI_RATE_PREAMBLE_HE && mcs > ATH11K_HE_MCS_MAX) {
 		ath11k_warn(ab, "Invalid HE mcs %d peer stats",  mcs);
 		return;
diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index 646ad79f309c..5abb38cc3b55 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -933,20 +933,14 @@ static int ath11k_pci_claim(struct ath11k_pci *ab_pci, struct pci_dev *pdev)
 		goto disable_device;
 	}
 
-	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(ATH11K_PCI_DMA_MASK));
+	ret = dma_set_mask_and_coherent(&pdev->dev,
+					DMA_BIT_MASK(ATH11K_PCI_DMA_MASK));
 	if (ret) {
 		ath11k_err(ab, "failed to set pci dma mask to %d: %d\n",
 			   ATH11K_PCI_DMA_MASK, ret);
 		goto release_region;
 	}
 
-	ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(ATH11K_PCI_DMA_MASK));
-	if (ret) {
-		ath11k_err(ab, "failed to set pci consistent dma mask to %d: %d\n",
-			   ATH11K_PCI_DMA_MASK, ret);
-		goto release_region;
-	}
-
 	pci_set_master(pdev);
 
 	ab->mem_len = pci_resource_len(pdev, ATH11K_PCI_BAR_NUM);
diff --git a/drivers/net/wireless/ath/ath5k/pci.c b/drivers/net/wireless/ath/ath5k/pci.c
index 43b4ae86e5fb..86b8cb975b1a 100644
--- a/drivers/net/wireless/ath/ath5k/pci.c
+++ b/drivers/net/wireless/ath/ath5k/pci.c
@@ -191,7 +191,7 @@ ath5k_pci_probe(struct pci_dev *pdev,
 	}
 
 	/* XXX 32-bit addressing only */
-	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
 	if (ret) {
 		dev_err(&pdev->dev, "32-bit DMA not available\n");
 		goto err_dis;
diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c
index b137e7f34397..bd1ef6334997 100644
--- a/drivers/net/wireless/ath/ath6kl/wmi.c
+++ b/drivers/net/wireless/ath/ath6kl/wmi.c
@@ -2504,8 +2504,10 @@ static int ath6kl_wmi_sync_point(struct wmi *wmi, u8 if_idx)
 		goto free_data_skb;
 
 	for (index = 0; index < num_pri_streams; index++) {
-		if (WARN_ON(!data_sync_bufs[index].skb))
+		if (WARN_ON(!data_sync_bufs[index].skb)) {
+			ret = -ENOMEM;
 			goto free_data_skb;
+		}
 
 		ep_id = ath6kl_ac2_endpoint_id(wmi->parent_dev,
 					       data_sync_bufs[index].
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
index b4885a700296..b0a4ca3559fd 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
@@ -3351,7 +3351,8 @@ found:
 			"Found block at %x: code=%d ref=%d length=%d major=%d minor=%d\n",
 			cptr, code, reference, length, major, minor);
 		if ((!AR_SREV_9485(ah) && length >= 1024) ||
-		    (AR_SREV_9485(ah) && length > EEPROM_DATA_LEN_9485)) {
+		    (AR_SREV_9485(ah) && length > EEPROM_DATA_LEN_9485) ||
+		    (length > cptr)) {
 			ath_dbg(common, EEPROM, "Skipping bad header\n");
 			cptr -= COMP_HDR_LEN;
 			continue;
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 2ca3b86714a9..172081ffe477 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -1621,7 +1621,6 @@ static void ath9k_hw_apply_gpio_override(struct ath_hw *ah)
 		ath9k_hw_gpio_request_out(ah, i, NULL,
 					  AR_GPIO_OUTPUT_MUX_AS_OUTPUT);
 		ath9k_hw_set_gpio(ah, i, !!(ah->gpio_val & BIT(i)));
-		ath9k_hw_gpio_free(ah, i);
 	}
 }
 
@@ -2728,14 +2727,17 @@ static void ath9k_hw_gpio_cfg_output_mux(struct ath_hw *ah, u32 gpio, u32 type)
 static void ath9k_hw_gpio_cfg_soc(struct ath_hw *ah, u32 gpio, bool out,
 				  const char *label)
 {
+	int err;
+
 	if (ah->caps.gpio_requested & BIT(gpio))
 		return;
 
-	/* may be requested by BSP, free anyway */
-	gpio_free(gpio);
-
-	if (gpio_request_one(gpio, out ? GPIOF_OUT_INIT_LOW : GPIOF_IN, label))
+	err = gpio_request_one(gpio, out ? GPIOF_OUT_INIT_LOW : GPIOF_IN, label);
+	if (err) {
+		ath_err(ath9k_hw_common(ah), "request GPIO%d failed:%d\n",
+			gpio, err);
 		return;
+	}
 
 	ah->caps.gpio_requested |= BIT(gpio);
 }
diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c
index cff9af3af38d..a074e23013c5 100644
--- a/drivers/net/wireless/ath/ath9k/pci.c
+++ b/drivers/net/wireless/ath/ath9k/pci.c
@@ -896,18 +896,12 @@ static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (pcim_enable_device(pdev))
 		return -EIO;
 
-	ret =  pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 	if (ret) {
 		pr_err("32-bit DMA not available\n");
 		return ret;
 	}
 
-	ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
-	if (ret) {
-		pr_err("32-bit DMA consistent DMA enable failed\n");
-		return ret;
-	}
-
 	/*
 	 * Cache line size is used to size and align various
 	 * structures used to communicate with the hardware.
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index d202f2128df2..ec913ec991f3 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -408,13 +408,14 @@ static int wcn36xx_config(struct ieee80211_hw *hw, u32 changed)
 		wcn36xx_dbg(WCN36XX_DBG_MAC, "wcn36xx_config channel switch=%d\n",
 			    ch);
 
-		if (wcn->sw_scan_opchannel == ch) {
+		if (wcn->sw_scan_opchannel == ch && wcn->sw_scan_channel) {
 			/* If channel is the initial operating channel, we may
 			 * want to receive/transmit regular data packets, then
 			 * simply stop the scan session and exit PS mode.
 			 */
 			wcn36xx_smd_finish_scan(wcn, HAL_SYS_MODE_SCAN,
 						wcn->sw_scan_vif);
+			wcn->sw_scan_channel = 0;
 		} else if (wcn->sw_scan) {
 			/* A scan is ongoing, do not change the operating
 			 * channel, but start a scan session on the channel.
@@ -422,6 +423,7 @@ static int wcn36xx_config(struct ieee80211_hw *hw, u32 changed)
 			wcn36xx_smd_init_scan(wcn, HAL_SYS_MODE_SCAN,
 					      wcn->sw_scan_vif);
 			wcn36xx_smd_start_scan(wcn, ch);
+			wcn->sw_scan_channel = ch;
 		} else {
 			wcn36xx_change_opchannel(wcn, ch);
 		}
@@ -702,6 +704,7 @@ static void wcn36xx_sw_scan_start(struct ieee80211_hw *hw,
 
 	wcn->sw_scan = true;
 	wcn->sw_scan_vif = vif;
+	wcn->sw_scan_channel = 0;
 	if (vif_priv->sta_assoc)
 		wcn->sw_scan_opchannel = WCN36XX_HW_CHANNEL(wcn);
 	else
@@ -1500,6 +1503,13 @@ static int wcn36xx_probe(struct platform_device *pdev)
 		goto out_wq;
 	}
 
+	wcn->nv_file = WLAN_NV_FILE;
+	ret = of_property_read_string(wcn->dev->parent->of_node, "firmware-name", &wcn->nv_file);
+	if (ret < 0 && ret != -EINVAL) {
+		wcn36xx_err("failed to read \"firmware-name\" property: %d\n", ret);
+		goto out_wq;
+	}
+
 	wcn->smd_channel = qcom_wcnss_open_channel(wcnss, "WLAN_CTRL", wcn36xx_smd_rsp_process, hw);
 	if (IS_ERR(wcn->smd_channel)) {
 		wcn36xx_err("failed to open WLAN_CTRL channel\n");
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c
index 0e3be17d8cea..57fa857b290b 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.c
+++ b/drivers/net/wireless/ath/wcn36xx/smd.c
@@ -504,10 +504,10 @@ int wcn36xx_smd_load_nv(struct wcn36xx *wcn)
 	u16 fm_offset = 0;
 
 	if (!wcn->nv) {
-		ret = request_firmware(&wcn->nv, WLAN_NV_FILE, wcn->dev);
+		ret = request_firmware(&wcn->nv, wcn->nv_file, wcn->dev);
 		if (ret) {
 			wcn36xx_err("Failed to load nv file %s: %d\n",
-				      WLAN_NV_FILE, ret);
+				    wcn->nv_file, ret);
 			goto out;
 		}
 	}
diff --git a/drivers/net/wireless/ath/wcn36xx/txrx.c b/drivers/net/wireless/ath/wcn36xx/txrx.c
index 1b831157ede1..cab196bb38cd 100644
--- a/drivers/net/wireless/ath/wcn36xx/txrx.c
+++ b/drivers/net/wireless/ath/wcn36xx/txrx.c
@@ -287,6 +287,10 @@ int wcn36xx_rx_skb(struct wcn36xx *wcn, struct sk_buff *skb)
 		status.rate_idx = 0;
 	}
 
+	if (ieee80211_is_beacon(hdr->frame_control) ||
+	    ieee80211_is_probe_resp(hdr->frame_control))
+		status.boottime_ns = ktime_get_boottime_ns();
+
 	memcpy(IEEE80211_SKB_RXCB(skb), &status, sizeof(status));
 
 	if (ieee80211_is_beacon(hdr->frame_control)) {
diff --git a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
index 6121d8a5641a..add6e527e833 100644
--- a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
+++ b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
@@ -199,6 +199,7 @@ struct wcn36xx {
 	struct device		*dev;
 	struct list_head	vif_list;
 
+	const char		*nv_file;
 	const struct firmware	*nv;
 
 	u8			fw_revision;
@@ -246,6 +247,7 @@ struct wcn36xx {
 	struct cfg80211_scan_request *scan_req;
 	bool			sw_scan;
 	u8			sw_scan_opchannel;
+	u8			sw_scan_channel;
 	struct ieee80211_vif	*sw_scan_vif;
 	struct mutex		scan_lock;
 	bool			scan_aborted;
diff --git a/drivers/net/wireless/ath/wil6210/ethtool.c b/drivers/net/wireless/ath/wil6210/ethtool.c
index e481674485c2..29a9f17c2df0 100644
--- a/drivers/net/wireless/ath/wil6210/ethtool.c
+++ b/drivers/net/wireless/ath/wil6210/ethtool.c
@@ -11,8 +11,11 @@
 
 #include "wil6210.h"
 
-static int wil_ethtoolops_get_coalesce(struct net_device *ndev,
-				       struct ethtool_coalesce *cp)
+static int
+wil_ethtoolops_get_coalesce(struct net_device *ndev,
+			    struct ethtool_coalesce *cp,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct wil6210_priv *wil = ndev_to_wil(ndev);
 	u32 tx_itr_en, tx_itr_val = 0;
@@ -45,8 +48,11 @@ out:
 	return ret;
 }
 
-static int wil_ethtoolops_set_coalesce(struct net_device *ndev,
-				       struct ethtool_coalesce *cp)
+static int
+wil_ethtoolops_set_coalesce(struct net_device *ndev,
+			    struct ethtool_coalesce *cp,
+			    struct kernel_ethtool_coalesce *kernel_coal,
+			    struct netlink_ext_ack *extack)
 {
 	struct wil6210_priv *wil = ndev_to_wil(ndev);
 	struct wireless_dev *wdev = ndev->ieee80211_ptr;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile
index 9b15bc3f6054..13c13504a6e8 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile
@@ -23,7 +23,8 @@ brcmfmac-objs += \
 		feature.o \
 		btcoex.o \
 		vendor.o \
-		pno.o
+		pno.o \
+		xtlv.o
 brcmfmac-$(CONFIG_BRCMFMAC_PROTO_BCDC) += \
 		bcdc.o \
 		fwsignal.o
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 633d0ab19031..ac02244a6fdf 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -128,7 +128,8 @@ int brcmf_sdiod_intr_register(struct brcmf_sdio_dev *sdiodev)
 
 		if (sdiodev->bus_if->chip == BRCM_CC_43362_CHIP_ID) {
 			/* assign GPIO to SDIO core */
-			addr = CORE_CC_REG(SI_ENUM_BASE, gpiocontrol);
+			addr = brcmf_chip_enum_base(sdiodev->func1->device);
+			addr = CORE_CC_REG(addr, gpiocontrol);
 			gpiocontrol = brcmf_sdiod_readl(sdiodev, addr, &ret);
 			gpiocontrol |= 0x2;
 			brcmf_sdiod_writel(sdiodev, addr, gpiocontrol, &ret);
@@ -990,6 +991,7 @@ static const struct sdio_device_id brcmf_sdmmc_ids[] = {
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4359),
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_CYPRESS_4373),
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_CYPRESS_43012),
+	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752),
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_CYPRESS_89359),
 	{ /* end: all zeroes */ }
 };
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index cedba56fc448..f7b96cd69242 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -1829,6 +1829,14 @@ brcmf_set_key_mgmt(struct net_device *ndev, struct cfg80211_connect_params *sme)
 				profile->use_fwsup = BRCMF_PROFILE_FWSUP_SAE;
 			}
 			break;
+		case WLAN_AKM_SUITE_FT_OVER_SAE:
+			val = WPA3_AUTH_SAE_PSK | WPA2_AUTH_FT;
+			profile->is_ft = true;
+			if (sme->crypto.sae_pwd) {
+				brcmf_dbg(INFO, "using SAE offload\n");
+				profile->use_fwsup = BRCMF_PROFILE_FWSUP_SAE;
+			}
+			break;
 		default:
 			bphy_err(drvr, "invalid cipher group (%d)\n",
 				 sme->crypto.cipher_group);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
index 45037decba40..1ee49f9e325d 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
@@ -139,6 +139,8 @@ struct sbconfig {
 	u32 sbidhigh;	/* identification */
 };
 
+#define INVALID_RAMBASE			((u32)(~0))
+
 /* bankidx and bankinfo reg defines corerev >= 8 */
 #define SOCRAM_BANKINFO_RETNTRAM_MASK	0x00010000
 #define SOCRAM_BANKINFO_SZMASK		0x0000007f
@@ -527,7 +529,7 @@ static int brcmf_chip_cores_check(struct brcmf_chip_priv *ci)
 	int idx = 1;
 
 	list_for_each_entry(core, &ci->cores, list) {
-		brcmf_dbg(INFO, " [%-2d] core 0x%x:%-2d base 0x%08x wrap 0x%08x\n",
+		brcmf_dbg(INFO, " [%-2d] core 0x%x:%-3d base 0x%08x wrap 0x%08x\n",
 			  idx++, core->pub.id, core->pub.rev, core->pub.base,
 			  core->wrapbase);
 
@@ -727,11 +729,13 @@ static u32 brcmf_chip_tcm_rambase(struct brcmf_chip_priv *ci)
 	case BRCM_CC_4364_CHIP_ID:
 	case CY_CC_4373_CHIP_ID:
 		return 0x160000;
+	case CY_CC_43752_CHIP_ID:
+		return 0x170000;
 	default:
 		brcmf_err("unknown chip: %s\n", ci->pub.name);
 		break;
 	}
-	return 0;
+	return INVALID_RAMBASE;
 }
 
 int brcmf_chip_get_raminfo(struct brcmf_chip *pub)
@@ -746,7 +750,7 @@ int brcmf_chip_get_raminfo(struct brcmf_chip *pub)
 		mem_core = container_of(mem, struct brcmf_core_priv, pub);
 		ci->pub.ramsize = brcmf_chip_tcm_ramsize(mem_core);
 		ci->pub.rambase = brcmf_chip_tcm_rambase(ci);
-		if (!ci->pub.rambase) {
+		if (ci->pub.rambase == INVALID_RAMBASE) {
 			brcmf_err("RAM base not provided with ARM CR4 core\n");
 			return -EINVAL;
 		}
@@ -757,7 +761,7 @@ int brcmf_chip_get_raminfo(struct brcmf_chip *pub)
 						pub);
 			ci->pub.ramsize = brcmf_chip_sysmem_ramsize(mem_core);
 			ci->pub.rambase = brcmf_chip_tcm_rambase(ci);
-			if (!ci->pub.rambase) {
+			if (ci->pub.rambase == INVALID_RAMBASE) {
 				brcmf_err("RAM base not provided with ARM CA7 core\n");
 				return -EINVAL;
 			}
@@ -894,7 +898,8 @@ int brcmf_chip_dmp_erom_scan(struct brcmf_chip_priv *ci)
 	u32 base, wrap;
 	int err;
 
-	eromaddr = ci->ops->read32(ci->ctx, CORE_CC_REG(SI_ENUM_BASE, eromptr));
+	eromaddr = ci->ops->read32(ci->ctx,
+				   CORE_CC_REG(ci->pub.enum_base, eromptr));
 
 	while (desc_type != DMP_DESC_EOT) {
 		val = brcmf_chip_dmp_get_desc(ci, &eromaddr, &desc_type);
@@ -942,6 +947,11 @@ int brcmf_chip_dmp_erom_scan(struct brcmf_chip_priv *ci)
 	return 0;
 }
 
+u32 brcmf_chip_enum_base(u16 devid)
+{
+	return SI_ENUM_BASE_DEFAULT;
+}
+
 static int brcmf_chip_recognition(struct brcmf_chip_priv *ci)
 {
 	struct brcmf_core *core;
@@ -954,7 +964,8 @@ static int brcmf_chip_recognition(struct brcmf_chip_priv *ci)
 	 * For different chiptypes or old sdio hosts w/o chipcommon,
 	 * other ways of recognition should be added here.
 	 */
-	regdata = ci->ops->read32(ci->ctx, CORE_CC_REG(SI_ENUM_BASE, chipid));
+	regdata = ci->ops->read32(ci->ctx,
+				  CORE_CC_REG(ci->pub.enum_base, chipid));
 	ci->pub.chip = regdata & CID_ID_MASK;
 	ci->pub.chiprev = (regdata & CID_REV_MASK) >> CID_REV_SHIFT;
 	socitype = (regdata & CID_TYPE_MASK) >> CID_TYPE_SHIFT;
@@ -974,7 +985,7 @@ static int brcmf_chip_recognition(struct brcmf_chip_priv *ci)
 		ci->resetcore = brcmf_chip_sb_resetcore;
 
 		core = brcmf_chip_add_core(ci, BCMA_CORE_CHIPCOMMON,
-					   SI_ENUM_BASE, 0);
+					   SI_ENUM_BASE_DEFAULT, 0);
 		brcmf_chip_sb_corerev(ci, core);
 		core = brcmf_chip_add_core(ci, BCMA_CORE_SDIO_DEV,
 					   BCM4329_CORE_BUS_BASE, 0);
@@ -1088,7 +1099,7 @@ static int brcmf_chip_setup(struct brcmf_chip_priv *chip)
 	return ret;
 }
 
-struct brcmf_chip *brcmf_chip_attach(void *ctx,
+struct brcmf_chip *brcmf_chip_attach(void *ctx, u16 devid,
 				     const struct brcmf_buscore_ops *ops)
 {
 	struct brcmf_chip_priv *chip;
@@ -1113,6 +1124,7 @@ struct brcmf_chip *brcmf_chip_attach(void *ctx,
 	chip->num_cores = 0;
 	chip->ops = ops;
 	chip->ctx = ctx;
+	chip->pub.enum_base = brcmf_chip_enum_base(devid);
 
 	err = ops->prepare(ctx);
 	if (err < 0)
@@ -1411,6 +1423,7 @@ bool brcmf_chip_sr_capable(struct brcmf_chip *pub)
 		reg = chip->ops->read32(chip->ctx, addr);
 		return (reg & CC_SR_CTL0_ENABLE_MASK) != 0;
 	case BRCM_CC_4359_CHIP_ID:
+	case CY_CC_43752_CHIP_ID:
 	case CY_CC_43012_CHIP_ID:
 		addr = CORE_CC_REG(pmu->base, retention_ctl);
 		reg = chip->ops->read32(chip->ctx, addr);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.h
index 8fa38658e727..d69f101f5834 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.h
@@ -15,6 +15,7 @@
  *
  * @chip: chip identifier.
  * @chiprev: chip revision.
+ * @enum_base: base address of core enumeration space.
  * @cc_caps: chipcommon core capabilities.
  * @cc_caps_ext: chipcommon core extended capabilities.
  * @pmucaps: PMU capabilities.
@@ -27,6 +28,7 @@
 struct brcmf_chip {
 	u32 chip;
 	u32 chiprev;
+	u32 enum_base;
 	u32 cc_caps;
 	u32 cc_caps_ext;
 	u32 pmucaps;
@@ -70,7 +72,7 @@ struct brcmf_buscore_ops {
 };
 
 int brcmf_chip_get_raminfo(struct brcmf_chip *pub);
-struct brcmf_chip *brcmf_chip_attach(void *ctx,
+struct brcmf_chip *brcmf_chip_attach(void *ctx, u16 devid,
 				     const struct brcmf_buscore_ops *ops);
 void brcmf_chip_detach(struct brcmf_chip *chip);
 struct brcmf_core *brcmf_chip_get_core(struct brcmf_chip *chip, u16 coreid);
@@ -85,5 +87,6 @@ void brcmf_chip_set_passive(struct brcmf_chip *ci);
 bool brcmf_chip_set_active(struct brcmf_chip *ci, u32 rstvec);
 bool brcmf_chip_sr_capable(struct brcmf_chip *pub);
 char *brcmf_chip_name(u32 chipid, u32 chiprev, char *buf, uint len);
+u32 brcmf_chip_enum_base(u16 devid);
 
 #endif /* BRCMF_AXIDMP_H */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
index d40104b8df55..0eb13e5df517 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
@@ -431,8 +431,6 @@ struct brcmf_fw {
 	void (*done)(struct device *dev, int err, struct brcmf_fw_request *req);
 };
 
-static void brcmf_fw_request_done(const struct firmware *fw, void *ctx);
-
 #ifdef CONFIG_EFI
 /* In some cases the EFI-var stored nvram contains "ccode=ALL" or "ccode=XV"
  * to specify "worldwide" compatible settings, but these 2 ccode-s do not work
@@ -594,28 +592,47 @@ static int brcmf_fw_complete_request(const struct firmware *fw,
 	return (cur->flags & BRCMF_FW_REQF_OPTIONAL) ? 0 : ret;
 }
 
+static char *brcm_alt_fw_path(const char *path, const char *board_type)
+{
+	char alt_path[BRCMF_FW_NAME_LEN];
+	char suffix[5];
+
+	strscpy(alt_path, path, BRCMF_FW_NAME_LEN);
+	/* At least one character + suffix */
+	if (strlen(alt_path) < 5)
+		return NULL;
+
+	/* strip .txt or .bin at the end */
+	strscpy(suffix, alt_path + strlen(alt_path) - 4, 5);
+	alt_path[strlen(alt_path) - 4] = 0;
+	strlcat(alt_path, ".", BRCMF_FW_NAME_LEN);
+	strlcat(alt_path, board_type, BRCMF_FW_NAME_LEN);
+	strlcat(alt_path, suffix, BRCMF_FW_NAME_LEN);
+
+	return kstrdup(alt_path, GFP_KERNEL);
+}
+
 static int brcmf_fw_request_firmware(const struct firmware **fw,
 				     struct brcmf_fw *fwctx)
 {
 	struct brcmf_fw_item *cur = &fwctx->req->items[fwctx->curpos];
 	int ret;
 
-	/* nvram files are board-specific, first try a board-specific path */
+	/* Files can be board-specific, first try a board-specific path */
 	if (cur->type == BRCMF_FW_TYPE_NVRAM && fwctx->req->board_type) {
-		char alt_path[BRCMF_FW_NAME_LEN];
+		char *alt_path;
 
-		strlcpy(alt_path, cur->path, BRCMF_FW_NAME_LEN);
-		/* strip .txt at the end */
-		alt_path[strlen(alt_path) - 4] = 0;
-		strlcat(alt_path, ".", BRCMF_FW_NAME_LEN);
-		strlcat(alt_path, fwctx->req->board_type, BRCMF_FW_NAME_LEN);
-		strlcat(alt_path, ".txt", BRCMF_FW_NAME_LEN);
+		alt_path = brcm_alt_fw_path(cur->path, fwctx->req->board_type);
+		if (!alt_path)
+			goto fallback;
 
 		ret = request_firmware(fw, alt_path, fwctx->dev);
+		kfree(alt_path);
 		if (ret == 0)
 			return ret;
 	}
 
+fallback:
 	return request_firmware(fw, cur->path, fwctx->dev);
 }
 
@@ -639,6 +656,22 @@ static void brcmf_fw_request_done(const struct firmware *fw, void *ctx)
 	kfree(fwctx);
 }
 
+static void brcmf_fw_request_done_alt_path(const struct firmware *fw, void *ctx)
+{
+	struct brcmf_fw *fwctx = ctx;
+	struct brcmf_fw_item *first = &fwctx->req->items[0];
+	int ret = 0;
+
+	/* Fall back to canonical path if board firmware not found */
+	if (!fw)
+		ret = request_firmware_nowait(THIS_MODULE, true, first->path,
+					      fwctx->dev, GFP_KERNEL, fwctx,
+					      brcmf_fw_request_done);
+
+	if (fw || ret < 0)
+		brcmf_fw_request_done(fw, ctx);
+}
+
 static bool brcmf_fw_request_is_valid(struct brcmf_fw_request *req)
 {
 	struct brcmf_fw_item *item;
@@ -660,6 +693,7 @@ int brcmf_fw_get_firmwares(struct device *dev, struct brcmf_fw_request *req,
 {
 	struct brcmf_fw_item *first = &req->items[0];
 	struct brcmf_fw *fwctx;
+	char *alt_path;
 	int ret;
 
 	brcmf_dbg(TRACE, "enter: dev=%s\n", dev_name(dev));
@@ -677,9 +711,18 @@ int brcmf_fw_get_firmwares(struct device *dev, struct brcmf_fw_request *req,
 	fwctx->req = req;
 	fwctx->done = fw_cb;
 
-	ret = request_firmware_nowait(THIS_MODULE, true, first->path,
-				      fwctx->dev, GFP_KERNEL, fwctx,
-				      brcmf_fw_request_done);
+	/* First try alternative board-specific path if any */
+	alt_path = brcm_alt_fw_path(first->path, fwctx->req->board_type);
+	if (alt_path) {
+		ret = request_firmware_nowait(THIS_MODULE, true, alt_path,
+					      fwctx->dev, GFP_KERNEL, fwctx,
+					      brcmf_fw_request_done_alt_path);
+		kfree(alt_path);
+	} else {
+		ret = request_firmware_nowait(THIS_MODULE, true, first->path,
+					      fwctx->dev, GFP_KERNEL, fwctx,
+					      brcmf_fw_request_done);
+	}
 	if (ret < 0)
 		brcmf_fw_request_done(NULL, fwctx);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c
index 9ed85420f3ca..d5578ca681bb 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c
@@ -15,6 +15,7 @@
 #include "bus.h"
 #include "debug.h"
 #include "tracepoint.h"
+#include "xtlv.h"
 #include "fwil.h"
 #include "proto.h"
 
@@ -150,7 +151,8 @@ brcmf_fil_cmd_data_get(struct brcmf_if *ifp, u32 cmd, void *data, u32 len)
 	mutex_lock(&ifp->drvr->proto_block);
 	err = brcmf_fil_cmd_data(ifp, cmd, data, len, false);
 
-	brcmf_dbg(FIL, "ifidx=%d, cmd=%d, len=%d\n", ifp->ifidx, cmd, len);
+	brcmf_dbg(FIL, "ifidx=%d, cmd=%d, len=%d, err=%d\n", ifp->ifidx, cmd,
+		  len, err);
 	brcmf_dbg_hex_dump(BRCMF_FIL_ON(), data,
 			   min_t(uint, len, MAX_HEX_DUMP_LEN), "data\n");
 
@@ -260,7 +262,8 @@ brcmf_fil_iovar_data_get(struct brcmf_if *ifp, char *name, void *data,
 		bphy_err(drvr, "Creating iovar failed\n");
 	}
 
-	brcmf_dbg(FIL, "ifidx=%d, name=%s, len=%d\n", ifp->ifidx, name, len);
+	brcmf_dbg(FIL, "ifidx=%d, name=%s, len=%d, err=%d\n", ifp->ifidx, name,
+		  len, err);
 	brcmf_dbg_hex_dump(BRCMF_FIL_ON(), data,
 			   min_t(uint, len, MAX_HEX_DUMP_LEN), "data\n");
 
@@ -383,14 +386,13 @@ brcmf_fil_bsscfg_data_get(struct brcmf_if *ifp, char *name,
 		err = -EPERM;
 		bphy_err(drvr, "Creating bsscfg failed\n");
 	}
-	brcmf_dbg(FIL, "ifidx=%d, bsscfgidx=%d, name=%s, len=%d\n", ifp->ifidx,
-		  ifp->bsscfgidx, name, len);
+	brcmf_dbg(FIL, "ifidx=%d, bsscfgidx=%d, name=%s, len=%d, err=%d\n",
+		  ifp->ifidx, ifp->bsscfgidx, name, len, err);
 	brcmf_dbg_hex_dump(BRCMF_FIL_ON(), data,
 			   min_t(uint, len, MAX_HEX_DUMP_LEN), "data\n");
 
 	mutex_unlock(&drvr->proto_block);
 	return err;
-
 }
 
 s32
@@ -414,3 +416,117 @@ brcmf_fil_bsscfg_int_get(struct brcmf_if *ifp, char *name, u32 *data)
 		*data = le32_to_cpu(data_le);
 	return err;
 }
+
+static u32 brcmf_create_xtlv(char *name, u16 id, char *data, u32 len,
+			     char *buf, u32 buflen)
+{
+	u32 iolen;
+	u32 nmlen;
+
+	nmlen = strlen(name) + 1;
+	iolen = nmlen + brcmf_xtlv_data_size(len, BRCMF_XTLV_OPTION_ALIGN32);
+
+	if (iolen > buflen) {
+		brcmf_err("buffer is too short\n");
+		return 0;
+	}
+
+	memcpy(buf, name, nmlen);
+	brcmf_xtlv_pack_header((void *)(buf + nmlen), id, len, data,
+			       BRCMF_XTLV_OPTION_ALIGN32);
+
+	return iolen;
+}
+
+s32 brcmf_fil_xtlv_data_set(struct brcmf_if *ifp, char *name, u16 id,
+			    void *data, u32 len)
+{
+	struct brcmf_pub *drvr = ifp->drvr;
+	s32 err;
+	u32 buflen;
+
+	mutex_lock(&drvr->proto_block);
+
+	brcmf_dbg(FIL, "ifidx=%d, name=%s, id=%u, len=%u\n", ifp->ifidx, name,
+		  id, len);
+	brcmf_dbg_hex_dump(BRCMF_FIL_ON(), data,
+			   min_t(uint, len, MAX_HEX_DUMP_LEN), "data\n");
+
+	buflen = brcmf_create_xtlv(name, id, data, len,
+				   drvr->proto_buf, sizeof(drvr->proto_buf));
+	if (buflen) {
+		err = brcmf_fil_cmd_data(ifp, BRCMF_C_SET_VAR, drvr->proto_buf,
+					 buflen, true);
+	} else {
+		err = -EPERM;
+		bphy_err(drvr, "Creating xtlv failed\n");
+	}
+
+	mutex_unlock(&drvr->proto_block);
+	return err;
+}
+
+s32 brcmf_fil_xtlv_data_get(struct brcmf_if *ifp, char *name, u16 id,
+			    void *data, u32 len)
+{
+	struct brcmf_pub *drvr = ifp->drvr;
+	s32 err;
+	u32 buflen;
+
+	mutex_lock(&drvr->proto_block);
+
+	buflen = brcmf_create_xtlv(name, id, data, len,
+				   drvr->proto_buf, sizeof(drvr->proto_buf));
+	if (buflen) {
+		err = brcmf_fil_cmd_data(ifp, BRCMF_C_GET_VAR, drvr->proto_buf,
+					 buflen, false);
+		if (err == 0)
+			memcpy(data, drvr->proto_buf, len);
+	} else {
+		err = -EPERM;
+		bphy_err(drvr, "Creating bsscfg failed\n");
+	}
+	brcmf_dbg(FIL, "ifidx=%d, name=%s, id=%u, len=%u, err=%d\n",
+		  ifp->ifidx, name, id, len, err);
+	brcmf_dbg_hex_dump(BRCMF_FIL_ON(), data,
+			   min_t(uint, len, MAX_HEX_DUMP_LEN), "data\n");
+
+	mutex_unlock(&drvr->proto_block);
+	return err;
+}
+
+s32 brcmf_fil_xtlv_int_set(struct brcmf_if *ifp, char *name, u16 id, u32 data)
+{
+	__le32 data_le = cpu_to_le32(data);
+
+	return brcmf_fil_xtlv_data_set(ifp, name, id, &data_le,
+					 sizeof(data_le));
+}
+
+s32 brcmf_fil_xtlv_int_get(struct brcmf_if *ifp, char *name, u16 id, u32 *data)
+{
+	__le32 data_le = cpu_to_le32(*data);
+	s32 err;
+
+	err = brcmf_fil_xtlv_data_get(ifp, name, id, &data_le, sizeof(data_le));
+	if (err == 0)
+		*data = le32_to_cpu(data_le);
+	return err;
+}
+
+s32 brcmf_fil_xtlv_int8_get(struct brcmf_if *ifp, char *name, u16 id, u8 *data)
+{
+	return brcmf_fil_xtlv_data_get(ifp, name, id, data, sizeof(*data));
+}
+
+s32 brcmf_fil_xtlv_int16_get(struct brcmf_if *ifp, char *name, u16 id, u16 *data)
+{
+	__le16 data_le = cpu_to_le16(*data);
+	s32 err;
+
+	err = brcmf_fil_xtlv_data_get(ifp, name, id, &data_le, sizeof(data_le));
+	if (err == 0)
+		*data = le16_to_cpu(data_le);
+	return err;
+}
+
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
index ae4cf4372908..cb26f8c59c21 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
@@ -97,5 +97,13 @@ s32 brcmf_fil_bsscfg_data_get(struct brcmf_if *ifp, char *name, void *data,
 			      u32 len);
 s32 brcmf_fil_bsscfg_int_set(struct brcmf_if *ifp, char *name, u32 data);
 s32 brcmf_fil_bsscfg_int_get(struct brcmf_if *ifp, char *name, u32 *data);
+s32 brcmf_fil_xtlv_data_set(struct brcmf_if *ifp, char *name, u16 id,
+			    void *data, u32 len);
+s32 brcmf_fil_xtlv_data_get(struct brcmf_if *ifp, char *name, u16 id,
+			    void *data, u32 len);
+s32 brcmf_fil_xtlv_int_set(struct brcmf_if *ifp, char *name, u16 id, u32 data);
+s32 brcmf_fil_xtlv_int_get(struct brcmf_if *ifp, char *name, u16 id, u32 *data);
+s32 brcmf_fil_xtlv_int8_get(struct brcmf_if *ifp, char *name, u16 id, u8 *data);
+s32 brcmf_fil_xtlv_int16_get(struct brcmf_if *ifp, char *name, u16 id, u16 *data);
 
 #endif /* _fwil_h_ */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index c49dd0c36ae4..8b149996fc00 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -1886,7 +1886,8 @@ brcmf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	devinfo->pdev = pdev;
 	pcie_bus_dev = NULL;
-	devinfo->ci = brcmf_chip_attach(devinfo, &brcmf_pcie_buscore_ops);
+	devinfo->ci = brcmf_chip_attach(devinfo, pdev->device,
+					&brcmf_pcie_buscore_ops);
 	if (IS_ERR(devinfo->ci)) {
 		ret = PTR_ERR(devinfo->ci);
 		devinfo->ci = NULL;
@@ -2075,7 +2076,7 @@ cleanup:
 
 	err = brcmf_pcie_probe(pdev, NULL);
 	if (err)
-		brcmf_err(bus, "probe after resume failed, err=%d\n", err);
+		__brcmf_err(NULL, __func__, "probe after resume failed, err=%d\n", err);
 
 	return err;
 }
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 97ee9e2e2e35..8effeb7a7269 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -617,6 +617,7 @@ BRCMF_FW_DEF(4339, "brcmfmac4339-sdio");
 BRCMF_FW_DEF(43430A0, "brcmfmac43430a0-sdio");
 /* Note the names are not postfixed with a1 for backward compatibility */
 BRCMF_FW_CLM_DEF(43430A1, "brcmfmac43430-sdio");
+BRCMF_FW_DEF(43430B0, "brcmfmac43430b0-sdio");
 BRCMF_FW_CLM_DEF(43455, "brcmfmac43455-sdio");
 BRCMF_FW_DEF(43456, "brcmfmac43456-sdio");
 BRCMF_FW_CLM_DEF(4354, "brcmfmac4354-sdio");
@@ -624,11 +625,15 @@ BRCMF_FW_CLM_DEF(4356, "brcmfmac4356-sdio");
 BRCMF_FW_DEF(4359, "brcmfmac4359-sdio");
 BRCMF_FW_CLM_DEF(4373, "brcmfmac4373-sdio");
 BRCMF_FW_CLM_DEF(43012, "brcmfmac43012-sdio");
+BRCMF_FW_CLM_DEF(43752, "brcmfmac43752-sdio");
 
 /* firmware config files */
 MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-sdio.*.txt");
 MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-pcie.*.txt");
 
+/* per-board firmware binaries */
+MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-sdio.*.bin");
+
 static const struct brcmf_firmware_mapping brcmf_sdio_fwnames[] = {
 	BRCMF_FW_ENTRY(BRCM_CC_43143_CHIP_ID, 0xFFFFFFFF, 43143),
 	BRCMF_FW_ENTRY(BRCM_CC_43241_CHIP_ID, 0x0000001F, 43241B0),
@@ -643,14 +648,16 @@ static const struct brcmf_firmware_mapping brcmf_sdio_fwnames[] = {
 	BRCMF_FW_ENTRY(BRCM_CC_43362_CHIP_ID, 0xFFFFFFFE, 43362),
 	BRCMF_FW_ENTRY(BRCM_CC_4339_CHIP_ID, 0xFFFFFFFF, 4339),
 	BRCMF_FW_ENTRY(BRCM_CC_43430_CHIP_ID, 0x00000001, 43430A0),
-	BRCMF_FW_ENTRY(BRCM_CC_43430_CHIP_ID, 0xFFFFFFFE, 43430A1),
+	BRCMF_FW_ENTRY(BRCM_CC_43430_CHIP_ID, 0x00000002, 43430A1),
+	BRCMF_FW_ENTRY(BRCM_CC_43430_CHIP_ID, 0xFFFFFFFC, 43430B0),
 	BRCMF_FW_ENTRY(BRCM_CC_4345_CHIP_ID, 0x00000200, 43456),
 	BRCMF_FW_ENTRY(BRCM_CC_4345_CHIP_ID, 0xFFFFFDC0, 43455),
 	BRCMF_FW_ENTRY(BRCM_CC_4354_CHIP_ID, 0xFFFFFFFF, 4354),
 	BRCMF_FW_ENTRY(BRCM_CC_4356_CHIP_ID, 0xFFFFFFFF, 4356),
 	BRCMF_FW_ENTRY(BRCM_CC_4359_CHIP_ID, 0xFFFFFFFF, 4359),
 	BRCMF_FW_ENTRY(CY_CC_4373_CHIP_ID, 0xFFFFFFFF, 4373),
-	BRCMF_FW_ENTRY(CY_CC_43012_CHIP_ID, 0xFFFFFFFF, 43012)
+	BRCMF_FW_ENTRY(CY_CC_43012_CHIP_ID, 0xFFFFFFFF, 43012),
+	BRCMF_FW_ENTRY(CY_CC_43752_CHIP_ID, 0xFFFFFFFF, 43752)
 };
 
 #define TXCTL_CREDITS	2
@@ -3416,7 +3423,8 @@ err:
 
 static bool brcmf_sdio_aos_no_decode(struct brcmf_sdio *bus)
 {
-	if (bus->ci->chip == CY_CC_43012_CHIP_ID)
+	if (bus->ci->chip == CY_CC_43012_CHIP_ID ||
+	    bus->ci->chip == CY_CC_43752_CHIP_ID)
 		return true;
 	else
 		return false;
@@ -3907,7 +3915,7 @@ static u32 brcmf_sdio_buscore_read32(void *ctx, u32 addr)
 	 * It can be identified as 4339 by looking at the chip revision. It
 	 * is corrected here so the chip.c module has the right info.
 	 */
-	if (addr == CORE_CC_REG(SI_ENUM_BASE, chipid) &&
+	if (addr == CORE_CC_REG(SI_ENUM_BASE_DEFAULT, chipid) &&
 	    (sdiodev->func1->device == SDIO_DEVICE_ID_BROADCOM_4339 ||
 	     sdiodev->func1->device == SDIO_DEVICE_ID_BROADCOM_4335_4339)) {
 		rev = (val & CID_REV_MASK) >> CID_REV_SHIFT;
@@ -3943,12 +3951,15 @@ brcmf_sdio_probe_attach(struct brcmf_sdio *bus)
 	int reg_addr;
 	u32 reg_val;
 	u32 drivestrength;
+	u32 enum_base;
 
 	sdiodev = bus->sdiodev;
 	sdio_claim_host(sdiodev->func1);
 
-	pr_debug("F1 signature read @0x18000000=0x%4x\n",
-		 brcmf_sdiod_readl(sdiodev, SI_ENUM_BASE, NULL));
+	enum_base = brcmf_chip_enum_base(sdiodev->func1->device);
+
+	pr_debug("F1 signature read @0x%08x=0x%4x\n", enum_base,
+		 brcmf_sdiod_readl(sdiodev, enum_base, NULL));
 
 	/*
 	 * Force PLL off until brcmf_chip_attach()
@@ -3967,7 +3978,8 @@ brcmf_sdio_probe_attach(struct brcmf_sdio *bus)
 		goto fail;
 	}
 
-	bus->ci = brcmf_chip_attach(sdiodev, &brcmf_sdio_buscore_ops);
+	bus->ci = brcmf_chip_attach(sdiodev, sdiodev->func1->device,
+				    &brcmf_sdio_buscore_ops);
 	if (IS_ERR(bus->ci)) {
 		brcmf_err("brcmf_chip_attach failed!\n");
 		bus->ci = NULL;
@@ -4257,6 +4269,7 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 
 		switch (sdiod->func1->device) {
 		case SDIO_DEVICE_ID_BROADCOM_CYPRESS_4373:
+		case SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752:
 			brcmf_dbg(INFO, "set F2 watermark to 0x%x*4 bytes\n",
 				  CY_4373_F2_WATERMARK);
 			brcmf_sdiod_writeb(sdiod, SBSDIO_WATERMARK,
@@ -4442,7 +4455,7 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
 	bus->tx_seq = SDPCM_SEQ_WRAP - 1;
 
 	/* single-threaded workqueue */
-	wq = alloc_ordered_workqueue("brcmf_wq/%s", WQ_MEM_RECLAIM,
+	wq = alloc_ordered_workqueue("brcmf_wq/%s", WQ_MEM_RECLAIM | WQ_HIGHPRI,
 				     dev_name(&sdiodev->func1->dev));
 	if (!wq) {
 		brcmf_err("insufficient memory to create txworkqueue\n");
@@ -4616,4 +4629,3 @@ int brcmf_sdio_sleep(struct brcmf_sdio *bus, bool sleep)
 
 	return ret;
 }
-
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c
new file mode 100644
index 000000000000..2f3c451148db
--- /dev/null
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: ISC
+/*
+ * Copyright (c) 2019 Broadcom
+ */
+
+#include <asm/unaligned.h>
+#include <linux/string.h>
+#include <linux/bug.h>
+
+#include "xtlv.h"
+
+static int brcmf_xtlv_header_size(u16 opts)
+{
+	int len = (int)offsetof(struct brcmf_xtlv, data);
+
+	if (opts & BRCMF_XTLV_OPTION_IDU8)
+		--len;
+	if (opts & BRCMF_XTLV_OPTION_LENU8)
+		--len;
+
+	return len;
+}
+
+int brcmf_xtlv_data_size(int dlen, u16 opts)
+{
+	int hsz;
+
+	hsz = brcmf_xtlv_header_size(opts);
+	if (opts & BRCMF_XTLV_OPTION_ALIGN32)
+		return roundup(dlen + hsz, 4);
+
+	return dlen + hsz;
+}
+
+void brcmf_xtlv_pack_header(struct brcmf_xtlv *xtlv, u16 id, u16 len,
+			    const u8 *data, u16 opts)
+{
+	u8 *data_buf;
+	u16 mask = BRCMF_XTLV_OPTION_IDU8 | BRCMF_XTLV_OPTION_LENU8;
+
+	if (!(opts & mask)) {
+		u8 *idp = (u8 *)xtlv;
+		u8 *lenp = idp + sizeof(xtlv->id);
+
+		put_unaligned_le16(id, idp);
+		put_unaligned_le16(len, lenp);
+		data_buf = lenp + sizeof(u16);
+	} else if ((opts & mask) == mask) { /* u8 id and u8 len */
+		u8 *idp = (u8 *)xtlv;
+		u8 *lenp = idp + 1;
+
+		*idp = (u8)id;
+		*lenp = (u8)len;
+		data_buf = lenp + sizeof(u8);
+	} else if (opts & BRCMF_XTLV_OPTION_IDU8) { /* u8 id, u16 len */
+		u8 *idp = (u8 *)xtlv;
+		u8 *lenp = idp + 1;
+
+		*idp = (u8)id;
+		put_unaligned_le16(len, lenp);
+		data_buf = lenp + sizeof(u16);
+	} else if (opts & BRCMF_XTLV_OPTION_LENU8) { /* u16 id, u8 len */
+		u8 *idp = (u8 *)xtlv;
+		u8 *lenp = idp + sizeof(u16);
+
+		put_unaligned_le16(id, idp);
+		*lenp = (u8)len;
+		data_buf = lenp + sizeof(u8);
+	} else {
+		WARN(true, "Unexpected xtlv option");
+		return;
+	}
+
+	if (opts & BRCMF_XTLV_OPTION_LENU8) {
+		WARN_ON(len > 0x00ff);
+		len &= 0xff;
+	}
+
+	if (data)
+		memcpy(data_buf, data, len);
+}
+
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.h
new file mode 100644
index 000000000000..e1930ce1b642
--- /dev/null
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.h
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: ISC
+/*
+ * Copyright (c) 2019 Broadcom
+ */
+#ifndef __BRCMF_XTLV_H
+#define __BRCMF_XTLV_H
+
+#include <linux/types.h>
+#include <linux/bits.h>
+
+/* bcm type(id), length, value with w/16 bit id/len. The structure below
+ * is nominal, and is used to support variable length id and type. See
+ * xtlv options below.
+ */
+struct brcmf_xtlv {
+	u16 id;
+	u16 len;
+	u8 data[0];
+};
+
+enum brcmf_xtlv_option {
+	BRCMF_XTLV_OPTION_ALIGN32 = BIT(0),
+	BRCMF_XTLV_OPTION_IDU8 = BIT(1),
+	BRCMF_XTLV_OPTION_LENU8 = BIT(2),
+};
+
+int brcmf_xtlv_data_size(int dlen, u16 opts);
+void brcmf_xtlv_pack_header(struct brcmf_xtlv *xtlv, u16 id, u16 len,
+			    const u8 *data, u16 opts);
+
+#endif /* __BRCMF_XTLV_H */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
index 26de1bd7fee9..8ddfc3d06687 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
@@ -704,7 +704,7 @@ static void brcms_c_write_inits(struct brcms_hardware *wlc_hw,
 static void brcms_c_write_mhf(struct brcms_hardware *wlc_hw, u16 *mhfs)
 {
 	u8 idx;
-	u16 addr[] = {
+	static const u16 addr[] = {
 		M_HOST_FLAGS1, M_HOST_FLAGS2, M_HOST_FLAGS3, M_HOST_FLAGS4,
 		M_HOST_FLAGS5
 	};
diff --git a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
index 00309b272a0e..9d81320164ce 100644
--- a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
+++ b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
@@ -52,6 +52,7 @@
 #define BRCM_CC_4371_CHIP_ID		0x4371
 #define CY_CC_4373_CHIP_ID		0x4373
 #define CY_CC_43012_CHIP_ID		43012
+#define CY_CC_43752_CHIP_ID		43752
 
 /* USB Device IDs */
 #define BRCM_USB_43143_DEVICE_ID	0xbd1e
diff --git a/drivers/net/wireless/broadcom/brcm80211/include/soc.h b/drivers/net/wireless/broadcom/brcm80211/include/soc.h
index 92d942b44f2c..824921191366 100644
--- a/drivers/net/wireless/broadcom/brcm80211/include/soc.h
+++ b/drivers/net/wireless/broadcom/brcm80211/include/soc.h
@@ -6,7 +6,7 @@
 #ifndef	_BRCM_SOC_H
 #define	_BRCM_SOC_H
 
-#define SI_ENUM_BASE		0x18000000	/* Enumeration space base */
+#define SI_ENUM_BASE_DEFAULT	0x18000000
 
 /* Common core control flags */
 #define	SICF_BIST_EN		0x8000
diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index fd37d4d2983b..65dd8cff1b01 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -1144,7 +1144,7 @@ static int waitbusy(struct airo_info *ai);
 static irqreturn_t airo_interrupt(int irq, void* dev_id);
 static int airo_thread(void *data);
 static void timer_func(struct net_device *dev);
-static int airo_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
+static int airo_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *, int cmd);
 static struct iw_statistics *airo_get_wireless_stats(struct net_device *dev);
 #ifdef CISCO_EXT
 static int readrids(struct net_device *dev, aironet_ioctl *comp);
@@ -2664,7 +2664,7 @@ static const struct net_device_ops airo11_netdev_ops = {
 	.ndo_start_xmit 	= airo_start_xmit11,
 	.ndo_get_stats 		= airo_get_stats,
 	.ndo_set_mac_address	= airo_set_mac_address,
-	.ndo_do_ioctl		= airo_ioctl,
+	.ndo_siocdevprivate	= airo_siocdevprivate,
 };
 
 static void wifi_setup(struct net_device *dev)
@@ -2764,7 +2764,7 @@ static const struct net_device_ops airo_netdev_ops = {
 	.ndo_get_stats		= airo_get_stats,
 	.ndo_set_rx_mode	= airo_set_multicast_list,
 	.ndo_set_mac_address	= airo_set_mac_address,
-	.ndo_do_ioctl		= airo_ioctl,
+	.ndo_siocdevprivate	= airo_siocdevprivate,
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
@@ -2775,7 +2775,7 @@ static const struct net_device_ops mpi_netdev_ops = {
 	.ndo_get_stats		= airo_get_stats,
 	.ndo_set_rx_mode	= airo_set_multicast_list,
 	.ndo_set_mac_address	= airo_set_mac_address,
-	.ndo_do_ioctl		= airo_ioctl,
+	.ndo_siocdevprivate	= airo_siocdevprivate,
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
@@ -7661,7 +7661,8 @@ static const struct iw_handler_def	airo_handler_def =
  * Javier Achirica did a great job of merging code from the unnamed CISCO
  * developer that added support for flashing the card.
  */
-static int airo_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+static int airo_siocdevprivate(struct net_device *dev, struct ifreq *rq,
+			       void __user *data, int cmd)
 {
 	int rc = 0;
 	struct airo_info *ai = dev->ml_priv;
@@ -7678,7 +7679,7 @@ static int airo_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	{
 		int val = AIROMAGIC;
 		aironet_ioctl com;
-		if (copy_from_user(&com, rq->ifr_data, sizeof(com)))
+		if (copy_from_user(&com, data, sizeof(com)))
 			rc = -EFAULT;
 		else if (copy_to_user(com.data, (char *)&val, sizeof(val)))
 			rc = -EFAULT;
@@ -7694,7 +7695,7 @@ static int airo_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		 */
 	{
 		aironet_ioctl com;
-		if (copy_from_user(&com, rq->ifr_data, sizeof(com))) {
+		if (copy_from_user(&com, data, sizeof(com))) {
 			rc = -EFAULT;
 			break;
 		}
diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_rx.c b/drivers/net/wireless/intel/ipw2x00/libipw_rx.c
index 5a2a723e480b..7a684b76f39b 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw_rx.c
+++ b/drivers/net/wireless/intel/ipw2x00/libipw_rx.c
@@ -927,7 +927,8 @@ static u8 qos_oui[QOS_OUI_LEN] = { 0x00, 0x50, 0xF2 };
 static int libipw_verify_qos_info(struct libipw_qos_information_element
 				     *info_element, int sub_type)
 {
-
+	if (info_element->elementID != QOS_ELEMENT_ID)
+		return -1;
 	if (info_element->qui_subtype != sub_type)
 		return -1;
 	if (memcmp(info_element->qui, qos_oui, QOS_OUI_LEN))
@@ -943,57 +944,34 @@ static int libipw_verify_qos_info(struct libipw_qos_information_element
 /*
  * Parse a QoS parameter element
  */
-static int libipw_read_qos_param_element(struct libipw_qos_parameter_info
-					    *element_param, struct libipw_info_element
-					    *info_element)
+static int libipw_read_qos_param_element(
+			struct libipw_qos_parameter_info *element_param,
+			struct libipw_info_element *info_element)
 {
-	int ret = 0;
-	u16 size = sizeof(struct libipw_qos_parameter_info) - 2;
+	size_t size = sizeof(*element_param);
 
-	if ((info_element == NULL) || (element_param == NULL))
+	if (!element_param || !info_element || info_element->len != size - 2)
 		return -1;
 
-	if (info_element->id == QOS_ELEMENT_ID && info_element->len == size) {
-		memcpy(element_param->info_element.qui, info_element->data,
-		       info_element->len);
-		element_param->info_element.elementID = info_element->id;
-		element_param->info_element.length = info_element->len;
-	} else
-		ret = -1;
-	if (ret == 0)
-		ret = libipw_verify_qos_info(&element_param->info_element,
-						QOS_OUI_PARAM_SUB_TYPE);
-	return ret;
+	memcpy(element_param, info_element, size);
+	return libipw_verify_qos_info(&element_param->info_element,
+				      QOS_OUI_PARAM_SUB_TYPE);
 }
 
 /*
  * Parse a QoS information element
  */
-static int libipw_read_qos_info_element(struct
-					   libipw_qos_information_element
-					   *element_info, struct libipw_info_element
-					   *info_element)
+static int libipw_read_qos_info_element(
+			struct libipw_qos_information_element *element_info,
+			struct libipw_info_element *info_element)
 {
-	int ret = 0;
-	u16 size = sizeof(struct libipw_qos_information_element) - 2;
+	size_t size = sizeof(struct libipw_qos_information_element) - 2;
 
-	if (element_info == NULL)
+	if (!element_info || !info_element || info_element->len != size - 2)
 		return -1;
-	if (info_element == NULL)
-		return -1;
-
-	if ((info_element->id == QOS_ELEMENT_ID) && (info_element->len == size)) {
-		memcpy(element_info->qui, info_element->data,
-		       info_element->len);
-		element_info->elementID = info_element->id;
-		element_info->length = info_element->len;
-	} else
-		ret = -1;
 
-	if (ret == 0)
-		ret = libipw_verify_qos_info(element_info,
-						QOS_OUI_INFO_SUB_TYPE);
-	return ret;
+	memcpy(element_info, info_element, size);
+	return libipw_verify_qos_info(element_info, QOS_OUI_INFO_SUB_TYPE);
 }
 
 /*
diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_tx.c b/drivers/net/wireless/intel/ipw2x00/libipw_tx.c
index d9baa2fa603b..36d1e6b2568d 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw_tx.c
+++ b/drivers/net/wireless/intel/ipw2x00/libipw_tx.c
@@ -179,8 +179,8 @@ static struct libipw_txb *libipw_alloc_txb(int nr_frags, int txb_size,
 {
 	struct libipw_txb *txb;
 	int i;
-	txb = kmalloc(sizeof(struct libipw_txb) + (sizeof(u8 *) * nr_frags),
-		      gfp_mask);
+
+	txb = kmalloc(struct_size(txb, fragments, nr_frags), gfp_mask);
 	if (!txb)
 		return NULL;
 
diff --git a/drivers/net/wireless/intel/iwlegacy/3945-mac.c b/drivers/net/wireless/intel/iwlegacy/3945-mac.c
index 6ff2674f8466..45abb25b65a9 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945-mac.c
@@ -571,20 +571,18 @@ il3945_tx_skb(struct il_priv *il,
 
 	/* Physical address of this Tx command's header (not MAC header!),
 	 * within command buffer array. */
-	txcmd_phys =
-	    pci_map_single(il->pci_dev, &out_cmd->hdr, firstlen,
-			   PCI_DMA_TODEVICE);
-	if (unlikely(pci_dma_mapping_error(il->pci_dev, txcmd_phys)))
+	txcmd_phys = dma_map_single(&il->pci_dev->dev, &out_cmd->hdr, firstlen,
+				    DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(&il->pci_dev->dev, txcmd_phys)))
 		goto drop_unlock;
 
 	/* Set up TFD's 2nd entry to point directly to remainder of skb,
 	 * if any (802.11 null frames have no payload). */
 	secondlen = skb->len - hdr_len;
 	if (secondlen > 0) {
-		phys_addr =
-		    pci_map_single(il->pci_dev, skb->data + hdr_len, secondlen,
-				   PCI_DMA_TODEVICE);
-		if (unlikely(pci_dma_mapping_error(il->pci_dev, phys_addr)))
+		phys_addr = dma_map_single(&il->pci_dev->dev, skb->data + hdr_len,
+					   secondlen, DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(&il->pci_dev->dev, phys_addr)))
 			goto drop_unlock;
 	}
 
@@ -1015,11 +1013,11 @@ il3945_rx_allocate(struct il_priv *il, gfp_t priority)
 
 		/* Get physical address of RB/SKB */
 		page_dma =
-		    pci_map_page(il->pci_dev, page, 0,
+		    dma_map_page(&il->pci_dev->dev, page, 0,
 				 PAGE_SIZE << il->hw_params.rx_page_order,
-				 PCI_DMA_FROMDEVICE);
+				 DMA_FROM_DEVICE);
 
-		if (unlikely(pci_dma_mapping_error(il->pci_dev, page_dma))) {
+		if (unlikely(dma_mapping_error(&il->pci_dev->dev, page_dma))) {
 			__free_pages(page, il->hw_params.rx_page_order);
 			break;
 		}
@@ -1028,9 +1026,9 @@ il3945_rx_allocate(struct il_priv *il, gfp_t priority)
 
 		if (list_empty(&rxq->rx_used)) {
 			spin_unlock_irqrestore(&rxq->lock, flags);
-			pci_unmap_page(il->pci_dev, page_dma,
+			dma_unmap_page(&il->pci_dev->dev, page_dma,
 				       PAGE_SIZE << il->hw_params.rx_page_order,
-				       PCI_DMA_FROMDEVICE);
+				       DMA_FROM_DEVICE);
 			__free_pages(page, il->hw_params.rx_page_order);
 			return;
 		}
@@ -1062,9 +1060,10 @@ il3945_rx_queue_reset(struct il_priv *il, struct il_rx_queue *rxq)
 		/* In the reset function, these buffers may have been allocated
 		 * to an SKB, so we need to unmap and free potential storage */
 		if (rxq->pool[i].page != NULL) {
-			pci_unmap_page(il->pci_dev, rxq->pool[i].page_dma,
+			dma_unmap_page(&il->pci_dev->dev,
+				       rxq->pool[i].page_dma,
 				       PAGE_SIZE << il->hw_params.rx_page_order,
-				       PCI_DMA_FROMDEVICE);
+				       DMA_FROM_DEVICE);
 			__il_free_pages(il, rxq->pool[i].page);
 			rxq->pool[i].page = NULL;
 		}
@@ -1111,9 +1110,10 @@ il3945_rx_queue_free(struct il_priv *il, struct il_rx_queue *rxq)
 	int i;
 	for (i = 0; i < RX_QUEUE_SIZE + RX_FREE_BUFFERS; i++) {
 		if (rxq->pool[i].page != NULL) {
-			pci_unmap_page(il->pci_dev, rxq->pool[i].page_dma,
+			dma_unmap_page(&il->pci_dev->dev,
+				       rxq->pool[i].page_dma,
 				       PAGE_SIZE << il->hw_params.rx_page_order,
-				       PCI_DMA_FROMDEVICE);
+				       DMA_FROM_DEVICE);
 			__il_free_pages(il, rxq->pool[i].page);
 			rxq->pool[i].page = NULL;
 		}
@@ -1213,9 +1213,9 @@ il3945_rx_handle(struct il_priv *il)
 
 		rxq->queue[i] = NULL;
 
-		pci_unmap_page(il->pci_dev, rxb->page_dma,
+		dma_unmap_page(&il->pci_dev->dev, rxb->page_dma,
 			       PAGE_SIZE << il->hw_params.rx_page_order,
-			       PCI_DMA_FROMDEVICE);
+			       DMA_FROM_DEVICE);
 		pkt = rxb_addr(rxb);
 
 		len = le32_to_cpu(pkt->len_n_flags) & IL_RX_FRAME_SIZE_MSK;
@@ -1260,11 +1260,11 @@ il3945_rx_handle(struct il_priv *il)
 		spin_lock_irqsave(&rxq->lock, flags);
 		if (rxb->page != NULL) {
 			rxb->page_dma =
-			    pci_map_page(il->pci_dev, rxb->page, 0,
-					 PAGE_SIZE << il->hw_params.
-					 rx_page_order, PCI_DMA_FROMDEVICE);
-			if (unlikely(pci_dma_mapping_error(il->pci_dev,
-							   rxb->page_dma))) {
+			    dma_map_page(&il->pci_dev->dev, rxb->page, 0,
+					 PAGE_SIZE << il->hw_params.rx_page_order,
+					 DMA_FROM_DEVICE);
+			if (unlikely(dma_mapping_error(&il->pci_dev->dev,
+						       rxb->page_dma))) {
 				__il_free_pages(il, rxb->page);
 				rxb->page = NULL;
 				list_add_tail(&rxb->list, &rxq->rx_used);
@@ -3616,9 +3616,7 @@ il3945_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_master(pdev);
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-	if (!err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 	if (err) {
 		IL_WARN("No suitable DMA available.\n");
 		goto out_pci_disable_device;
diff --git a/drivers/net/wireless/intel/iwlegacy/3945.c b/drivers/net/wireless/intel/iwlegacy/3945.c
index 0597d828bee1..a773939b8c2a 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945.c
@@ -652,16 +652,16 @@ il3945_hw_txq_free_tfd(struct il_priv *il, struct il_tx_queue *txq)
 
 	/* Unmap tx_cmd */
 	if (counter)
-		pci_unmap_single(dev, dma_unmap_addr(&txq->meta[idx], mapping),
+		dma_unmap_single(&dev->dev,
+				 dma_unmap_addr(&txq->meta[idx], mapping),
 				 dma_unmap_len(&txq->meta[idx], len),
-				 PCI_DMA_TODEVICE);
+				 DMA_TO_DEVICE);
 
 	/* unmap chunks if any */
 
 	for (i = 1; i < counter; i++)
-		pci_unmap_single(dev, le32_to_cpu(tfd->tbs[i].addr),
-				 le32_to_cpu(tfd->tbs[i].len),
-				 PCI_DMA_TODEVICE);
+		dma_unmap_single(&dev->dev, le32_to_cpu(tfd->tbs[i].addr),
+				 le32_to_cpu(tfd->tbs[i].len), DMA_TO_DEVICE);
 
 	/* free SKB */
 	if (txq->skbs) {
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index 341d6a2bc690..0223532fd56a 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -94,9 +94,10 @@ il4965_rx_queue_reset(struct il_priv *il, struct il_rx_queue *rxq)
 		/* In the reset function, these buffers may have been allocated
 		 * to an SKB, so we need to unmap and free potential storage */
 		if (rxq->pool[i].page != NULL) {
-			pci_unmap_page(il->pci_dev, rxq->pool[i].page_dma,
+			dma_unmap_page(&il->pci_dev->dev,
+				       rxq->pool[i].page_dma,
 				       PAGE_SIZE << il->hw_params.rx_page_order,
-				       PCI_DMA_FROMDEVICE);
+				       DMA_FROM_DEVICE);
 			__il_free_pages(il, rxq->pool[i].page);
 			rxq->pool[i].page = NULL;
 		}
@@ -342,11 +343,10 @@ il4965_rx_allocate(struct il_priv *il, gfp_t priority)
 		}
 
 		/* Get physical address of the RB */
-		page_dma =
-		    pci_map_page(il->pci_dev, page, 0,
-				 PAGE_SIZE << il->hw_params.rx_page_order,
-				 PCI_DMA_FROMDEVICE);
-		if (unlikely(pci_dma_mapping_error(il->pci_dev, page_dma))) {
+		page_dma = dma_map_page(&il->pci_dev->dev, page, 0,
+					PAGE_SIZE << il->hw_params.rx_page_order,
+					DMA_FROM_DEVICE);
+		if (unlikely(dma_mapping_error(&il->pci_dev->dev, page_dma))) {
 			__free_pages(page, il->hw_params.rx_page_order);
 			break;
 		}
@@ -355,9 +355,9 @@ il4965_rx_allocate(struct il_priv *il, gfp_t priority)
 
 		if (list_empty(&rxq->rx_used)) {
 			spin_unlock_irqrestore(&rxq->lock, flags);
-			pci_unmap_page(il->pci_dev, page_dma,
+			dma_unmap_page(&il->pci_dev->dev, page_dma,
 				       PAGE_SIZE << il->hw_params.rx_page_order,
-				       PCI_DMA_FROMDEVICE);
+				       DMA_FROM_DEVICE);
 			__free_pages(page, il->hw_params.rx_page_order);
 			return;
 		}
@@ -409,9 +409,10 @@ il4965_rx_queue_free(struct il_priv *il, struct il_rx_queue *rxq)
 	int i;
 	for (i = 0; i < RX_QUEUE_SIZE + RX_FREE_BUFFERS; i++) {
 		if (rxq->pool[i].page != NULL) {
-			pci_unmap_page(il->pci_dev, rxq->pool[i].page_dma,
+			dma_unmap_page(&il->pci_dev->dev,
+				       rxq->pool[i].page_dma,
 				       PAGE_SIZE << il->hw_params.rx_page_order,
-				       PCI_DMA_FROMDEVICE);
+				       DMA_FROM_DEVICE);
 			__il_free_pages(il, rxq->pool[i].page);
 			rxq->pool[i].page = NULL;
 		}
@@ -1815,20 +1816,18 @@ il4965_tx_skb(struct il_priv *il,
 
 	/* Physical address of this Tx command's header (not MAC header!),
 	 * within command buffer array. */
-	txcmd_phys =
-	    pci_map_single(il->pci_dev, &out_cmd->hdr, firstlen,
-			   PCI_DMA_BIDIRECTIONAL);
-	if (unlikely(pci_dma_mapping_error(il->pci_dev, txcmd_phys)))
+	txcmd_phys = dma_map_single(&il->pci_dev->dev, &out_cmd->hdr, firstlen,
+				    DMA_BIDIRECTIONAL);
+	if (unlikely(dma_mapping_error(&il->pci_dev->dev, txcmd_phys)))
 		goto drop_unlock;
 
 	/* Set up TFD's 2nd entry to point directly to remainder of skb,
 	 * if any (802.11 null frames have no payload). */
 	secondlen = skb->len - hdr_len;
 	if (secondlen > 0) {
-		phys_addr =
-		    pci_map_single(il->pci_dev, skb->data + hdr_len, secondlen,
-				   PCI_DMA_TODEVICE);
-		if (unlikely(pci_dma_mapping_error(il->pci_dev, phys_addr)))
+		phys_addr = dma_map_single(&il->pci_dev->dev, skb->data + hdr_len,
+					   secondlen, DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(&il->pci_dev->dev, phys_addr)))
 			goto drop_unlock;
 	}
 
@@ -1853,8 +1852,8 @@ il4965_tx_skb(struct il_priv *il,
 	    offsetof(struct il_tx_cmd, scratch);
 
 	/* take back ownership of DMA buffer to enable update */
-	pci_dma_sync_single_for_cpu(il->pci_dev, txcmd_phys, firstlen,
-				    PCI_DMA_BIDIRECTIONAL);
+	dma_sync_single_for_cpu(&il->pci_dev->dev, txcmd_phys, firstlen,
+				DMA_BIDIRECTIONAL);
 	tx_cmd->dram_lsb_ptr = cpu_to_le32(scratch_phys);
 	tx_cmd->dram_msb_ptr = il_get_dma_hi_addr(scratch_phys);
 
@@ -1869,8 +1868,8 @@ il4965_tx_skb(struct il_priv *il,
 	if (info->flags & IEEE80211_TX_CTL_AMPDU)
 		il->ops->txq_update_byte_cnt_tbl(il, txq, le16_to_cpu(tx_cmd->len));
 
-	pci_dma_sync_single_for_device(il->pci_dev, txcmd_phys, firstlen,
-				       PCI_DMA_BIDIRECTIONAL);
+	dma_sync_single_for_device(&il->pci_dev->dev, txcmd_phys, firstlen,
+				   DMA_BIDIRECTIONAL);
 
 	/* Tell device the write idx *just past* this latest filled TFD */
 	q->write_ptr = il_queue_inc_wrap(q->write_ptr, q->n_bd);
@@ -3929,15 +3928,15 @@ il4965_hw_txq_free_tfd(struct il_priv *il, struct il_tx_queue *txq)
 
 	/* Unmap tx_cmd */
 	if (num_tbs)
-		pci_unmap_single(dev, dma_unmap_addr(&txq->meta[idx], mapping),
+		dma_unmap_single(&dev->dev,
+				 dma_unmap_addr(&txq->meta[idx], mapping),
 				 dma_unmap_len(&txq->meta[idx], len),
-				 PCI_DMA_BIDIRECTIONAL);
+				 DMA_BIDIRECTIONAL);
 
 	/* Unmap chunks, if any. */
 	for (i = 1; i < num_tbs; i++)
-		pci_unmap_single(dev, il4965_tfd_tb_get_addr(tfd, i),
-				 il4965_tfd_tb_get_len(tfd, i),
-				 PCI_DMA_TODEVICE);
+		dma_unmap_single(&dev->dev, il4965_tfd_tb_get_addr(tfd, i),
+				 il4965_tfd_tb_get_len(tfd, i), DMA_TO_DEVICE);
 
 	/* free SKB */
 	if (txq->skbs) {
@@ -4243,9 +4242,9 @@ il4965_rx_handle(struct il_priv *il)
 
 		rxq->queue[i] = NULL;
 
-		pci_unmap_page(il->pci_dev, rxb->page_dma,
+		dma_unmap_page(&il->pci_dev->dev, rxb->page_dma,
 			       PAGE_SIZE << il->hw_params.rx_page_order,
-			       PCI_DMA_FROMDEVICE);
+			       DMA_FROM_DEVICE);
 		pkt = rxb_addr(rxb);
 
 		len = le32_to_cpu(pkt->len_n_flags) & IL_RX_FRAME_SIZE_MSK;
@@ -4290,12 +4289,12 @@ il4965_rx_handle(struct il_priv *il)
 		spin_lock_irqsave(&rxq->lock, flags);
 		if (rxb->page != NULL) {
 			rxb->page_dma =
-			    pci_map_page(il->pci_dev, rxb->page, 0,
-					 PAGE_SIZE << il->hw_params.
-					 rx_page_order, PCI_DMA_FROMDEVICE);
+			    dma_map_page(&il->pci_dev->dev, rxb->page, 0,
+					 PAGE_SIZE << il->hw_params.rx_page_order,
+					 DMA_FROM_DEVICE);
 
-			if (unlikely(pci_dma_mapping_error(il->pci_dev,
-							   rxb->page_dma))) {
+			if (unlikely(dma_mapping_error(&il->pci_dev->dev,
+						       rxb->page_dma))) {
 				__il_free_pages(il, rxb->page);
 				rxb->page = NULL;
 				list_add_tail(&rxb->list, &rxq->rx_used);
@@ -6514,14 +6513,9 @@ il4965_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_master(pdev);
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(36));
-	if (!err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(36));
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(36));
 	if (err) {
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (!err)
-			err =
-			    pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 		/* both attempts failed: */
 		if (err) {
 			IL_WARN("No suitable DMA available.\n");
diff --git a/drivers/net/wireless/intel/iwlegacy/common.c b/drivers/net/wireless/intel/iwlegacy/common.c
index 219fed91cac5..683b632981ed 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.c
+++ b/drivers/net/wireless/intel/iwlegacy/common.c
@@ -2819,10 +2819,10 @@ il_cmd_queue_unmap(struct il_priv *il)
 		i = il_get_cmd_idx(q, q->read_ptr, 0);
 
 		if (txq->meta[i].flags & CMD_MAPPED) {
-			pci_unmap_single(il->pci_dev,
+			dma_unmap_single(&il->pci_dev->dev,
 					 dma_unmap_addr(&txq->meta[i], mapping),
 					 dma_unmap_len(&txq->meta[i], len),
-					 PCI_DMA_BIDIRECTIONAL);
+					 DMA_BIDIRECTIONAL);
 			txq->meta[i].flags = 0;
 		}
 
@@ -2831,10 +2831,10 @@ il_cmd_queue_unmap(struct il_priv *il)
 
 	i = q->n_win;
 	if (txq->meta[i].flags & CMD_MAPPED) {
-		pci_unmap_single(il->pci_dev,
+		dma_unmap_single(&il->pci_dev->dev,
 				 dma_unmap_addr(&txq->meta[i], mapping),
 				 dma_unmap_len(&txq->meta[i], len),
-				 PCI_DMA_BIDIRECTIONAL);
+				 DMA_BIDIRECTIONAL);
 		txq->meta[i].flags = 0;
 	}
 }
@@ -3197,10 +3197,9 @@ il_enqueue_hcmd(struct il_priv *il, struct il_host_cmd *cmd)
 	}
 #endif
 
-	phys_addr =
-	    pci_map_single(il->pci_dev, &out_cmd->hdr, fix_size,
-			   PCI_DMA_BIDIRECTIONAL);
-	if (unlikely(pci_dma_mapping_error(il->pci_dev, phys_addr))) {
+	phys_addr = dma_map_single(&il->pci_dev->dev, &out_cmd->hdr, fix_size,
+				   DMA_BIDIRECTIONAL);
+	if (unlikely(dma_mapping_error(&il->pci_dev->dev, phys_addr))) {
 		idx = -ENOMEM;
 		goto out;
 	}
@@ -3298,8 +3297,8 @@ il_tx_cmd_complete(struct il_priv *il, struct il_rx_buf *rxb)
 
 	txq->time_stamp = jiffies;
 
-	pci_unmap_single(il->pci_dev, dma_unmap_addr(meta, mapping),
-			 dma_unmap_len(meta, len), PCI_DMA_BIDIRECTIONAL);
+	dma_unmap_single(&il->pci_dev->dev, dma_unmap_addr(meta, mapping),
+			 dma_unmap_len(meta, len), DMA_BIDIRECTIONAL);
 
 	/* Input error checking is done when commands are added to queue. */
 	if (meta->flags & CMD_WANT_SKB) {
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index 7f1faa9d97b4..52d1d391f4c6 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -9,7 +9,7 @@
 #include "iwl-prph.h"
 
 /* Highest firmware API version supported */
-#define IWL_22000_UCODE_API_MAX	64
+#define IWL_22000_UCODE_API_MAX	65
 
 /* Lowest firmware API version supported */
 #define IWL_22000_UCODE_API_MIN	39
@@ -154,7 +154,7 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 	.apmg_not_supported = true,					\
 	.trans.mq_rx_supported = true,					\
 	.vht_mu_mimo_supported = true,					\
-	.mac_addr_from_csr = true,					\
+	.mac_addr_from_csr = 0x380,					\
 	.ht_params = &iwl_22000_ht_params,				\
 	.nvm_ver = IWL_22000_NVM_VERSION,				\
 	.trans.use_tfh = true,						\
@@ -215,6 +215,67 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 		},							\
 	}
 
+#define IWL_DEVICE_BZ_COMMON						\
+	.ucode_api_max = IWL_22000_UCODE_API_MAX,			\
+	.ucode_api_min = IWL_22000_UCODE_API_MIN,			\
+	.led_mode = IWL_LED_RF_STATE,					\
+	.nvm_hw_section_num = 10,					\
+	.non_shared_ant = ANT_B,					\
+	.dccm_offset = IWL_22000_DCCM_OFFSET,				\
+	.dccm_len = IWL_22000_DCCM_LEN,					\
+	.dccm2_offset = IWL_22000_DCCM2_OFFSET,				\
+	.dccm2_len = IWL_22000_DCCM2_LEN,				\
+	.smem_offset = IWL_22000_SMEM_OFFSET,				\
+	.smem_len = IWL_22000_SMEM_LEN,					\
+	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,		\
+	.apmg_not_supported = true,					\
+	.trans.mq_rx_supported = true,					\
+	.vht_mu_mimo_supported = true,					\
+	.mac_addr_from_csr = 0x30,					\
+	.ht_params = &iwl_22000_ht_params,				\
+	.nvm_ver = IWL_22000_NVM_VERSION,				\
+	.trans.use_tfh = true,						\
+	.trans.rf_id = true,						\
+	.trans.gen2 = true,						\
+	.nvm_type = IWL_NVM_EXT,					\
+	.dbgc_supported = true,						\
+	.min_umac_error_event_table = 0x400000,				\
+	.d3_debug_data_base_addr = 0x401000,				\
+	.d3_debug_data_length = 60 * 1024,				\
+	.mon_smem_regs = {						\
+		.write_ptr = {						\
+			.addr = LDBG_M2S_BUF_WPTR,			\
+			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,		\
+	},								\
+		.cycle_cnt = {						\
+			.addr = LDBG_M2S_BUF_WRAP_CNT,			\
+			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,		\
+		},							\
+	}
+
+#define IWL_DEVICE_BZ							\
+	IWL_DEVICE_BZ_COMMON,						\
+	.trans.umac_prph_offset = 0x300000,				\
+	.trans.device_family = IWL_DEVICE_FAMILY_BZ,			\
+	.trans.base_params = &iwl_ax210_base_params,			\
+	.min_txq_size = 128,						\
+	.gp2_reg_addr = 0xd02c68,					\
+	.min_256_ba_txq_size = 1024,					\
+	.mon_dram_regs = {						\
+		.write_ptr = {						\
+			.addr = DBGC_CUR_DBGBUF_STATUS,			\
+			.mask = DBGC_CUR_DBGBUF_STATUS_OFFSET_MSK,	\
+		},							\
+		.cycle_cnt = {						\
+			.addr = DBGC_DBGBUF_WRAP_AROUND,		\
+			.mask = 0xffffffff,				\
+		},							\
+		.cur_frag = {						\
+			.addr = DBGC_CUR_DBGBUF_STATUS,			\
+			.mask = DBGC_CUR_DBGBUF_STATUS_IDX_MSK,		\
+		},							\
+	}
+
 const struct iwl_cfg_trans_params iwl_qnj_trans_cfg = {
 	.mq_rx_supported = true,
 	.use_tfh = true,
@@ -373,7 +434,7 @@ const struct iwl_cfg_trans_params iwl_ma_trans_cfg = {
 };
 
 const struct iwl_cfg_trans_params iwl_bz_trans_cfg = {
-	.device_family = IWL_DEVICE_FAMILY_AX210,
+	.device_family = IWL_DEVICE_FAMILY_BZ,
 	.base_params = &iwl_ax210_base_params,
 	.mq_rx_supported = true,
 	.use_tfh = true,
@@ -394,6 +455,7 @@ const char iwl_ax211_name[] = "Intel(R) Wi-Fi 6E AX211 160MHz";
 const char iwl_ax221_name[] = "Intel(R) Wi-Fi 6E AX221 160MHz";
 const char iwl_ax231_name[] = "Intel(R) Wi-Fi 6E AX231 160MHz";
 const char iwl_ax411_name[] = "Intel(R) Wi-Fi 6E AX411 160MHz";
+const char iwl_bz_name[] = "Intel(R) TBD Bz device";
 
 const char iwl_ax200_killer_1650w_name[] =
 	"Killer(R) Wi-Fi 6 AX1650w 160MHz Wireless Network Adapter (200D2W)";
@@ -763,28 +825,28 @@ const struct iwl_cfg iwl_cfg_quz_a0_hr_b0 = {
 const struct iwl_cfg iwl_cfg_bz_a0_hr_b0 = {
 	.fw_name_pre = IWL_BZ_A_HR_B_FW_PRE,
 	.uhb_supported = true,
-	IWL_DEVICE_AX210,
+	IWL_DEVICE_BZ,
 	.num_rbds = IWL_NUM_RBDS_AX210_HE,
 };
 
 const struct iwl_cfg iwl_cfg_bz_a0_gf_a0 = {
 	.fw_name_pre = IWL_BZ_A_GF_A_FW_PRE,
 	.uhb_supported = true,
-	IWL_DEVICE_AX210,
+	IWL_DEVICE_BZ,
 	.num_rbds = IWL_NUM_RBDS_AX210_HE,
 };
 
 const struct iwl_cfg iwl_cfg_bz_a0_gf4_a0 = {
 	.fw_name_pre = IWL_BZ_A_GF4_A_FW_PRE,
 	.uhb_supported = true,
-	IWL_DEVICE_AX210,
+	IWL_DEVICE_BZ,
 	.num_rbds = IWL_NUM_RBDS_AX210_HE,
 };
 
 const struct iwl_cfg iwl_cfg_bz_a0_mr_a0 = {
 	.fw_name_pre = IWL_BZ_A_MR_A_FW_PRE,
 	.uhb_supported = true,
-	IWL_DEVICE_AX210,
+	IWL_DEVICE_BZ,
 	.num_rbds = IWL_NUM_RBDS_AX210_HE,
 };
 
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
index 871533beff30..7a7ca06d46c1 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
@@ -89,7 +89,7 @@ static const struct iwl_tt_params iwl9000_tt_params = {
 	.apmg_not_supported = true,					\
 	.num_rbds = 512,						\
 	.vht_mu_mimo_supported = true,					\
-	.mac_addr_from_csr = true,					\
+	.mac_addr_from_csr = 0x380,					\
 	.nvm_type = IWL_NVM_EXT,					\
 	.dbgc_supported = true,						\
 	.min_umac_error_event_table = 0x800000,				\
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
index c01523f64bfc..cc7b69fd14d3 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /******************************************************************************
  *
- * Copyright(c) 2003 - 2014, 2018 - 2020  Intel Corporation. All rights reserved.
+ * Copyright(c) 2003 - 2014, 2018 - 2021  Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Deutschland GmbH
  *
  * Portions of this file are derived from the ipw3945 project, as well
@@ -1950,7 +1950,7 @@ static void iwlagn_fw_error(struct iwl_priv *priv, bool ondemand)
 	}
 }
 
-static void iwl_nic_error(struct iwl_op_mode *op_mode)
+static void iwl_nic_error(struct iwl_op_mode *op_mode, bool sync)
 {
 	struct iwl_priv *priv = IWL_OP_MODE_GET_DVM(op_mode);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rx.c b/drivers/net/wireless/intel/iwlwifi/dvm/rx.c
index 80475c7a6fba..3cd7b423c588 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/rx.c
@@ -318,7 +318,7 @@ iwlagn_accumulative_statistics(struct iwl_priv *priv,
 		    (__le32 *)&priv->delta_stats._name,		\
 		    (__le32 *)&priv->max_delta_stats._name,	\
 		    (__le32 *)&priv->accum_stats._name,		\
-		    sizeof(*_name));
+		    sizeof(*_name))
 
 	ACCUM(common);
 	ACCUM(rx_non_phy);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index 34933f133a0a..1efac0b2a94d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -264,7 +264,7 @@ int iwl_acpi_get_tas(struct iwl_fw_runtime *fwrt,
 		goto out_free;
 	}
 
-	enabled = !!wifi_pkg->package.elements[0].integer.value;
+	enabled = !!wifi_pkg->package.elements[1].integer.value;
 
 	if (!enabled) {
 		*block_list_size = -1;
@@ -273,15 +273,15 @@ int iwl_acpi_get_tas(struct iwl_fw_runtime *fwrt,
 		goto out_free;
 	}
 
-	if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER ||
-	    wifi_pkg->package.elements[1].integer.value >
+	if (wifi_pkg->package.elements[2].type != ACPI_TYPE_INTEGER ||
+	    wifi_pkg->package.elements[2].integer.value >
 	    APCI_WTAS_BLACK_LIST_MAX) {
 		IWL_DEBUG_RADIO(fwrt, "TAS invalid array size %llu\n",
 				wifi_pkg->package.elements[1].integer.value);
 		ret = -EINVAL;
 		goto out_free;
 	}
-	*block_list_size = wifi_pkg->package.elements[1].integer.value;
+	*block_list_size = wifi_pkg->package.elements[2].integer.value;
 
 	IWL_DEBUG_RADIO(fwrt, "TAS array size %d\n", *block_list_size);
 	if (*block_list_size > APCI_WTAS_BLACK_LIST_MAX) {
@@ -294,15 +294,15 @@ int iwl_acpi_get_tas(struct iwl_fw_runtime *fwrt,
 	for (i = 0; i < *block_list_size; i++) {
 		u32 country;
 
-		if (wifi_pkg->package.elements[2 + i].type !=
+		if (wifi_pkg->package.elements[3 + i].type !=
 		    ACPI_TYPE_INTEGER) {
 			IWL_DEBUG_RADIO(fwrt,
-					"TAS invalid array elem %d\n", 2 + i);
+					"TAS invalid array elem %d\n", 3 + i);
 			ret = -EINVAL;
 			goto out_free;
 		}
 
-		country = wifi_pkg->package.elements[2 + i].integer.value;
+		country = wifi_pkg->package.elements[3 + i].integer.value;
 		block_list_array[i] = cpu_to_le32(country);
 		IWL_DEBUG_RADIO(fwrt, "TAS block list country %d\n", country);
 	}
@@ -412,20 +412,35 @@ IWL_EXPORT_SYMBOL(iwl_acpi_get_eckv);
 
 static int iwl_sar_set_profile(union acpi_object *table,
 			       struct iwl_sar_profile *profile,
-			       bool enabled)
+			       bool enabled, u8 num_chains, u8 num_sub_bands)
 {
-	int i;
-
-	profile->enabled = enabled;
-
-	for (i = 0; i < ACPI_SAR_TABLE_SIZE; i++) {
-		if (table[i].type != ACPI_TYPE_INTEGER ||
-		    table[i].integer.value > U8_MAX)
-			return -EINVAL;
+	int i, j, idx = 0;
 
-		profile->table[i] = table[i].integer.value;
+	/*
+	 * The table from ACPI is flat, but we store it in a
+	 * structured array.
+	 */
+	for (i = 0; i < ACPI_SAR_NUM_CHAINS_REV2; i++) {
+		for (j = 0; j < ACPI_SAR_NUM_SUB_BANDS_REV2; j++) {
+			/* if we don't have the values, use the default */
+			if (i >= num_chains || j >= num_sub_bands) {
+				profile->chains[i].subbands[j] = 0;
+			} else {
+				if (table[idx].type != ACPI_TYPE_INTEGER ||
+				    table[idx].integer.value > U8_MAX)
+					return -EINVAL;
+
+				profile->chains[i].subbands[j] =
+					table[idx].integer.value;
+
+				idx++;
+			}
+		}
 	}
 
+	/* Only if all values were valid can the profile be enabled */
+	profile->enabled = enabled;
+
 	return 0;
 }
 
@@ -433,10 +448,10 @@ static int iwl_sar_fill_table(struct iwl_fw_runtime *fwrt,
 			      __le16 *per_chain, u32 n_subbands,
 			      int prof_a, int prof_b)
 {
-	int profs[ACPI_SAR_NUM_CHAIN_LIMITS] = { prof_a, prof_b };
-	int i, j, idx;
+	int profs[ACPI_SAR_NUM_CHAINS_REV0] = { prof_a, prof_b };
+	int i, j;
 
-	for (i = 0; i < ACPI_SAR_NUM_CHAIN_LIMITS; i++) {
+	for (i = 0; i < ACPI_SAR_NUM_CHAINS_REV0; i++) {
 		struct iwl_sar_profile *prof;
 
 		/* don't allow SAR to be disabled (profile 0 means disable) */
@@ -467,11 +482,10 @@ static int iwl_sar_fill_table(struct iwl_fw_runtime *fwrt,
 			       i, profs[i]);
 		IWL_DEBUG_RADIO(fwrt, "  Chain[%d]:\n", i);
 		for (j = 0; j < n_subbands; j++) {
-			idx = i * ACPI_SAR_NUM_SUB_BANDS + j;
 			per_chain[i * n_subbands + j] =
-				cpu_to_le16(prof->table[idx]);
+				cpu_to_le16(prof->chains[i].subbands[j]);
 			IWL_DEBUG_RADIO(fwrt, "    Band[%d] = %d * .125dBm\n",
-					j, prof->table[idx]);
+					j, prof->chains[i].subbands[j]);
 		}
 	}
 
@@ -486,7 +500,7 @@ int iwl_sar_select_profile(struct iwl_fw_runtime *fwrt,
 
 	for (i = 0; i < n_tables; i++) {
 		ret = iwl_sar_fill_table(fwrt,
-			 &per_chain[i * n_subbands * ACPI_SAR_NUM_CHAIN_LIMITS],
+			 &per_chain[i * n_subbands * ACPI_SAR_NUM_CHAINS_REV0],
 			 n_subbands, prof_a, prof_b);
 		if (ret)
 			break;
@@ -501,28 +515,71 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt)
 	union acpi_object *wifi_pkg, *table, *data;
 	bool enabled;
 	int ret, tbl_rev;
+	u8 num_chains, num_sub_bands;
 
 	data = iwl_acpi_get_object(fwrt->dev, ACPI_WRDS_METHOD);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
+	/* start by trying to read revision 2 */
 	wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data,
-					 ACPI_WRDS_WIFI_DATA_SIZE, &tbl_rev);
-	if (IS_ERR(wifi_pkg)) {
-		ret = PTR_ERR(wifi_pkg);
-		goto out_free;
+					 ACPI_WRDS_WIFI_DATA_SIZE_REV2,
+					 &tbl_rev);
+	if (!IS_ERR(wifi_pkg)) {
+		if (tbl_rev != 2) {
+			ret = PTR_ERR(wifi_pkg);
+			goto out_free;
+		}
+
+		num_chains = ACPI_SAR_NUM_CHAINS_REV2;
+		num_sub_bands = ACPI_SAR_NUM_SUB_BANDS_REV2;
+
+		goto read_table;
 	}
 
-	if (tbl_rev != 0) {
-		ret = -EINVAL;
-		goto out_free;
+	/* then try revision 1 */
+	wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data,
+					 ACPI_WRDS_WIFI_DATA_SIZE_REV1,
+					 &tbl_rev);
+	if (!IS_ERR(wifi_pkg)) {
+		if (tbl_rev != 1) {
+			ret = PTR_ERR(wifi_pkg);
+			goto out_free;
+		}
+
+		num_chains = ACPI_SAR_NUM_CHAINS_REV1;
+		num_sub_bands = ACPI_SAR_NUM_SUB_BANDS_REV1;
+
+		goto read_table;
+	}
+
+	/* then finally revision 0 */
+	wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data,
+					 ACPI_WRDS_WIFI_DATA_SIZE_REV0,
+					 &tbl_rev);
+	if (!IS_ERR(wifi_pkg)) {
+		if (tbl_rev != 0) {
+			ret = PTR_ERR(wifi_pkg);
+			goto out_free;
+		}
+
+		num_chains = ACPI_SAR_NUM_CHAINS_REV0;
+		num_sub_bands = ACPI_SAR_NUM_SUB_BANDS_REV0;
+
+		goto read_table;
 	}
 
+	ret = PTR_ERR(wifi_pkg);
+	goto out_free;
+
+read_table:
 	if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) {
 		ret = -EINVAL;
 		goto out_free;
 	}
 
+	IWL_DEBUG_RADIO(fwrt, "Reading WRDS tbl_rev=%d\n", tbl_rev);
+
 	enabled = !!(wifi_pkg->package.elements[1].integer.value);
 
 	/* position of the actual table */
@@ -531,7 +588,8 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt)
 	/* The profile from WRDS is officially profile 1, but goes
 	 * into sar_profiles[0] (because we don't have a profile 0).
 	 */
-	ret = iwl_sar_set_profile(table, &fwrt->sar_profiles[0], enabled);
+	ret = iwl_sar_set_profile(table, &fwrt->sar_profiles[0], enabled,
+				  num_chains, num_sub_bands);
 out_free:
 	kfree(data);
 	return ret;
@@ -544,23 +602,64 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
 	bool enabled;
 	int i, n_profiles, tbl_rev, pos;
 	int ret = 0;
+	u8 num_chains, num_sub_bands;
 
 	data = iwl_acpi_get_object(fwrt->dev, ACPI_EWRD_METHOD);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
+	/* start by trying to read revision 2 */
 	wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data,
-					 ACPI_EWRD_WIFI_DATA_SIZE, &tbl_rev);
-	if (IS_ERR(wifi_pkg)) {
-		ret = PTR_ERR(wifi_pkg);
-		goto out_free;
+					 ACPI_EWRD_WIFI_DATA_SIZE_REV2,
+					 &tbl_rev);
+	if (!IS_ERR(wifi_pkg)) {
+		if (tbl_rev != 2) {
+			ret = PTR_ERR(wifi_pkg);
+			goto out_free;
+		}
+
+		num_chains = ACPI_SAR_NUM_CHAINS_REV2;
+		num_sub_bands = ACPI_SAR_NUM_SUB_BANDS_REV2;
+
+		goto read_table;
 	}
 
-	if (tbl_rev != 0) {
-		ret = -EINVAL;
-		goto out_free;
+	/* then try revision 1 */
+	wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data,
+					 ACPI_EWRD_WIFI_DATA_SIZE_REV1,
+					 &tbl_rev);
+	if (!IS_ERR(wifi_pkg)) {
+		if (tbl_rev != 1) {
+			ret = PTR_ERR(wifi_pkg);
+			goto out_free;
+		}
+
+		num_chains = ACPI_SAR_NUM_CHAINS_REV1;
+		num_sub_bands = ACPI_SAR_NUM_SUB_BANDS_REV1;
+
+		goto read_table;
+	}
+
+	/* then finally revision 0 */
+	wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data,
+					 ACPI_EWRD_WIFI_DATA_SIZE_REV0,
+					 &tbl_rev);
+	if (!IS_ERR(wifi_pkg)) {
+		if (tbl_rev != 0) {
+			ret = PTR_ERR(wifi_pkg);
+			goto out_free;
+		}
+
+		num_chains = ACPI_SAR_NUM_CHAINS_REV0;
+		num_sub_bands = ACPI_SAR_NUM_SUB_BANDS_REV0;
+
+		goto read_table;
 	}
 
+	ret = PTR_ERR(wifi_pkg);
+	goto out_free;
+
+read_table:
 	if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER ||
 	    wifi_pkg->package.elements[2].type != ACPI_TYPE_INTEGER) {
 		ret = -EINVAL;
@@ -589,13 +688,13 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
 		 * have profile 0).  So in the array we start from 1.
 		 */
 		ret = iwl_sar_set_profile(&wifi_pkg->package.elements[pos],
-					  &fwrt->sar_profiles[i + 1],
-					  enabled);
+					  &fwrt->sar_profiles[i + 1], enabled,
+					  num_chains, num_sub_bands);
 		if (ret < 0)
 			break;
 
 		/* go to the next table */
-		pos += ACPI_SAR_TABLE_SIZE;
+		pos += num_chains * num_sub_bands;
 	}
 
 out_free:
@@ -607,41 +706,93 @@ IWL_EXPORT_SYMBOL(iwl_sar_get_ewrd_table);
 int iwl_sar_get_wgds_table(struct iwl_fw_runtime *fwrt)
 {
 	union acpi_object *wifi_pkg, *data;
-	int i, j, ret, tbl_rev;
-	int idx = 1;
+	int i, j, k, ret, tbl_rev;
+	int idx = 1; /* start from one to skip the domain */
+	u8 num_bands;
 
 	data = iwl_acpi_get_object(fwrt->dev, ACPI_WGDS_METHOD);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
+	/* start by trying to read revision 2 */
 	wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data,
-					 ACPI_WGDS_WIFI_DATA_SIZE, &tbl_rev);
+					 ACPI_WGDS_WIFI_DATA_SIZE_REV2,
+					 &tbl_rev);
+	if (!IS_ERR(wifi_pkg)) {
+		if (tbl_rev != 2) {
+			ret = PTR_ERR(wifi_pkg);
+			goto out_free;
+		}
 
-	if (IS_ERR(wifi_pkg)) {
-		ret = PTR_ERR(wifi_pkg);
-		goto out_free;
+		num_bands = ACPI_GEO_NUM_BANDS_REV2;
+
+		goto read_table;
 	}
 
-	if (tbl_rev > 1) {
-		ret = -EINVAL;
-		goto out_free;
+	/* then try revision 0 (which is the same as 1) */
+	wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data,
+					 ACPI_WGDS_WIFI_DATA_SIZE_REV0,
+					 &tbl_rev);
+	if (!IS_ERR(wifi_pkg)) {
+		if (tbl_rev != 0 && tbl_rev != 1) {
+			ret = PTR_ERR(wifi_pkg);
+			goto out_free;
+		}
+
+		num_bands = ACPI_GEO_NUM_BANDS_REV0;
+
+		goto read_table;
 	}
 
+	ret = PTR_ERR(wifi_pkg);
+	goto out_free;
+
+read_table:
 	fwrt->geo_rev = tbl_rev;
 	for (i = 0; i < ACPI_NUM_GEO_PROFILES; i++) {
-		for (j = 0; j < ACPI_GEO_TABLE_SIZE; j++) {
+		for (j = 0; j < ACPI_GEO_NUM_BANDS_REV2; j++) {
 			union acpi_object *entry;
 
-			entry = &wifi_pkg->package.elements[idx++];
-			if (entry->type != ACPI_TYPE_INTEGER ||
-			    entry->integer.value > U8_MAX) {
-				ret = -EINVAL;
-				goto out_free;
+			/*
+			 * num_bands is either 2 or 3, if it's only 2 then
+			 * fill the third band (6 GHz) with the values from
+			 * 5 GHz (second band)
+			 */
+			if (j >= num_bands) {
+				fwrt->geo_profiles[i].bands[j].max =
+					fwrt->geo_profiles[i].bands[1].max;
+			} else {
+				entry = &wifi_pkg->package.elements[idx++];
+				if (entry->type != ACPI_TYPE_INTEGER ||
+				    entry->integer.value > U8_MAX) {
+					ret = -EINVAL;
+					goto out_free;
+				}
+
+				fwrt->geo_profiles[i].bands[j].max =
+					entry->integer.value;
 			}
 
-			fwrt->geo_profiles[i].values[j] = entry->integer.value;
+			for (k = 0; k < ACPI_GEO_NUM_CHAINS; k++) {
+				/* same here as above */
+				if (j >= num_bands) {
+					fwrt->geo_profiles[i].bands[j].chains[k] =
+						fwrt->geo_profiles[i].bands[1].chains[k];
+				} else {
+					entry = &wifi_pkg->package.elements[idx++];
+					if (entry->type != ACPI_TYPE_INTEGER ||
+					    entry->integer.value > U8_MAX) {
+						ret = -EINVAL;
+						goto out_free;
+					}
+
+					fwrt->geo_profiles[i].bands[j].chains[k] =
+						entry->integer.value;
+				}
+			}
 		}
 	}
+
 	ret = 0;
 out_free:
 	kfree(data);
@@ -673,43 +824,26 @@ IWL_EXPORT_SYMBOL(iwl_sar_geo_support);
 int iwl_sar_geo_init(struct iwl_fw_runtime *fwrt,
 		     struct iwl_per_chain_offset *table, u32 n_bands)
 {
-	int ret, i, j;
+	int i, j;
 
 	if (!iwl_sar_geo_support(fwrt))
 		return -EOPNOTSUPP;
 
-	ret = iwl_sar_get_wgds_table(fwrt);
-	if (ret < 0) {
-		IWL_DEBUG_RADIO(fwrt,
-				"Geo SAR BIOS table invalid or unavailable. (%d)\n",
-				ret);
-		/* we don't fail if the table is not available */
-		return -ENOENT;
-	}
-
 	for (i = 0; i < ACPI_NUM_GEO_PROFILES; i++) {
 		for (j = 0; j < n_bands; j++) {
 			struct iwl_per_chain_offset *chain =
 				&table[i * n_bands + j];
-			u8 *value;
-
-			if (j * ACPI_GEO_PER_CHAIN_SIZE >=
-			    ARRAY_SIZE(fwrt->geo_profiles[0].values))
-				/*
-				 * Currently we only store lb an hb values, and
-				 * don't have any special ones for uhb. So leave
-				 * those empty for the time being
-				 */
-				break;
-
-			value = &fwrt->geo_profiles[i].values[j *
-				ACPI_GEO_PER_CHAIN_SIZE];
-			chain->max_tx_power = cpu_to_le16(value[0]);
-			chain->chain_a = value[1];
-			chain->chain_b = value[2];
+
+			chain->max_tx_power =
+				cpu_to_le16(fwrt->geo_profiles[i].bands[j].max);
+			chain->chain_a = fwrt->geo_profiles[i].bands[j].chains[0];
+			chain->chain_b = fwrt->geo_profiles[i].bands[j].chains[1];
 			IWL_DEBUG_RADIO(fwrt,
 					"SAR geographic profile[%d] Band[%d]: chain A = %d chain B = %d max_tx_power = %d\n",
-					i, j, value[1], value[2], value[0]);
+					i, j,
+					fwrt->geo_profiles[i].bands[j].chains[0],
+					fwrt->geo_profiles[i].bands[j].chains[1],
+					fwrt->geo_profiles[i].bands[j].max);
 		}
 	}
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h
index b858e998999c..16ed0995b51e 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h
@@ -26,21 +26,46 @@
 
 #define ACPI_WIFI_DOMAIN	(0x07)
 
-#define ACPI_SAR_TABLE_SIZE		10
 #define ACPI_SAR_PROFILE_NUM		4
 
-#define ACPI_GEO_TABLE_SIZE		6
 #define ACPI_NUM_GEO_PROFILES		3
 #define ACPI_GEO_PER_CHAIN_SIZE		3
 
-#define ACPI_SAR_NUM_CHAIN_LIMITS	2
-#define ACPI_SAR_NUM_SUB_BANDS		5
-#define ACPI_SAR_NUM_TABLES		1
+#define ACPI_SAR_NUM_CHAINS_REV0	2
+#define ACPI_SAR_NUM_CHAINS_REV1	2
+#define ACPI_SAR_NUM_CHAINS_REV2	4
+#define ACPI_SAR_NUM_SUB_BANDS_REV0	5
+#define ACPI_SAR_NUM_SUB_BANDS_REV1	11
+#define ACPI_SAR_NUM_SUB_BANDS_REV2	11
+
+#define ACPI_WRDS_WIFI_DATA_SIZE_REV0	(ACPI_SAR_NUM_CHAINS_REV0 * \
+					 ACPI_SAR_NUM_SUB_BANDS_REV0 + 2)
+#define ACPI_WRDS_WIFI_DATA_SIZE_REV1	(ACPI_SAR_NUM_CHAINS_REV1 * \
+					 ACPI_SAR_NUM_SUB_BANDS_REV1 + 2)
+#define ACPI_WRDS_WIFI_DATA_SIZE_REV2	(ACPI_SAR_NUM_CHAINS_REV2 * \
+					 ACPI_SAR_NUM_SUB_BANDS_REV2 + 2)
+#define ACPI_EWRD_WIFI_DATA_SIZE_REV0	((ACPI_SAR_PROFILE_NUM - 1) * \
+					 ACPI_SAR_NUM_CHAINS_REV0 * \
+					 ACPI_SAR_NUM_SUB_BANDS_REV0 + 3)
+#define ACPI_EWRD_WIFI_DATA_SIZE_REV1	((ACPI_SAR_PROFILE_NUM - 1) * \
+					 ACPI_SAR_NUM_CHAINS_REV1 * \
+					 ACPI_SAR_NUM_SUB_BANDS_REV1 + 3)
+#define ACPI_EWRD_WIFI_DATA_SIZE_REV2	((ACPI_SAR_PROFILE_NUM - 1) * \
+					 ACPI_SAR_NUM_CHAINS_REV2 * \
+					 ACPI_SAR_NUM_SUB_BANDS_REV2 + 3)
+
+/* revision 0 and 1 are identical, except for the semantics in the FW */
+#define ACPI_GEO_NUM_BANDS_REV0		2
+#define ACPI_GEO_NUM_BANDS_REV2		3
+#define ACPI_GEO_NUM_CHAINS		2
+
+#define ACPI_WGDS_WIFI_DATA_SIZE_REV0	(ACPI_NUM_GEO_PROFILES *   \
+					 ACPI_GEO_NUM_BANDS_REV0 * \
+					 ACPI_GEO_PER_CHAIN_SIZE + 1)
+#define ACPI_WGDS_WIFI_DATA_SIZE_REV2	(ACPI_NUM_GEO_PROFILES *   \
+					 ACPI_GEO_NUM_BANDS_REV2 * \
+					 ACPI_GEO_PER_CHAIN_SIZE + 1)
 
-#define ACPI_WRDS_WIFI_DATA_SIZE	(ACPI_SAR_TABLE_SIZE + 2)
-#define ACPI_EWRD_WIFI_DATA_SIZE	((ACPI_SAR_PROFILE_NUM - 1) * \
-					 ACPI_SAR_TABLE_SIZE + 3)
-#define ACPI_WGDS_WIFI_DATA_SIZE	19
 #define ACPI_WRDD_WIFI_DATA_SIZE	2
 #define ACPI_SPLC_WIFI_DATA_SIZE	2
 #define ACPI_ECKV_WIFI_DATA_SIZE	2
@@ -51,8 +76,6 @@
 #define APCI_WTAS_BLACK_LIST_MAX	16
 #define ACPI_WTAS_WIFI_DATA_SIZE	(3 + APCI_WTAS_BLACK_LIST_MAX)
 
-#define ACPI_WGDS_TABLE_SIZE		3
-
 #define ACPI_PPAG_WIFI_DATA_SIZE_V1	((IWL_NUM_CHAIN_LIMITS * \
 					  IWL_NUM_SUB_BANDS_V1) + 2)
 #define ACPI_PPAG_WIFI_DATA_SIZE_V2	((IWL_NUM_CHAIN_LIMITS * \
@@ -64,13 +87,28 @@
 #define ACPI_PPAG_MIN_HB -16
 #define ACPI_PPAG_MAX_HB 40
 
+/*
+ * The profile for revision 2 is a superset of revision 1, which is in
+ * turn a superset of revision 0.  So we can store all revisions
+ * inside revision 2, which is what we represent here.
+ */
+struct iwl_sar_profile_chain {
+	u8 subbands[ACPI_SAR_NUM_SUB_BANDS_REV2];
+};
+
 struct iwl_sar_profile {
 	bool enabled;
-	u8 table[ACPI_SAR_TABLE_SIZE];
+	struct iwl_sar_profile_chain chains[ACPI_SAR_NUM_CHAINS_REV2];
+};
+
+/* Same thing as with SAR, all revisions fit in revision 2 */
+struct iwl_geo_profile_band {
+	u8 max;
+	u8 chains[ACPI_GEO_NUM_CHAINS];
 };
 
 struct iwl_geo_profile {
-	u8 values[ACPI_GEO_TABLE_SIZE];
+	struct iwl_geo_profile_band bands[ACPI_GEO_NUM_BANDS_REV2];
 };
 
 enum iwl_dsm_funcs_rev_0 {
@@ -234,7 +272,7 @@ static inline int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
 
 static inline int iwl_sar_get_wgds_table(struct iwl_fw_runtime *fwrt)
 {
-	return -ENOENT;
+	return 1;
 }
 
 static inline bool iwl_sar_geo_support(struct iwl_fw_runtime *fwrt)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h b/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h
index 01580c9175f3..3e81e9369224 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h
@@ -142,7 +142,7 @@ enum iwl_bt_mxbox_dw3 {
 					 "\t%s: %d%s",			    \
 					 #_field,			    \
 					 BT_MBOX_MSG(notif, _num, _field),  \
-					 true ? "\n" : ", ");
+					 true ? "\n" : ", ")
 enum iwl_bt_activity_grading {
 	BT_OFF			= 0,
 	BT_ON_NO_CONNECTION	= 1,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index ce060c3dfd7b..ee6b5844a871 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -550,7 +550,8 @@ enum iwl_legacy_cmds {
 	WOWLAN_CONFIGURATION = 0xe1,
 
 	/**
-	 * @WOWLAN_TSC_RSC_PARAM: &struct iwl_wowlan_rsc_tsc_params_cmd
+	 * @WOWLAN_TSC_RSC_PARAM: &struct iwl_wowlan_rsc_tsc_params_cmd_v4,
+	 *	&struct iwl_wowlan_rsc_tsc_params_cmd
 	 */
 	WOWLAN_TSC_RSC_PARAM = 0xe2,
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h b/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h
index b2e7ef3ddc88..3ec82cae3981 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h
@@ -6,6 +6,7 @@
  */
 #ifndef __iwl_fw_api_d3_h__
 #define __iwl_fw_api_d3_h__
+#include <iwl-trans.h>
 
 /**
  * enum iwl_d0i3_flags - d0i3 flags
@@ -389,11 +390,14 @@ struct iwl_wowlan_config_cmd {
 	u8 reserved;
 } __packed; /* WOWLAN_CONFIG_API_S_VER_5 */
 
+#define IWL_NUM_RSC	16
+#define WOWLAN_KEY_MAX_SIZE	32
+#define WOWLAN_GTK_KEYS_NUM     2
+#define WOWLAN_IGTK_KEYS_NUM	2
+
 /*
  * WOWLAN_TSC_RSC_PARAMS
  */
-#define IWL_NUM_RSC	16
-
 struct tkip_sc {
 	__le16 iv16;
 	__le16 pad;
@@ -425,11 +429,19 @@ struct iwl_wowlan_rsc_tsc_params_cmd_ver_2 {
 	union iwl_all_tsc_rsc all_tsc_rsc;
 } __packed; /* ALL_TSC_RSC_API_S_VER_2 */
 
-struct iwl_wowlan_rsc_tsc_params_cmd {
+struct iwl_wowlan_rsc_tsc_params_cmd_v4 {
 	struct iwl_wowlan_rsc_tsc_params_cmd_ver_2 params;
 	__le32 sta_id;
 } __packed; /* ALL_TSC_RSC_API_S_VER_4 */
 
+struct iwl_wowlan_rsc_tsc_params_cmd {
+	__le64 ucast_rsc[IWL_MAX_TID_COUNT];
+	__le64 mcast_rsc[WOWLAN_GTK_KEYS_NUM][IWL_MAX_TID_COUNT];
+	__le32 sta_id;
+#define IWL_MCAST_KEY_MAP_INVALID	0xff
+	u8 mcast_key_id_map[4];
+} __packed; /* ALL_TSC_RSC_API_S_VER_5 */
+
 #define IWL_MIC_KEY_SIZE	8
 struct iwl_mic_keys {
 	u8 tx[IWL_MIC_KEY_SIZE];
@@ -541,10 +553,6 @@ struct iwl_wowlan_gtk_status_v1 {
 	struct iwl_wowlan_rsc_tsc_params_cmd_ver_2 rsc;
 } __packed; /* WOWLAN_GTK_MATERIAL_VER_1 */
 
-#define WOWLAN_KEY_MAX_SIZE	32
-#define WOWLAN_GTK_KEYS_NUM     2
-#define WOWLAN_IGTK_KEYS_NUM	2
-
 /**
  * struct iwl_wowlan_gtk_status - GTK status
  * @key: GTK material
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
index 5a2d9a1f7e73..d8b5870d6e9a 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
@@ -33,12 +33,11 @@ struct iwl_fw_ini_hcmd {
  *
  * @version: TLV version
  * @domain: domain of the TLV. One of &enum iwl_fw_ini_dbg_domain
- * @data: TLV data
  */
 struct iwl_fw_ini_header {
 	__le32 version;
 	__le32 domain;
-	u8 data[];
+	/* followed by the data */
 } __packed; /* FW_TLV_DEBUG_HEADER_S_VER_1 */
 
 /**
@@ -130,6 +129,7 @@ struct iwl_fw_ini_region_internal_buffer {
  *	&IWL_FW_INI_REGION_PERIPHERY_PHY, &IWL_FW_INI_REGION_PERIPHERY_AUX,
  *	&IWL_FW_INI_REGION_PAGING, &IWL_FW_INI_REGION_CSR,
  *	&IWL_FW_INI_REGION_DRAM_IMR and &IWL_FW_INI_REGION_PCI_IOSF_CONFIG
+ *	&IWL_FW_INI_REGION_DBGI_SRAM, &FW_TLV_DEBUG_REGION_TYPE_DBGI_SRAM,
  * @fifos: fifos configuration. Used by &IWL_FW_INI_REGION_TXF and
  *	&IWL_FW_INI_REGION_RXF
  * @err_table: error table configuration. Used by
@@ -249,7 +249,6 @@ struct iwl_fw_ini_hcmd_tlv {
  * @IWL_FW_INI_ALLOCATION_ID_DBGC1: allocation meant for DBGC1 configuration
  * @IWL_FW_INI_ALLOCATION_ID_DBGC2: allocation meant for DBGC2 configuration
  * @IWL_FW_INI_ALLOCATION_ID_DBGC3: allocation meant for DBGC3 configuration
- * @IWL_FW_INI_ALLOCATION_ID_INTERNAL: allocation meant for Intreanl SMEM in D3
  * @IWL_FW_INI_ALLOCATION_NUM: number of allocation ids
 */
 enum iwl_fw_ini_allocation_id {
@@ -257,7 +256,6 @@ enum iwl_fw_ini_allocation_id {
 	IWL_FW_INI_ALLOCATION_ID_DBGC1,
 	IWL_FW_INI_ALLOCATION_ID_DBGC2,
 	IWL_FW_INI_ALLOCATION_ID_DBGC3,
-	IWL_FW_INI_ALLOCATION_ID_INTERNAL,
 	IWL_FW_INI_ALLOCATION_NUM,
 }; /* FW_DEBUG_TLV_ALLOCATION_ID_E_VER_1 */
 
@@ -298,6 +296,7 @@ enum iwl_fw_ini_buffer_location {
  * @IWL_FW_INI_REGION_DRAM_IMR: IMR memory
  * @IWL_FW_INI_REGION_PCI_IOSF_CONFIG: PCI/IOSF config
  * @IWL_FW_INI_REGION_SPECIAL_DEVICE_MEMORY: special device memory
+ * @IWL_FW_INI_REGION_DBGI_SRAM: periphery registers of DBGI SRAM
  * @IWL_FW_INI_REGION_NUM: number of region types
  */
 enum iwl_fw_ini_region_type {
@@ -319,6 +318,7 @@ enum iwl_fw_ini_region_type {
 	IWL_FW_INI_REGION_DRAM_IMR,
 	IWL_FW_INI_REGION_PCI_IOSF_CONFIG,
 	IWL_FW_INI_REGION_SPECIAL_DEVICE_MEMORY,
+	IWL_FW_INI_REGION_DBGI_SRAM,
 	IWL_FW_INI_REGION_NUM
 }; /* FW_TLV_DEBUG_REGION_TYPE_API_E */
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
index 0e38eb1cd75d..6bbb8b8c91cd 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
  */
 #ifndef __iwl_fw_api_location_h__
 #define __iwl_fw_api_location_h__
@@ -151,6 +151,10 @@ enum iwl_tof_mcsi_enable {
  *	is valid
  * @IWL_TOF_RESPONDER_CMD_VALID_NDP_PARAMS: NDP parameters are valid
  * @IWL_TOF_RESPONDER_CMD_VALID_LMR_FEEDBACK: LMR feedback support is valid
+ * @IWL_TOF_RESPONDER_CMD_VALID_SESSION_ID: session id flag is valid
+ * @IWL_TOF_RESPONDER_CMD_VALID_BSS_COLOR: the bss_color field is valid
+ * @IWL_TOF_RESPONDER_CMD_VALID_MIN_MAX_TIME_BETWEEN_MSR: the
+ *	min_time_between_msr and max_time_between_msr fields are valid
  */
 enum iwl_tof_responder_cmd_valid_field {
 	IWL_TOF_RESPONDER_CMD_VALID_CHAN_INFO = BIT(0),
@@ -169,6 +173,9 @@ enum iwl_tof_responder_cmd_valid_field {
 	IWL_TOF_RESPONDER_CMD_VALID_NDP_SUPPORT = BIT(22),
 	IWL_TOF_RESPONDER_CMD_VALID_NDP_PARAMS = BIT(23),
 	IWL_TOF_RESPONDER_CMD_VALID_LMR_FEEDBACK = BIT(24),
+	IWL_TOF_RESPONDER_CMD_VALID_SESSION_ID = BIT(25),
+	IWL_TOF_RESPONDER_CMD_VALID_BSS_COLOR = BIT(26),
+	IWL_TOF_RESPONDER_CMD_VALID_MIN_MAX_TIME_BETWEEN_MSR = BIT(27),
 };
 
 /**
@@ -186,6 +193,8 @@ enum iwl_tof_responder_cmd_valid_field {
  * @IWL_TOF_RESPONDER_FLAGS_NDP_SUPPORT: support NDP ranging
  * @IWL_TOF_RESPONDER_FLAGS_LMR_FEEDBACK: request for LMR feedback if the
  *	initiator supports it
+ * @IWL_TOF_RESPONDER_FLAGS_SESSION_ID: send the session id in the initial FTM
+ *	frame.
  */
 enum iwl_tof_responder_cfg_flags {
 	IWL_TOF_RESPONDER_FLAGS_NON_ASAP_SUPPORT = BIT(0),
@@ -200,6 +209,7 @@ enum iwl_tof_responder_cfg_flags {
 	IWL_TOF_RESPONDER_FLAGS_FTM_TX_ANT = RATE_MCS_ANT_ABC_MSK,
 	IWL_TOF_RESPONDER_FLAGS_NDP_SUPPORT = BIT(24),
 	IWL_TOF_RESPONDER_FLAGS_LMR_FEEDBACK = BIT(25),
+	IWL_TOF_RESPONDER_FLAGS_SESSION_ID = BIT(27),
 };
 
 /**
@@ -297,13 +307,13 @@ struct iwl_tof_responder_config_cmd_v7 {
  * @r2i_ndp_params: parameters for R2I NDP.
  *	bits 0 - 2: max number of LTF repetitions
  *	bits 3 - 5: max number of spatial streams (supported values are < 2)
- *	bits 6 - 7: max number of total LTFs
- *		    (&enum ieee80211_range_params_max_total_ltf)
+ *	bits 6 - 7: max number of total LTFs see
+ *	&enum ieee80211_range_params_max_total_ltf
  * @i2r_ndp_params: parameters for I2R NDP.
  *	bits 0 - 2: max number of LTF repetitions
  *	bits 3 - 5: max number of spatial streams
- *	bits 6 - 7: max number of total LTFs
- *		    (&enum ieee80211_range_params_max_total_ltf)
+ *	bits 6 - 7: max number of total LTFs see
+ *	&enum ieee80211_range_params_max_total_ltf
  */
 struct iwl_tof_responder_config_cmd_v8 {
 	__le32 cmd_valid_fields;
@@ -322,6 +332,58 @@ struct iwl_tof_responder_config_cmd_v8 {
 	u8 i2r_ndp_params;
 } __packed; /* TOF_RESPONDER_CONFIG_CMD_API_S_VER_8 */
 
+/**
+ * struct iwl_tof_responder_config_cmd_v9 - ToF AP mode (for debug)
+ * @cmd_valid_fields: &iwl_tof_responder_cmd_valid_field
+ * @responder_cfg_flags: &iwl_tof_responder_cfg_flags
+ * @format_bw: bits 0 - 3: &enum iwl_location_frame_format.
+ *             bits 4 - 7: &enum iwl_location_bw.
+ * @bss_color: current AP bss_color
+ * @channel_num: current AP Channel
+ * @ctrl_ch_position: coding of the control channel position relative to
+ *	the center frequency, see iwl_mvm_get_ctrl_pos()
+ * @sta_id: index of the AP STA when in AP mode
+ * @reserved1: reserved
+ * @toa_offset: Artificial addition [pSec] for the ToA - to be used for debug
+ *	purposes, simulating station movement by adding various values
+ *	to this field
+ * @common_calib: XVT: common calibration value
+ * @specific_calib: XVT: specific calibration value
+ * @bssid: Current AP BSSID
+ * @r2i_ndp_params: parameters for R2I NDP.
+ *	bits 0 - 2: max number of LTF repetitions
+ *	bits 3 - 5: max number of spatial streams (supported values are < 2)
+ *	bits 6 - 7: max number of total LTFs see
+ *	&enum ieee80211_range_params_max_total_ltf
+ * @i2r_ndp_params: parameters for I2R NDP.
+ *	bits 0 - 2: max number of LTF repetitions
+ *	bits 3 - 5: max number of spatial streams
+ *	bits 6 - 7: max number of total LTFs see
+ *	&enum ieee80211_range_params_max_total_ltf
+ * @min_time_between_msr: for non trigger based NDP ranging, minimum time
+ *	between measurements in milliseconds.
+ * @max_time_between_msr: for non trigger based NDP ranging, maximum time
+ *	between measurements in milliseconds.
+ */
+struct iwl_tof_responder_config_cmd_v9 {
+	__le32 cmd_valid_fields;
+	__le32 responder_cfg_flags;
+	u8 format_bw;
+	u8 bss_color;
+	u8 channel_num;
+	u8 ctrl_ch_position;
+	u8 sta_id;
+	u8 reserved1;
+	__le16 toa_offset;
+	__le16 common_calib;
+	__le16 specific_calib;
+	u8 bssid[ETH_ALEN];
+	u8 r2i_ndp_params;
+	u8 i2r_ndp_params;
+	__le16 min_time_between_msr;
+	__le16 max_time_between_msr;
+} __packed; /* TOF_RESPONDER_CONFIG_CMD_API_S_VER_8 */
+
 #define IWL_LCI_CIVIC_IE_MAX_SIZE	400
 
 /**
@@ -489,6 +551,10 @@ struct iwl_tof_range_req_ap_entry_v2 {
  *      instead of fw internal values.
  * @IWL_INITIATOR_AP_FLAGS_PMF: request to protect the negotiation and LMR
  *      frames with protected management frames.
+ * @IWL_INITIATOR_AP_FLAGS_TERMINATE_ON_LMR_FEEDBACK: terminate the session if
+ *	the responder asked for LMR feedback although the initiator did not set
+ *	the LMR feedback bit in the FTM request. If not set, the initiator will
+ *	continue with the session and will provide the LMR feedback.
  */
 enum iwl_initiator_ap_flags {
 	IWL_INITIATOR_AP_FLAGS_ASAP = BIT(1),
@@ -504,6 +570,7 @@ enum iwl_initiator_ap_flags {
 	IWL_INITIATOR_AP_FLAGS_LMR_FEEDBACK = BIT(12),
 	IWL_INITIATOR_AP_FLAGS_USE_CALIB = BIT(13),
 	IWL_INITIATOR_AP_FLAGS_PMF = BIT(14),
+	IWL_INITIATOR_AP_FLAGS_TERMINATE_ON_LMR_FEEDBACK = BIT(15),
 };
 
 /**
@@ -795,6 +862,90 @@ struct iwl_tof_range_req_ap_entry_v8 {
 } __packed; /* LOCATION_RANGE_REQ_AP_ENTRY_CMD_API_S_VER_8 */
 
 /**
+ * struct iwl_tof_range_req_ap_entry_v9 - AP configuration parameters
+ * @initiator_ap_flags: see &enum iwl_initiator_ap_flags.
+ * @channel_num: AP Channel number
+ * @format_bw: bits 0 - 3: &enum iwl_location_frame_format.
+ *             bits 4 - 7: &enum iwl_location_bw.
+ * @ctrl_ch_position: Coding of the control channel position relative to the
+ *	center frequency, see iwl_mvm_get_ctrl_pos().
+ * @ftmr_max_retries: Max number of retries to send the FTMR in case of no
+ *	reply from the AP.
+ * @bssid: AP's BSSID
+ * @burst_period: For EDCA based ranging: Recommended value to be sent to the
+ *	AP. Measurement periodicity In units of 100ms. ignored if
+ *	num_of_bursts_exp = 0.
+ *	For non trigger based NDP ranging, the maximum time between
+ *	measurements in units of milliseconds.
+ * @samples_per_burst: the number of FTMs pairs in single Burst (1-31);
+ * @num_of_bursts: Recommended value to be sent to the AP. 2s Exponent of
+ *	the number of measurement iterations (min 2^0 = 1, max 2^14)
+ * @sta_id: the station id of the AP. Only relevant when associated to the AP,
+ *	otherwise should be set to &IWL_MVM_INVALID_STA.
+ * @cipher: pairwise cipher suite for secured measurement.
+ *          &enum iwl_location_cipher.
+ * @hltk: HLTK to be used for secured 11az measurement
+ * @tk: TK to be used for secured 11az measurement
+ * @calib: An array of calibration values per FTM rx bandwidth.
+ *         If &IWL_INITIATOR_AP_FLAGS_USE_CALIB is set, the fw will use the
+ *         calibration value that corresponds to the rx bandwidth of the FTM
+ *         frame.
+ * @beacon_interval: beacon interval of the AP in TUs. Only required if
+ *	&IWL_INITIATOR_AP_FLAGS_TB is set.
+ * @bss_color: the BSS color of the responder. Only valid if
+ *	&IWL_INITIATOR_AP_FLAGS_TB or &IWL_INITIATOR_AP_FLAGS_NON_TB is set.
+ * @rx_pn: the next expected PN for protected management frames Rx. LE byte
+ *	order. Only valid if &IWL_INITIATOR_AP_FLAGS_SECURED is set and sta_id
+ *	is set to &IWL_MVM_INVALID_STA.
+ * @tx_pn: the next PN to use for protected management frames Tx. LE byte
+ *	order. Only valid if &IWL_INITIATOR_AP_FLAGS_SECURED is set and sta_id
+ *	is set to &IWL_MVM_INVALID_STA.
+ * @r2i_ndp_params: parameters for R2I NDP ranging negotiation.
+ *      bits 0 - 2: max LTF repetitions
+ *      bits 3 - 5: max number of spatial streams
+ *      bits 6 - 7: reserved
+ * @i2r_ndp_params: parameters for I2R NDP ranging negotiation.
+ *      bits 0 - 2: max LTF repetitions
+ *      bits 3 - 5: max number of spatial streams (supported values are < 2)
+ *      bits 6 - 7: reserved
+ * @r2i_max_total_ltf: R2I Max Total LTFs for NDP ranging negotiation.
+ *      One of &enum ieee80211_range_params_max_total_ltf.
+ * @i2r_max_total_ltf: I2R Max Total LTFs for NDP ranging negotiation.
+ *      One of &enum ieee80211_range_params_max_total_ltf.
+ * @bss_color: the BSS color of the responder. Only valid if
+ *	&IWL_INITIATOR_AP_FLAGS_NON_TB or &IWL_INITIATOR_AP_FLAGS_TB is set.
+ * @band: 0 for 5.2 GHz, 1 for 2.4 GHz, 2 for 6GHz
+ * @min_time_between_msr: For non trigger based NDP ranging, the minimum time
+ *	between measurements in units of milliseconds
+ */
+struct iwl_tof_range_req_ap_entry_v9 {
+	__le32 initiator_ap_flags;
+	u8 channel_num;
+	u8 format_bw;
+	u8 ctrl_ch_position;
+	u8 ftmr_max_retries;
+	u8 bssid[ETH_ALEN];
+	__le16 burst_period;
+	u8 samples_per_burst;
+	u8 num_of_bursts;
+	u8 sta_id;
+	u8 cipher;
+	u8 hltk[HLTK_11AZ_LEN];
+	u8 tk[TK_11AZ_LEN];
+	__le16 calib[IWL_TOF_BW_NUM];
+	u16 beacon_interval;
+	u8 rx_pn[IEEE80211_CCMP_PN_LEN];
+	u8 tx_pn[IEEE80211_CCMP_PN_LEN];
+	u8 r2i_ndp_params;
+	u8 i2r_ndp_params;
+	u8 r2i_max_total_ltf;
+	u8 i2r_max_total_ltf;
+	u8 bss_color;
+	u8 band;
+	__le16 min_time_between_msr;
+} __packed; /* LOCATION_RANGE_REQ_AP_ENTRY_CMD_API_S_VER_9 */
+
+/**
  * enum iwl_tof_response_mode
  * @IWL_MVM_TOF_RESPONSE_ASAP: report each AP measurement separately as soon as
  *			       possible (not supported for this release)
@@ -1043,6 +1194,34 @@ struct iwl_tof_range_req_cmd_v12 {
 	struct iwl_tof_range_req_ap_entry_v8 ap[IWL_MVM_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_12 */
 
+/**
+ * struct iwl_tof_range_req_cmd_v13 - start measurement cmd
+ * @initiator_flags: see flags @ iwl_tof_initiator_flags
+ * @request_id: A Token incremented per request. The same Token will be
+ *		sent back in the range response
+ * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS)
+ * @range_req_bssid: ranging request BSSID
+ * @macaddr_mask: Bits set to 0 shall be copied from the MAC address template.
+ *		  Bits set to 1 shall be randomized by the UMAC
+ * @macaddr_template: MAC address template to use for non-randomized bits
+ * @req_timeout_ms: Requested timeout of the response in units of milliseconds.
+ *	This is the session time for completing the measurement.
+ * @tsf_mac_id: report the measurement start time for each ap in terms of the
+ *	TSF of this mac id. 0xff to disable TSF reporting.
+ * @ap: per-AP request data, see &struct iwl_tof_range_req_ap_entry_v9.
+ */
+struct iwl_tof_range_req_cmd_v13 {
+	__le32 initiator_flags;
+	u8 request_id;
+	u8 num_of_ap;
+	u8 range_req_bssid[ETH_ALEN];
+	u8 macaddr_mask[ETH_ALEN];
+	u8 macaddr_template[ETH_ALEN];
+	__le32 req_timeout_ms;
+	__le32 tsf_mac_id;
+	struct iwl_tof_range_req_ap_entry_v9 ap[IWL_MVM_TOF_MAX_APS];
+} __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_13 */
+
 /*
  * enum iwl_tof_range_request_status - status of the sent request
  * @IWL_TOF_RANGE_REQUEST_STATUS_SUCCESSFUL - FW successfully received the
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
index 93084bbad534..7be7715b431d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2020 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2021 Intel Corporation
  * Copyright (C) 2017 Intel Deutschland GmbH
  */
 #ifndef __iwl_fw_api_mac_h__
@@ -137,12 +137,14 @@ struct iwl_mac_data_ibss {
  *	early termination detection.
  * @FLEXIBLE_TWT_SUPPORTED: AP supports flexible TWT schedule
  * @PROTECTED_TWT_SUPPORTED: AP supports protected TWT frames (with 11w)
+ * @BROADCAST_TWT_SUPPORTED: AP and STA support broadcast TWT
  */
 enum iwl_mac_data_policy {
 	TWT_SUPPORTED = BIT(0),
 	MORE_DATA_ACK_SUPPORTED = BIT(1),
 	FLEXIBLE_TWT_SUPPORTED = BIT(2),
 	PROTECTED_TWT_SUPPORTED = BIT(3),
+	BROADCAST_TWT_SUPPORTED = BIT(4),
 };
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/offload.h b/drivers/net/wireless/intel/iwlwifi/fw/api/offload.h
index f06214d418aa..5204aa94e72a 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/offload.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/offload.h
@@ -3,6 +3,7 @@
  * Copyright (C) 2012-2014 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
+ * Copyright (C) 2021 Intel Corporation
  */
 #ifndef __iwl_fw_api_offload_h__
 #define __iwl_fw_api_offload_h__
@@ -20,7 +21,7 @@ enum iwl_prot_offload_subcmd_ids {
 #define MAX_STORED_BEACON_SIZE 600
 
 /**
- * struct iwl_stored_beacon_notif - Stored beacon notification
+ * struct iwl_stored_beacon_notif_common - Stored beacon notif common fields
  *
  * @system_time: system time on air rise
  * @tsf: TSF on air rise
@@ -29,9 +30,8 @@ enum iwl_prot_offload_subcmd_ids {
  * @channel: channel this beacon was received on
  * @rates: rate in ucode internal format
  * @byte_count: frame's byte count
- * @data: beacon data, length in @byte_count
  */
-struct iwl_stored_beacon_notif {
+struct iwl_stored_beacon_notif_common {
 	__le32 system_time;
 	__le64 tsf;
 	__le32 beacon_timestamp;
@@ -39,7 +39,32 @@ struct iwl_stored_beacon_notif {
 	__le16 channel;
 	__le32 rates;
 	__le32 byte_count;
+} __packed;
+
+/**
+ * struct iwl_stored_beacon_notif - Stored beacon notification
+ *
+ * @common: fields common for all versions
+ * @data: beacon data, length in @byte_count
+ */
+struct iwl_stored_beacon_notif_v2 {
+	struct iwl_stored_beacon_notif_common common;
 	u8 data[MAX_STORED_BEACON_SIZE];
 } __packed; /* WOWLAN_STROED_BEACON_INFO_S_VER_2 */
 
+/**
+ * struct iwl_stored_beacon_notif_v3 - Stored beacon notification
+ *
+ * @common: fields common for all versions
+ * @sta_id: station for which the beacon was received
+ * @reserved: reserved for alignment
+ * @data: beacon data, length in @byte_count
+ */
+struct iwl_stored_beacon_notif_v3 {
+	struct iwl_stored_beacon_notif_common common;
+	u8 sta_id;
+	u8 reserved[3];
+	u8 data[MAX_STORED_BEACON_SIZE];
+} __packed; /* WOWLAN_STROED_BEACON_INFO_S_VER_3 */
+
 #endif /* __iwl_fw_api_offload_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
index b2605aefc290..8b200379f7c2 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2020 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2021 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -874,7 +874,7 @@ struct iwl_scan_probe_params_v3 {
 	u8 reserved;
 	struct iwl_ssid_ie direct_scan[PROBE_OPTION_MAX];
 	__le32 short_ssid[SCAN_SHORT_SSID_MAX_SIZE];
-	u8 bssid_array[ETH_ALEN][SCAN_BSSID_MAX_SIZE];
+	u8 bssid_array[SCAN_BSSID_MAX_SIZE][ETH_ALEN];
 } __packed; /* SCAN_PROBE_PARAMS_API_S_VER_3 */
 
 /**
@@ -894,7 +894,7 @@ struct iwl_scan_probe_params_v4 {
 	__le16 reserved;
 	struct iwl_ssid_ie direct_scan[PROBE_OPTION_MAX];
 	__le32 short_ssid[SCAN_SHORT_SSID_MAX_SIZE];
-	u8 bssid_array[ETH_ALEN][SCAN_BSSID_MAX_SIZE];
+	u8 bssid_array[SCAN_BSSID_MAX_SIZE][ETH_ALEN];
 } __packed; /* SCAN_PROBE_PARAMS_API_S_VER_4 */
 
 #define SCAN_MAX_NUM_CHANS_V3 67
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h
index 12b2f2c48387..f1a3e14880e7 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2020 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2021 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -384,13 +384,17 @@ struct iwl_mvm_add_sta_key_cmd_v1 {
  * @rx_mic_key: TKIP RX unicast or multicast key
  * @tx_mic_key: TKIP TX key
  * @transmit_seq_cnt: TSC, transmit packet number
+ *
+ * Note: This is used for both v2 and v3, the difference being
+ * in the way the common.rx_secur_seq_cnt is used, in v2 that's
+ * the strange hole format, in v3 it's just a u64.
  */
 struct iwl_mvm_add_sta_key_cmd {
 	struct iwl_mvm_add_sta_key_common common;
 	__le64 rx_mic_key;
 	__le64 tx_mic_key;
 	__le64 transmit_seq_cnt;
-} __packed; /* ADD_MODIFY_STA_KEY_API_S_VER_2 */
+} __packed; /* ADD_MODIFY_STA_KEY_API_S_VER_2, ADD_MODIFY_STA_KEY_API_S_VER_3 */
 
 /**
  * enum iwl_mvm_add_sta_rsp_status - status in the response to ADD_STA command
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index df7c55e06f54..6dcafd0a3d4b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1517,6 +1517,37 @@ iwl_dump_ini_special_mem_iter(struct iwl_fw_runtime *fwrt,
 	return sizeof(*range) + le32_to_cpu(range->range_data_size);
 }
 
+static int
+iwl_dump_ini_dbgi_sram_iter(struct iwl_fw_runtime *fwrt,
+			    struct iwl_dump_ini_region_data *reg_data,
+			    void *range_ptr, int idx)
+{
+	struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data;
+	struct iwl_fw_ini_error_dump_range *range = range_ptr;
+	__le32 *val = range->data;
+	u32 prph_data;
+	int i;
+
+	if (!iwl_trans_grab_nic_access(fwrt->trans))
+		return -EBUSY;
+
+	range->range_data_size = reg->dev_addr.size;
+	iwl_write_prph_no_grab(fwrt->trans, DBGI_SRAM_TARGET_ACCESS_CFG,
+			       DBGI_SRAM_TARGET_ACCESS_CFG_RESET_ADDRESS_MSK);
+	for (i = 0; i < (le32_to_cpu(reg->dev_addr.size) / 4); i++) {
+		prph_data = iwl_read_prph(fwrt->trans, (i % 2) ?
+					  DBGI_SRAM_TARGET_ACCESS_RDATA_MSB :
+					  DBGI_SRAM_TARGET_ACCESS_RDATA_LSB);
+		if (prph_data == 0x5a5a5a5a) {
+			iwl_trans_release_nic_access(fwrt->trans);
+			return -EBUSY;
+		}
+		*val++ = cpu_to_le32(prph_data);
+	}
+	iwl_trans_release_nic_access(fwrt->trans);
+	return sizeof(*range) + le32_to_cpu(range->range_data_size);
+}
+
 static int iwl_dump_ini_fw_pkt_iter(struct iwl_fw_runtime *fwrt,
 				    struct iwl_dump_ini_region_data *reg_data,
 				    void *range_ptr, int idx)
@@ -1547,7 +1578,7 @@ iwl_dump_ini_mem_fill_header(struct iwl_fw_runtime *fwrt,
 
 	dump->header.version = cpu_to_le32(IWL_INI_DUMP_VER);
 
-	return dump->ranges;
+	return dump->data;
 }
 
 /**
@@ -1611,7 +1642,7 @@ iwl_dump_ini_mon_fill_header(struct iwl_fw_runtime *fwrt,
 
 	data->header.version = cpu_to_le32(IWL_INI_DUMP_VER);
 
-	return data->ranges;
+	return data->data;
 }
 
 static void *
@@ -1647,7 +1678,7 @@ iwl_dump_ini_err_table_fill_header(struct iwl_fw_runtime *fwrt,
 	dump->header.version = cpu_to_le32(IWL_INI_DUMP_VER);
 	dump->version = reg->err_table.version;
 
-	return dump->ranges;
+	return dump->data;
 }
 
 static void *
@@ -1662,7 +1693,7 @@ iwl_dump_ini_special_mem_fill_header(struct iwl_fw_runtime *fwrt,
 	dump->type = reg->special_mem.type;
 	dump->version = reg->special_mem.version;
 
-	return dump->ranges;
+	return dump->data;
 }
 
 static u32 iwl_dump_ini_mem_ranges(struct iwl_fw_runtime *fwrt,
@@ -2189,6 +2220,12 @@ static const struct iwl_dump_ini_mem_ops iwl_dump_ini_region_ops[] = {
 		.fill_mem_hdr = iwl_dump_ini_special_mem_fill_header,
 		.fill_range = iwl_dump_ini_special_mem_iter,
 	},
+	[IWL_FW_INI_REGION_DBGI_SRAM] = {
+		.get_num_of_ranges = iwl_dump_ini_mem_ranges,
+		.get_size = iwl_dump_ini_mem_get_size,
+		.fill_mem_hdr = iwl_dump_ini_mem_fill_header,
+		.fill_range = iwl_dump_ini_dbgi_sram_iter,
+	},
 };
 
 static u32 iwl_dump_ini_trigger(struct iwl_fw_runtime *fwrt,
@@ -2321,7 +2358,7 @@ static void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 		return;
 
 	if (dump_data->monitor_only)
-		dump_mask &= IWL_FW_ERROR_DUMP_FW_MONITOR;
+		dump_mask &= BIT(IWL_FW_ERROR_DUMP_FW_MONITOR);
 
 	fw_error_dump.trans_ptr = iwl_trans_dump_data(fwrt->trans, dump_mask);
 	file_len = le32_to_cpu(dump_file->file_len);
@@ -2530,51 +2567,6 @@ int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
 }
 IWL_EXPORT_SYMBOL(iwl_fw_dbg_collect);
 
-int iwl_fw_dbg_ini_collect(struct iwl_fw_runtime *fwrt,
-			   struct iwl_fwrt_dump_data *dump_data)
-{
-	struct iwl_fw_ini_trigger_tlv *trig = dump_data->trig;
-	enum iwl_fw_ini_time_point tp_id = le32_to_cpu(trig->time_point);
-	u32 occur, delay;
-	unsigned long idx;
-
-	if (!iwl_fw_ini_trigger_on(fwrt, trig)) {
-		IWL_WARN(fwrt, "WRT: Trigger %d is not active, aborting dump\n",
-			 tp_id);
-		return -EINVAL;
-	}
-
-	delay = le32_to_cpu(trig->dump_delay);
-	occur = le32_to_cpu(trig->occurrences);
-	if (!occur)
-		return 0;
-
-	trig->occurrences = cpu_to_le32(--occur);
-
-	/* Check there is an available worker.
-	 * ffz return value is undefined if no zero exists,
-	 * so check against ~0UL first.
-	 */
-	if (fwrt->dump.active_wks == ~0UL)
-		return -EBUSY;
-
-	idx = ffz(fwrt->dump.active_wks);
-
-	if (idx >= IWL_FW_RUNTIME_DUMP_WK_NUM ||
-	    test_and_set_bit(fwrt->dump.wks[idx].idx, &fwrt->dump.active_wks))
-		return -EBUSY;
-
-	fwrt->dump.wks[idx].dump_data = *dump_data;
-
-	IWL_WARN(fwrt,
-		 "WRT: Collecting data: ini trigger %d fired (delay=%dms).\n",
-		 tp_id, (u32)(delay / USEC_PER_MSEC));
-
-	schedule_delayed_work(&fwrt->dump.wks[idx].wk, usecs_to_jiffies(delay));
-
-	return 0;
-}
-
 int iwl_fw_dbg_collect_trig(struct iwl_fw_runtime *fwrt,
 			    struct iwl_fw_dbg_trigger_tlv *trigger,
 			    const char *fmt, ...)
@@ -2703,6 +2695,58 @@ out:
 	clear_bit(wk_idx, &fwrt->dump.active_wks);
 }
 
+int iwl_fw_dbg_ini_collect(struct iwl_fw_runtime *fwrt,
+			   struct iwl_fwrt_dump_data *dump_data,
+			   bool sync)
+{
+	struct iwl_fw_ini_trigger_tlv *trig = dump_data->trig;
+	enum iwl_fw_ini_time_point tp_id = le32_to_cpu(trig->time_point);
+	u32 occur, delay;
+	unsigned long idx;
+
+	if (!iwl_fw_ini_trigger_on(fwrt, trig)) {
+		IWL_WARN(fwrt, "WRT: Trigger %d is not active, aborting dump\n",
+			 tp_id);
+		return -EINVAL;
+	}
+
+	delay = le32_to_cpu(trig->dump_delay);
+	occur = le32_to_cpu(trig->occurrences);
+	if (!occur)
+		return 0;
+
+	trig->occurrences = cpu_to_le32(--occur);
+
+	/* Check there is an available worker.
+	 * ffz return value is undefined if no zero exists,
+	 * so check against ~0UL first.
+	 */
+	if (fwrt->dump.active_wks == ~0UL)
+		return -EBUSY;
+
+	idx = ffz(fwrt->dump.active_wks);
+
+	if (idx >= IWL_FW_RUNTIME_DUMP_WK_NUM ||
+	    test_and_set_bit(fwrt->dump.wks[idx].idx, &fwrt->dump.active_wks))
+		return -EBUSY;
+
+	fwrt->dump.wks[idx].dump_data = *dump_data;
+
+	if (sync)
+		delay = 0;
+
+	IWL_WARN(fwrt,
+		 "WRT: Collecting data: ini trigger %d fired (delay=%dms).\n",
+		 tp_id, (u32)(delay / USEC_PER_MSEC));
+
+	schedule_delayed_work(&fwrt->dump.wks[idx].wk, usecs_to_jiffies(delay));
+
+	if (sync)
+		iwl_fw_dbg_collect_sync(fwrt, idx);
+
+	return 0;
+}
+
 void iwl_fw_error_dump_wk(struct work_struct *work)
 {
 	struct iwl_fwrt_wk_data *wks =
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index c0e84ef84f5d..8c3c890066b0 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -46,7 +46,8 @@ int iwl_fw_dbg_collect_desc(struct iwl_fw_runtime *fwrt,
 int iwl_fw_dbg_error_collect(struct iwl_fw_runtime *fwrt,
 			     enum iwl_fw_dbg_trigger trig_type);
 int iwl_fw_dbg_ini_collect(struct iwl_fw_runtime *fwrt,
-			   struct iwl_fwrt_dump_data *dump_data);
+			   struct iwl_fwrt_dump_data *dump_data,
+			   bool sync);
 int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
 		       enum iwl_fw_dbg_trigger trig, const char *str,
 		       size_t len, struct iwl_fw_dbg_trigger_tlv *trigger);
@@ -284,7 +285,7 @@ static inline void iwl_fw_umac_set_alive_err_table(struct iwl_trans *trans,
 		trans->dbg.umac_error_event_table = umac_error_event_table;
 }
 
-static inline void iwl_fw_error_collect(struct iwl_fw_runtime *fwrt)
+static inline void iwl_fw_error_collect(struct iwl_fw_runtime *fwrt, bool sync)
 {
 	enum iwl_fw_ini_time_point tp_id;
 
@@ -300,7 +301,7 @@ static inline void iwl_fw_error_collect(struct iwl_fw_runtime *fwrt)
 		tp_id = IWL_FW_INI_TIME_POINT_FW_ASSERT;
 	}
 
-	iwl_dbg_tlv_time_point(fwrt, tp_id, NULL);
+	_iwl_dbg_tlv_time_point(fwrt, tp_id, NULL, sync);
 }
 
 void iwl_fw_error_print_fseq_regs(struct iwl_fw_runtime *fwrt);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
index 9fffac903b93..521ca2bb0e92 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2014, 2018-2020 Intel Corporation
+ * Copyright (C) 2014, 2018-2021 Intel Corporation
  * Copyright (C) 2014-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -305,11 +305,12 @@ struct iwl_fw_ini_error_dump_header {
 /**
  * struct iwl_fw_ini_error_dump - ini region dump
  * @header: the header of this region
- * @ranges: the memory ranges of this region
+ * @data: data of memory ranges in this region,
+ *	see &struct iwl_fw_ini_error_dump_range
  */
 struct iwl_fw_ini_error_dump {
 	struct iwl_fw_ini_error_dump_header header;
-	struct iwl_fw_ini_error_dump_range ranges[];
+	u8 data[];
 } __packed;
 
 /* This bit is used to differentiate between lmac and umac rxf */
@@ -399,12 +400,13 @@ struct iwl_fw_ini_dump_info {
  * struct iwl_fw_ini_err_table_dump - ini error table dump
  * @header: header of the region
  * @version: error table version
- * @ranges: the memory ranges of this this region
+ * @data: data of memory ranges in this region,
+ *	see &struct iwl_fw_ini_error_dump_range
  */
 struct iwl_fw_ini_err_table_dump {
 	struct iwl_fw_ini_error_dump_header header;
 	__le32 version;
-	struct iwl_fw_ini_error_dump_range ranges[];
+	u8 data[];
 } __packed;
 
 /**
@@ -427,14 +429,15 @@ struct iwl_fw_error_dump_rb {
  * @write_ptr: write pointer position in the buffer
  * @cycle_cnt: cycles count
  * @cur_frag: current fragment in use
- * @ranges: the memory ranges of this this region
+ * @data: data of memory ranges in this region,
+ *	see &struct iwl_fw_ini_error_dump_range
  */
 struct iwl_fw_ini_monitor_dump {
 	struct iwl_fw_ini_error_dump_header header;
 	__le32 write_ptr;
 	__le32 cycle_cnt;
 	__le32 cur_frag;
-	struct iwl_fw_ini_error_dump_range ranges[];
+	u8 data[];
 } __packed;
 
 /**
@@ -442,13 +445,14 @@ struct iwl_fw_ini_monitor_dump {
  * @header: header of the region
  * @type: type of special memory
  * @version: struct special memory version
- * @ranges: the memory ranges of this this region
+ * @data: data of memory ranges in this region,
+ *	see &struct iwl_fw_ini_error_dump_range
  */
 struct iwl_fw_ini_special_device_memory {
 	struct iwl_fw_ini_error_dump_header header;
 	__le16 type;
 	__le16 version;
-	struct iwl_fw_ini_error_dump_range ranges[];
+	u8 data[];
 } __packed;
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h
index 9a8c7b7a0816..6c8e9f3a6af2 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/file.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h
@@ -414,6 +414,7 @@ enum iwl_ucode_tlv_capa {
 	IWL_UCODE_TLV_CAPA_PROTECTED_TWT		= (__force iwl_ucode_tlv_capa_t)56,
 	IWL_UCODE_TLV_CAPA_FW_RESET_HANDSHAKE		= (__force iwl_ucode_tlv_capa_t)57,
 	IWL_UCODE_TLV_CAPA_PASSIVE_6GHZ_SCAN		= (__force iwl_ucode_tlv_capa_t)58,
+	IWL_UCODE_TLV_CAPA_HIDDEN_6GHZ_SCAN		= (__force iwl_ucode_tlv_capa_t)59,
 	IWL_UCODE_TLV_CAPA_BROADCAST_TWT		= (__force iwl_ucode_tlv_capa_t)60,
 
 	/* set 2 */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c
index b4b1f75b9c2a..314ed90c23dd 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c
@@ -24,7 +24,7 @@ static bool iwl_pnvm_complete_fn(struct iwl_notif_wait_data *notif_wait,
 	struct iwl_pnvm_init_complete_ntfy *pnvm_ntf = (void *)pkt->data;
 
 	IWL_DEBUG_FW(trans,
-		     "PNVM complete notification received with status %d\n",
+		     "PNVM complete notification received with status 0x%0x\n",
 		     le32_to_cpu(pnvm_ntf->status));
 
 	return true;
@@ -230,19 +230,10 @@ static int iwl_pnvm_parse(struct iwl_trans *trans, const u8 *data,
 static int iwl_pnvm_get_from_fs(struct iwl_trans *trans, u8 **data, size_t *len)
 {
 	const struct firmware *pnvm;
-	char pnvm_name[64];
+	char pnvm_name[MAX_PNVM_NAME];
 	int ret;
 
-	/*
-	 * The prefix unfortunately includes a hyphen at the end, so
-	 * don't add the dot here...
-	 */
-	snprintf(pnvm_name, sizeof(pnvm_name), "%spnvm",
-		 trans->cfg->fw_name_pre);
-
-	/* ...but replace the hyphen with the dot here. */
-	if (strlen(trans->cfg->fw_name_pre) < sizeof(pnvm_name))
-		pnvm_name[strlen(trans->cfg->fw_name_pre) - 1] = '.';
+	iwl_pnvm_get_fs_name(trans, pnvm_name, sizeof(pnvm_name));
 
 	ret = firmware_request_nowarn(&pnvm, pnvm_name, trans->dev);
 	if (ret) {
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.h b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.h
index 61d3d4e0b7d9..203c367dd4de 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.h
@@ -12,7 +12,27 @@
 
 #define MVM_UCODE_PNVM_TIMEOUT	(HZ / 4)
 
+#define MAX_PNVM_NAME  64
+
 int iwl_pnvm_load(struct iwl_trans *trans,
 		  struct iwl_notif_wait_data *notif_wait);
 
+static inline
+void iwl_pnvm_get_fs_name(struct iwl_trans *trans,
+			  u8 *pnvm_name, size_t max_len)
+{
+	int pre_len;
+
+	/*
+	 * The prefix unfortunately includes a hyphen at the end, so
+	 * don't add the dot here...
+	 */
+	snprintf(pnvm_name, max_len, "%spnvm", trans->cfg->fw_name_pre);
+
+	/* ...but replace the hyphen with the dot here. */
+	pre_len = strlen(trans->cfg->fw_name_pre);
+	if (pre_len < max_len && pre_len > 0)
+		pnvm_name[pre_len - 1] = '.';
+}
+
 #endif /* __IWL_PNVM_H__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index bf6ee56d4d96..7eb534df5331 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -33,6 +33,7 @@ enum iwl_device_family {
 	IWL_DEVICE_FAMILY_9000,
 	IWL_DEVICE_FAMILY_22000,
 	IWL_DEVICE_FAMILY_AX210,
+	IWL_DEVICE_FAMILY_BZ,
 };
 
 /*
@@ -321,7 +322,7 @@ struct iwl_fw_mon_regs {
  * @host_interrupt_operation_mode: device needs host interrupt operation
  *	mode set
  * @nvm_hw_section_num: the ID of the HW NVM section
- * @mac_addr_from_csr: read HW address from CSR registers
+ * @mac_addr_from_csr: read HW address from CSR registers at this offset
  * @features: hw features, any combination of feature_passlist
  * @pwr_tx_backoffs: translation table between power limits and backoffs
  * @max_tx_agg_size: max TX aggregation size of the ADDBA request/response
@@ -343,6 +344,8 @@ struct iwl_fw_mon_regs {
  *	supports 256 BA aggregation
  * @num_rbds: number of receive buffer descriptors to use
  *	(only used for multi-queue capable devices)
+ * @mac_addr_csr_base: CSR base register for MAC address access, if not set
+ *	assume 0x380
  *
  * We enable the driver to be backward compatible wrt. hardware features.
  * API differences in uCode shouldn't be handled here but through TLVs
@@ -378,7 +381,7 @@ struct iwl_cfg {
 	    internal_wimax_coex:1,
 	    host_interrupt_operation_mode:1,
 	    high_temp:1,
-	    mac_addr_from_csr:1,
+	    mac_addr_from_csr:10,
 	    lp_xtal_workaround:1,
 	    disable_dummy_notification:1,
 	    apmg_not_supported:1,
@@ -512,6 +515,7 @@ extern const char iwl_ax211_name[];
 extern const char iwl_ax221_name[];
 extern const char iwl_ax231_name[];
 extern const char iwl_ax411_name[];
+extern const char iwl_bz_name[];
 #if IS_ENABLED(CONFIG_IWLDVM)
 extern const struct iwl_cfg iwl5300_agn_cfg;
 extern const struct iwl_cfg iwl5100_agn_cfg;
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index 47e5a17c0f48..cf796403c45c 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -104,6 +104,10 @@
 /* GIO Chicken Bits (PCI Express bus link power management) */
 #define CSR_GIO_CHICKEN_BITS    (CSR_BASE+0x100)
 
+/* Doorbell NMI (since Bz) */
+#define CSR_DOORBELL_VECTOR	(CSR_BASE + 0x130)
+#define CSR_DOORBELL_VECTOR_NMI	BIT(1)
+
 /* host chicken bits */
 #define CSR_HOST_CHICKEN	(CSR_BASE + 0x204)
 #define CSR_HOST_CHICKEN_PM_IDLE_SRC_DIS_SB_PME	BIT(19)
@@ -266,6 +270,14 @@
 #define CSR_GP_CNTRL_REG_FLAG_RFKILL_WAKE_L1A_EN     (0x04000000)
 #define CSR_GP_CNTRL_REG_FLAG_HW_RF_KILL_SW          (0x08000000)
 
+/* From Bz we use these instead during init/reset flow */
+#define CSR_GP_CNTRL_REG_FLAG_MAC_INIT			BIT(6)
+#define CSR_GP_CNTRL_REG_FLAG_ROM_START			BIT(7)
+#define CSR_GP_CNTRL_REG_FLAG_MAC_STATUS		BIT(20)
+#define CSR_GP_CNTRL_REG_FLAG_BZ_MAC_ACCESS_REQ		BIT(21)
+#define CSR_GP_CNTRL_REG_FLAG_BUS_MASTER_DISABLE_STATUS	BIT(28)
+#define CSR_GP_CNTRL_REG_FLAG_BUS_MASTER_DISABLE_REQ	BIT(29)
+#define CSR_GP_CNTRL_REG_FLAG_SW_RESET			BIT(31)
 
 /* HW REV */
 #define CSR_HW_REV_DASH(_val)          (((_val) & 0x0000003) >> 0)
@@ -604,10 +616,10 @@ enum msix_hw_int_causes {
  *                     HW address related registers                          *
  *****************************************************************************/
 
-#define CSR_ADDR_BASE			(0x380)
-#define CSR_MAC_ADDR0_OTP		(CSR_ADDR_BASE)
-#define CSR_MAC_ADDR1_OTP		(CSR_ADDR_BASE + 4)
-#define CSR_MAC_ADDR0_STRAP		(CSR_ADDR_BASE + 8)
-#define CSR_MAC_ADDR1_STRAP		(CSR_ADDR_BASE + 0xC)
+#define CSR_ADDR_BASE(trans)			((trans)->cfg->mac_addr_from_csr)
+#define CSR_MAC_ADDR0_OTP(trans)		(CSR_ADDR_BASE(trans) + 0x00)
+#define CSR_MAC_ADDR1_OTP(trans)		(CSR_ADDR_BASE(trans) + 0x04)
+#define CSR_MAC_ADDR0_STRAP(trans)		(CSR_ADDR_BASE(trans) + 0x08)
+#define CSR_MAC_ADDR1_STRAP(trans)		(CSR_ADDR_BASE(trans) + 0x0c)
 
 #endif /* !__iwl_csr_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index 0ddd255a8cc1..125479b5c0d6 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -131,8 +131,7 @@ static int iwl_dbg_tlv_alloc_buf_alloc(struct iwl_trans *trans,
 		goto err;
 
 	if (buf_location == IWL_FW_INI_LOCATION_SRAM_PATH &&
-	    alloc_id != IWL_FW_INI_ALLOCATION_ID_DBGC1 &&
-	    alloc_id != IWL_FW_INI_ALLOCATION_ID_INTERNAL)
+	    alloc_id != IWL_FW_INI_ALLOCATION_ID_DBGC1)
 		goto err;
 
 	trans->dbg.fw_mon_cfg[alloc_id] = *alloc;
@@ -435,13 +434,16 @@ static int iwl_dbg_tlv_parse_bin(struct iwl_trans *trans, const u8 *data,
 void iwl_dbg_tlv_load_bin(struct device *dev, struct iwl_trans *trans)
 {
 	const struct firmware *fw;
+	const char *yoyo_bin = "iwl-debug-yoyo.bin";
 	int res;
 
 	if (!iwlwifi_mod_params.enable_ini ||
 	    trans->trans_cfg->device_family <= IWL_DEVICE_FAMILY_9000)
 		return;
 
-	res = firmware_request_nowarn(&fw, "iwl-debug-yoyo.bin", dev);
+	res = firmware_request_nowarn(&fw, yoyo_bin, dev);
+	IWL_DEBUG_FW(trans, "%s %s\n", res ? "didn't load" : "loaded", yoyo_bin);
+
 	if (res)
 		return;
 
@@ -621,6 +623,7 @@ static int iwl_dbg_tlv_apply_buffer(struct iwl_fw_runtime *fwrt,
 			.id = WIDE_ID(DEBUG_GROUP, BUFFER_ALLOCATION),
 			.data[0] = &data,
 			.len[0] = sizeof(data),
+			.flags = CMD_SEND_IN_RFKILL,
 		};
 		int ret, j;
 
@@ -683,7 +686,7 @@ static void iwl_dbg_tlv_periodic_trig_handler(struct timer_list *t)
 	};
 	int ret;
 
-	ret = iwl_fw_dbg_ini_collect(timer_node->fwrt, &dump_data);
+	ret = iwl_fw_dbg_ini_collect(timer_node->fwrt, &dump_data, false);
 	if (!ret || ret == -EBUSY) {
 		u32 occur = le32_to_cpu(dump_data.trig->occurrences);
 		u32 collect_interval = le32_to_cpu(dump_data.trig->data[0]);
@@ -927,7 +930,7 @@ static bool iwl_dbg_tlv_check_fw_pkt(struct iwl_fw_runtime *fwrt,
 }
 
 static int
-iwl_dbg_tlv_tp_trigger(struct iwl_fw_runtime *fwrt,
+iwl_dbg_tlv_tp_trigger(struct iwl_fw_runtime *fwrt, bool sync,
 		       struct list_head *active_trig_list,
 		       union iwl_dbg_tlv_tp_data *tp_data,
 		       bool (*data_check)(struct iwl_fw_runtime *fwrt,
@@ -946,7 +949,7 @@ iwl_dbg_tlv_tp_trigger(struct iwl_fw_runtime *fwrt,
 		int ret, i;
 
 		if (!num_data) {
-			ret = iwl_fw_dbg_ini_collect(fwrt, &dump_data);
+			ret = iwl_fw_dbg_ini_collect(fwrt, &dump_data, sync);
 			if (ret)
 				return ret;
 		}
@@ -955,7 +958,7 @@ iwl_dbg_tlv_tp_trigger(struct iwl_fw_runtime *fwrt,
 			if (!data_check ||
 			    data_check(fwrt, &dump_data, tp_data,
 				       le32_to_cpu(dump_data.trig->data[i]))) {
-				ret = iwl_fw_dbg_ini_collect(fwrt, &dump_data);
+				ret = iwl_fw_dbg_ini_collect(fwrt, &dump_data, sync);
 				if (ret)
 					return ret;
 
@@ -1043,9 +1046,10 @@ static void iwl_dbg_tlv_init_cfg(struct iwl_fw_runtime *fwrt)
 	}
 }
 
-void iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
-			    enum iwl_fw_ini_time_point tp_id,
-			    union iwl_dbg_tlv_tp_data *tp_data)
+void _iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
+			     enum iwl_fw_ini_time_point tp_id,
+			     union iwl_dbg_tlv_tp_data *tp_data,
+			     bool sync)
 {
 	struct list_head *hcmd_list, *trig_list;
 
@@ -1060,12 +1064,12 @@ void iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
 	switch (tp_id) {
 	case IWL_FW_INI_TIME_POINT_EARLY:
 		iwl_dbg_tlv_init_cfg(fwrt);
-		iwl_dbg_tlv_tp_trigger(fwrt, trig_list, tp_data, NULL);
+		iwl_dbg_tlv_tp_trigger(fwrt, sync, trig_list, tp_data, NULL);
 		break;
 	case IWL_FW_INI_TIME_POINT_AFTER_ALIVE:
 		iwl_dbg_tlv_apply_buffers(fwrt);
 		iwl_dbg_tlv_send_hcmds(fwrt, hcmd_list);
-		iwl_dbg_tlv_tp_trigger(fwrt, trig_list, tp_data, NULL);
+		iwl_dbg_tlv_tp_trigger(fwrt, sync, trig_list, tp_data, NULL);
 		break;
 	case IWL_FW_INI_TIME_POINT_PERIODIC:
 		iwl_dbg_tlv_set_periodic_trigs(fwrt);
@@ -1075,13 +1079,13 @@ void iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
 	case IWL_FW_INI_TIME_POINT_MISSED_BEACONS:
 	case IWL_FW_INI_TIME_POINT_FW_DHC_NOTIFICATION:
 		iwl_dbg_tlv_send_hcmds(fwrt, hcmd_list);
-		iwl_dbg_tlv_tp_trigger(fwrt, trig_list, tp_data,
+		iwl_dbg_tlv_tp_trigger(fwrt, sync, trig_list, tp_data,
 				       iwl_dbg_tlv_check_fw_pkt);
 		break;
 	default:
 		iwl_dbg_tlv_send_hcmds(fwrt, hcmd_list);
-		iwl_dbg_tlv_tp_trigger(fwrt, trig_list, tp_data, NULL);
+		iwl_dbg_tlv_tp_trigger(fwrt, sync, trig_list, tp_data, NULL);
 		break;
 	}
 }
-IWL_EXPORT_SYMBOL(iwl_dbg_tlv_time_point);
+IWL_EXPORT_SYMBOL(_iwl_dbg_tlv_time_point);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h
index 92c720527946..c12b1fd3f479 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
  */
 #ifndef __iwl_dbg_tlv_h__
 #define __iwl_dbg_tlv_h__
@@ -48,9 +48,25 @@ void iwl_dbg_tlv_free(struct iwl_trans *trans);
 void iwl_dbg_tlv_alloc(struct iwl_trans *trans, const struct iwl_ucode_tlv *tlv,
 		       bool ext);
 void iwl_dbg_tlv_init(struct iwl_trans *trans);
-void iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
-			    enum iwl_fw_ini_time_point tp_id,
-			    union iwl_dbg_tlv_tp_data *tp_data);
+void _iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
+			     enum iwl_fw_ini_time_point tp_id,
+			     union iwl_dbg_tlv_tp_data *tp_data,
+			     bool sync);
+
+static inline void iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
+					  enum iwl_fw_ini_time_point tp_id,
+					  union iwl_dbg_tlv_tp_data *tp_data)
+{
+	_iwl_dbg_tlv_time_point(fwrt, tp_id, tp_data, false);
+}
+
+static inline void iwl_dbg_tlv_time_point_sync(struct iwl_fw_runtime *fwrt,
+					       enum iwl_fw_ini_time_point tp_id,
+					       union iwl_dbg_tlv_tp_data *tp_data)
+{
+	_iwl_dbg_tlv_time_point(fwrt, tp_id, tp_data, true);
+}
+
 void iwl_dbg_tlv_del_timers(struct iwl_trans *trans);
 
 #endif /* __iwl_dbg_tlv_h__*/
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 977dce686bdb..77124b8b235e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -78,7 +78,7 @@ enum {
 };
 
 /* Protects the table contents, i.e. the ops pointer & drv list */
-static struct mutex iwlwifi_opmode_table_mtx;
+static DEFINE_MUTEX(iwlwifi_opmode_table_mtx);
 static struct iwlwifi_opmode_table {
 	const char *name;			/* name: iwldvm, iwlmvm, etc */
 	const struct iwl_op_mode_ops *ops;	/* pointer to op_mode ops */
@@ -1754,8 +1754,6 @@ static int __init iwl_drv_init(void)
 {
 	int i, err;
 
-	mutex_init(&iwlwifi_opmode_table_mtx);
-
 	for (i = 0; i < ARRAY_SIZE(iwlwifi_opmode_table); i++)
 		INIT_LIST_HEAD(&iwlwifi_opmode_table[i].drv);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-io.c b/drivers/net/wireless/intel/iwlwifi/iwl-io.c
index 33d42e08d5b8..2517c4ae07ab 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-io.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-io.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2003-2014, 2018-2020 Intel Corporation
+ * Copyright (C) 2003-2014, 2018-2021 Intel Corporation
  * Copyright (C) 2015-2016 Intel Deutschland GmbH
  */
 #include <linux/delay.h>
@@ -213,9 +213,12 @@ void iwl_force_nmi(struct iwl_trans *trans)
 	else if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		iwl_write_umac_prph(trans, UREG_NIC_SET_NMI_DRIVER,
 				UREG_NIC_SET_NMI_DRIVER_NMI_FROM_DRIVER);
-	else
+	else if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_BZ)
 		iwl_write_umac_prph(trans, UREG_DOORBELL_TO_ISR6,
 				    UREG_DOORBELL_TO_ISR6_NMI_BIT);
+	else
+		iwl_write32(trans, CSR_DOORBELL_VECTOR,
+			    CSR_DOORBELL_VECTOR_NMI);
 }
 IWL_EXPORT_SYMBOL(iwl_force_nmi);
 
@@ -398,6 +401,7 @@ int iwl_dump_fh(struct iwl_trans *trans, char **buf)
 int iwl_finish_nic_init(struct iwl_trans *trans,
 			const struct iwl_cfg_trans_params *cfg_trans)
 {
+	u32 poll_ready;
 	int err;
 
 	if (cfg_trans->bisr_workaround) {
@@ -409,7 +413,16 @@ int iwl_finish_nic_init(struct iwl_trans *trans,
 	 * Set "initialization complete" bit to move adapter from
 	 * D0U* --> D0A* (powered-up active) state.
 	 */
-	iwl_set_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+	if (cfg_trans->device_family >= IWL_DEVICE_FAMILY_BZ) {
+		iwl_set_bit(trans, CSR_GP_CNTRL,
+			    CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY |
+			    CSR_GP_CNTRL_REG_FLAG_MAC_INIT);
+		poll_ready = CSR_GP_CNTRL_REG_FLAG_MAC_STATUS;
+	} else {
+		iwl_set_bit(trans, CSR_GP_CNTRL,
+			    CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+		poll_ready = CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY;
+	}
 
 	if (cfg_trans->device_family == IWL_DEVICE_FAMILY_8000)
 		udelay(2);
@@ -419,10 +432,7 @@ int iwl_finish_nic_init(struct iwl_trans *trans,
 	 * device-internal resources is supported, e.g. iwl_write_prph()
 	 * and accesses to uCode SRAM.
 	 */
-	err = iwl_poll_bit(trans, CSR_GP_CNTRL,
-			   CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
-			   CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
-			   25000);
+	err = iwl_poll_bit(trans, CSR_GP_CNTRL, poll_ready, poll_ready, 25000);
 	if (err < 0)
 		IWL_DEBUG_INFO(trans, "Failed to wake NIC\n");
 
@@ -468,5 +478,5 @@ void iwl_trans_sync_nmi_with_addr(struct iwl_trans *trans, u32 inta_addr,
 	if (interrupts_enabled)
 		iwl_trans_interrupts(trans, true);
 
-	iwl_trans_fw_error(trans);
+	iwl_trans_fw_error(trans, false);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 850648ebd61c..475f951d4b1e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -549,7 +549,8 @@ static const struct ieee80211_sband_iftype_data iwl_he_capa[] = {
 				.mac_cap_info[2] =
 					IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP,
 				.mac_cap_info[3] =
-					IEEE80211_HE_MAC_CAP3_OMI_CONTROL,
+					IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
+					IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS,
 				.mac_cap_info[4] =
 					IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU |
 					IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39,
@@ -568,7 +569,8 @@ static const struct ieee80211_sband_iftype_data iwl_he_capa[] = {
 					IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A |
 					IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD,
 				.phy_cap_info[2] =
-					IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US,
+					IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US |
+					IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ,
 				.phy_cap_info[3] =
 					IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM |
 					IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 |
@@ -595,6 +597,8 @@ static const struct ieee80211_sband_iftype_data iwl_he_capa[] = {
 					IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB |
 					IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB |
 					IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED,
+				.phy_cap_info[10] =
+					IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF,
 			},
 			/*
 			 * Set default Tx/Rx HE MCS NSS Support field.
@@ -634,6 +638,7 @@ static const struct ieee80211_sband_iftype_data iwl_he_capa[] = {
 				.phy_cap_info[1] =
 					IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD,
 				.phy_cap_info[2] =
+					IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ |
 					IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US,
 				.phy_cap_info[3] =
 					IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM |
@@ -742,6 +747,8 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 			IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G;
 
 	if ((tx_chains & rx_chains) == ANT_AB) {
+		iftype_data->he_cap.he_cap_elem.phy_cap_info[2] |=
+			IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ;
 		iftype_data->he_cap.he_cap_elem.phy_cap_info[5] |=
 			IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 |
 			IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2;
@@ -958,8 +965,10 @@ static void iwl_flip_hw_address(__le32 mac_addr0, __le32 mac_addr1, u8 *dest)
 static void iwl_set_hw_address_from_csr(struct iwl_trans *trans,
 					struct iwl_nvm_data *data)
 {
-	__le32 mac_addr0 = cpu_to_le32(iwl_read32(trans, CSR_MAC_ADDR0_STRAP));
-	__le32 mac_addr1 = cpu_to_le32(iwl_read32(trans, CSR_MAC_ADDR1_STRAP));
+	__le32 mac_addr0 = cpu_to_le32(iwl_read32(trans,
+						  CSR_MAC_ADDR0_STRAP(trans)));
+	__le32 mac_addr1 = cpu_to_le32(iwl_read32(trans,
+						  CSR_MAC_ADDR1_STRAP(trans)));
 
 	iwl_flip_hw_address(mac_addr0, mac_addr1, data->hw_addr);
 	/*
@@ -969,8 +978,8 @@ static void iwl_set_hw_address_from_csr(struct iwl_trans *trans,
 	if (is_valid_ether_addr(data->hw_addr))
 		return;
 
-	mac_addr0 = cpu_to_le32(iwl_read32(trans, CSR_MAC_ADDR0_OTP));
-	mac_addr1 = cpu_to_le32(iwl_read32(trans, CSR_MAC_ADDR1_OTP));
+	mac_addr0 = cpu_to_le32(iwl_read32(trans, CSR_MAC_ADDR0_OTP(trans)));
+	mac_addr1 = cpu_to_le32(iwl_read32(trans, CSR_MAC_ADDR1_OTP(trans)));
 
 	iwl_flip_hw_address(mac_addr0, mac_addr1, data->hw_addr);
 }
@@ -1373,6 +1382,25 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 		reg_query_regdb_wmm(regd->alpha2, center_freq, rule);
 	}
 
+	/*
+	 * Certain firmware versions might report no valid channels
+	 * if booted in RF-kill, i.e. not all calibrations etc. are
+	 * running. We'll get out of this situation later when the
+	 * rfkill is removed and we update the regdomain again, but
+	 * since cfg80211 doesn't accept an empty regdomain, add a
+	 * dummy (unusable) rule here in this case so we can init.
+	 */
+	if (!valid_rules) {
+		valid_rules = 1;
+		rule = &regd->reg_rules[valid_rules - 1];
+		rule->freq_range.start_freq_khz = MHZ_TO_KHZ(2412);
+		rule->freq_range.end_freq_khz = MHZ_TO_KHZ(2413);
+		rule->freq_range.max_bandwidth_khz = MHZ_TO_KHZ(1);
+		rule->power_rule.max_antenna_gain = DBI_TO_MBI(6);
+		rule->power_rule.max_eirp =
+			DBM_TO_MBM(IWL_DEFAULT_MAX_TX_POWER);
+	}
+
 	regd->n_reg_rules = valid_rules;
 
 	/*
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
index cf9c64090014..af5f9b210f22 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
@@ -78,7 +78,7 @@ struct iwl_cfg;
  *	there are Tx packets pending in the transport layer.
  *	Must be atomic
  * @nic_error: error notification. Must be atomic and must be called with BH
- *	disabled.
+ *	disabled, unless the sync parameter is true.
  * @cmd_queue_full: Called when the command queue gets full. Must be atomic and
  *	called with BH disabled.
  * @nic_config: configure NIC, called before firmware is started.
@@ -102,7 +102,7 @@ struct iwl_op_mode_ops {
 	void (*queue_not_full)(struct iwl_op_mode *op_mode, int queue);
 	bool (*hw_rf_kill)(struct iwl_op_mode *op_mode, bool state);
 	void (*free_skb)(struct iwl_op_mode *op_mode, struct sk_buff *skb);
-	void (*nic_error)(struct iwl_op_mode *op_mode);
+	void (*nic_error)(struct iwl_op_mode *op_mode, bool sync);
 	void (*cmd_queue_full)(struct iwl_op_mode *op_mode);
 	void (*nic_config)(struct iwl_op_mode *op_mode);
 	void (*wimax_active)(struct iwl_op_mode *op_mode);
@@ -181,9 +181,9 @@ static inline void iwl_op_mode_free_skb(struct iwl_op_mode *op_mode,
 	op_mode->ops->free_skb(op_mode, skb);
 }
 
-static inline void iwl_op_mode_nic_error(struct iwl_op_mode *op_mode)
+static inline void iwl_op_mode_nic_error(struct iwl_op_mode *op_mode, bool sync)
 {
-	op_mode->ops->nic_error(op_mode);
+	op_mode->ops->nic_error(op_mode, sync);
 }
 
 static inline void iwl_op_mode_cmd_queue_full(struct iwl_op_mode *op_mode)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
index 9a9e714bf9af..d0a7d58336a9 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
@@ -348,6 +348,13 @@
 #define RFIC_REG_RD			0xAD0470
 #define WFPM_CTRL_REG			0xA03030
 #define WFPM_GP2			0xA030B4
+
+/* DBGI SRAM Register details */
+#define DBGI_SRAM_TARGET_ACCESS_CFG			0x00A2E14C
+#define DBGI_SRAM_TARGET_ACCESS_CFG_RESET_ADDRESS_MSK	0x10000
+#define DBGI_SRAM_TARGET_ACCESS_RDATA_LSB		0x00A2E154
+#define DBGI_SRAM_TARGET_ACCESS_RDATA_MSB		0x00A2E158
+
 enum {
 	ENABLE_WFPM = BIT(31),
 	WFPM_AUX_CTL_AUX_IF_MAC_OWNER_MSK	= 0x80000000,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 0199d7a5a648..8f0ff540f439 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -887,7 +887,7 @@ struct iwl_trans_txqs {
 	bool bc_table_dword;
 	u8 page_offs;
 	u8 dev_cmd_offs;
-	struct __percpu iwl_tso_hdr_page * tso_hdr_page;
+	struct iwl_tso_hdr_page __percpu *tso_hdr_page;
 
 	struct {
 		u8 fifo;
@@ -1385,14 +1385,14 @@ iwl_trans_release_nic_access(struct iwl_trans *trans)
 	__release(nic_access);
 }
 
-static inline void iwl_trans_fw_error(struct iwl_trans *trans)
+static inline void iwl_trans_fw_error(struct iwl_trans *trans, bool sync)
 {
 	if (WARN_ON_ONCE(!trans->op_mode))
 		return;
 
 	/* prevent double restarts due to the same erroneous FW */
 	if (!test_and_set_bit(STATUS_FW_ERROR, &trans->status)) {
-		iwl_op_mode_nic_error(trans->op_mode);
+		iwl_op_mode_nic_error(trans->op_mode, sync);
 		trans->state = IWL_TRANS_NO_FW;
 	}
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
index 1343f25f1090..9d0d01f27d92 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
- * Copyright (C) 2013-2014, 2018-2020 Intel Corporation
+ * Copyright (C) 2013-2014, 2018-2021 Intel Corporation
  * Copyright (C) 2015 Intel Deutschland GmbH
  */
 #ifndef __MVM_CONSTANTS_H
@@ -93,6 +93,7 @@
 #define IWL_MVM_ENABLE_EBS			1
 #define IWL_MVM_FTM_INITIATOR_ALGO		IWL_TOF_ALGO_TYPE_MAX_LIKE
 #define IWL_MVM_FTM_INITIATOR_DYNACK		true
+#define IWL_MVM_FTM_LMR_FEEDBACK_TERMINATE	false
 #define IWL_MVM_FTM_R2I_MAX_REP			7
 #define IWL_MVM_FTM_I2R_MAX_REP			7
 #define IWL_MVM_FTM_R2I_MAX_STS			1
@@ -102,6 +103,8 @@
 #define IWL_MVM_FTM_INITIATOR_SECURE_LTF	false
 #define IWL_MVM_FTM_RESP_NDP_SUPPORT		true
 #define IWL_MVM_FTM_RESP_LMR_FEEDBACK_SUPPORT	true
+#define IWL_MVM_FTM_NON_TB_MIN_TIME_BETWEEN_MSR	5
+#define IWL_MVM_FTM_NON_TB_MAX_TIME_BETWEEN_MSR	1000
 #define IWL_MVM_D3_DEBUG			false
 #define IWL_MVM_USE_TWT				true
 #define IWL_MVM_AMPDU_CONSEC_DROPS_DELBA	10
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 6a259d867d90..0e97d5e6c644 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -101,11 +101,8 @@ static const u8 *iwl_mvm_find_max_pn(struct ieee80211_key_conf *key,
 	return ret;
 }
 
-struct wowlan_key_data {
-	struct iwl_wowlan_rsc_tsc_params_cmd *rsc_tsc;
-	struct iwl_wowlan_tkip_params_cmd *tkip;
-	struct iwl_wowlan_kek_kck_material_cmd_v4 *kek_kck_cmd;
-	bool error, use_rsc_tsc, use_tkip, configure_keys;
+struct wowlan_key_reprogram_data {
+	bool error;
 	int wep_key_idx;
 };
 
@@ -117,15 +114,8 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	struct wowlan_key_data *data = _data;
-	struct aes_sc *aes_sc, *aes_tx_sc = NULL;
-	struct tkip_sc *tkip_sc, *tkip_tx_sc = NULL;
-	struct iwl_p1k_cache *rx_p1ks;
-	u8 *rx_mic_key;
-	struct ieee80211_key_seq seq;
-	u32 cur_rx_iv32 = 0;
-	u16 p1k[IWL_P1K_SIZE];
-	int ret, i;
+	struct wowlan_key_reprogram_data *data = _data;
+	int ret;
 
 	switch (key->cipher) {
 	case WLAN_CIPHER_SUITE_WEP40:
@@ -162,18 +152,14 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 			wkc.wep_key.key_offset = data->wep_key_idx;
 		}
 
-		if (data->configure_keys) {
-			mutex_lock(&mvm->mutex);
-			ret = iwl_mvm_send_cmd_pdu(mvm, WEP_KEY, 0,
-						   sizeof(wkc), &wkc);
-			data->error = ret != 0;
-
-			mvm->ptk_ivlen = key->iv_len;
-			mvm->ptk_icvlen = key->icv_len;
-			mvm->gtk_ivlen = key->iv_len;
-			mvm->gtk_icvlen = key->icv_len;
-			mutex_unlock(&mvm->mutex);
-		}
+		mutex_lock(&mvm->mutex);
+		ret = iwl_mvm_send_cmd_pdu(mvm, WEP_KEY, 0, sizeof(wkc), &wkc);
+		data->error = ret != 0;
+
+		mvm->ptk_ivlen = key->iv_len;
+		mvm->ptk_icvlen = key->icv_len;
+		mvm->gtk_ivlen = key->iv_len;
+		mvm->gtk_icvlen = key->icv_len;
 
 		/* don't upload key again */
 		return;
@@ -183,10 +169,8 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 		return;
 	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
 	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
-		data->kek_kck_cmd->igtk_cipher = cpu_to_le32(STA_KEY_FLG_GCMP);
 		return;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
-		data->kek_kck_cmd->igtk_cipher = cpu_to_le32(STA_KEY_FLG_CCM);
 		/*
 		 * Ignore CMAC keys -- the WoWLAN firmware doesn't support them
 		 * but we also shouldn't abort suspend due to that. It does have
@@ -196,6 +180,58 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 		 */
 		return;
 	case WLAN_CIPHER_SUITE_TKIP:
+	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		break;
+	}
+
+	mutex_lock(&mvm->mutex);
+	/*
+	 * The D3 firmware hardcodes the key offset 0 as the key it
+	 * uses to transmit packets to the AP, i.e. the PTK.
+	 */
+	if (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) {
+		mvm->ptk_ivlen = key->iv_len;
+		mvm->ptk_icvlen = key->icv_len;
+		ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, 0);
+	} else {
+		/*
+		 * firmware only supports TSC/RSC for a single key,
+		 * so if there are multiple keep overwriting them
+		 * with new ones -- this relies on mac80211 doing
+		 * list_add_tail().
+		 */
+		mvm->gtk_ivlen = key->iv_len;
+		mvm->gtk_icvlen = key->icv_len;
+		ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, 1);
+	}
+	mutex_unlock(&mvm->mutex);
+	data->error = ret != 0;
+}
+
+struct wowlan_key_rsc_tsc_data {
+	struct iwl_wowlan_rsc_tsc_params_cmd_v4 *rsc_tsc;
+	bool have_rsc_tsc;
+};
+
+static void iwl_mvm_wowlan_get_rsc_tsc_data(struct ieee80211_hw *hw,
+					    struct ieee80211_vif *vif,
+					    struct ieee80211_sta *sta,
+					    struct ieee80211_key_conf *key,
+					    void *_data)
+{
+	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
+	struct wowlan_key_rsc_tsc_data *data = _data;
+	struct aes_sc *aes_sc;
+	struct tkip_sc *tkip_sc, *tkip_tx_sc = NULL;
+	struct ieee80211_key_seq seq;
+	int i;
+
+	switch (key->cipher) {
+	default:
+		break;
+	case WLAN_CIPHER_SUITE_TKIP:
 		if (sta) {
 			u64 pn64;
 
@@ -204,28 +240,12 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 			tkip_tx_sc =
 				&data->rsc_tsc->params.all_tsc_rsc.tkip.tsc;
 
-			rx_p1ks = data->tkip->rx_uni;
-
 			pn64 = atomic64_read(&key->tx_pn);
 			tkip_tx_sc->iv16 = cpu_to_le16(TKIP_PN_TO_IV16(pn64));
 			tkip_tx_sc->iv32 = cpu_to_le32(TKIP_PN_TO_IV32(pn64));
-
-			ieee80211_get_tkip_p1k_iv(key, TKIP_PN_TO_IV32(pn64),
-						  p1k);
-			iwl_mvm_convert_p1k(p1k, data->tkip->tx.p1k);
-
-			memcpy(data->tkip->mic_keys.tx,
-			       &key->key[NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY],
-			       IWL_MIC_KEY_SIZE);
-
-			rx_mic_key = data->tkip->mic_keys.rx_unicast;
 		} else {
 			tkip_sc =
 			  data->rsc_tsc->params.all_tsc_rsc.tkip.multicast_rsc;
-			rx_p1ks = data->tkip->rx_multi;
-			rx_mic_key = data->tkip->mic_keys.rx_mcast;
-			data->kek_kck_cmd->gtk_cipher =
-				cpu_to_le32(STA_KEY_FLG_TKIP);
 		}
 
 		/*
@@ -237,29 +257,15 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 			ieee80211_get_key_rx_seq(key, i, &seq);
 			tkip_sc[i].iv16 = cpu_to_le16(seq.tkip.iv16);
 			tkip_sc[i].iv32 = cpu_to_le32(seq.tkip.iv32);
-			/* wrapping isn't allowed, AP must rekey */
-			if (seq.tkip.iv32 > cur_rx_iv32)
-				cur_rx_iv32 = seq.tkip.iv32;
 		}
 
-		ieee80211_get_tkip_rx_p1k(key, vif->bss_conf.bssid,
-					  cur_rx_iv32, p1k);
-		iwl_mvm_convert_p1k(p1k, rx_p1ks[0].p1k);
-		ieee80211_get_tkip_rx_p1k(key, vif->bss_conf.bssid,
-					  cur_rx_iv32 + 1, p1k);
-		iwl_mvm_convert_p1k(p1k, rx_p1ks[1].p1k);
-
-		memcpy(rx_mic_key,
-		       &key->key[NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY],
-		       IWL_MIC_KEY_SIZE);
-
-		data->use_tkip = true;
-		data->use_rsc_tsc = true;
+		data->have_rsc_tsc = true;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		if (sta) {
+			struct aes_sc *aes_tx_sc;
 			u64 pn64;
 
 			aes_sc =
@@ -272,10 +278,6 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 		} else {
 			aes_sc =
 			   data->rsc_tsc->params.all_tsc_rsc.aes.multicast_rsc;
-			data->kek_kck_cmd->gtk_cipher =
-				key->cipher == WLAN_CIPHER_SUITE_CCMP ?
-				cpu_to_le32(STA_KEY_FLG_CCM) :
-				cpu_to_le32(STA_KEY_FLG_GCMP);
 		}
 
 		/*
@@ -320,35 +322,301 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 							   ((u64)pn[0] << 40));
 			}
 		}
-		data->use_rsc_tsc = true;
+		data->have_rsc_tsc = true;
 		break;
 	}
+}
 
-	IWL_DEBUG_WOWLAN(mvm, "GTK cipher %d\n", data->kek_kck_cmd->gtk_cipher);
+struct wowlan_key_rsc_v5_data {
+	struct iwl_wowlan_rsc_tsc_params_cmd *rsc;
+	bool have_rsc;
+	int gtks;
+	int gtk_ids[4];
+};
 
-	if (data->configure_keys) {
-		mutex_lock(&mvm->mutex);
+static void iwl_mvm_wowlan_get_rsc_v5_data(struct ieee80211_hw *hw,
+					   struct ieee80211_vif *vif,
+					   struct ieee80211_sta *sta,
+					   struct ieee80211_key_conf *key,
+					   void *_data)
+{
+	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
+	struct wowlan_key_rsc_v5_data *data = _data;
+	struct ieee80211_key_seq seq;
+	__le64 *rsc;
+	int i;
+
+	/* only for ciphers that can be PTK/GTK */
+	switch (key->cipher) {
+	default:
+		return;
+	case WLAN_CIPHER_SUITE_TKIP:
+	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		break;
+	}
+
+	if (sta) {
+		rsc = data->rsc->ucast_rsc;
+	} else {
+		if (WARN_ON(data->gtks > ARRAY_SIZE(data->gtk_ids)))
+			return;
+		data->gtk_ids[data->gtks] = key->keyidx;
+		rsc = data->rsc->mcast_rsc[data->gtks % 2];
+		if (WARN_ON(key->keyidx >
+				ARRAY_SIZE(data->rsc->mcast_key_id_map)))
+			return;
+		data->rsc->mcast_key_id_map[key->keyidx] = data->gtks % 2;
+		if (data->gtks >= 2) {
+			int prev = data->gtks - 2;
+			int prev_idx = data->gtk_ids[prev];
+
+			data->rsc->mcast_key_id_map[prev_idx] =
+				IWL_MCAST_KEY_MAP_INVALID;
+		}
+		data->gtks++;
+	}
+
+	switch (key->cipher) {
+	default:
+		WARN_ON(1);
+		break;
+	case WLAN_CIPHER_SUITE_TKIP:
+
+		/*
+		 * For non-QoS this relies on the fact that both the uCode and
+		 * mac80211 use TID 0 (as they need to to avoid replay attacks)
+		 * for checking the IV in the frames.
+		 */
+		for (i = 0; i < IWL_MAX_TID_COUNT; i++) {
+			ieee80211_get_key_rx_seq(key, i, &seq);
+
+			rsc[i] = cpu_to_le64(((u64)seq.tkip.iv32 << 16) |
+					     seq.tkip.iv16);
+		}
+
+		data->have_rsc = true;
+		break;
+	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
 		/*
-		 * The D3 firmware hardcodes the key offset 0 as the key it
-		 * uses to transmit packets to the AP, i.e. the PTK.
+		 * For non-QoS this relies on the fact that both the uCode and
+		 * mac80211/our RX code use TID 0 for checking the PN.
 		 */
-		if (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) {
-			mvm->ptk_ivlen = key->iv_len;
-			mvm->ptk_icvlen = key->icv_len;
-			ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, 0);
+		if (sta) {
+			struct iwl_mvm_sta *mvmsta;
+			struct iwl_mvm_key_pn *ptk_pn;
+			const u8 *pn;
+
+			mvmsta = iwl_mvm_sta_from_mac80211(sta);
+			rcu_read_lock();
+			ptk_pn = rcu_dereference(mvmsta->ptk_pn[key->keyidx]);
+			if (WARN_ON(!ptk_pn)) {
+				rcu_read_unlock();
+				break;
+			}
+
+			for (i = 0; i < IWL_MAX_TID_COUNT; i++) {
+				pn = iwl_mvm_find_max_pn(key, ptk_pn, &seq, i,
+						mvm->trans->num_rx_queues);
+				rsc[i] = cpu_to_le64((u64)pn[5] |
+						     ((u64)pn[4] << 8) |
+						     ((u64)pn[3] << 16) |
+						     ((u64)pn[2] << 24) |
+						     ((u64)pn[1] << 32) |
+						     ((u64)pn[0] << 40));
+			}
+
+			rcu_read_unlock();
 		} else {
-			/*
-			 * firmware only supports TSC/RSC for a single key,
-			 * so if there are multiple keep overwriting them
-			 * with new ones -- this relies on mac80211 doing
-			 * list_add_tail().
-			 */
-			mvm->gtk_ivlen = key->iv_len;
-			mvm->gtk_icvlen = key->icv_len;
-			ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, 1);
+			for (i = 0; i < IWL_MAX_TID_COUNT; i++) {
+				u8 *pn = seq.ccmp.pn;
+
+				ieee80211_get_key_rx_seq(key, i, &seq);
+				rsc[i] = cpu_to_le64((u64)pn[5] |
+						     ((u64)pn[4] << 8) |
+						     ((u64)pn[3] << 16) |
+						     ((u64)pn[2] << 24) |
+						     ((u64)pn[1] << 32) |
+						     ((u64)pn[0] << 40));
+			}
 		}
-		mutex_unlock(&mvm->mutex);
-		data->error = ret != 0;
+		data->have_rsc = true;
+		break;
+	}
+}
+
+static int iwl_mvm_wowlan_config_rsc_tsc(struct iwl_mvm *mvm,
+					 struct ieee80211_vif *vif)
+{
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	int ver = iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP,
+					WOWLAN_TSC_RSC_PARAM,
+					IWL_FW_CMD_VER_UNKNOWN);
+	int ret;
+
+	if (ver == 5) {
+		struct wowlan_key_rsc_v5_data data = {};
+		int i;
+
+		data.rsc = kmalloc(sizeof(*data.rsc), GFP_KERNEL);
+		if (!data.rsc)
+			return -ENOMEM;
+
+		memset(data.rsc, 0xff, sizeof(*data.rsc));
+
+		for (i = 0; i < ARRAY_SIZE(data.rsc->mcast_key_id_map); i++)
+			data.rsc->mcast_key_id_map[i] =
+				IWL_MCAST_KEY_MAP_INVALID;
+		data.rsc->sta_id = cpu_to_le32(mvmvif->ap_sta_id);
+
+		ieee80211_iter_keys(mvm->hw, vif,
+				    iwl_mvm_wowlan_get_rsc_v5_data,
+				    &data);
+
+		if (data.have_rsc)
+			ret = iwl_mvm_send_cmd_pdu(mvm, WOWLAN_TSC_RSC_PARAM,
+						   CMD_ASYNC, sizeof(*data.rsc),
+						   data.rsc);
+		else
+			ret = 0;
+		kfree(data.rsc);
+	} else if (ver == 4 || ver == 2 || ver == IWL_FW_CMD_VER_UNKNOWN) {
+		struct wowlan_key_rsc_tsc_data data = {};
+		int size;
+
+		data.rsc_tsc = kzalloc(sizeof(*data.rsc_tsc), GFP_KERNEL);
+		if (!data.rsc_tsc)
+			return -ENOMEM;
+
+		if (ver == 4) {
+			size = sizeof(*data.rsc_tsc);
+			data.rsc_tsc->sta_id = cpu_to_le32(mvmvif->ap_sta_id);
+		} else {
+			/* ver == 2 || ver == IWL_FW_CMD_VER_UNKNOWN */
+			size = sizeof(data.rsc_tsc->params);
+		}
+
+		ieee80211_iter_keys(mvm->hw, vif,
+				    iwl_mvm_wowlan_get_rsc_tsc_data,
+				    &data);
+
+		if (data.have_rsc_tsc)
+			ret = iwl_mvm_send_cmd_pdu(mvm, WOWLAN_TSC_RSC_PARAM,
+						   CMD_ASYNC, size,
+						   data.rsc_tsc);
+		else
+			ret = 0;
+		kfree(data.rsc_tsc);
+	} else {
+		ret = 0;
+		WARN_ON_ONCE(1);
+	}
+
+	return ret;
+}
+
+struct wowlan_key_tkip_data {
+	struct iwl_wowlan_tkip_params_cmd tkip;
+	bool have_tkip_keys;
+};
+
+static void iwl_mvm_wowlan_get_tkip_data(struct ieee80211_hw *hw,
+					 struct ieee80211_vif *vif,
+					 struct ieee80211_sta *sta,
+					 struct ieee80211_key_conf *key,
+					 void *_data)
+{
+	struct wowlan_key_tkip_data *data = _data;
+	struct iwl_p1k_cache *rx_p1ks;
+	u8 *rx_mic_key;
+	struct ieee80211_key_seq seq;
+	u32 cur_rx_iv32 = 0;
+	u16 p1k[IWL_P1K_SIZE];
+	int i;
+
+	switch (key->cipher) {
+	default:
+		break;
+	case WLAN_CIPHER_SUITE_TKIP:
+		if (sta) {
+			u64 pn64;
+
+			rx_p1ks = data->tkip.rx_uni;
+
+			pn64 = atomic64_read(&key->tx_pn);
+
+			ieee80211_get_tkip_p1k_iv(key, TKIP_PN_TO_IV32(pn64),
+						  p1k);
+			iwl_mvm_convert_p1k(p1k, data->tkip.tx.p1k);
+
+			memcpy(data->tkip.mic_keys.tx,
+			       &key->key[NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY],
+			       IWL_MIC_KEY_SIZE);
+
+			rx_mic_key = data->tkip.mic_keys.rx_unicast;
+		} else {
+			rx_p1ks = data->tkip.rx_multi;
+			rx_mic_key = data->tkip.mic_keys.rx_mcast;
+		}
+
+		for (i = 0; i < IWL_NUM_RSC; i++) {
+			/* wrapping isn't allowed, AP must rekey */
+			if (seq.tkip.iv32 > cur_rx_iv32)
+				cur_rx_iv32 = seq.tkip.iv32;
+		}
+
+		ieee80211_get_tkip_rx_p1k(key, vif->bss_conf.bssid,
+					  cur_rx_iv32, p1k);
+		iwl_mvm_convert_p1k(p1k, rx_p1ks[0].p1k);
+		ieee80211_get_tkip_rx_p1k(key, vif->bss_conf.bssid,
+					  cur_rx_iv32 + 1, p1k);
+		iwl_mvm_convert_p1k(p1k, rx_p1ks[1].p1k);
+
+		memcpy(rx_mic_key,
+		       &key->key[NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY],
+		       IWL_MIC_KEY_SIZE);
+
+		data->have_tkip_keys = true;
+		break;
+	}
+}
+
+struct wowlan_key_gtk_type_iter {
+	struct iwl_wowlan_kek_kck_material_cmd_v4 *kek_kck_cmd;
+};
+
+static void iwl_mvm_wowlan_gtk_type_iter(struct ieee80211_hw *hw,
+					 struct ieee80211_vif *vif,
+					 struct ieee80211_sta *sta,
+					 struct ieee80211_key_conf *key,
+					 void *_data)
+{
+	struct wowlan_key_gtk_type_iter *data = _data;
+
+	switch (key->cipher) {
+	default:
+		return;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		data->kek_kck_cmd->igtk_cipher = cpu_to_le32(STA_KEY_FLG_GCMP);
+		return;
+	case WLAN_CIPHER_SUITE_AES_CMAC:
+		data->kek_kck_cmd->igtk_cipher = cpu_to_le32(STA_KEY_FLG_CCM);
+		return;
+	case WLAN_CIPHER_SUITE_CCMP:
+		if (!sta)
+			data->kek_kck_cmd->gtk_cipher =
+				cpu_to_le32(STA_KEY_FLG_CCM);
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		if (!sta)
+			data->kek_kck_cmd->gtk_cipher =
+				cpu_to_le32(STA_KEY_FLG_GCMP);
+		break;
 	}
 }
 
@@ -713,109 +981,81 @@ iwl_mvm_get_wowlan_config(struct iwl_mvm *mvm,
 }
 
 static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
-					    struct ieee80211_vif *vif,
-					    u32 cmd_flags)
+					    struct ieee80211_vif *vif)
 {
-	struct iwl_wowlan_kek_kck_material_cmd_v4 kek_kck_cmd = {};
-	struct iwl_wowlan_kek_kck_material_cmd_v4 *_kek_kck_cmd = &kek_kck_cmd;
-	struct iwl_wowlan_tkip_params_cmd tkip_cmd = {};
 	bool unified = fw_has_capa(&mvm->fw->ucode_capa,
 				   IWL_UCODE_TLV_CAPA_CNSLDTD_D3_D0_IMG);
-	struct wowlan_key_data key_data = {
-		.configure_keys = !unified,
-		.use_rsc_tsc = false,
-		.tkip = &tkip_cmd,
-		.use_tkip = false,
-		.kek_kck_cmd = _kek_kck_cmd,
-	};
+	struct wowlan_key_reprogram_data key_data = {};
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	int ret;
 	u8 cmd_ver;
 	size_t cmd_size;
 
-	key_data.rsc_tsc = kzalloc(sizeof(*key_data.rsc_tsc), GFP_KERNEL);
-	if (!key_data.rsc_tsc)
-		return -ENOMEM;
-
-	/*
-	 * if we have to configure keys, call ieee80211_iter_keys(),
-	 * as we need non-atomic context in order to take the
-	 * required locks.
-	 */
-	/*
-	 * Note that currently we don't propagate cmd_flags
-	 * to the iterator. In case of key_data.configure_keys,
-	 * all the configured commands are SYNC, and
-	 * iwl_mvm_wowlan_program_keys() will take care of
-	 * locking/unlocking mvm->mutex.
-	 */
-	ieee80211_iter_keys(mvm->hw, vif, iwl_mvm_wowlan_program_keys,
-			    &key_data);
+	if (!unified) {
+		/*
+		 * if we have to configure keys, call ieee80211_iter_keys(),
+		 * as we need non-atomic context in order to take the
+		 * required locks.
+		 */
+		/*
+		 * Note that currently we don't use CMD_ASYNC in the iterator.
+		 * In case of key_data.configure_keys, all the configured
+		 * commands are SYNC, and iwl_mvm_wowlan_program_keys() will
+		 * take care of locking/unlocking mvm->mutex.
+		 */
+		ieee80211_iter_keys(mvm->hw, vif, iwl_mvm_wowlan_program_keys,
+				    &key_data);
 
-	if (key_data.error) {
-		ret = -EIO;
-		goto out;
+		if (key_data.error)
+			return -EIO;
 	}
 
-	if (key_data.use_rsc_tsc) {
-		int ver = iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP,
-						WOWLAN_TSC_RSC_PARAM,
-						IWL_FW_CMD_VER_UNKNOWN);
-		int size;
-
-		if (ver == 4) {
-			size = sizeof(*key_data.rsc_tsc);
-			key_data.rsc_tsc->sta_id =
-				cpu_to_le32(mvmvif->ap_sta_id);
-
-		} else if (ver == 2 || ver == IWL_FW_CMD_VER_UNKNOWN) {
-			size = sizeof(key_data.rsc_tsc->params);
-		} else {
-			ret = 0;
-			WARN_ON_ONCE(1);
-			goto out;
-		}
-
-		ret = iwl_mvm_send_cmd_pdu(mvm, WOWLAN_TSC_RSC_PARAM,
-					   cmd_flags,
-					   size,
-					   key_data.rsc_tsc);
-
-		if (ret)
-			goto out;
-	}
+	ret = iwl_mvm_wowlan_config_rsc_tsc(mvm, vif);
+	if (ret)
+		return ret;
 
-	if (key_data.use_tkip &&
-	    !fw_has_api(&mvm->fw->ucode_capa,
+	if (!fw_has_api(&mvm->fw->ucode_capa,
 			IWL_UCODE_TLV_API_TKIP_MIC_KEYS)) {
 		int ver = iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP,
 						WOWLAN_TKIP_PARAM,
 						IWL_FW_CMD_VER_UNKNOWN);
+		struct wowlan_key_tkip_data tkip_data = {};
 		int size;
 
 		if (ver == 2) {
-			size = sizeof(tkip_cmd);
-			key_data.tkip->sta_id =
+			size = sizeof(tkip_data.tkip);
+			tkip_data.tkip.sta_id =
 				cpu_to_le32(mvmvif->ap_sta_id);
 		} else if (ver == 1 || ver == IWL_FW_CMD_VER_UNKNOWN) {
 			size = sizeof(struct iwl_wowlan_tkip_params_cmd_ver_1);
 		} else {
-			ret =  -EINVAL;
 			WARN_ON_ONCE(1);
-			goto out;
+			return -EINVAL;
 		}
 
-		/* send relevant data according to CMD version */
-		ret = iwl_mvm_send_cmd_pdu(mvm,
-					   WOWLAN_TKIP_PARAM,
-					   cmd_flags, size,
-					   &tkip_cmd);
-		if (ret)
-			goto out;
+		ieee80211_iter_keys(mvm->hw, vif, iwl_mvm_wowlan_get_tkip_data,
+				    &tkip_data);
+
+		if (tkip_data.have_tkip_keys) {
+			/* send relevant data according to CMD version */
+			ret = iwl_mvm_send_cmd_pdu(mvm,
+						   WOWLAN_TKIP_PARAM,
+						   CMD_ASYNC, size,
+						   &tkip_data.tkip);
+			if (ret)
+				return ret;
+		}
 	}
 
 	/* configure rekey data only if offloaded rekey is supported (d3) */
 	if (mvmvif->rekey_data.valid) {
+		struct iwl_wowlan_kek_kck_material_cmd_v4 kek_kck_cmd = {};
+		struct iwl_wowlan_kek_kck_material_cmd_v4 *_kek_kck_cmd =
+			&kek_kck_cmd;
+		struct wowlan_key_gtk_type_iter gtk_type_data = {
+			.kek_kck_cmd = _kek_kck_cmd,
+		};
+
 		cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw,
 						IWL_ALWAYS_LONG_GROUP,
 						WOWLAN_KEK_KCK_MATERIAL,
@@ -824,6 +1064,9 @@ static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
 			    cmd_ver != IWL_FW_CMD_VER_UNKNOWN))
 			return -EINVAL;
 
+		ieee80211_iter_keys(mvm->hw, vif, iwl_mvm_wowlan_gtk_type_iter,
+				    &gtk_type_data);
+
 		memcpy(kek_kck_cmd.kck, mvmvif->rekey_data.kck,
 		       mvmvif->rekey_data.kck_len);
 		kek_kck_cmd.kck_len = cpu_to_le16(mvmvif->rekey_data.kck_len);
@@ -851,17 +1094,13 @@ static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
 		IWL_DEBUG_WOWLAN(mvm, "setting akm %d\n",
 				 mvmvif->rekey_data.akm);
 
-		ret = iwl_mvm_send_cmd_pdu(mvm,
-					   WOWLAN_KEK_KCK_MATERIAL, cmd_flags,
-					   cmd_size,
-					   _kek_kck_cmd);
+		ret = iwl_mvm_send_cmd_pdu(mvm, WOWLAN_KEK_KCK_MATERIAL,
+					   CMD_ASYNC, cmd_size, _kek_kck_cmd);
 		if (ret)
-			goto out;
+			return ret;
 	}
-	ret = 0;
-out:
-	kfree(key_data.rsc_tsc);
-	return ret;
+
+	return 0;
 }
 
 static int
@@ -893,7 +1132,7 @@ iwl_mvm_wowlan_config(struct iwl_mvm *mvm,
 	 * that isn't really a problem though.
 	 */
 	mutex_unlock(&mvm->mutex);
-	ret = iwl_mvm_wowlan_config_key_params(mvm, vif, CMD_ASYNC);
+	ret = iwl_mvm_wowlan_config_key_params(mvm, vif);
 	mutex_lock(&mvm->mutex);
 	if (ret)
 		return ret;
@@ -1694,9 +1933,12 @@ iwl_mvm_send_wowlan_get_status(struct iwl_mvm *mvm, u8 sta_id)
 
 		status->gtk[0] = v7->gtk[0];
 		status->igtk[0] = v7->igtk[0];
-	} else if (notif_ver == 9 || notif_ver == 10) {
+	} else if (notif_ver == 9 || notif_ver == 10 || notif_ver == 11) {
 		struct iwl_wowlan_status_v9 *v9 = (void *)cmd.resp_pkt->data;
 
+		/* these three command versions have same layout and size, the
+		 * difference is only in a few not used (reserved) fields.
+		 */
 		status = iwl_mvm_parse_wowlan_status_common_v9(mvm,
 							       cmd.resp_pkt->data,
 							       len);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 95f883aba148..5dc39fbb74d6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -305,7 +305,6 @@ static ssize_t iwl_dbgfs_sar_geo_profile_read(struct file *file,
 	int pos = 0;
 	int bufsz = sizeof(buf);
 	int tbl_idx;
-	u8 *value;
 
 	if (!iwl_mvm_firmware_running(mvm))
 		return -EIO;
@@ -321,16 +320,18 @@ static ssize_t iwl_dbgfs_sar_geo_profile_read(struct file *file,
 		pos = scnprintf(buf, bufsz,
 				"SAR geographic profile disabled\n");
 	} else {
-		value = &mvm->fwrt.geo_profiles[tbl_idx - 1].values[0];
-
 		pos += scnprintf(buf + pos, bufsz - pos,
 				 "Use geographic profile %d\n", tbl_idx);
 		pos += scnprintf(buf + pos, bufsz - pos,
 				 "2.4GHz:\n\tChain A offset: %hhu dBm\n\tChain B offset: %hhu dBm\n\tmax tx power: %hhu dBm\n",
-				 value[1], value[2], value[0]);
+				 mvm->fwrt.geo_profiles[tbl_idx - 1].bands[0].chains[0],
+				 mvm->fwrt.geo_profiles[tbl_idx - 1].bands[0].chains[1],
+				 mvm->fwrt.geo_profiles[tbl_idx - 1].bands[0].max);
 		pos += scnprintf(buf + pos, bufsz - pos,
 				 "5.2GHz:\n\tChain A offset: %hhu dBm\n\tChain B offset: %hhu dBm\n\tmax tx power: %hhu dBm\n",
-				 value[4], value[5], value[3]);
+				 mvm->fwrt.geo_profiles[tbl_idx - 1].bands[1].chains[0],
+				 mvm->fwrt.geo_profiles[tbl_idx - 1].bands[1].chains[1],
+				 mvm->fwrt.geo_profiles[tbl_idx - 1].bands[1].max);
 	}
 	mutex_unlock(&mvm->mutex);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index 59cef0d89a6d..03e5bf5cb909 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -754,6 +754,33 @@ iwl_mvm_ftm_set_ndp_params(struct iwl_mvm *mvm,
 	target->i2r_max_total_ltf = IWL_MVM_FTM_I2R_MAX_TOTAL_LTF;
 }
 
+static int
+iwl_mvm_ftm_put_target_v8(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			  struct cfg80211_pmsr_request_peer *peer,
+			  struct iwl_tof_range_req_ap_entry_v8 *target)
+{
+	u32 flags;
+	int ret = iwl_mvm_ftm_put_target_v7(mvm, vif, peer, (void *)target);
+
+	if (ret)
+		return ret;
+
+	iwl_mvm_ftm_set_ndp_params(mvm, target);
+
+	/*
+	 * If secure LTF is turned off, replace the flag with PMF only
+	 */
+	flags = le32_to_cpu(target->initiator_ap_flags);
+	if ((flags & IWL_INITIATOR_AP_FLAGS_SECURED) &&
+	    !IWL_MVM_FTM_INITIATOR_SECURE_LTF) {
+		flags &= ~IWL_INITIATOR_AP_FLAGS_SECURED;
+		flags |= IWL_INITIATOR_AP_FLAGS_PMF;
+		target->initiator_ap_flags = cpu_to_le32(flags);
+	}
+
+	return 0;
+}
+
 static int iwl_mvm_ftm_start_v12(struct iwl_mvm *mvm,
 				 struct ieee80211_vif *vif,
 				 struct cfg80211_pmsr_request *req)
@@ -773,24 +800,53 @@ static int iwl_mvm_ftm_start_v12(struct iwl_mvm *mvm,
 	for (i = 0; i < cmd.num_of_ap; i++) {
 		struct cfg80211_pmsr_request_peer *peer = &req->peers[i];
 		struct iwl_tof_range_req_ap_entry_v8 *target = &cmd.ap[i];
-		u32 flags;
 
-		err = iwl_mvm_ftm_put_target_v7(mvm, vif, peer, (void *)target);
+		err = iwl_mvm_ftm_put_target_v8(mvm, vif, peer, target);
 		if (err)
 			return err;
+	}
 
-		iwl_mvm_ftm_set_ndp_params(mvm, target);
-
-		/*
-		 * If secure LTF is turned off, replace the flag with PMF only
-		 */
-		flags = le32_to_cpu(target->initiator_ap_flags);
-		if ((flags & IWL_INITIATOR_AP_FLAGS_SECURED) &&
-		    !IWL_MVM_FTM_INITIATOR_SECURE_LTF) {
-			flags &= ~IWL_INITIATOR_AP_FLAGS_SECURED;
-			flags |= IWL_INITIATOR_AP_FLAGS_PMF;
-			target->initiator_ap_flags = cpu_to_le32(flags);
+	return iwl_mvm_ftm_send_cmd(mvm, &hcmd);
+}
+
+static int iwl_mvm_ftm_start_v13(struct iwl_mvm *mvm,
+				 struct ieee80211_vif *vif,
+				 struct cfg80211_pmsr_request *req)
+{
+	struct iwl_tof_range_req_cmd_v13 cmd;
+	struct iwl_host_cmd hcmd = {
+		.id = iwl_cmd_id(TOF_RANGE_REQ_CMD, LOCATION_GROUP, 0),
+		.dataflags[0] = IWL_HCMD_DFL_DUP,
+		.data[0] = &cmd,
+		.len[0] = sizeof(cmd),
+	};
+	u8 i;
+	int err;
+
+	iwl_mvm_ftm_cmd_common(mvm, vif, (void *)&cmd, req);
+
+	for (i = 0; i < cmd.num_of_ap; i++) {
+		struct cfg80211_pmsr_request_peer *peer = &req->peers[i];
+		struct iwl_tof_range_req_ap_entry_v9 *target = &cmd.ap[i];
+
+		err = iwl_mvm_ftm_put_target_v8(mvm, vif, peer, (void *)target);
+		if (err)
+			return err;
+
+		if (peer->ftm.trigger_based || peer->ftm.non_trigger_based)
+			target->bss_color = peer->ftm.bss_color;
+
+		if (peer->ftm.non_trigger_based) {
+			target->min_time_between_msr =
+				cpu_to_le16(IWL_MVM_FTM_NON_TB_MIN_TIME_BETWEEN_MSR);
+			target->burst_period =
+				cpu_to_le16(IWL_MVM_FTM_NON_TB_MAX_TIME_BETWEEN_MSR);
+		} else {
+			target->min_time_between_msr = cpu_to_le16(0);
 		}
+
+		target->band =
+			iwl_mvm_phy_band_from_nl80211(peer->chandef.chan->band);
 	}
 
 	return iwl_mvm_ftm_send_cmd(mvm, &hcmd);
@@ -814,6 +870,9 @@ int iwl_mvm_ftm_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 						   IWL_FW_CMD_VER_UNKNOWN);
 
 		switch (cmd_ver) {
+		case 13:
+			err = iwl_mvm_ftm_start_v13(mvm, vif, req);
+			break;
 		case 12:
 			err = iwl_mvm_ftm_start_v12(mvm, vif, req);
 			break;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
index 5a249ea97eb2..eba5433c2626 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
  */
 #include <net/cfg80211.h>
 #include <linux/etherdevice.h>
@@ -77,7 +77,7 @@ static int iwl_mvm_ftm_responder_set_bw_v2(struct cfg80211_chan_def *chandef,
 
 static void
 iwl_mvm_ftm_responder_set_ndp(struct iwl_mvm *mvm,
-			      struct iwl_tof_responder_config_cmd_v8 *cmd)
+			      struct iwl_tof_responder_config_cmd_v9 *cmd)
 {
 	/* Up to 2 R2I STS are allowed on the responder */
 	u32 r2i_max_sts = IWL_MVM_FTM_R2I_MAX_STS < 2 ?
@@ -104,7 +104,7 @@ iwl_mvm_ftm_responder_cmd(struct iwl_mvm *mvm,
 	 * field interpretation is different), so the same struct can be use
 	 * for all cases.
 	 */
-	struct iwl_tof_responder_config_cmd_v8 cmd = {
+	struct iwl_tof_responder_config_cmd_v9 cmd = {
 		.channel_num = chandef->chan->hw_value,
 		.cmd_valid_fields =
 			cpu_to_le32(IWL_TOF_RESPONDER_CMD_VALID_CHAN_INFO |
@@ -115,10 +115,27 @@ iwl_mvm_ftm_responder_cmd(struct iwl_mvm *mvm,
 	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, LOCATION_GROUP,
 					   TOF_RESPONDER_CONFIG_CMD, 6);
 	int err;
+	int cmd_size;
 
 	lockdep_assert_held(&mvm->mutex);
 
-if (cmd_ver == 8)
+	/* Use a default of bss_color=1 for now */
+	if (cmd_ver == 9) {
+		cmd.cmd_valid_fields |=
+			cpu_to_le32(IWL_TOF_RESPONDER_CMD_VALID_BSS_COLOR |
+				    IWL_TOF_RESPONDER_CMD_VALID_MIN_MAX_TIME_BETWEEN_MSR);
+		cmd.bss_color = 1;
+		cmd.min_time_between_msr =
+			cpu_to_le16(IWL_MVM_FTM_NON_TB_MIN_TIME_BETWEEN_MSR);
+		cmd.max_time_between_msr =
+			cpu_to_le16(IWL_MVM_FTM_NON_TB_MAX_TIME_BETWEEN_MSR);
+		cmd_size = sizeof(struct iwl_tof_responder_config_cmd_v9);
+	} else {
+		/* All versions up to version 8 have the same size */
+		cmd_size = sizeof(struct iwl_tof_responder_config_cmd_v8);
+	}
+
+	if (cmd_ver >= 8)
 		iwl_mvm_ftm_responder_set_ndp(mvm, &cmd);
 
 	if (cmd_ver >= 7)
@@ -137,7 +154,7 @@ if (cmd_ver == 8)
 
 	return iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(TOF_RESPONDER_CONFIG_CMD,
 						    LOCATION_GROUP, 0),
-				    0, sizeof(cmd), &cmd);
+				    0, cmd_size, &cmd);
 }
 
 static int
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 38fd5886af2d..74404c96063b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -743,7 +743,8 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 	/* all structs have the same common part, add it */
 	len += sizeof(cmd.common);
 
-	ret = iwl_sar_select_profile(&mvm->fwrt, per_chain, ACPI_SAR_NUM_TABLES,
+	ret = iwl_sar_select_profile(&mvm->fwrt, per_chain,
+				     IWL_NUM_CHAIN_TABLES,
 				     n_subbands, prof_a, prof_b);
 
 	/* return on error or if the profile is disabled (positive number) */
@@ -1057,16 +1058,7 @@ static const struct dmi_system_id dmi_ppag_approved_list[] = {
 
 static int iwl_mvm_ppag_init(struct iwl_mvm *mvm)
 {
-	int ret;
-
-	ret = iwl_mvm_get_ppag_table(mvm);
-	if (ret < 0) {
-		IWL_DEBUG_RADIO(mvm,
-				"PPAG BIOS table invalid or unavailable. (%d)\n",
-				ret);
-		return 0;
-	}
-
+	/* no need to read the table, done in INIT stage */
 	if (!dmi_check_system(dmi_ppag_approved_list)) {
 		IWL_DEBUG_RADIO(mvm,
 				"System vendor '%s' is not in the approved list, disabling PPAG.\n",
@@ -1191,12 +1183,65 @@ static void iwl_mvm_lari_cfg(struct iwl_mvm *mvm)
 					ret);
 	}
 }
+
+void iwl_mvm_get_acpi_tables(struct iwl_mvm *mvm)
+{
+	int ret;
+
+	/* read PPAG table */
+	ret = iwl_mvm_get_ppag_table(mvm);
+	if (ret < 0) {
+		IWL_DEBUG_RADIO(mvm,
+				"PPAG BIOS table invalid or unavailable. (%d)\n",
+				ret);
+	}
+
+	/* read SAR tables */
+	ret = iwl_sar_get_wrds_table(&mvm->fwrt);
+	if (ret < 0) {
+		IWL_DEBUG_RADIO(mvm,
+				"WRDS SAR BIOS table invalid or unavailable. (%d)\n",
+				ret);
+		/*
+		 * If not available, don't fail and don't bother with EWRD and
+		 * WGDS */
+
+		if (!iwl_sar_get_wgds_table(&mvm->fwrt)) {
+			/*
+			 * If basic SAR is not available, we check for WGDS,
+			 * which should *not* be available either.  If it is
+			 * available, issue an error, because we can't use SAR
+			 * Geo without basic SAR.
+			 */
+			IWL_ERR(mvm, "BIOS contains WGDS but no WRDS\n");
+		}
+
+	} else {
+		ret = iwl_sar_get_ewrd_table(&mvm->fwrt);
+		/* if EWRD is not available, we can still use
+		* WRDS, so don't fail */
+		if (ret < 0)
+			IWL_DEBUG_RADIO(mvm,
+					"EWRD SAR BIOS table invalid or unavailable. (%d)\n",
+					ret);
+
+		/* read geo SAR table */
+		if (iwl_sar_geo_support(&mvm->fwrt)) {
+			ret = iwl_sar_get_wgds_table(&mvm->fwrt);
+			if (ret < 0)
+				IWL_DEBUG_RADIO(mvm,
+						"Geo SAR BIOS table invalid or unavailable. (%d)\n",
+						ret);
+				/* we don't fail if the table is not available */
+		}
+	}
+}
 #else /* CONFIG_ACPI */
 
 inline int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm,
 				      int prof_a, int prof_b)
 {
-	return -ENOENT;
+	return 1;
 }
 
 inline int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm)
@@ -1231,6 +1276,10 @@ static u8 iwl_mvm_eval_dsm_rfi(struct iwl_mvm *mvm)
 {
 	return DSM_VALUE_RFI_DISABLE;
 }
+
+void iwl_mvm_get_acpi_tables(struct iwl_mvm *mvm)
+{
+}
 #endif /* CONFIG_ACPI */
 
 void iwl_mvm_send_recovery_cmd(struct iwl_mvm *mvm, u32 flags)
@@ -1286,27 +1335,6 @@ void iwl_mvm_send_recovery_cmd(struct iwl_mvm *mvm, u32 flags)
 
 static int iwl_mvm_sar_init(struct iwl_mvm *mvm)
 {
-	int ret;
-
-	ret = iwl_sar_get_wrds_table(&mvm->fwrt);
-	if (ret < 0) {
-		IWL_DEBUG_RADIO(mvm,
-				"WRDS SAR BIOS table invalid or unavailable. (%d)\n",
-				ret);
-		/*
-		 * If not available, don't fail and don't bother with EWRD.
-		 * Return 1 to tell that we can't use WGDS either.
-		 */
-		return 1;
-	}
-
-	ret = iwl_sar_get_ewrd_table(&mvm->fwrt);
-	/* if EWRD is not available, we can still use WRDS, so don't fail */
-	if (ret < 0)
-		IWL_DEBUG_RADIO(mvm,
-				"EWRD SAR BIOS table invalid or unavailable. (%d)\n",
-				ret);
-
 	return iwl_mvm_sar_select_profile(mvm, 1, 1);
 }
 
@@ -1542,19 +1570,9 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 		goto error;
 
 	ret = iwl_mvm_sar_init(mvm);
-	if (ret == 0) {
+	if (ret == 0)
 		ret = iwl_mvm_sar_geo_init(mvm);
-	} else if (ret == -ENOENT && !iwl_sar_get_wgds_table(&mvm->fwrt)) {
-		/*
-		 * If basic SAR is not available, we check for WGDS,
-		 * which should *not* be available either.  If it is
-		 * available, issue an error, because we can't use SAR
-		 * Geo without basic SAR.
-		 */
-		IWL_ERR(mvm, "BIOS contains WGDS but no WRDS\n");
-	}
-
-	if (ret < 0)
+	else if (ret < 0)
 		goto error;
 
 	iwl_mvm_tas_init(mvm);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index fd5e08961651..fd352b2624a6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2020 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2021 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -647,12 +647,14 @@ static int iwl_mvm_mac_ctxt_cmd_sta(struct iwl_mvm *mvm,
 
 	if (vif->bss_conf.he_support && !iwlwifi_mod_params.disable_11ax) {
 		cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_11AX);
-		if (vif->bss_conf.twt_requester && IWL_MVM_USE_TWT) {
+		if (vif->bss_conf.twt_requester && IWL_MVM_USE_TWT)
 			ctxt_sta->data_policy |= cpu_to_le32(TWT_SUPPORTED);
-			if (vif->bss_conf.twt_protected)
-				ctxt_sta->data_policy |=
-					cpu_to_le32(PROTECTED_TWT_SUPPORTED);
-		}
+		if (vif->bss_conf.twt_protected)
+			ctxt_sta->data_policy |=
+				cpu_to_le32(PROTECTED_TWT_SUPPORTED);
+		if (vif->bss_conf.twt_broadcast)
+			ctxt_sta->data_policy |=
+				cpu_to_le32(BROADCAST_TWT_SUPPORTED);
 	}
 
 
@@ -1005,8 +1007,10 @@ int iwl_mvm_mac_ctxt_beacon_changed(struct iwl_mvm *mvm,
 		return -ENOMEM;
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
-	if (mvm->beacon_inject_active)
+	if (mvm->beacon_inject_active) {
+		dev_kfree_skb(beacon);
 		return -EBUSY;
+	}
 #endif
 
 	ret = iwl_mvm_mac_ctxt_send_beacon(mvm, vif, beacon);
@@ -1427,14 +1431,34 @@ void iwl_mvm_rx_stored_beacon_notif(struct iwl_mvm *mvm,
 {
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	unsigned int pkt_len = iwl_rx_packet_payload_len(pkt);
-	struct iwl_stored_beacon_notif *sb = (void *)pkt->data;
+	struct iwl_stored_beacon_notif_common *sb = (void *)pkt->data;
 	struct ieee80211_rx_status rx_status;
 	struct sk_buff *skb;
+	u8 *data;
 	u32 size = le32_to_cpu(sb->byte_count);
+	int ver = iwl_fw_lookup_cmd_ver(mvm->fw, PROT_OFFLOAD_GROUP,
+					STORED_BEACON_NTF, 0);
 
-	if (size == 0 || pkt_len < struct_size(sb, data, size))
+	if (size == 0)
 		return;
 
+	/* handle per-version differences */
+	if (ver <= 2) {
+		struct iwl_stored_beacon_notif_v2 *sb_v2 = (void *)pkt->data;
+
+		if (pkt_len < struct_size(sb_v2, data, size))
+			return;
+
+		data = sb_v2->data;
+	} else {
+		struct iwl_stored_beacon_notif_v3 *sb_v3 = (void *)pkt->data;
+
+		if (pkt_len < struct_size(sb_v3, data, size))
+			return;
+
+		data = sb_v3->data;
+	}
+
 	skb = alloc_skb(size, GFP_ATOMIC);
 	if (!skb) {
 		IWL_ERR(mvm, "alloc_skb failed\n");
@@ -1455,7 +1479,7 @@ void iwl_mvm_rx_stored_beacon_notif(struct iwl_mvm *mvm,
 					       rx_status.band);
 
 	/* copy the data */
-	skb_put_data(skb, sb->data, size);
+	skb_put_data(skb, data, size);
 	memcpy(IEEE80211_SKB_RXCB(skb), &rx_status, sizeof(rx_status));
 
 	/* pass it as regular rx to mac80211 */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 70ebecb73c24..3a4585222d6d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -390,7 +390,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	if (mvm->trans->max_skb_frags)
 		hw->netdev_features = NETIF_F_HIGHDMA | NETIF_F_SG;
 
-	hw->queues = IEEE80211_MAX_QUEUES;
+	hw->queues = IEEE80211_NUM_ACS;
 	hw->offchannel_tx_hw_queue = IWL_MVM_OFFCHANNEL_QUEUE;
 	hw->radiotap_mcs_details |= IEEE80211_RADIOTAP_MCS_HAVE_FEC |
 				    IEEE80211_RADIOTAP_MCS_HAVE_STBC;
@@ -762,11 +762,11 @@ static void iwl_mvm_mac_tx(struct ieee80211_hw *hw,
 	    !test_bit(IWL_MVM_STATUS_ROC_AUX_RUNNING, &mvm->status))
 		goto drop;
 
-	/* treat non-bufferable MMPDUs on AP interfaces as broadcast */
-	if ((info->control.vif->type == NL80211_IFTYPE_AP ||
-	     info->control.vif->type == NL80211_IFTYPE_ADHOC) &&
-	    ieee80211_is_mgmt(hdr->frame_control) &&
-	    !ieee80211_is_bufferable_mmpdu(hdr->frame_control))
+	/*
+	 * bufferable MMPDUs or MMPDUs on STA interfaces come via TXQs
+	 * so we treat the others as broadcast
+	 */
+	if (ieee80211_is_mgmt(hdr->frame_control))
 		sta = NULL;
 
 	/* If there is no sta, and it's not offchannel - send through AP */
@@ -2440,6 +2440,9 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 		IWL_DEBUG_MAC80211(mvm, "arp filter changed\n");
 		iwl_mvm_configure_bcast_filter(mvm);
 	}
+
+	if (changes & BSS_CHANGED_BANDWIDTH)
+		iwl_mvm_apply_fw_smps_request(vif);
 }
 
 static int iwl_mvm_start_ap_ibss(struct ieee80211_hw *hw,
@@ -2987,16 +2990,20 @@ static void iwl_mvm_check_he_obss_narrow_bw_ru_iter(struct wiphy *wiphy,
 						    void *_data)
 {
 	struct iwl_mvm_he_obss_narrow_bw_ru_data *data = _data;
+	const struct cfg80211_bss_ies *ies;
 	const struct element *elem;
 
-	elem = cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, bss->ies->data,
-				  bss->ies->len);
+	rcu_read_lock();
+	ies = rcu_dereference(bss->ies);
+	elem = cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, ies->data,
+				  ies->len);
 
 	if (!elem || elem->datalen < 10 ||
 	    !(elem->data[10] &
 	      WLAN_EXT_CAPA10_OBSS_NARROW_BW_RU_TOLERANCE_SUPPORT)) {
 		data->tolerated = false;
 	}
+	rcu_read_unlock();
 }
 
 static void iwl_mvm_check_he_obss_narrow_bw_ru(struct ieee80211_hw *hw,
@@ -5035,22 +5042,14 @@ static void iwl_mvm_event_mlme_callback_ini(struct iwl_mvm *mvm,
 					    struct ieee80211_vif *vif,
 					    const  struct ieee80211_mlme_event *mlme)
 {
-	if (mlme->data == ASSOC_EVENT && (mlme->status == MLME_DENIED ||
-					  mlme->status == MLME_TIMEOUT)) {
+	if ((mlme->data == ASSOC_EVENT || mlme->data == AUTH_EVENT) &&
+	    (mlme->status == MLME_DENIED || mlme->status == MLME_TIMEOUT)) {
 		iwl_dbg_tlv_time_point(&mvm->fwrt,
 				       IWL_FW_INI_TIME_POINT_ASSOC_FAILED,
 				       NULL);
 		return;
 	}
 
-	if (mlme->data == AUTH_EVENT && (mlme->status == MLME_DENIED ||
-					 mlme->status == MLME_TIMEOUT)) {
-		iwl_dbg_tlv_time_point(&mvm->fwrt,
-				       IWL_FW_INI_TIME_POINT_EAPOL_FAILED,
-				       NULL);
-		return;
-	}
-
 	if (mlme->data == DEAUTH_RX_EVENT || mlme->data == DEAUTH_TX_EVENT) {
 		iwl_dbg_tlv_time_point(&mvm->fwrt,
 				       IWL_FW_INI_TIME_POINT_DEASSOC,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index b50942f28bb7..f877d86b038e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -431,8 +431,6 @@ struct iwl_mvm_vif {
 static inline struct iwl_mvm_vif *
 iwl_mvm_vif_from_mac80211(struct ieee80211_vif *vif)
 {
-	if (!vif)
-		return NULL;
 	return (void *)vif->drv_priv;
 }
 
@@ -2045,6 +2043,7 @@ void iwl_mvm_event_frame_timeout_callback(struct iwl_mvm *mvm,
 int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b);
 int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm);
 int iwl_mvm_ppag_send_cmd(struct iwl_mvm *mvm);
+void iwl_mvm_get_acpi_tables(struct iwl_mvm *mvm);
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 void iwl_mvm_sta_add_debugfs(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
index 7fb4e618f76e..da705fcaf0fc 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2019 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2019, 2021 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -416,7 +416,7 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2,
 	struct iwl_rx_packet *pkt;
 	struct iwl_host_cmd cmd = {
 		.id = MCC_UPDATE_CMD,
-		.flags = CMD_WANT_SKB,
+		.flags = CMD_WANT_SKB | CMD_SEND_IN_RFKILL,
 		.data = { &mcc_update_cmd },
 	};
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 20e8d343a950..6f60018feed1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -78,7 +78,6 @@ module_exit(iwl_mvm_exit);
 static void iwl_mvm_nic_config(struct iwl_op_mode *op_mode)
 {
 	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
-	struct iwl_trans_debug *dbg = &mvm->trans->dbg;
 	u8 radio_cfg_type, radio_cfg_step, radio_cfg_dash;
 	u32 reg_val = 0;
 	u32 phy_config = iwl_mvm_get_phy_config(mvm);
@@ -115,10 +114,7 @@ static void iwl_mvm_nic_config(struct iwl_op_mode *op_mode)
 	if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_8000)
 		reg_val |= CSR_HW_IF_CONFIG_REG_BIT_RADIO_SI;
 
-	if (iwl_fw_dbg_is_d3_debug_enabled(&mvm->fwrt) ||
-	    (iwl_trans_dbg_ini_valid(mvm->trans) &&
-	     dbg->fw_mon_cfg[IWL_FW_INI_ALLOCATION_ID_INTERNAL].buf_location)
-	    )
+	if (iwl_fw_dbg_is_d3_debug_enabled(&mvm->fwrt))
 		reg_val |= CSR_HW_IF_CONFIG_REG_D3_DEBUG;
 
 	iwl_trans_set_bits_mask(mvm->trans, CSR_HW_IF_CONFIG_REG,
@@ -214,11 +210,14 @@ void iwl_mvm_apply_fw_smps_request(struct ieee80211_vif *vif)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	struct iwl_mvm *mvm = mvmvif->mvm;
+	enum ieee80211_smps_mode mode = IEEE80211_SMPS_AUTOMATIC;
 
-	iwl_mvm_update_smps(mvm, vif, IWL_MVM_SMPS_REQ_FW,
-			    mvm->fw_static_smps_request ?
-				IEEE80211_SMPS_STATIC :
-				IEEE80211_SMPS_AUTOMATIC);
+	if (mvm->fw_static_smps_request &&
+	    vif->bss_conf.chandef.width == NL80211_CHAN_WIDTH_160 &&
+	    vif->bss_conf.he_support)
+		mode = IEEE80211_SMPS_STATIC;
+
+	iwl_mvm_update_smps(mvm, vif, IWL_MVM_SMPS_REQ_FW, mode);
 }
 
 static void iwl_mvm_intf_dual_chain_req(void *data, u8 *mac,
@@ -374,7 +373,7 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = {
 		       struct iwl_mfu_assert_dump_notif),
 	RX_HANDLER_GRP(PROT_OFFLOAD_GROUP, STORED_BEACON_NTF,
 		       iwl_mvm_rx_stored_beacon_notif, RX_HANDLER_SYNC,
-		       struct iwl_stored_beacon_notif),
+		       struct iwl_stored_beacon_notif_v2),
 	RX_HANDLER_GRP(DATA_PATH_GROUP, MU_GROUP_MGMT_NOTIF,
 		       iwl_mvm_mu_mimo_grp_notif, RX_HANDLER_SYNC,
 		       struct iwl_mu_group_mgmt_notif),
@@ -693,11 +692,16 @@ static int iwl_mvm_start_get_nvm(struct iwl_mvm *mvm)
 
 	if (ret && ret != -ERFKILL)
 		iwl_fw_dbg_error_collect(&mvm->fwrt, FW_DBG_TRIGGER_DRIVER);
+	if (!ret && iwl_mvm_is_lar_supported(mvm)) {
+		mvm->hw->wiphy->regulatory_flags |= REGULATORY_WIPHY_SELF_MANAGED;
+		ret = iwl_mvm_init_mcc(mvm);
+	}
 
 	if (!iwlmvm_mod_params.init_dbg || !ret)
 		iwl_mvm_stop_device(mvm);
 
 	mutex_unlock(&mvm->mutex);
+	rtnl_unlock();
 
 	if (ret < 0)
 		IWL_ERR(mvm, "Failed to run INIT ucode: %d\n", ret);
@@ -772,6 +776,8 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	iwl_fw_runtime_init(&mvm->fwrt, trans, fw, &iwl_mvm_fwrt_ops, mvm,
 			    dbgfs_dir);
 
+	iwl_mvm_get_acpi_tables(mvm);
+
 	mvm->init_status = 0;
 
 	if (iwl_mvm_has_new_rx_api(mvm)) {
@@ -792,10 +798,26 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 	mvm->fw_restart = iwlwifi_mod_params.fw_restart ? -1 : 0;
 
-	mvm->aux_queue = IWL_MVM_DQA_AUX_QUEUE;
-	mvm->snif_queue = IWL_MVM_DQA_INJECT_MONITOR_QUEUE;
-	mvm->probe_queue = IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
-	mvm->p2p_dev_queue = IWL_MVM_DQA_P2P_DEVICE_QUEUE;
+	if (iwl_mvm_has_new_tx_api(mvm)) {
+		/*
+		 * If we have the new TX/queue allocation API initialize them
+		 * all to invalid numbers. We'll rewrite the ones that we need
+		 * later, but that doesn't happen for all of them all of the
+		 * time (e.g. P2P Device is optional), and if a dynamic queue
+		 * ends up getting number 2 (IWL_MVM_DQA_P2P_DEVICE_QUEUE) then
+		 * iwl_mvm_is_static_queue() erroneously returns true, and we
+		 * might have things getting stuck.
+		 */
+		mvm->aux_queue = IWL_MVM_INVALID_QUEUE;
+		mvm->snif_queue = IWL_MVM_INVALID_QUEUE;
+		mvm->probe_queue = IWL_MVM_INVALID_QUEUE;
+		mvm->p2p_dev_queue = IWL_MVM_INVALID_QUEUE;
+	} else {
+		mvm->aux_queue = IWL_MVM_DQA_AUX_QUEUE;
+		mvm->snif_queue = IWL_MVM_DQA_INJECT_MONITOR_QUEUE;
+		mvm->probe_queue = IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
+		mvm->p2p_dev_queue = IWL_MVM_DQA_P2P_DEVICE_QUEUE;
+	}
 
 	mvm->sf_state = SF_UNINIT;
 	if (iwl_mvm_has_unified_ucode(mvm))
@@ -1400,7 +1422,7 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error)
 	 * can't recover this since we're already half suspended.
 	 */
 	if (!mvm->fw_restart && fw_error) {
-		iwl_fw_error_collect(&mvm->fwrt);
+		iwl_fw_error_collect(&mvm->fwrt, false);
 	} else if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) {
 		struct iwl_mvm_reprobe *reprobe;
 
@@ -1451,7 +1473,7 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error)
 			}
 		}
 
-		iwl_fw_error_collect(&mvm->fwrt);
+		iwl_fw_error_collect(&mvm->fwrt, false);
 
 		if (fw_error && mvm->fw_restart > 0)
 			mvm->fw_restart--;
@@ -1459,13 +1481,31 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error)
 	}
 }
 
-static void iwl_mvm_nic_error(struct iwl_op_mode *op_mode)
+static void iwl_mvm_nic_error(struct iwl_op_mode *op_mode, bool sync)
 {
 	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
 
 	if (!test_bit(STATUS_TRANS_DEAD, &mvm->trans->status))
 		iwl_mvm_dump_nic_error_log(mvm);
 
+	if (sync) {
+		iwl_fw_error_collect(&mvm->fwrt, true);
+		/*
+		 * Currently, the only case for sync=true is during
+		 * shutdown, so just stop in this case. If/when that
+		 * changes, we need to be a bit smarter here.
+		 */
+		return;
+	}
+
+	/*
+	 * If the firmware crashes while we're already considering it
+	 * to be dead then don't ask for a restart, that cannot do
+	 * anything useful anyway.
+	 */
+	if (!test_bit(IWL_MVM_STATUS_FIRMWARE_RUNNING, &mvm->status))
+		return;
+
 	iwl_mvm_nic_restart(mvm, true);
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c
index 0b818067067c..44344216a1a9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c
@@ -11,7 +11,7 @@
  * DDR needs frequency in units of 16.666MHz, so provide FW with the
  * frequency values in the adjusted format.
  */
-const static struct iwl_rfi_lut_entry iwl_rfi_table[IWL_RFI_LUT_SIZE] = {
+static const struct iwl_rfi_lut_entry iwl_rfi_table[IWL_RFI_LUT_SIZE] = {
 	/* LPDDR4 */
 
 	/* frequency 3733MHz */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index c0babb8d5b5c..c12f303cf652 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -69,8 +69,8 @@ static inline int iwl_mvm_check_pn(struct iwl_mvm *mvm, struct sk_buff *skb,
 
 	/* if we are here - this for sure is either CCMP or GCMP */
 	if (IS_ERR_OR_NULL(sta)) {
-		IWL_ERR(mvm,
-			"expected hw-decrypted unicast frame for station\n");
+		IWL_DEBUG_DROP(mvm,
+			       "expected hw-decrypted unicast frame for station\n");
 		return -1;
 	}
 
@@ -279,7 +279,6 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta,
 {
 	struct iwl_mvm_sta *mvmsta;
 	struct iwl_mvm_vif *mvmvif;
-	u8 fwkeyid = u32_get_bits(status, IWL_RX_MPDU_STATUS_KEY);
 	u8 keyid;
 	struct ieee80211_key_conf *key;
 	u32 len = le16_to_cpu(desc->mpdu_len);
@@ -299,6 +298,10 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta,
 	if (!ieee80211_is_beacon(hdr->frame_control))
 		return 0;
 
+	/* key mismatch - will also report !MIC_OK but we shouldn't count it */
+	if (!(status & IWL_RX_MPDU_STATUS_KEY_VALID))
+		return -1;
+
 	/* good cases */
 	if (likely(status & IWL_RX_MPDU_STATUS_MIC_OK &&
 		   !(status & IWL_RX_MPDU_STATUS_REPLAY_ERROR)))
@@ -309,26 +312,36 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta,
 
 	mvmsta = iwl_mvm_sta_from_mac80211(sta);
 
-	/* what? */
-	if (fwkeyid != 6 && fwkeyid != 7)
-		return -1;
-
 	mvmvif = iwl_mvm_vif_from_mac80211(mvmsta->vif);
 
-	key = rcu_dereference(mvmvif->bcn_prot.keys[fwkeyid - 6]);
-	if (!key)
-		return -1;
+	/*
+	 * both keys will have the same cipher and MIC length, use
+	 * whichever one is available
+	 */
+	key = rcu_dereference(mvmvif->bcn_prot.keys[0]);
+	if (!key) {
+		key = rcu_dereference(mvmvif->bcn_prot.keys[1]);
+		if (!key)
+			return -1;
+	}
 
 	if (len < key->icv_len + IEEE80211_GMAC_PN_LEN + 2)
 		return -1;
 
-	/*
-	 * See if the key ID matches - if not this may be due to a
-	 * switch and the firmware may erroneously report !MIC_OK.
-	 */
+	/* get the real key ID */
 	keyid = frame[len - key->icv_len - IEEE80211_GMAC_PN_LEN - 2];
-	if (keyid != fwkeyid)
-		return -1;
+	/* and if that's the other key, look it up */
+	if (keyid != key->keyidx) {
+		/*
+		 * shouldn't happen since firmware checked, but be safe
+		 * in case the MIC length is wrong too, for example
+		 */
+		if (keyid != 6 && keyid != 7)
+			return -1;
+		key = rcu_dereference(mvmvif->bcn_prot.keys[keyid - 6]);
+		if (!key)
+			return -1;
+	}
 
 	/* Report status to mac80211 */
 	if (!(status & IWL_RX_MPDU_STATUS_MIC_OK))
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 0368b7101222..d78e436fa8b5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1648,7 +1648,7 @@ iwl_mvm_umac_scan_cfg_channels_v6(struct iwl_mvm *mvm,
 		struct iwl_scan_channel_cfg_umac *cfg = &cp->channel_config[i];
 		u32 n_aps_flag =
 			iwl_mvm_scan_ch_n_aps_flag(vif_type,
-						   cfg->v2.channel_num);
+						   channels[i]->hw_value);
 
 		cfg->flags = cpu_to_le32(flags | n_aps_flag);
 		cfg->v2.channel_num = channels[i]->hw_value;
@@ -1661,22 +1661,32 @@ iwl_mvm_umac_scan_cfg_channels_v6(struct iwl_mvm *mvm,
 }
 
 static int
-iwl_mvm_umac_scan_fill_6g_chan_list(struct iwl_mvm_scan_params *params,
-				    __le32 *cmd_short_ssid, u8 *cmd_bssid,
-				    u8 *scan_ssid_num, u8 *bssid_num)
+iwl_mvm_umac_scan_fill_6g_chan_list(struct iwl_mvm *mvm,
+				    struct iwl_mvm_scan_params *params,
+				     struct iwl_scan_probe_params_v4 *pp)
 {
 	int j, idex_s = 0, idex_b = 0;
 	struct cfg80211_scan_6ghz_params *scan_6ghz_params =
 		params->scan_6ghz_params;
+	bool hidden_supported = fw_has_capa(&mvm->fw->ucode_capa,
+					    IWL_UCODE_TLV_CAPA_HIDDEN_6GHZ_SCAN);
 
-	if (!params->n_6ghz_params) {
-		for (j = 0; j < params->n_ssids; j++) {
-			cmd_short_ssid[idex_s++] =
-				cpu_to_le32(~crc32_le(~0, params->ssids[j].ssid,
-						      params->ssids[j].ssid_len));
-			(*scan_ssid_num)++;
+	for (j = 0; j < params->n_ssids && idex_s < SCAN_SHORT_SSID_MAX_SIZE;
+	     j++) {
+		if (!params->ssids[j].ssid_len)
+			continue;
+
+		pp->short_ssid[idex_s] =
+			cpu_to_le32(~crc32_le(~0, params->ssids[j].ssid,
+					      params->ssids[j].ssid_len));
+
+		if (hidden_supported) {
+			pp->direct_scan[idex_s].id = WLAN_EID_SSID;
+			pp->direct_scan[idex_s].len = params->ssids[j].ssid_len;
+			memcpy(pp->direct_scan[idex_s].ssid, params->ssids[j].ssid,
+			       params->ssids[j].ssid_len);
 		}
-		return 0;
+		idex_s++;
 	}
 
 	/*
@@ -1693,40 +1703,40 @@ iwl_mvm_umac_scan_fill_6g_chan_list(struct iwl_mvm_scan_params *params,
 		/* First, try to place the short SSID */
 		if (scan_6ghz_params[j].short_ssid_valid) {
 			for (k = 0; k < idex_s; k++) {
-				if (cmd_short_ssid[k] ==
+				if (pp->short_ssid[k] ==
 				    cpu_to_le32(scan_6ghz_params[j].short_ssid))
 					break;
 			}
 
 			if (k == idex_s && idex_s < SCAN_SHORT_SSID_MAX_SIZE) {
-				cmd_short_ssid[idex_s++] =
+				pp->short_ssid[idex_s++] =
 					cpu_to_le32(scan_6ghz_params[j].short_ssid);
-				(*scan_ssid_num)++;
 			}
 		}
 
 		/* try to place BSSID for the same entry */
 		for (k = 0; k < idex_b; k++) {
-			if (!memcmp(&cmd_bssid[ETH_ALEN * k],
+			if (!memcmp(&pp->bssid_array[k],
 				    scan_6ghz_params[j].bssid, ETH_ALEN))
 				break;
 		}
 
 		if (k == idex_b && idex_b < SCAN_BSSID_MAX_SIZE) {
-			memcpy(&cmd_bssid[ETH_ALEN * idex_b++],
+			memcpy(&pp->bssid_array[idex_b++],
 			       scan_6ghz_params[j].bssid, ETH_ALEN);
-			(*bssid_num)++;
 		}
 	}
+
+	pp->short_ssid_num = idex_s;
+	pp->bssid_num = idex_b;
 	return 0;
 }
 
 /* TODO: this function can be merged with iwl_mvm_scan_umac_fill_ch_p_v6 */
 static void
 iwl_mvm_umac_scan_cfg_channels_v6_6g(struct iwl_mvm_scan_params *params,
-				     u32 n_channels, __le32 *cmd_short_ssid,
-				     u8 *cmd_bssid, u8 scan_ssid_num,
-				     u8 bssid_num,
+				     u32 n_channels,
+				     struct iwl_scan_probe_params_v4 *pp,
 				     struct iwl_scan_channel_params_v6 *cp,
 				     enum nl80211_iftype vif_type)
 {
@@ -1741,7 +1751,7 @@ iwl_mvm_umac_scan_cfg_channels_v6_6g(struct iwl_mvm_scan_params *params,
 
 		u32 s_ssid_bitmap = 0, bssid_bitmap = 0, flags = 0;
 		u8 j, k, s_max = 0, b_max = 0, n_used_bssid_entries;
-		bool force_passive, found = false,
+		bool force_passive, found = false, allow_passive = true,
 		     unsolicited_probe_on_chan = false, psc_no_listen = false;
 
 		cfg->v1.channel_num = params->channels[i]->hw_value;
@@ -1766,9 +1776,9 @@ iwl_mvm_umac_scan_cfg_channels_v6_6g(struct iwl_mvm_scan_params *params,
 				scan_6ghz_params[j].unsolicited_probe;
 			psc_no_listen |= scan_6ghz_params[j].psc_no_listen;
 
-			for (k = 0; k < scan_ssid_num; k++) {
+			for (k = 0; k < pp->short_ssid_num; k++) {
 				if (!scan_6ghz_params[j].unsolicited_probe &&
-				    le32_to_cpu(cmd_short_ssid[k]) ==
+				    le32_to_cpu(pp->short_ssid[k]) ==
 				    scan_6ghz_params[j].short_ssid) {
 					/* Relevant short SSID bit set */
 					if (s_ssid_bitmap & BIT(k)) {
@@ -1778,7 +1788,10 @@ iwl_mvm_umac_scan_cfg_channels_v6_6g(struct iwl_mvm_scan_params *params,
 
 					/*
 					 * Use short SSID only to create a new
-					 * iteration during channel dwell.
+					 * iteration during channel dwell or in
+					 * case that the short SSID has a
+					 * matching SSID, i.e., scan for hidden
+					 * APs.
 					 */
 					if (n_used_bssid_entries >= 3) {
 						s_ssid_bitmap |= BIT(k);
@@ -1786,6 +1799,12 @@ iwl_mvm_umac_scan_cfg_channels_v6_6g(struct iwl_mvm_scan_params *params,
 						n_used_bssid_entries -= 3;
 						found = true;
 						break;
+					} else if (pp->direct_scan[k].len) {
+						s_ssid_bitmap |= BIT(k);
+						s_max++;
+						found = true;
+						allow_passive = false;
+						break;
 					}
 				}
 			}
@@ -1793,8 +1812,8 @@ iwl_mvm_umac_scan_cfg_channels_v6_6g(struct iwl_mvm_scan_params *params,
 			if (found)
 				continue;
 
-			for (k = 0; k < bssid_num; k++) {
-				if (!memcmp(&cmd_bssid[ETH_ALEN * k],
+			for (k = 0; k < pp->bssid_num; k++) {
+				if (!memcmp(&pp->bssid_array[k],
 					    scan_6ghz_params[j].bssid,
 					    ETH_ALEN)) {
 					if (!(bssid_bitmap & BIT(k))) {
@@ -1849,7 +1868,7 @@ iwl_mvm_umac_scan_cfg_channels_v6_6g(struct iwl_mvm_scan_params *params,
 			force_passive |= (unsolicited_probe_on_chan &&
 					  (s_max > 1 || b_max > 3));
 		}
-		if (force_passive ||
+		if ((allow_passive && force_passive) ||
 		    (!flags && !cfg80211_channel_is_psc(params->channels[i])))
 			flags |= IWL_UHB_CHAN_CFG_FLAG_FORCE_PASSIVE;
 
@@ -2368,32 +2387,28 @@ static int iwl_mvm_scan_umac_v14(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	if (ret)
 		return ret;
 
-	iwl_mvm_scan_umac_fill_probe_p_v4(params, &scan_p->probe_params,
-					  &bitmap_ssid);
 	if (!params->scan_6ghz) {
+		iwl_mvm_scan_umac_fill_probe_p_v4(params, &scan_p->probe_params,
+					  &bitmap_ssid);
 		iwl_mvm_scan_umac_fill_ch_p_v6(mvm, params, vif,
-					       &scan_p->channel_params, bitmap_ssid);
+				       &scan_p->channel_params, bitmap_ssid);
 
 		return 0;
+	} else {
+		pb->preq = params->preq;
 	}
+
 	cp->flags = iwl_mvm_scan_umac_chan_flags_v2(mvm, params, vif);
 	cp->n_aps_override[0] = IWL_SCAN_ADWELL_N_APS_GO_FRIENDLY;
 	cp->n_aps_override[1] = IWL_SCAN_ADWELL_N_APS_SOCIAL_CHS;
 
-	ret = iwl_mvm_umac_scan_fill_6g_chan_list(params, pb->short_ssid,
-						  pb->bssid_array[0],
-						  &pb->short_ssid_num,
-						  &pb->bssid_num);
+	ret = iwl_mvm_umac_scan_fill_6g_chan_list(mvm, params, pb);
 	if (ret)
 		return ret;
 
 	iwl_mvm_umac_scan_cfg_channels_v6_6g(params,
 					     params->n_channels,
-					     pb->short_ssid,
-					     pb->bssid_array[0],
-					     pb->short_ssid_num,
-					     pb->bssid_num, cp,
-					     vif->type);
+					     pb, cp, vif->type);
 	cp->count = params->n_channels;
 	if (!params->n_ssids ||
 	    (params->n_ssids == 1 && !params->ssids[0].ssid_len))
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 9c45a64c5009..a64874c05ced 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -316,8 +316,9 @@ static int iwl_mvm_invalidate_sta_queue(struct iwl_mvm *mvm, int queue,
 }
 
 static int iwl_mvm_disable_txq(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
-			       int queue, u8 tid, u8 flags)
+			       u16 *queueptr, u8 tid, u8 flags)
 {
+	int queue = *queueptr;
 	struct iwl_scd_txq_cfg_cmd cmd = {
 		.scd_queue = queue,
 		.action = SCD_CFG_DISABLE_QUEUE,
@@ -326,6 +327,7 @@ static int iwl_mvm_disable_txq(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 
 	if (iwl_mvm_has_new_tx_api(mvm)) {
 		iwl_trans_txq_free(mvm->trans, queue);
+		*queueptr = IWL_MVM_INVALID_QUEUE;
 
 		return 0;
 	}
@@ -487,6 +489,7 @@ static int iwl_mvm_free_inactive_queue(struct iwl_mvm *mvm, int queue,
 	u8 sta_id, tid;
 	unsigned long disable_agg_tids = 0;
 	bool same_sta;
+	u16 queue_tmp = queue;
 	int ret;
 
 	lockdep_assert_held(&mvm->mutex);
@@ -509,7 +512,7 @@ static int iwl_mvm_free_inactive_queue(struct iwl_mvm *mvm, int queue,
 		iwl_mvm_invalidate_sta_queue(mvm, queue,
 					     disable_agg_tids, false);
 
-	ret = iwl_mvm_disable_txq(mvm, old_sta, queue, tid, 0);
+	ret = iwl_mvm_disable_txq(mvm, old_sta, &queue_tmp, tid, 0);
 	if (ret) {
 		IWL_ERR(mvm,
 			"Failed to free inactive queue %d (ret=%d)\n",
@@ -1184,6 +1187,7 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 	unsigned int wdg_timeout =
 		iwl_mvm_get_wd_timeout(mvm, mvmsta->vif, false, false);
 	int queue = -1;
+	u16 queue_tmp;
 	unsigned long disable_agg_tids = 0;
 	enum iwl_mvm_agg_state queue_state;
 	bool shared_queue = false, inc_ssn;
@@ -1332,7 +1336,8 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 	return 0;
 
 out_err:
-	iwl_mvm_disable_txq(mvm, sta, queue, tid, 0);
+	queue_tmp = queue;
+	iwl_mvm_disable_txq(mvm, sta, &queue_tmp, tid, 0);
 
 	return ret;
 }
@@ -1779,7 +1784,7 @@ static void iwl_mvm_disable_sta_queues(struct iwl_mvm *mvm,
 		if (mvm_sta->tid_data[i].txq_id == IWL_MVM_INVALID_QUEUE)
 			continue;
 
-		iwl_mvm_disable_txq(mvm, sta, mvm_sta->tid_data[i].txq_id, i,
+		iwl_mvm_disable_txq(mvm, sta, &mvm_sta->tid_data[i].txq_id, i,
 				    0);
 		mvm_sta->tid_data[i].txq_id = IWL_MVM_INVALID_QUEUE;
 	}
@@ -1987,7 +1992,7 @@ static int iwl_mvm_add_int_sta_with_queue(struct iwl_mvm *mvm, int macidx,
 	ret = iwl_mvm_add_int_sta_common(mvm, sta, addr, macidx, maccolor);
 	if (ret) {
 		if (!iwl_mvm_has_new_tx_api(mvm))
-			iwl_mvm_disable_txq(mvm, NULL, *queue,
+			iwl_mvm_disable_txq(mvm, NULL, queue,
 					    IWL_MAX_TID_COUNT, 0);
 		return ret;
 	}
@@ -2060,7 +2065,7 @@ int iwl_mvm_rm_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 	if (WARN_ON_ONCE(mvm->snif_sta.sta_id == IWL_MVM_INVALID_STA))
 		return -EINVAL;
 
-	iwl_mvm_disable_txq(mvm, NULL, mvm->snif_queue, IWL_MAX_TID_COUNT, 0);
+	iwl_mvm_disable_txq(mvm, NULL, &mvm->snif_queue, IWL_MAX_TID_COUNT, 0);
 	ret = iwl_mvm_rm_sta_common(mvm, mvm->snif_sta.sta_id);
 	if (ret)
 		IWL_WARN(mvm, "Failed sending remove station\n");
@@ -2077,7 +2082,7 @@ int iwl_mvm_rm_aux_sta(struct iwl_mvm *mvm)
 	if (WARN_ON_ONCE(mvm->aux_sta.sta_id == IWL_MVM_INVALID_STA))
 		return -EINVAL;
 
-	iwl_mvm_disable_txq(mvm, NULL, mvm->aux_queue, IWL_MAX_TID_COUNT, 0);
+	iwl_mvm_disable_txq(mvm, NULL, &mvm->aux_queue, IWL_MAX_TID_COUNT, 0);
 	ret = iwl_mvm_rm_sta_common(mvm, mvm->aux_sta.sta_id);
 	if (ret)
 		IWL_WARN(mvm, "Failed sending remove station\n");
@@ -2173,7 +2178,7 @@ static void iwl_mvm_free_bcast_sta_queues(struct iwl_mvm *mvm,
 					  struct ieee80211_vif *vif)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	int queue;
+	u16 *queueptr, queue;
 
 	lockdep_assert_held(&mvm->mutex);
 
@@ -2182,10 +2187,10 @@ static void iwl_mvm_free_bcast_sta_queues(struct iwl_mvm *mvm,
 	switch (vif->type) {
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_ADHOC:
-		queue = mvm->probe_queue;
+		queueptr = &mvm->probe_queue;
 		break;
 	case NL80211_IFTYPE_P2P_DEVICE:
-		queue = mvm->p2p_dev_queue;
+		queueptr = &mvm->p2p_dev_queue;
 		break;
 	default:
 		WARN(1, "Can't free bcast queue on vif type %d\n",
@@ -2193,7 +2198,8 @@ static void iwl_mvm_free_bcast_sta_queues(struct iwl_mvm *mvm,
 		return;
 	}
 
-	iwl_mvm_disable_txq(mvm, NULL, queue, IWL_MAX_TID_COUNT, 0);
+	queue = *queueptr;
+	iwl_mvm_disable_txq(mvm, NULL, queueptr, IWL_MAX_TID_COUNT, 0);
 	if (iwl_mvm_has_new_tx_api(mvm))
 		return;
 
@@ -2428,7 +2434,7 @@ int iwl_mvm_rm_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 
 	iwl_mvm_flush_sta(mvm, &mvmvif->mcast_sta, true);
 
-	iwl_mvm_disable_txq(mvm, NULL, mvmvif->cab_queue, 0, 0);
+	iwl_mvm_disable_txq(mvm, NULL, &mvmvif->cab_queue, 0, 0);
 
 	ret = iwl_mvm_rm_sta_common(mvm, mvmvif->mcast_sta.sta_id);
 	if (ret)
@@ -3190,6 +3196,20 @@ static struct iwl_mvm_sta *iwl_mvm_get_key_sta(struct iwl_mvm *mvm,
 	return NULL;
 }
 
+static int iwl_mvm_pn_cmp(const u8 *pn1, const u8 *pn2, int len)
+{
+	int i;
+
+	for (i = len - 1; i >= 0; i--) {
+		if (pn1[i] > pn2[i])
+			return 1;
+		if (pn1[i] < pn2[i])
+			return -1;
+	}
+
+	return 0;
+}
+
 static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
 				u32 sta_id,
 				struct ieee80211_key_conf *key, bool mcast,
@@ -3208,6 +3228,9 @@ static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
 	int i, size;
 	bool new_api = fw_has_api(&mvm->fw->ucode_capa,
 				  IWL_UCODE_TLV_API_TKIP_MIC_KEYS);
+	int api_ver = iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP,
+					    ADD_STA_KEY,
+					    new_api ? 2 : 1);
 
 	if (sta_id == IWL_MVM_INVALID_STA)
 		return -EINVAL;
@@ -3220,7 +3243,7 @@ static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
 	switch (key->cipher) {
 	case WLAN_CIPHER_SUITE_TKIP:
 		key_flags |= cpu_to_le16(STA_KEY_FLG_TKIP);
-		if (new_api) {
+		if (api_ver >= 2) {
 			memcpy((void *)&u.cmd.tx_mic_key,
 			       &key->key[NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY],
 			       IWL_MIC_KEY_SIZE);
@@ -3241,7 +3264,7 @@ static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
 	case WLAN_CIPHER_SUITE_CCMP:
 		key_flags |= cpu_to_le16(STA_KEY_FLG_CCM);
 		memcpy(u.cmd.common.key, key->key, key->keylen);
-		if (new_api)
+		if (api_ver >= 2)
 			pn = atomic64_read(&key->tx_pn);
 		break;
 	case WLAN_CIPHER_SUITE_WEP104:
@@ -3257,7 +3280,7 @@ static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
 	case WLAN_CIPHER_SUITE_GCMP:
 		key_flags |= cpu_to_le16(STA_KEY_FLG_GCMP);
 		memcpy(u.cmd.common.key, key->key, key->keylen);
-		if (new_api)
+		if (api_ver >= 2)
 			pn = atomic64_read(&key->tx_pn);
 		break;
 	default:
@@ -3274,7 +3297,46 @@ static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
 	u.cmd.common.key_flags = key_flags;
 	u.cmd.common.sta_id = sta_id;
 
-	if (new_api) {
+	if (key->cipher == WLAN_CIPHER_SUITE_TKIP)
+		i = 0;
+	else
+		i = -1;
+
+	for (; i < IEEE80211_NUM_TIDS; i++) {
+		struct ieee80211_key_seq seq = {};
+		u8 _rx_pn[IEEE80211_MAX_PN_LEN] = {}, *rx_pn = _rx_pn;
+		int rx_pn_len = 8;
+		/* there's a hole at 2/3 in FW format depending on version */
+		int hole = api_ver >= 3 ? 0 : 2;
+
+		ieee80211_get_key_rx_seq(key, i, &seq);
+
+		if (key->cipher == WLAN_CIPHER_SUITE_TKIP) {
+			rx_pn[0] = seq.tkip.iv16;
+			rx_pn[1] = seq.tkip.iv16 >> 8;
+			rx_pn[2 + hole] = seq.tkip.iv32;
+			rx_pn[3 + hole] = seq.tkip.iv32 >> 8;
+			rx_pn[4 + hole] = seq.tkip.iv32 >> 16;
+			rx_pn[5 + hole] = seq.tkip.iv32 >> 24;
+		} else if (key_flags & cpu_to_le16(STA_KEY_FLG_EXT)) {
+			rx_pn = seq.hw.seq;
+			rx_pn_len = seq.hw.seq_len;
+		} else {
+			rx_pn[0] = seq.ccmp.pn[0];
+			rx_pn[1] = seq.ccmp.pn[1];
+			rx_pn[2 + hole] = seq.ccmp.pn[2];
+			rx_pn[3 + hole] = seq.ccmp.pn[3];
+			rx_pn[4 + hole] = seq.ccmp.pn[4];
+			rx_pn[5 + hole] = seq.ccmp.pn[5];
+		}
+
+		if (iwl_mvm_pn_cmp(rx_pn, (u8 *)&u.cmd.common.rx_secur_seq_cnt,
+				   rx_pn_len) > 0)
+			memcpy(&u.cmd.common.rx_secur_seq_cnt, rx_pn,
+			       rx_pn_len);
+	}
+
+	if (api_ver >= 2) {
 		u.cmd.transmit_seq_cnt = cpu_to_le64(pn);
 		size = sizeof(u.cmd);
 	} else {
@@ -3411,7 +3473,6 @@ static int __iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
 				 u8 key_offset,
 				 bool mcast)
 {
-	int ret;
 	const u8 *addr;
 	struct ieee80211_key_seq seq;
 	u16 p1k[5];
@@ -3433,30 +3494,19 @@ static int __iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
 		return -EINVAL;
 	}
 
-	switch (keyconf->cipher) {
-	case WLAN_CIPHER_SUITE_TKIP:
+	if (keyconf->cipher == WLAN_CIPHER_SUITE_TKIP) {
 		addr = iwl_mvm_get_mac_addr(mvm, vif, sta);
 		/* get phase 1 key from mac80211 */
 		ieee80211_get_key_rx_seq(keyconf, 0, &seq);
 		ieee80211_get_tkip_rx_p1k(keyconf, addr, seq.tkip.iv32, p1k);
-		ret = iwl_mvm_send_sta_key(mvm, sta_id, keyconf, mcast,
-					   seq.tkip.iv32, p1k, 0, key_offset,
-					   mfp);
-		break;
-	case WLAN_CIPHER_SUITE_CCMP:
-	case WLAN_CIPHER_SUITE_WEP40:
-	case WLAN_CIPHER_SUITE_WEP104:
-	case WLAN_CIPHER_SUITE_GCMP:
-	case WLAN_CIPHER_SUITE_GCMP_256:
-		ret = iwl_mvm_send_sta_key(mvm, sta_id, keyconf, mcast,
-					   0, NULL, 0, key_offset, mfp);
-		break;
-	default:
-		ret = iwl_mvm_send_sta_key(mvm, sta_id, keyconf, mcast,
-					   0, NULL, 0, key_offset, mfp);
+
+		return iwl_mvm_send_sta_key(mvm, sta_id, keyconf, mcast,
+					    seq.tkip.iv32, p1k, 0, key_offset,
+					    mfp);
 	}
 
-	return ret;
+	return iwl_mvm_send_sta_key(mvm, sta_id, keyconf, mcast,
+				    0, NULL, 0, key_offset, mfp);
 }
 
 int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index d3307a11fcac..25af88a3edce 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -168,6 +168,16 @@ static bool iwl_mvm_te_check_disconnect(struct iwl_mvm *mvm,
 		rcu_read_unlock();
 	}
 
+	if (vif->bss_conf.assoc) {
+		/*
+		 * When not associated, this will be called from
+		 * iwl_mvm_event_mlme_callback_ini()
+		 */
+		iwl_dbg_tlv_time_point(&mvm->fwrt,
+				       IWL_FW_INI_TIME_POINT_ASSOC_FAILED,
+				       NULL);
+	}
+
 	iwl_mvm_connection_loss(mvm, vif, errmsg);
 	return true;
 }
@@ -246,6 +256,18 @@ static void iwl_mvm_te_check_trigger(struct iwl_mvm *mvm,
 	}
 }
 
+static void iwl_mvm_p2p_roc_finished(struct iwl_mvm *mvm)
+{
+	/*
+	 * If the IWL_MVM_STATUS_NEED_FLUSH_P2P is already set, then the
+	 * roc_done_wk is already scheduled or running, so don't schedule it
+	 * again to avoid a race where the roc_done_wk clears this bit after
+	 * it is set here, affecting the next run of the roc_done_wk.
+	 */
+	if (!test_and_set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status))
+		iwl_mvm_roc_finished(mvm);
+}
+
 /*
  * Handles a FW notification for an event that is known to the driver.
  *
@@ -297,8 +319,7 @@ static void iwl_mvm_te_handle_notif(struct iwl_mvm *mvm,
 		switch (te_data->vif->type) {
 		case NL80211_IFTYPE_P2P_DEVICE:
 			ieee80211_remain_on_channel_expired(mvm->hw);
-			set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status);
-			iwl_mvm_roc_finished(mvm);
+			iwl_mvm_p2p_roc_finished(mvm);
 			break;
 		case NL80211_IFTYPE_STATION:
 			/*
@@ -674,8 +695,7 @@ static bool __iwl_mvm_remove_time_event(struct iwl_mvm *mvm,
 			/* Session protection is still ongoing. Cancel it */
 			iwl_mvm_cancel_session_protection(mvm, mvmvif, id);
 			if (iftype == NL80211_IFTYPE_P2P_DEVICE) {
-				set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status);
-				iwl_mvm_roc_finished(mvm);
+				iwl_mvm_p2p_roc_finished(mvm);
 			}
 		}
 		return false;
@@ -842,8 +862,7 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm,
 		/* End TE, notify mac80211 */
 		mvmvif->time_event_data.id = SESSION_PROTECT_CONF_MAX_ID;
 		ieee80211_remain_on_channel_expired(mvm->hw);
-		set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status);
-		iwl_mvm_roc_finished(mvm);
+		iwl_mvm_p2p_roc_finished(mvm);
 	} else if (le32_to_cpu(notif->start)) {
 		if (WARN_ON(mvmvif->time_event_data.id !=
 				le32_to_cpu(notif->conf_id)))
@@ -1004,14 +1023,13 @@ void iwl_mvm_stop_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 		if (vif->type == NL80211_IFTYPE_P2P_DEVICE) {
 			iwl_mvm_cancel_session_protection(mvm, mvmvif,
 							  mvmvif->time_event_data.id);
-			set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status);
+			iwl_mvm_p2p_roc_finished(mvm);
 		} else {
 			iwl_mvm_remove_aux_roc_te(mvm, mvmvif,
 						  &mvmvif->time_event_data);
+			iwl_mvm_roc_finished(mvm);
 		}
 
-		iwl_mvm_roc_finished(mvm);
-
 		return;
 	}
 
@@ -1025,12 +1043,11 @@ void iwl_mvm_stop_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 
 	if (te_data->vif->type == NL80211_IFTYPE_P2P_DEVICE) {
 		iwl_mvm_remove_time_event(mvm, mvmvif, te_data);
-		set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status);
+		iwl_mvm_p2p_roc_finished(mvm);
 	} else {
 		iwl_mvm_remove_aux_roc_te(mvm, mvmvif, te_data);
+		iwl_mvm_roc_finished(mvm);
 	}
-
-	iwl_mvm_roc_finished(mvm);
 }
 
 void iwl_mvm_remove_csa_period(struct iwl_mvm *mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 0b8a0cd3b652..8dc1b8eecb86 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1093,22 +1093,22 @@ static const struct iwl_dev_info iwl_dev_info_table[] = {
 		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY,
 		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_bz_a0_hr_b0, iwl_ax201_name),
+		      iwl_cfg_bz_a0_hr_b0, iwl_bz_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY,
 		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_bz_a0_gf_a0, iwl_ax211_name),
+		      iwl_cfg_bz_a0_gf_a0, iwl_bz_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY,
 		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_CDB,
-		      iwl_cfg_bz_a0_gf4_a0, iwl_ax211_name),
+		      iwl_cfg_bz_a0_gf4_a0, iwl_bz_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_MR, IWL_CFG_ANY,
 		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_bz_a0_mr_a0, iwl_ax211_name),
+		      iwl_cfg_bz_a0_mr_a0, iwl_bz_name),
 
 /* SoF with JF2 */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index cc550f6ef957..a43e56c7689f 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -42,6 +42,7 @@ struct iwl_host_cmd;
  * struct iwl_rx_mem_buffer
  * @page_dma: bus address of rxb page
  * @page: driver's pointer to the rxb page
+ * @list: list entry for the membuffer
  * @invalid: rxb is in driver ownership - not owned by HW
  * @vid: index of this rxb in the global table
  * @offset: indicates which offset of the page (in bytes)
@@ -50,10 +51,10 @@ struct iwl_host_cmd;
 struct iwl_rx_mem_buffer {
 	dma_addr_t page_dma;
 	struct page *page;
-	u16 vid;
-	bool invalid;
 	struct list_head list;
 	u32 offset;
+	u16 vid;
+	bool invalid;
 };
 
 /**
@@ -253,6 +254,13 @@ struct cont_rec {
 };
 #endif
 
+enum iwl_pcie_fw_reset_state {
+	FW_RESET_IDLE,
+	FW_RESET_REQUESTED,
+	FW_RESET_OK,
+	FW_RESET_ERROR,
+};
+
 /**
  * struct iwl_trans_pcie - PCIe transport specific data
  * @rxq: all the RX queue data
@@ -404,7 +412,7 @@ struct iwl_trans_pcie {
 	dma_addr_t base_rb_stts_dma;
 
 	bool fw_reset_handshake;
-	bool fw_reset_done;
+	enum iwl_pcie_fw_reset_state fw_reset_state;
 	wait_queue_head_t fw_reset_waitq;
 
 	char rf_name[32];
@@ -670,19 +678,19 @@ static inline const char *queue_name(struct device *dev,
 			  IWL_SHARED_IRQ_FIRST_RSS ? 1 : 0;
 
 		if (i == 0)
-			return DRV_NAME ": shared IRQ";
+			return DRV_NAME ":shared_IRQ";
 
 		return devm_kasprintf(dev, GFP_KERNEL,
-				      DRV_NAME ": queue %d", i + vec);
+				      DRV_NAME ":queue_%d", i + vec);
 	}
 	if (i == 0)
-		return DRV_NAME ": default queue";
+		return DRV_NAME ":default_queue";
 
 	if (i == trans_p->alloc_vecs - 1)
-		return DRV_NAME ": exception";
+		return DRV_NAME ":exception";
 
 	return devm_kasprintf(dev, GFP_KERNEL,
-			      DRV_NAME  ": queue %d", i);
+			      DRV_NAME  ":queue_%d", i);
 }
 
 static inline void iwl_enable_rfkill_int(struct iwl_trans *trans)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 4f6f4b2720f0..8e45eb38304b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -487,6 +487,9 @@ void iwl_pcie_free_rbs_pool(struct iwl_trans *trans)
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int i;
 
+	if (!trans_pcie->rx_pool)
+		return;
+
 	for (i = 0; i < RX_POOL_SIZE(trans_pcie->num_rx_bufs); i++) {
 		if (!trans_pcie->rx_pool[i].page)
 			continue;
@@ -1062,7 +1065,7 @@ static int _iwl_pcie_rx_init(struct iwl_trans *trans)
 	INIT_LIST_HEAD(&rba->rbd_empty);
 	spin_unlock_bh(&rba->lock);
 
-	/* free all first - we might be reconfigured for a different size */
+	/* free all first - we overwrite everything here */
 	iwl_pcie_free_rbs_pool(trans);
 
 	for (i = 0; i < RX_QUEUE_SIZE; i++)
@@ -1653,7 +1656,7 @@ static void iwl_pcie_irq_handle_error(struct iwl_trans *trans)
 
 	/* The STATUS_FW_ERROR bit is set in this function. This must happen
 	 * before we wake up the command caller, to ensure a proper cleanup. */
-	iwl_trans_fw_error(trans);
+	iwl_trans_fw_error(trans, false);
 
 	clear_bit(STATUS_SYNC_HCMD_ACTIVE, &trans->status);
 	wake_up(&trans->wait_command_queue);
@@ -2225,7 +2228,13 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id)
 			"Microcode SW error detected. Restarting 0x%X.\n",
 			inta_fh);
 		isr_stats->sw++;
-		iwl_pcie_irq_handle_error(trans);
+		/* during FW reset flow report errors from there */
+		if (trans_pcie->fw_reset_state == FW_RESET_REQUESTED) {
+			trans_pcie->fw_reset_state = FW_RESET_ERROR;
+			wake_up(&trans_pcie->fw_reset_waitq);
+		} else {
+			iwl_pcie_irq_handle_error(trans);
+		}
 	}
 
 	/* After checking FH register check HW register */
@@ -2293,7 +2302,7 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id)
 
 	if (inta_hw & MSIX_HW_INT_CAUSES_REG_RESET_DONE) {
 		IWL_DEBUG_ISR(trans, "Reset flow completed\n");
-		trans_pcie->fw_reset_done = true;
+		trans_pcie->fw_reset_state = FW_RESET_OK;
 		wake_up(&trans_pcie->fw_reset_waitq);
 	}
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
index a34009357227..bf0c32a74ca4 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -87,7 +87,12 @@ static void iwl_pcie_gen2_apm_stop(struct iwl_trans *trans, bool op_mode_leave)
 	 * Clear "initialization complete" bit to move adapter from
 	 * D0A* (powered-up Active) --> D0U* (Uninitialized) state.
 	 */
-	iwl_clear_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+		iwl_clear_bit(trans, CSR_GP_CNTRL,
+			      CSR_GP_CNTRL_REG_FLAG_MAC_INIT);
+	else
+		iwl_clear_bit(trans, CSR_GP_CNTRL,
+			      CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
 }
 
 static void iwl_trans_pcie_fw_reset_handshake(struct iwl_trans *trans)
@@ -95,7 +100,7 @@ static void iwl_trans_pcie_fw_reset_handshake(struct iwl_trans *trans)
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int ret;
 
-	trans_pcie->fw_reset_done = false;
+	trans_pcie->fw_reset_state = FW_RESET_REQUESTED;
 
 	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		iwl_write_umac_prph(trans, UREG_NIC_SET_NMI_DRIVER,
@@ -106,10 +111,15 @@ static void iwl_trans_pcie_fw_reset_handshake(struct iwl_trans *trans)
 
 	/* wait 200ms */
 	ret = wait_event_timeout(trans_pcie->fw_reset_waitq,
-				 trans_pcie->fw_reset_done, FW_RESET_TIMEOUT);
-	if (!ret)
+				 trans_pcie->fw_reset_state != FW_RESET_REQUESTED,
+				 FW_RESET_TIMEOUT);
+	if (!ret || trans_pcie->fw_reset_state == FW_RESET_ERROR) {
 		IWL_INFO(trans,
 			 "firmware didn't ACK the reset - continue anyway\n");
+		iwl_trans_fw_error(trans, true);
+	}
+
+	trans_pcie->fw_reset_state = FW_RESET_IDLE;
 }
 
 void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans)
@@ -121,9 +131,21 @@ void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans)
 	if (trans_pcie->is_down)
 		return;
 
-	if (trans_pcie->fw_reset_handshake &&
-	    trans->state >= IWL_TRANS_FW_STARTED)
-		iwl_trans_pcie_fw_reset_handshake(trans);
+	if (trans->state >= IWL_TRANS_FW_STARTED) {
+		if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+			iwl_set_bit(trans, CSR_GP_CNTRL,
+				    CSR_GP_CNTRL_REG_FLAG_BUS_MASTER_DISABLE_REQ);
+			iwl_poll_bit(trans, CSR_GP_CNTRL,
+				     CSR_GP_CNTRL_REG_FLAG_BUS_MASTER_DISABLE_STATUS,
+				     CSR_GP_CNTRL_REG_FLAG_BUS_MASTER_DISABLE_STATUS,
+				     5000);
+			msleep(100);
+			iwl_set_bit(trans, CSR_GP_CNTRL,
+				    CSR_GP_CNTRL_REG_FLAG_SW_RESET);
+		} else if (trans_pcie->fw_reset_handshake) {
+			iwl_trans_pcie_fw_reset_handshake(trans);
+		}
+	}
 
 	trans_pcie->is_down = true;
 
@@ -154,9 +176,17 @@ void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans)
 		iwl_pcie_ctxt_info_free(trans);
 
 	/* Make sure (redundant) we've released our request to stay awake */
-	iwl_clear_bit(trans, CSR_GP_CNTRL,
-		      CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+		iwl_clear_bit(trans, CSR_GP_CNTRL,
+			      CSR_GP_CNTRL_REG_FLAG_BZ_MAC_ACCESS_REQ);
+	else
+		iwl_clear_bit(trans, CSR_GP_CNTRL,
+			      CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
 
+	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+		iwl_set_bit(trans, CSR_GP_CNTRL,
+			    CSR_GP_CNTRL_REG_FLAG_SW_RESET);
+	}
 	/* Stop the device, and put it in low power state */
 	iwl_pcie_gen2_apm_stop(trans, false);
 
@@ -436,7 +466,10 @@ int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
 
 	iwl_pcie_set_ltr(trans);
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+		iwl_set_bit(trans, CSR_GP_CNTRL,
+			    CSR_GP_CNTRL_REG_FLAG_ROM_START);
+	else if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
 		iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1);
 	else
 		iwl_write_prph(trans, UREG_CPU_INIT_RUN, 1);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index bee6b4574226..f252680f18e8 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -449,11 +449,23 @@ void iwl_pcie_apm_stop_master(struct iwl_trans *trans)
 	int ret;
 
 	/* stop device's busmaster DMA activity */
-	iwl_set_bit(trans, CSR_RESET, CSR_RESET_REG_FLAG_STOP_MASTER);
 
-	ret = iwl_poll_bit(trans, CSR_RESET,
-			   CSR_RESET_REG_FLAG_MASTER_DISABLED,
-			   CSR_RESET_REG_FLAG_MASTER_DISABLED, 100);
+	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+		iwl_set_bit(trans, CSR_GP_CNTRL,
+			    CSR_GP_CNTRL_REG_FLAG_BUS_MASTER_DISABLE_REQ);
+
+		ret = iwl_poll_bit(trans, CSR_GP_CNTRL,
+				   CSR_GP_CNTRL_REG_FLAG_BUS_MASTER_DISABLE_STATUS,
+				   CSR_GP_CNTRL_REG_FLAG_BUS_MASTER_DISABLE_STATUS,
+				   100);
+	} else {
+		iwl_set_bit(trans, CSR_RESET, CSR_RESET_REG_FLAG_STOP_MASTER);
+
+		ret = iwl_poll_bit(trans, CSR_RESET,
+				   CSR_RESET_REG_FLAG_MASTER_DISABLED,
+				   CSR_RESET_REG_FLAG_MASTER_DISABLED, 100);
+	}
+
 	if (ret < 0)
 		IWL_WARN(trans, "Master Disable Timed Out, 100 usec\n");
 
@@ -1866,6 +1878,9 @@ static void iwl_trans_pcie_configure(struct iwl_trans *trans,
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
+	/* free all first - we might be reconfigured for a different size */
+	iwl_pcie_free_rbs_pool(trans);
+
 	trans->txqs.cmd.q_id = trans_cfg->cmd_queue;
 	trans->txqs.cmd.fifo = trans_cfg->cmd_fifo;
 	trans->txqs.cmd.wdg_timeout = trans_cfg->cmd_q_wdg_timeout;
@@ -1992,15 +2007,24 @@ bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
 {
 	int ret;
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	u32 write = CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ;
+	u32 mask = CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY |
+		   CSR_GP_CNTRL_REG_FLAG_GOING_TO_SLEEP;
+	u32 poll = CSR_GP_CNTRL_REG_VAL_MAC_ACCESS_EN;
 
 	spin_lock(&trans_pcie->reg_lock);
 
 	if (trans_pcie->cmd_hold_nic_awake)
 		goto out;
 
+	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+		write = CSR_GP_CNTRL_REG_FLAG_BZ_MAC_ACCESS_REQ;
+		mask = CSR_GP_CNTRL_REG_FLAG_MAC_STATUS;
+		poll = CSR_GP_CNTRL_REG_FLAG_MAC_STATUS;
+	}
+
 	/* this bit wakes up the NIC */
-	__iwl_trans_pcie_set_bit(trans, CSR_GP_CNTRL,
-				 CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+	__iwl_trans_pcie_set_bit(trans, CSR_GP_CNTRL, write);
 	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_8000)
 		udelay(2);
 
@@ -2024,10 +2048,7 @@ bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
 	 * 5000 series and later (including 1000 series) have non-volatile SRAM,
 	 * and do not save/restore SRAM when power cycling.
 	 */
-	ret = iwl_poll_bit(trans, CSR_GP_CNTRL,
-			   CSR_GP_CNTRL_REG_VAL_MAC_ACCESS_EN,
-			   (CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY |
-			    CSR_GP_CNTRL_REG_FLAG_GOING_TO_SLEEP), 15000);
+	ret = iwl_poll_bit(trans, CSR_GP_CNTRL, poll, mask, 15000);
 	if (unlikely(ret < 0)) {
 		u32 cntrl = iwl_read32(trans, CSR_GP_CNTRL);
 
@@ -2947,8 +2968,8 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans,
 		struct iwl_rx_mem_buffer *rxb = rxq->queue[i];
 		struct iwl_fw_error_dump_rb *rb;
 
-		dma_unmap_page(trans->dev, rxb->page_dma, max_len,
-			       DMA_FROM_DEVICE);
+		dma_sync_single_for_cpu(trans->dev, rxb->page_dma,
+					max_len, DMA_FROM_DEVICE);
 
 		rb_len += sizeof(**data) + sizeof(*rb) + max_len;
 
@@ -2957,10 +2978,6 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans,
 		rb = (void *)(*data)->data;
 		rb->index = cpu_to_le32(i);
 		memcpy(rb->data, page_address(rxb->page), max_len);
-		/* remap the page for the free benefit */
-		rxb->page_dma = dma_map_page(trans->dev, rxb->page,
-					     rxb->offset, max_len,
-					     DMA_FROM_DEVICE);
 
 		*data = iwl_fw_error_next_data(*data);
 	}
@@ -3489,15 +3506,9 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 	pci_set_master(pdev);
 
 	addr_size = trans->txqs.tfd.addr_size;
-	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(addr_size));
-	if (!ret)
-		ret = pci_set_consistent_dma_mask(pdev,
-						  DMA_BIT_MASK(addr_size));
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(addr_size));
 	if (ret) {
-		ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (!ret)
-			ret = pci_set_consistent_dma_mask(pdev,
-							  DMA_BIT_MASK(32));
+		ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 		/* both attempts failed: */
 		if (ret) {
 			dev_err(&pdev->dev, "No suitable DMA available\n");
diff --git a/drivers/net/wireless/intersil/Kconfig b/drivers/net/wireless/intersil/Kconfig
index c52d9b535623..bd6bf70ece03 100644
--- a/drivers/net/wireless/intersil/Kconfig
+++ b/drivers/net/wireless/intersil/Kconfig
@@ -16,24 +16,4 @@ source "drivers/net/wireless/intersil/hostap/Kconfig"
 source "drivers/net/wireless/intersil/orinoco/Kconfig"
 source "drivers/net/wireless/intersil/p54/Kconfig"
 
-config PRISM54
-	tristate 'Intersil Prism GT/Duette/Indigo PCI/Cardbus (DEPRECATED)'
-	depends on PCI
-	select WIRELESS_EXT
-	select WEXT_SPY
-	select WEXT_PRIV
-	select FW_LOADER
-	help
-	  This enables support for FullMAC PCI/Cardbus prism54 devices. This
-	  driver is now deprecated in favor for the SoftMAC driver, p54pci.
-	  p54pci supports FullMAC PCI/Cardbus devices as well.
-
-	  For more information refer to the p54 wiki:
-
-	  http://wireless.wiki.kernel.org/en/users/Drivers/p54
-
-	  Note: You need a motherboard with DMA support to use any of these cards
-
-	  When built as module you get the module prism54
-
 endif # WLAN_VENDOR_INTERSIL
diff --git a/drivers/net/wireless/intersil/Makefile b/drivers/net/wireless/intersil/Makefile
index aa630e9c3d3d..65281d1b3d85 100644
--- a/drivers/net/wireless/intersil/Makefile
+++ b/drivers/net/wireless/intersil/Makefile
@@ -2,4 +2,3 @@
 obj-$(CONFIG_HOSTAP)		+= hostap/
 obj-$(CONFIG_HERMES)		+= orinoco/
 obj-$(CONFIG_P54_COMMON)	+= p54/
-obj-$(CONFIG_PRISM54)		+= prism54/
diff --git a/drivers/net/wireless/intersil/hostap/hostap.h b/drivers/net/wireless/intersil/hostap/hostap.h
index c4b81ff7d7e4..c17ab6dbbb53 100644
--- a/drivers/net/wireless/intersil/hostap/hostap.h
+++ b/drivers/net/wireless/intersil/hostap/hostap.h
@@ -93,6 +93,7 @@ extern const struct iw_handler_def hostap_iw_handler_def;
 extern const struct ethtool_ops prism2_ethtool_ops;
 
 int hostap_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
-
+int hostap_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			  void __user *data, int cmd);
 
 #endif /* HOSTAP_H */
diff --git a/drivers/net/wireless/intersil/hostap/hostap_ioctl.c b/drivers/net/wireless/intersil/hostap/hostap_ioctl.c
index 49766b285230..0a376f112db9 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_ioctl.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_ioctl.c
@@ -3941,7 +3941,8 @@ const struct iw_handler_def hostap_iw_handler_def =
 	.get_wireless_stats = hostap_get_wireless_stats,
 };
 
-
+/* Private ioctls (iwpriv) that have not yet been converted
+ * into new wireless extensions API */
 int hostap_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct iwreq *wrq = (struct iwreq *) ifr;
@@ -3953,9 +3954,6 @@ int hostap_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	local = iface->local;
 
 	switch (cmd) {
-		/* Private ioctls (iwpriv) that have not yet been converted
-		 * into new wireless extensions API */
-
 	case PRISM2_IOCTL_INQUIRE:
 		if (!capable(CAP_NET_ADMIN)) ret = -EPERM;
 		else ret = prism2_ioctl_priv_inquire(dev, (int *) wrq->u.name);
@@ -4009,11 +4007,31 @@ int hostap_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 					       wrq->u.ap_addr.sa_data);
 		break;
 #endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	return ret;
+}
 
+/* Private ioctls that are not used with iwpriv;
+ * in SIOCDEVPRIVATE range */
+int hostap_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			  void __user *data, int cmd)
+{
+	struct iwreq *wrq = (struct iwreq *)ifr;
+	struct hostap_interface *iface;
+	local_info_t *local;
+	int ret = 0;
 
-		/* Private ioctls that are not used with iwpriv;
-		 * in SIOCDEVPRIVATE range */
+	iface = netdev_priv(dev);
+	local = iface->local;
+
+	if (in_compat_syscall()) /* not implemented yet */
+		return -EOPNOTSUPP;
 
+	switch (cmd) {
 #ifdef PRISM2_DOWNLOAD_SUPPORT
 	case PRISM2_IOCTL_DOWNLOAD:
 		if (!capable(CAP_NET_ADMIN)) ret = -EPERM;
diff --git a/drivers/net/wireless/intersil/hostap/hostap_main.c b/drivers/net/wireless/intersil/hostap/hostap_main.c
index de97b3304115..54f67b682b6a 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_main.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_main.c
@@ -797,6 +797,7 @@ static const struct net_device_ops hostap_netdev_ops = {
 	.ndo_open		= prism2_open,
 	.ndo_stop		= prism2_close,
 	.ndo_do_ioctl		= hostap_ioctl,
+	.ndo_siocdevprivate	= hostap_siocdevprivate,
 	.ndo_set_mac_address	= prism2_set_mac_address,
 	.ndo_set_rx_mode	= hostap_set_multicast_list,
 	.ndo_tx_timeout 	= prism2_tx_timeout,
@@ -809,6 +810,7 @@ static const struct net_device_ops hostap_mgmt_netdev_ops = {
 	.ndo_open		= prism2_open,
 	.ndo_stop		= prism2_close,
 	.ndo_do_ioctl		= hostap_ioctl,
+	.ndo_siocdevprivate	= hostap_siocdevprivate,
 	.ndo_set_mac_address	= prism2_set_mac_address,
 	.ndo_set_rx_mode	= hostap_set_multicast_list,
 	.ndo_tx_timeout 	= prism2_tx_timeout,
@@ -821,6 +823,7 @@ static const struct net_device_ops hostap_master_ops = {
 	.ndo_open		= prism2_open,
 	.ndo_stop		= prism2_close,
 	.ndo_do_ioctl		= hostap_ioctl,
+	.ndo_siocdevprivate	= hostap_siocdevprivate,
 	.ndo_set_mac_address	= prism2_set_mac_address,
 	.ndo_set_rx_mode	= hostap_set_multicast_list,
 	.ndo_tx_timeout 	= prism2_tx_timeout,
diff --git a/drivers/net/wireless/intersil/prism54/Makefile b/drivers/net/wireless/intersil/prism54/Makefile
deleted file mode 100644
index 4f5572dffb5e..000000000000
--- a/drivers/net/wireless/intersil/prism54/Makefile
+++ /dev/null
@@ -1,9 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-# $Id: Makefile.k26,v 1.7 2004/01/30 16:24:00 ajfa Exp $
-
-prism54-objs := islpci_eth.o islpci_mgt.o \
-                isl_38xx.o isl_ioctl.o islpci_dev.o \
-		islpci_hotplug.o oid_mgt.o
-
-obj-$(CONFIG_PRISM54) += prism54.o
-
diff --git a/drivers/net/wireless/intersil/prism54/isl_38xx.c b/drivers/net/wireless/intersil/prism54/isl_38xx.c
deleted file mode 100644
index ae964de347f7..000000000000
--- a/drivers/net/wireless/intersil/prism54/isl_38xx.c
+++ /dev/null
@@ -1,245 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  Copyright (C) 2002 Intersil Americas Inc.
- *  Copyright (C) 2003-2004 Luis R. Rodriguez <mcgrof@ruslug.rutgers.edu>_
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/delay.h>
-#include <linux/ktime.h>
-
-#include <linux/uaccess.h>
-#include <asm/io.h>
-
-#include "prismcompat.h"
-#include "isl_38xx.h"
-#include "islpci_dev.h"
-#include "islpci_mgt.h"
-
-/******************************************************************************
-    Device Interface & Control functions
-******************************************************************************/
-
-/**
- * isl38xx_disable_interrupts - disable all interrupts
- * @device: pci memory base address
- *
- *  Instructs the device to disable all interrupt reporting by asserting
- *  the IRQ line. New events may still show up in the interrupt identification
- *  register located at offset %ISL38XX_INT_IDENT_REG.
- */
-void
-isl38xx_disable_interrupts(void __iomem *device)
-{
-	isl38xx_w32_flush(device, 0x00000000, ISL38XX_INT_EN_REG);
-	udelay(ISL38XX_WRITEIO_DELAY);
-}
-
-void
-isl38xx_handle_sleep_request(isl38xx_control_block *control_block,
-			     int *powerstate, void __iomem *device_base)
-{
-	/* device requests to go into sleep mode
-	 * check whether the transmit queues for data and management are empty */
-	if (isl38xx_in_queue(control_block, ISL38XX_CB_TX_DATA_LQ))
-		/* data tx queue not empty */
-		return;
-
-	if (isl38xx_in_queue(control_block, ISL38XX_CB_TX_MGMTQ))
-		/* management tx queue not empty */
-		return;
-
-	/* check also whether received frames are pending */
-	if (isl38xx_in_queue(control_block, ISL38XX_CB_RX_DATA_LQ))
-		/* data rx queue not empty */
-		return;
-
-	if (isl38xx_in_queue(control_block, ISL38XX_CB_RX_MGMTQ))
-		/* management rx queue not empty */
-		return;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_TRACING, "Device going to sleep mode\n");
-#endif
-
-	/* all queues are empty, allow the device to go into sleep mode */
-	*powerstate = ISL38XX_PSM_POWERSAVE_STATE;
-
-	/* assert the Sleep interrupt in the Device Interrupt Register */
-	isl38xx_w32_flush(device_base, ISL38XX_DEV_INT_SLEEP,
-			  ISL38XX_DEV_INT_REG);
-	udelay(ISL38XX_WRITEIO_DELAY);
-}
-
-void
-isl38xx_handle_wakeup(isl38xx_control_block *control_block,
-		      int *powerstate, void __iomem *device_base)
-{
-	/* device is in active state, update the powerstate flag */
-	*powerstate = ISL38XX_PSM_ACTIVE_STATE;
-
-	/* now check whether there are frames pending for the card */
-	if (!isl38xx_in_queue(control_block, ISL38XX_CB_TX_DATA_LQ)
-	    && !isl38xx_in_queue(control_block, ISL38XX_CB_TX_MGMTQ))
-		return;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_ANYTHING, "Wake up handler trigger the device\n");
-#endif
-
-	/* either data or management transmit queue has a frame pending
-	 * trigger the device by setting the Update bit in the Device Int reg */
-	isl38xx_w32_flush(device_base, ISL38XX_DEV_INT_UPDATE,
-			  ISL38XX_DEV_INT_REG);
-	udelay(ISL38XX_WRITEIO_DELAY);
-}
-
-void
-isl38xx_trigger_device(int asleep, void __iomem *device_base)
-{
-	u32 reg;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	u32 counter = 0;
-	struct timespec64 current_ts64;
-	DEBUG(SHOW_FUNCTION_CALLS, "isl38xx trigger device\n");
-#endif
-
-	/* check whether the device is in power save mode */
-	if (asleep) {
-		/* device is in powersave, trigger the device for wakeup */
-#if VERBOSE > SHOW_ERROR_MESSAGES
-		ktime_get_real_ts64(&current_ts64);
-		DEBUG(SHOW_TRACING, "%lld.%09ld Device wakeup triggered\n",
-		      (s64)current_ts64.tv_sec, current_ts64.tv_nsec);
-
-		DEBUG(SHOW_TRACING, "%lld.%09ld Device register read %08x\n",
-		      (s64)current_ts64.tv_sec, current_ts64.tv_nsec,
-		      readl(device_base + ISL38XX_CTRL_STAT_REG));
-#endif
-
-		reg = readl(device_base + ISL38XX_INT_IDENT_REG);
-		if (reg == 0xabadface) {
-#if VERBOSE > SHOW_ERROR_MESSAGES
-			ktime_get_real_ts64(&current_ts64);
-			DEBUG(SHOW_TRACING,
-			      "%lld.%09ld Device register abadface\n",
-			      (s64)current_ts64.tv_sec, current_ts64.tv_nsec);
-#endif
-			/* read the Device Status Register until Sleepmode bit is set */
-			while (reg = readl(device_base + ISL38XX_CTRL_STAT_REG),
-			       (reg & ISL38XX_CTRL_STAT_SLEEPMODE) == 0) {
-				udelay(ISL38XX_WRITEIO_DELAY);
-#if VERBOSE > SHOW_ERROR_MESSAGES
-				counter++;
-#endif
-			}
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-			DEBUG(SHOW_TRACING,
-			      "%lld.%09ld Device register read %08x\n",
-			      (s64)current_ts64.tv_sec, current_ts64.tv_nsec,
-			      readl(device_base + ISL38XX_CTRL_STAT_REG));
-			ktime_get_real_ts64(&current_ts64);
-			DEBUG(SHOW_TRACING,
-			      "%lld.%09ld Device asleep counter %i\n",
-			      (s64)current_ts64.tv_sec, current_ts64.tv_nsec,
-			      counter);
-#endif
-		}
-		/* assert the Wakeup interrupt in the Device Interrupt Register */
-		isl38xx_w32_flush(device_base, ISL38XX_DEV_INT_WAKEUP,
-				  ISL38XX_DEV_INT_REG);
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-		udelay(ISL38XX_WRITEIO_DELAY);
-
-		/* perform another read on the Device Status Register */
-		reg = readl(device_base + ISL38XX_CTRL_STAT_REG);
-		ktime_get_real_ts64(&current_ts64);
-		DEBUG(SHOW_TRACING, "%lld.%00ld Device register read %08x\n",
-		      (s64)current_ts64.tv_sec, current_ts64.tv_nsec, reg);
-#endif
-	} else {
-		/* device is (still) awake  */
-#if VERBOSE > SHOW_ERROR_MESSAGES
-		DEBUG(SHOW_TRACING, "Device is in active state\n");
-#endif
-		/* trigger the device by setting the Update bit in the Device Int reg */
-
-		isl38xx_w32_flush(device_base, ISL38XX_DEV_INT_UPDATE,
-				  ISL38XX_DEV_INT_REG);
-	}
-}
-
-void
-isl38xx_interface_reset(void __iomem *device_base, dma_addr_t host_address)
-{
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_FUNCTION_CALLS, "isl38xx_interface_reset\n");
-#endif
-
-	/* load the address of the control block in the device */
-	isl38xx_w32_flush(device_base, host_address, ISL38XX_CTRL_BLK_BASE_REG);
-	udelay(ISL38XX_WRITEIO_DELAY);
-
-	/* set the reset bit in the Device Interrupt Register */
-	isl38xx_w32_flush(device_base, ISL38XX_DEV_INT_RESET, ISL38XX_DEV_INT_REG);
-	udelay(ISL38XX_WRITEIO_DELAY);
-
-	/* enable the interrupt for detecting initialization */
-
-	/* Note: Do not enable other interrupts here. We want the
-	 * device to have come up first 100% before allowing any other
-	 * interrupts. */
-	isl38xx_w32_flush(device_base, ISL38XX_INT_IDENT_INIT, ISL38XX_INT_EN_REG);
-	udelay(ISL38XX_WRITEIO_DELAY);  /* allow complete full reset */
-}
-
-void
-isl38xx_enable_common_interrupts(void __iomem *device_base)
-{
-	u32 reg;
-
-	reg = ISL38XX_INT_IDENT_UPDATE | ISL38XX_INT_IDENT_SLEEP |
-	      ISL38XX_INT_IDENT_WAKEUP;
-	isl38xx_w32_flush(device_base, reg, ISL38XX_INT_EN_REG);
-	udelay(ISL38XX_WRITEIO_DELAY);
-}
-
-int
-isl38xx_in_queue(isl38xx_control_block *cb, int queue)
-{
-	const s32 delta = (le32_to_cpu(cb->driver_curr_frag[queue]) -
-			   le32_to_cpu(cb->device_curr_frag[queue]));
-
-	/* determine the amount of fragments in the queue depending on the type
-	 * of the queue, either transmit or receive */
-
-	BUG_ON(delta < 0);	/* driver ptr must be ahead of device ptr */
-
-	switch (queue) {
-		/* send queues */
-	case ISL38XX_CB_TX_MGMTQ:
-		BUG_ON(delta > ISL38XX_CB_MGMT_QSIZE);
-		fallthrough;
-
-	case ISL38XX_CB_TX_DATA_LQ:
-	case ISL38XX_CB_TX_DATA_HQ:
-		BUG_ON(delta > ISL38XX_CB_TX_QSIZE);
-		return delta;
-
-		/* receive queues */
-	case ISL38XX_CB_RX_MGMTQ:
-		BUG_ON(delta > ISL38XX_CB_MGMT_QSIZE);
-		return ISL38XX_CB_MGMT_QSIZE - delta;
-
-	case ISL38XX_CB_RX_DATA_LQ:
-	case ISL38XX_CB_RX_DATA_HQ:
-		BUG_ON(delta > ISL38XX_CB_RX_QSIZE);
-		return ISL38XX_CB_RX_QSIZE - delta;
-	}
-	BUG();
-	return 0;
-}
diff --git a/drivers/net/wireless/intersil/prism54/isl_38xx.h b/drivers/net/wireless/intersil/prism54/isl_38xx.h
deleted file mode 100644
index 69218b8b2b23..000000000000
--- a/drivers/net/wireless/intersil/prism54/isl_38xx.h
+++ /dev/null
@@ -1,158 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  Copyright (C) 2002 Intersil Americas Inc.
- */
-
-#ifndef _ISL_38XX_H
-#define _ISL_38XX_H
-
-#include <asm/io.h>
-#include <asm/byteorder.h>
-
-#define ISL38XX_CB_RX_QSIZE                     8
-#define ISL38XX_CB_TX_QSIZE                     32
-
-/* ISL38XX Access Point Specific definitions */
-#define ISL38XX_MAX_WDS_LINKS                   8
-
-/* ISL38xx Client Specific definitions */
-#define ISL38XX_PSM_ACTIVE_STATE                0
-#define ISL38XX_PSM_POWERSAVE_STATE             1
-
-/* ISL38XX Host Interface Definitions */
-#define ISL38XX_PCI_MEM_SIZE                    0x02000
-#define ISL38XX_MEMORY_WINDOW_SIZE              0x01000
-#define ISL38XX_DEV_FIRMWARE_ADDRES             0x20000
-#define ISL38XX_WRITEIO_DELAY                   10	/* in us */
-#define ISL38XX_RESET_DELAY                     50	/* in ms */
-#define ISL38XX_WAIT_CYCLE                      10	/* in 10ms */
-#define ISL38XX_MAX_WAIT_CYCLES                 10
-
-/* PCI Memory Area */
-#define ISL38XX_HARDWARE_REG                    0x0000
-#define ISL38XX_CARDBUS_CIS                     0x0800
-#define ISL38XX_DIRECT_MEM_WIN                  0x1000
-
-/* Hardware registers */
-#define ISL38XX_DEV_INT_REG                     0x0000
-#define ISL38XX_INT_IDENT_REG                   0x0010
-#define ISL38XX_INT_ACK_REG                     0x0014
-#define ISL38XX_INT_EN_REG                      0x0018
-#define ISL38XX_GEN_PURP_COM_REG_1              0x0020
-#define ISL38XX_GEN_PURP_COM_REG_2              0x0024
-#define ISL38XX_CTRL_BLK_BASE_REG               ISL38XX_GEN_PURP_COM_REG_1
-#define ISL38XX_DIR_MEM_BASE_REG                0x0030
-#define ISL38XX_CTRL_STAT_REG                   0x0078
-
-/* High end mobos queue up pci writes, the following
- * is used to "read" from after a write to force flush */
-#define ISL38XX_PCI_POSTING_FLUSH		ISL38XX_INT_EN_REG
-
-/**
- * isl38xx_w32_flush - PCI iomem write helper
- * @base: (host) memory base address of the device
- * @val: 32bit value (host order) to write
- * @offset: byte offset into @base to write value to
- *
- *  This helper takes care of writing a 32bit datum to the
- *  specified offset into the device's pci memory space, and making sure
- *  the pci memory buffers get flushed by performing one harmless read
- *  from the %ISL38XX_PCI_POSTING_FLUSH offset.
- */
-static inline void
-isl38xx_w32_flush(void __iomem *base, u32 val, unsigned long offset)
-{
-	writel(val, base + offset);
-	(void) readl(base + ISL38XX_PCI_POSTING_FLUSH);
-}
-
-/* Device Interrupt register bits */
-#define ISL38XX_DEV_INT_RESET                   0x0001
-#define ISL38XX_DEV_INT_UPDATE                  0x0002
-#define ISL38XX_DEV_INT_WAKEUP                  0x0008
-#define ISL38XX_DEV_INT_SLEEP                   0x0010
-
-/* Interrupt Identification/Acknowledge/Enable register bits */
-#define ISL38XX_INT_IDENT_UPDATE                0x0002
-#define ISL38XX_INT_IDENT_INIT                  0x0004
-#define ISL38XX_INT_IDENT_WAKEUP                0x0008
-#define ISL38XX_INT_IDENT_SLEEP                 0x0010
-#define ISL38XX_INT_SOURCES                     0x001E
-
-/* Control/Status register bits */
-/* Looks like there are other meaningful bits
-    0x20004400 seen in normal operation,
-    0x200044db at 'timeout waiting for mgmt response'
-*/
-#define ISL38XX_CTRL_STAT_SLEEPMODE             0x00000200
-#define	ISL38XX_CTRL_STAT_CLKRUN		0x00800000
-#define ISL38XX_CTRL_STAT_RESET                 0x10000000
-#define ISL38XX_CTRL_STAT_RAMBOOT               0x20000000
-#define ISL38XX_CTRL_STAT_STARTHALTED           0x40000000
-#define ISL38XX_CTRL_STAT_HOST_OVERRIDE         0x80000000
-
-/* Control Block definitions */
-#define ISL38XX_CB_RX_DATA_LQ                   0
-#define ISL38XX_CB_TX_DATA_LQ                   1
-#define ISL38XX_CB_RX_DATA_HQ                   2
-#define ISL38XX_CB_TX_DATA_HQ                   3
-#define ISL38XX_CB_RX_MGMTQ                     4
-#define ISL38XX_CB_TX_MGMTQ                     5
-#define ISL38XX_CB_QCOUNT                       6
-#define ISL38XX_CB_MGMT_QSIZE                   4
-#define ISL38XX_MIN_QTHRESHOLD                  4	/* fragments */
-
-/* Memory Manager definitions */
-#define MGMT_FRAME_SIZE                         1500	/* >= size struct obj_bsslist */
-#define MGMT_TX_FRAME_COUNT                     24	/* max 4 + spare 4 + 8 init */
-#define MGMT_RX_FRAME_COUNT                     24	/* 4*4 + spare 8 */
-#define MGMT_FRAME_COUNT                        (MGMT_TX_FRAME_COUNT + MGMT_RX_FRAME_COUNT)
-#define CONTROL_BLOCK_SIZE                      1024	/* should be enough */
-#define PSM_FRAME_SIZE                          1536
-#define PSM_MINIMAL_STATION_COUNT               64
-#define PSM_FRAME_COUNT                         PSM_MINIMAL_STATION_COUNT
-#define PSM_BUFFER_SIZE                         PSM_FRAME_SIZE * PSM_FRAME_COUNT
-#define MAX_TRAP_RX_QUEUE                       4
-#define HOST_MEM_BLOCK                          CONTROL_BLOCK_SIZE + PSM_BUFFER_SIZE
-
-/* Fragment package definitions */
-#define FRAGMENT_FLAG_MF                        0x0001
-#define MAX_FRAGMENT_SIZE                       1536
-
-/* In monitor mode frames have a header. I don't know exactly how big those
- * frame can be but I've never seen any frame bigger than 1584... :
- */
-#define MAX_FRAGMENT_SIZE_RX	                1600
-
-typedef struct {
-	__le32 address;		/* physical address on host */
-	__le16 size;		/* packet size */
-	__le16 flags;		/* set of bit-wise flags */
-} isl38xx_fragment;
-
-struct isl38xx_cb {
-	__le32 driver_curr_frag[ISL38XX_CB_QCOUNT];
-	__le32 device_curr_frag[ISL38XX_CB_QCOUNT];
-	isl38xx_fragment rx_data_low[ISL38XX_CB_RX_QSIZE];
-	isl38xx_fragment tx_data_low[ISL38XX_CB_TX_QSIZE];
-	isl38xx_fragment rx_data_high[ISL38XX_CB_RX_QSIZE];
-	isl38xx_fragment tx_data_high[ISL38XX_CB_TX_QSIZE];
-	isl38xx_fragment rx_data_mgmt[ISL38XX_CB_MGMT_QSIZE];
-	isl38xx_fragment tx_data_mgmt[ISL38XX_CB_MGMT_QSIZE];
-};
-
-typedef struct isl38xx_cb isl38xx_control_block;
-
-/* determine number of entries currently in queue */
-int isl38xx_in_queue(isl38xx_control_block *cb, int queue);
-
-void isl38xx_disable_interrupts(void __iomem *);
-void isl38xx_enable_common_interrupts(void __iomem *);
-
-void isl38xx_handle_sleep_request(isl38xx_control_block *, int *,
-				  void __iomem *);
-void isl38xx_handle_wakeup(isl38xx_control_block *, int *, void __iomem *);
-void isl38xx_trigger_device(int, void __iomem *);
-void isl38xx_interface_reset(void __iomem *, dma_addr_t);
-
-#endif				/* _ISL_38XX_H */
diff --git a/drivers/net/wireless/intersil/prism54/isl_ioctl.c b/drivers/net/wireless/intersil/prism54/isl_ioctl.c
deleted file mode 100644
index 5e5ceafe098b..000000000000
--- a/drivers/net/wireless/intersil/prism54/isl_ioctl.c
+++ /dev/null
@@ -1,2909 +0,0 @@
-/*
- *  Copyright (C) 2002 Intersil Americas Inc.
- *            (C) 2003,2004 Aurelien Alleaume <slts@free.fr>
- *            (C) 2003 Herbert Valerio Riedel <hvr@gnu.org>
- *            (C) 2003 Luis R. Rodriguez <mcgrof@ruslug.rutgers.edu>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License
- *
- *  This program 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/>.
- *
- */
-
-#include <linux/capability.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/if_arp.h>
-#include <linux/slab.h>
-#include <linux/pci.h>
-#include <linux/etherdevice.h>
-
-#include <linux/uaccess.h>
-
-#include "prismcompat.h"
-#include "isl_ioctl.h"
-#include "islpci_mgt.h"
-#include "isl_oid.h"		/* additional types and defs for isl38xx fw */
-#include "oid_mgt.h"
-
-#include <net/iw_handler.h>	/* New driver API */
-
-#define KEY_SIZE_WEP104 13	/* 104/128-bit WEP keys */
-#define KEY_SIZE_WEP40  5	/* 40/64-bit WEP keys */
-/* KEY_SIZE_TKIP should match isl_oid.h, struct obj_key.key[] size */
-#define KEY_SIZE_TKIP   32	/* TKIP keys */
-
-static void prism54_wpa_bss_ie_add(islpci_private *priv, u8 *bssid,
-				u8 *wpa_ie, size_t wpa_ie_len);
-static size_t prism54_wpa_bss_ie_get(islpci_private *priv, u8 *bssid, u8 *wpa_ie);
-static int prism54_set_wpa(struct net_device *, struct iw_request_info *,
-				__u32 *, char *);
-
-/* In 500 kbps */
-static const unsigned char scan_rate_list[] = { 2, 4, 11, 22,
-						12, 18, 24, 36,
-						48, 72, 96, 108 };
-
-/**
- * prism54_mib_mode_helper - MIB change mode helper function
- * @priv: the &struct islpci_private object to modify
- * @iw_mode: new mode (%IW_MODE_*)
- *
- *  This is a helper function, hence it does not lock. Make sure
- *  caller deals with locking *if* necessary. This function sets the
- *  mode-dependent mib values and does the mapping of the Linux
- *  Wireless API modes to Device firmware modes. It also checks for
- *  correct valid Linux wireless modes.
- */
-static int
-prism54_mib_mode_helper(islpci_private *priv, u32 iw_mode)
-{
-	u32 config = INL_CONFIG_MANUALRUN;
-	u32 mode, bsstype;
-
-	/* For now, just catch early the Repeater and Secondary modes here */
-	if (iw_mode == IW_MODE_REPEAT || iw_mode == IW_MODE_SECOND) {
-		printk(KERN_DEBUG
-		       "%s(): Sorry, Repeater mode and Secondary mode "
-		       "are not yet supported by this driver.\n", __func__);
-		return -EINVAL;
-	}
-
-	priv->iw_mode = iw_mode;
-
-	switch (iw_mode) {
-	case IW_MODE_AUTO:
-		mode = INL_MODE_CLIENT;
-		bsstype = DOT11_BSSTYPE_ANY;
-		break;
-	case IW_MODE_ADHOC:
-		mode = INL_MODE_CLIENT;
-		bsstype = DOT11_BSSTYPE_IBSS;
-		break;
-	case IW_MODE_INFRA:
-		mode = INL_MODE_CLIENT;
-		bsstype = DOT11_BSSTYPE_INFRA;
-		break;
-	case IW_MODE_MASTER:
-		mode = INL_MODE_AP;
-		bsstype = DOT11_BSSTYPE_INFRA;
-		break;
-	case IW_MODE_MONITOR:
-		mode = INL_MODE_PROMISCUOUS;
-		bsstype = DOT11_BSSTYPE_ANY;
-		config |= INL_CONFIG_RXANNEX;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (init_wds)
-		config |= INL_CONFIG_WDS;
-	mgt_set(priv, DOT11_OID_BSSTYPE, &bsstype);
-	mgt_set(priv, OID_INL_CONFIG, &config);
-	mgt_set(priv, OID_INL_MODE, &mode);
-
-	return 0;
-}
-
-/*
- * prism54_mib_init - fill MIB cache with defaults
- *
- *  this function initializes the struct given as @mib with defaults,
- *  of which many are retrieved from the global module parameter
- *  variables.
- */
-void
-prism54_mib_init(islpci_private *priv)
-{
-	u32 channel, authen, wep, filter, dot1x, mlme, conformance, power, mode;
-	struct obj_buffer psm_buffer = {
-		.size = PSM_BUFFER_SIZE,
-		.addr = priv->device_psm_buffer
-	};
-
-	channel = CARD_DEFAULT_CHANNEL;
-	authen = CARD_DEFAULT_AUTHEN;
-	wep = CARD_DEFAULT_WEP;
-	filter = CARD_DEFAULT_FILTER; /* (0) Do not filter un-encrypted data */
-	dot1x = CARD_DEFAULT_DOT1X;
-	mlme = CARD_DEFAULT_MLME_MODE;
-	conformance = CARD_DEFAULT_CONFORMANCE;
-	power = 127;
-	mode = CARD_DEFAULT_IW_MODE;
-
-	mgt_set(priv, DOT11_OID_CHANNEL, &channel);
-	mgt_set(priv, DOT11_OID_AUTHENABLE, &authen);
-	mgt_set(priv, DOT11_OID_PRIVACYINVOKED, &wep);
-	mgt_set(priv, DOT11_OID_PSMBUFFER, &psm_buffer);
-	mgt_set(priv, DOT11_OID_EXUNENCRYPTED, &filter);
-	mgt_set(priv, DOT11_OID_DOT1XENABLE, &dot1x);
-	mgt_set(priv, DOT11_OID_MLMEAUTOLEVEL, &mlme);
-	mgt_set(priv, OID_INL_DOT11D_CONFORMANCE, &conformance);
-	mgt_set(priv, OID_INL_OUTPUTPOWER, &power);
-
-	/* This sets all of the mode-dependent values */
-	prism54_mib_mode_helper(priv, mode);
-}
-
-/* this will be executed outside of atomic context thanks to
- * schedule_work(), thus we can as well use sleeping semaphore
- * locking */
-void
-prism54_update_stats(struct work_struct *work)
-{
-	islpci_private *priv = container_of(work, islpci_private, stats_work);
-	char *data;
-	struct obj_bss bss, *bss2;
-	union oid_res_t r;
-
-	mutex_lock(&priv->stats_lock);
-
-/* Noise floor.
- * I'm not sure if the unit is dBm.
- * Note : If we are not connected, this value seems to be irrelevant. */
-
-	mgt_get_request(priv, DOT11_OID_NOISEFLOOR, 0, NULL, &r);
-	priv->local_iwstatistics.qual.noise = r.u;
-
-/* Get the rssi of the link. To do this we need to retrieve a bss. */
-
-	/* First get the MAC address of the AP we are associated with. */
-	mgt_get_request(priv, DOT11_OID_BSSID, 0, NULL, &r);
-	data = r.ptr;
-
-	/* copy this MAC to the bss */
-	memcpy(bss.address, data, ETH_ALEN);
-	kfree(data);
-
-	/* now ask for the corresponding bss */
-	mgt_get_request(priv, DOT11_OID_BSSFIND, 0, (void *) &bss, &r);
-	bss2 = r.ptr;
-	/* report the rssi and use it to calculate
-	 *  link quality through a signal-noise
-	 *  ratio */
-	priv->local_iwstatistics.qual.level = bss2->rssi;
-	priv->local_iwstatistics.qual.qual =
-	    bss2->rssi - priv->iwstatistics.qual.noise;
-
-	kfree(bss2);
-
-	/* report that the stats are new */
-	priv->local_iwstatistics.qual.updated = 0x7;
-
-/* Rx : unable to decrypt the MPDU */
-	mgt_get_request(priv, DOT11_OID_PRIVRXFAILED, 0, NULL, &r);
-	priv->local_iwstatistics.discard.code = r.u;
-
-/* Tx : Max MAC retries num reached */
-	mgt_get_request(priv, DOT11_OID_MPDUTXFAILED, 0, NULL, &r);
-	priv->local_iwstatistics.discard.retries = r.u;
-
-	mutex_unlock(&priv->stats_lock);
-}
-
-struct iw_statistics *
-prism54_get_wireless_stats(struct net_device *ndev)
-{
-	islpci_private *priv = netdev_priv(ndev);
-
-	/* If the stats are being updated return old data */
-	if (mutex_trylock(&priv->stats_lock)) {
-		memcpy(&priv->iwstatistics, &priv->local_iwstatistics,
-		       sizeof (struct iw_statistics));
-		/* They won't be marked updated for the next time */
-		priv->local_iwstatistics.qual.updated = 0;
-		mutex_unlock(&priv->stats_lock);
-	} else
-		priv->iwstatistics.qual.updated = 0;
-
-	/* Update our wireless stats, but do not schedule to often
-	 * (max 1 HZ) */
-	if ((priv->stats_timestamp == 0) ||
-	    time_after(jiffies, priv->stats_timestamp + 1 * HZ)) {
-		schedule_work(&priv->stats_work);
-		priv->stats_timestamp = jiffies;
-	}
-
-	return &priv->iwstatistics;
-}
-
-static int
-prism54_commit(struct net_device *ndev, struct iw_request_info *info,
-	       char *cwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-
-	/* simply re-set the last set SSID, this should commit most stuff */
-
-	/* Commit in Monitor mode is not necessary, also setting essid
-	 * in Monitor mode does not make sense and isn't allowed for this
-	 * device's firmware */
-	if (priv->iw_mode != IW_MODE_MONITOR)
-		return mgt_set_request(priv, DOT11_OID_SSID, 0, NULL);
-	return 0;
-}
-
-static int
-prism54_get_name(struct net_device *ndev, struct iw_request_info *info,
-		 char *cwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	char *capabilities;
-	union oid_res_t r;
-	int rvalue;
-
-	if (islpci_get_state(priv) < PRV_STATE_INIT) {
-		strncpy(cwrq, "NOT READY!", IFNAMSIZ);
-		return 0;
-	}
-	rvalue = mgt_get_request(priv, OID_INL_PHYCAPABILITIES, 0, NULL, &r);
-
-	switch (r.u) {
-	case INL_PHYCAP_5000MHZ:
-		capabilities = "IEEE 802.11a/b/g";
-		break;
-	case INL_PHYCAP_FAA:
-		capabilities = "IEEE 802.11b/g - FAA Support";
-		break;
-	case INL_PHYCAP_2400MHZ:
-	default:
-		capabilities = "IEEE 802.11b/g";	/* Default */
-		break;
-	}
-	strncpy(cwrq, capabilities, IFNAMSIZ);
-	return rvalue;
-}
-
-static int
-prism54_set_freq(struct net_device *ndev, struct iw_request_info *info,
-		 struct iw_freq *fwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	int rvalue;
-	u32 c;
-
-	if (fwrq->m < 1000)
-		/* we have a channel number */
-		c = fwrq->m;
-	else
-		c = (fwrq->e == 1) ? channel_of_freq(fwrq->m / 100000) : 0;
-
-	rvalue = c ? mgt_set_request(priv, DOT11_OID_CHANNEL, 0, &c) : -EINVAL;
-
-	/* Call commit handler */
-	return (rvalue ? rvalue : -EINPROGRESS);
-}
-
-static int
-prism54_get_freq(struct net_device *ndev, struct iw_request_info *info,
-		 struct iw_freq *fwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	union oid_res_t r;
-	int rvalue;
-
-	rvalue = mgt_get_request(priv, DOT11_OID_CHANNEL, 0, NULL, &r);
-	fwrq->i = r.u;
-	rvalue |= mgt_get_request(priv, DOT11_OID_FREQUENCY, 0, NULL, &r);
-	fwrq->m = r.u;
-	fwrq->e = 3;
-
-	return rvalue;
-}
-
-static int
-prism54_set_mode(struct net_device *ndev, struct iw_request_info *info,
-		 __u32 * uwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	u32 mlmeautolevel = CARD_DEFAULT_MLME_MODE;
-
-	/* Let's see if the user passed a valid Linux Wireless mode */
-	if (*uwrq > IW_MODE_MONITOR || *uwrq < IW_MODE_AUTO) {
-		printk(KERN_DEBUG
-		       "%s: %s() You passed a non-valid init_mode.\n",
-		       priv->ndev->name, __func__);
-		return -EINVAL;
-	}
-
-	down_write(&priv->mib_sem);
-
-	if (prism54_mib_mode_helper(priv, *uwrq)) {
-		up_write(&priv->mib_sem);
-		return -EOPNOTSUPP;
-	}
-
-	/* the ACL code needs an intermediate mlmeautolevel. The wpa stuff an
-	 * extended one.
-	 */
-	if ((*uwrq == IW_MODE_MASTER) && (priv->acl.policy != MAC_POLICY_OPEN))
-		mlmeautolevel = DOT11_MLME_INTERMEDIATE;
-	if (priv->wpa)
-		mlmeautolevel = DOT11_MLME_EXTENDED;
-
-	mgt_set(priv, DOT11_OID_MLMEAUTOLEVEL, &mlmeautolevel);
-
-	if (mgt_commit(priv)) {
-		up_write(&priv->mib_sem);
-		return -EIO;
-	}
-	priv->ndev->type = (priv->iw_mode == IW_MODE_MONITOR)
-	    ? priv->monitor_type : ARPHRD_ETHER;
-	up_write(&priv->mib_sem);
-
-	return 0;
-}
-
-/* Use mib cache */
-static int
-prism54_get_mode(struct net_device *ndev, struct iw_request_info *info,
-		 __u32 * uwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-
-	BUG_ON((priv->iw_mode < IW_MODE_AUTO) || (priv->iw_mode >
-						  IW_MODE_MONITOR));
-	*uwrq = priv->iw_mode;
-
-	return 0;
-}
-
-/* we use DOT11_OID_EDTHRESHOLD. From what I guess the card will not try to
- * emit data if (sensitivity > rssi - noise) (in dBm).
- * prism54_set_sens does not seem to work.
- */
-
-static int
-prism54_set_sens(struct net_device *ndev, struct iw_request_info *info,
-		 struct iw_param *vwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	u32 sens;
-
-	/* by default  the card sets this to 20. */
-	sens = vwrq->disabled ? 20 : vwrq->value;
-
-	return mgt_set_request(priv, DOT11_OID_EDTHRESHOLD, 0, &sens);
-}
-
-static int
-prism54_get_sens(struct net_device *ndev, struct iw_request_info *info,
-		 struct iw_param *vwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	union oid_res_t r;
-	int rvalue;
-
-	rvalue = mgt_get_request(priv, DOT11_OID_EDTHRESHOLD, 0, NULL, &r);
-
-	vwrq->value = r.u;
-	vwrq->disabled = (vwrq->value == 0);
-	vwrq->fixed = 1;
-
-	return rvalue;
-}
-
-static int
-prism54_get_range(struct net_device *ndev, struct iw_request_info *info,
-		  struct iw_point *dwrq, char *extra)
-{
-	struct iw_range *range = (struct iw_range *) extra;
-	islpci_private *priv = netdev_priv(ndev);
-	u8 *data;
-	int i, m, rvalue;
-	struct obj_frequencies *freq;
-	union oid_res_t r;
-
-	memset(range, 0, sizeof (struct iw_range));
-	dwrq->length = sizeof (struct iw_range);
-
-	/* set the wireless extension version number */
-	range->we_version_source = SUPPORTED_WIRELESS_EXT;
-	range->we_version_compiled = WIRELESS_EXT;
-
-	/* Now the encoding capabilities */
-	range->num_encoding_sizes = 3;
-	/* 64(40) bits WEP */
-	range->encoding_size[0] = 5;
-	/* 128(104) bits WEP */
-	range->encoding_size[1] = 13;
-	/* 256 bits for WPA-PSK */
-	range->encoding_size[2] = 32;
-	/* 4 keys are allowed */
-	range->max_encoding_tokens = 4;
-
-	/* we don't know the quality range... */
-	range->max_qual.level = 0;
-	range->max_qual.noise = 0;
-	range->max_qual.qual = 0;
-	/* these value describe an average quality. Needs more tweaking... */
-	range->avg_qual.level = -80;	/* -80 dBm */
-	range->avg_qual.noise = 0;	/* don't know what to put here */
-	range->avg_qual.qual = 0;
-
-	range->sensitivity = 200;
-
-	/* retry limit capabilities */
-	range->retry_capa = IW_RETRY_LIMIT | IW_RETRY_LIFETIME;
-	range->retry_flags = IW_RETRY_LIMIT;
-	range->r_time_flags = IW_RETRY_LIFETIME;
-
-	/* I don't know the range. Put stupid things here */
-	range->min_retry = 1;
-	range->max_retry = 65535;
-	range->min_r_time = 1024;
-	range->max_r_time = 65535 * 1024;
-
-	/* txpower is supported in dBm's */
-	range->txpower_capa = IW_TXPOW_DBM;
-
-	/* Event capability (kernel + driver) */
-	range->event_capa[0] = (IW_EVENT_CAPA_K_0 |
-	IW_EVENT_CAPA_MASK(SIOCGIWTHRSPY) |
-	IW_EVENT_CAPA_MASK(SIOCGIWAP));
-	range->event_capa[1] = IW_EVENT_CAPA_K_1;
-	range->event_capa[4] = IW_EVENT_CAPA_MASK(IWEVCUSTOM);
-
-	range->enc_capa = IW_ENC_CAPA_WPA | IW_ENC_CAPA_WPA2 |
-		IW_ENC_CAPA_CIPHER_TKIP;
-
-	if (islpci_get_state(priv) < PRV_STATE_INIT)
-		return 0;
-
-	/* Request the device for the supported frequencies
-	 * not really relevant since some devices will report the 5 GHz band
-	 * frequencies even if they don't support them.
-	 */
-	rvalue =
-	    mgt_get_request(priv, DOT11_OID_SUPPORTEDFREQUENCIES, 0, NULL, &r);
-	freq = r.ptr;
-
-	range->num_channels = freq->nr;
-	range->num_frequency = freq->nr;
-
-	m = min(IW_MAX_FREQUENCIES, (int) freq->nr);
-	for (i = 0; i < m; i++) {
-		range->freq[i].m = freq->mhz[i];
-		range->freq[i].e = 6;
-		range->freq[i].i = channel_of_freq(freq->mhz[i]);
-	}
-	kfree(freq);
-
-	rvalue |= mgt_get_request(priv, DOT11_OID_SUPPORTEDRATES, 0, NULL, &r);
-	data = r.ptr;
-
-	/* We got an array of char. It is NULL terminated. */
-	i = 0;
-	while ((i < IW_MAX_BITRATES) && (*data != 0)) {
-		/*       the result must be in bps. The card gives us 500Kbps */
-		range->bitrate[i] = *data * 500000;
-		i++;
-		data++;
-	}
-	range->num_bitrates = i;
-	kfree(r.ptr);
-
-	return rvalue;
-}
-
-/* Set AP address*/
-
-static int
-prism54_set_wap(struct net_device *ndev, struct iw_request_info *info,
-		struct sockaddr *awrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	char bssid[6];
-	int rvalue;
-
-	if (awrq->sa_family != ARPHRD_ETHER)
-		return -EINVAL;
-
-	/* prepare the structure for the set object */
-	memcpy(&bssid[0], awrq->sa_data, ETH_ALEN);
-
-	/* set the bssid -- does this make sense when in AP mode? */
-	rvalue = mgt_set_request(priv, DOT11_OID_BSSID, 0, &bssid);
-
-	return (rvalue ? rvalue : -EINPROGRESS);	/* Call commit handler */
-}
-
-/* get AP address*/
-
-static int
-prism54_get_wap(struct net_device *ndev, struct iw_request_info *info,
-		struct sockaddr *awrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	union oid_res_t r;
-	int rvalue;
-
-	rvalue = mgt_get_request(priv, DOT11_OID_BSSID, 0, NULL, &r);
-	memcpy(awrq->sa_data, r.ptr, ETH_ALEN);
-	awrq->sa_family = ARPHRD_ETHER;
-	kfree(r.ptr);
-
-	return rvalue;
-}
-
-static int
-prism54_set_scan(struct net_device *dev, struct iw_request_info *info,
-		 struct iw_param *vwrq, char *extra)
-{
-	/* hehe the device does this automagicaly */
-	return 0;
-}
-
-/* a little helper that will translate our data into a card independent
- * format that the Wireless Tools will understand. This was inspired by
- * the "Aironet driver for 4500 and 4800 series cards" (GPL)
- */
-
-static char *
-prism54_translate_bss(struct net_device *ndev, struct iw_request_info *info,
-		      char *current_ev, char *end_buf, struct obj_bss *bss,
-		      char noise)
-{
-	struct iw_event iwe;	/* Temporary buffer */
-	short cap;
-	islpci_private *priv = netdev_priv(ndev);
-	u8 wpa_ie[MAX_WPA_IE_LEN];
-	size_t wpa_ie_len;
-
-	/* The first entry must be the MAC address */
-	memcpy(iwe.u.ap_addr.sa_data, bss->address, ETH_ALEN);
-	iwe.u.ap_addr.sa_family = ARPHRD_ETHER;
-	iwe.cmd = SIOCGIWAP;
-	current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-					  &iwe, IW_EV_ADDR_LEN);
-
-	/* The following entries will be displayed in the same order we give them */
-
-	/* The ESSID. */
-	iwe.u.data.length = bss->ssid.length;
-	iwe.u.data.flags = 1;
-	iwe.cmd = SIOCGIWESSID;
-	current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-					  &iwe, bss->ssid.octets);
-
-	/* Capabilities */
-#define CAP_ESS 0x01
-#define CAP_IBSS 0x02
-#define CAP_CRYPT 0x10
-
-	/* Mode */
-	cap = bss->capinfo;
-	iwe.u.mode = 0;
-	if (cap & CAP_ESS)
-		iwe.u.mode = IW_MODE_MASTER;
-	else if (cap & CAP_IBSS)
-		iwe.u.mode = IW_MODE_ADHOC;
-	iwe.cmd = SIOCGIWMODE;
-	if (iwe.u.mode)
-		current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-						  &iwe, IW_EV_UINT_LEN);
-
-	/* Encryption capability */
-	if (cap & CAP_CRYPT)
-		iwe.u.data.flags = IW_ENCODE_ENABLED | IW_ENCODE_NOKEY;
-	else
-		iwe.u.data.flags = IW_ENCODE_DISABLED;
-	iwe.u.data.length = 0;
-	iwe.cmd = SIOCGIWENCODE;
-	current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-					  &iwe, NULL);
-
-	/* Add frequency. (short) bss->channel is the frequency in MHz */
-	iwe.u.freq.m = bss->channel;
-	iwe.u.freq.e = 6;
-	iwe.cmd = SIOCGIWFREQ;
-	current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-					  &iwe, IW_EV_FREQ_LEN);
-
-	/* Add quality statistics */
-	iwe.u.qual.level = bss->rssi;
-	iwe.u.qual.noise = noise;
-	/* do a simple SNR for quality */
-	iwe.u.qual.qual = bss->rssi - noise;
-	iwe.cmd = IWEVQUAL;
-	current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-					  &iwe, IW_EV_QUAL_LEN);
-
-	/* Add WPA/RSN Information Element, if any */
-	wpa_ie_len = prism54_wpa_bss_ie_get(priv, bss->address, wpa_ie);
-	if (wpa_ie_len > 0) {
-		iwe.cmd = IWEVGENIE;
-		iwe.u.data.length = min_t(size_t, wpa_ie_len, MAX_WPA_IE_LEN);
-		current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-						  &iwe, wpa_ie);
-	}
-	/* Do the bitrates */
-	{
-		char *current_val = current_ev + iwe_stream_lcp_len(info);
-		int i;
-		int mask;
-
-		iwe.cmd = SIOCGIWRATE;
-		/* Those two flags are ignored... */
-		iwe.u.bitrate.fixed = iwe.u.bitrate.disabled = 0;
-
-		/* Parse the bitmask */
-		mask = 0x1;
-		for(i = 0; i < sizeof(scan_rate_list); i++) {
-			if(bss->rates & mask) {
-				iwe.u.bitrate.value = (scan_rate_list[i] * 500000);
-				current_val = iwe_stream_add_value(
-					info, current_ev, current_val,
-					end_buf, &iwe, IW_EV_PARAM_LEN);
-			}
-			mask <<= 1;
-		}
-		/* Check if we added any event */
-		if ((current_val - current_ev) > iwe_stream_lcp_len(info))
-			current_ev = current_val;
-	}
-
-	return current_ev;
-}
-
-static int
-prism54_get_scan(struct net_device *ndev, struct iw_request_info *info,
-		 struct iw_point *dwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	int i, rvalue;
-	struct obj_bsslist *bsslist;
-	u32 noise = 0;
-	char *current_ev = extra;
-	union oid_res_t r;
-
-	if (islpci_get_state(priv) < PRV_STATE_INIT) {
-		/* device is not ready, fail gently */
-		dwrq->length = 0;
-		return 0;
-	}
-
-	/* first get the noise value. We will use it to report the link quality */
-	rvalue = mgt_get_request(priv, DOT11_OID_NOISEFLOOR, 0, NULL, &r);
-	noise = r.u;
-
-	/* Ask the device for a list of known bss.
-	* The old API, using SIOCGIWAPLIST, had a hard limit of IW_MAX_AP=64.
-	* The new API, using SIOCGIWSCAN, is only limited by the buffer size.
-	* WE-14->WE-16, the buffer is limited to IW_SCAN_MAX_DATA bytes.
-	* Starting with WE-17, the buffer can be as big as needed.
-	* But the device won't repport anything if you change the value
-	* of IWMAX_BSS=24. */
-
-	rvalue |= mgt_get_request(priv, DOT11_OID_BSSLIST, 0, NULL, &r);
-	bsslist = r.ptr;
-
-	/* ok now, scan the list and translate its info */
-	for (i = 0; i < (int) bsslist->nr; i++) {
-		current_ev = prism54_translate_bss(ndev, info, current_ev,
-						   extra + dwrq->length,
-						   &(bsslist->bsslist[i]),
-						   noise);
-
-		/* Check if there is space for one more entry */
-		if((extra + dwrq->length - current_ev) <= IW_EV_ADDR_LEN) {
-			/* Ask user space to try again with a bigger buffer */
-			rvalue = -E2BIG;
-			break;
-		}
-	}
-
-	kfree(bsslist);
-	dwrq->length = (current_ev - extra);
-	dwrq->flags = 0;	/* todo */
-
-	return rvalue;
-}
-
-static int
-prism54_set_essid(struct net_device *ndev, struct iw_request_info *info,
-		  struct iw_point *dwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct obj_ssid essid;
-
-	memset(essid.octets, 0, 33);
-
-	/* Check if we were asked for `any' */
-	if (dwrq->flags && dwrq->length) {
-		if (dwrq->length > 32)
-			return -E2BIG;
-		essid.length = dwrq->length;
-		memcpy(essid.octets, extra, dwrq->length);
-	} else
-		essid.length = 0;
-
-	if (priv->iw_mode != IW_MODE_MONITOR)
-		return mgt_set_request(priv, DOT11_OID_SSID, 0, &essid);
-
-	/* If in monitor mode, just save to mib */
-	mgt_set(priv, DOT11_OID_SSID, &essid);
-	return 0;
-
-}
-
-static int
-prism54_get_essid(struct net_device *ndev, struct iw_request_info *info,
-		  struct iw_point *dwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct obj_ssid *essid;
-	union oid_res_t r;
-	int rvalue;
-
-	rvalue = mgt_get_request(priv, DOT11_OID_SSID, 0, NULL, &r);
-	essid = r.ptr;
-
-	if (essid->length) {
-		dwrq->flags = 1;	/* set ESSID to ON for Wireless Extensions */
-		/* if it is too big, trunk it */
-		dwrq->length = min((u8)IW_ESSID_MAX_SIZE, essid->length);
-	} else {
-		dwrq->flags = 0;
-		dwrq->length = 0;
-	}
-	essid->octets[dwrq->length] = '\0';
-	memcpy(extra, essid->octets, dwrq->length);
-	kfree(essid);
-
-	return rvalue;
-}
-
-/* Provides no functionality, just completes the ioctl. In essence this is a
- * just a cosmetic ioctl.
- */
-static int
-prism54_set_nick(struct net_device *ndev, struct iw_request_info *info,
-		 struct iw_point *dwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-
-	if (dwrq->length > IW_ESSID_MAX_SIZE)
-		return -E2BIG;
-
-	down_write(&priv->mib_sem);
-	memset(priv->nickname, 0, sizeof (priv->nickname));
-	memcpy(priv->nickname, extra, dwrq->length);
-	up_write(&priv->mib_sem);
-
-	return 0;
-}
-
-static int
-prism54_get_nick(struct net_device *ndev, struct iw_request_info *info,
-		 struct iw_point *dwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-
-	dwrq->length = 0;
-
-	down_read(&priv->mib_sem);
-	dwrq->length = strlen(priv->nickname);
-	memcpy(extra, priv->nickname, dwrq->length);
-	up_read(&priv->mib_sem);
-
-	return 0;
-}
-
-/* Set the allowed Bitrates */
-
-static int
-prism54_set_rate(struct net_device *ndev,
-		 struct iw_request_info *info,
-		 struct iw_param *vwrq, char *extra)
-{
-
-	islpci_private *priv = netdev_priv(ndev);
-	u32 rate, profile;
-	char *data;
-	int ret, i;
-	union oid_res_t r;
-
-	if (vwrq->value == -1) {
-		/* auto mode. No limit. */
-		profile = 1;
-		return mgt_set_request(priv, DOT11_OID_PROFILES, 0, &profile);
-	}
-
-	ret = mgt_get_request(priv, DOT11_OID_SUPPORTEDRATES, 0, NULL, &r);
-	if (ret) {
-		kfree(r.ptr);
-		return ret;
-	}
-
-	rate = (u32) (vwrq->value / 500000);
-	data = r.ptr;
-	i = 0;
-
-	while (data[i]) {
-		if (rate && (data[i] == rate)) {
-			break;
-		}
-		if (vwrq->value == i) {
-			break;
-		}
-		data[i] |= 0x80;
-		i++;
-	}
-
-	if (!data[i]) {
-		kfree(r.ptr);
-		return -EINVAL;
-	}
-
-	data[i] |= 0x80;
-	data[i + 1] = 0;
-
-	/* Now, check if we want a fixed or auto value */
-	if (vwrq->fixed) {
-		data[0] = data[i];
-		data[1] = 0;
-	}
-
-/*
-	i = 0;
-	printk("prism54 rate: ");
-	while(data[i]) {
-		printk("%u ", data[i]);
-		i++;
-	}
-	printk("0\n");
-*/
-	profile = -1;
-	ret = mgt_set_request(priv, DOT11_OID_PROFILES, 0, &profile);
-	ret |= mgt_set_request(priv, DOT11_OID_EXTENDEDRATES, 0, data);
-	ret |= mgt_set_request(priv, DOT11_OID_RATES, 0, data);
-
-	kfree(r.ptr);
-
-	return ret;
-}
-
-/* Get the current bit rate */
-static int
-prism54_get_rate(struct net_device *ndev,
-		 struct iw_request_info *info,
-		 struct iw_param *vwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	int rvalue;
-	char *data;
-	union oid_res_t r;
-
-	/* Get the current bit rate */
-	if ((rvalue = mgt_get_request(priv, GEN_OID_LINKSTATE, 0, NULL, &r)))
-		return rvalue;
-	vwrq->value = r.u * 500000;
-
-	/* request the device for the enabled rates */
-	rvalue = mgt_get_request(priv, DOT11_OID_RATES, 0, NULL, &r);
-	if (rvalue) {
-		kfree(r.ptr);
-		return rvalue;
-	}
-	data = r.ptr;
-	vwrq->fixed = (data[0] != 0) && (data[1] == 0);
-	kfree(r.ptr);
-
-	return 0;
-}
-
-static int
-prism54_set_rts(struct net_device *ndev, struct iw_request_info *info,
-		struct iw_param *vwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-
-	return mgt_set_request(priv, DOT11_OID_RTSTHRESH, 0, &vwrq->value);
-}
-
-static int
-prism54_get_rts(struct net_device *ndev, struct iw_request_info *info,
-		struct iw_param *vwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	union oid_res_t r;
-	int rvalue;
-
-	/* get the rts threshold */
-	rvalue = mgt_get_request(priv, DOT11_OID_RTSTHRESH, 0, NULL, &r);
-	vwrq->value = r.u;
-
-	return rvalue;
-}
-
-static int
-prism54_set_frag(struct net_device *ndev, struct iw_request_info *info,
-		 struct iw_param *vwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-
-	return mgt_set_request(priv, DOT11_OID_FRAGTHRESH, 0, &vwrq->value);
-}
-
-static int
-prism54_get_frag(struct net_device *ndev, struct iw_request_info *info,
-		 struct iw_param *vwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	union oid_res_t r;
-	int rvalue;
-
-	rvalue = mgt_get_request(priv, DOT11_OID_FRAGTHRESH, 0, NULL, &r);
-	vwrq->value = r.u;
-
-	return rvalue;
-}
-
-/* Here we have (min,max) = max retries for (small frames, big frames). Where
- * big frame <=>  bigger than the rts threshold
- * small frame <=>  smaller than the rts threshold
- * This is not really the behavior expected by the wireless tool but it seems
- * to be a common behavior in other drivers.
- */
-
-static int
-prism54_set_retry(struct net_device *ndev, struct iw_request_info *info,
-		  struct iw_param *vwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	u32 slimit = 0, llimit = 0;	/* short and long limit */
-	u32 lifetime = 0;
-	int rvalue = 0;
-
-	if (vwrq->disabled)
-		/* we cannot disable this feature */
-		return -EINVAL;
-
-	if (vwrq->flags & IW_RETRY_LIMIT) {
-		if (vwrq->flags & IW_RETRY_SHORT)
-			slimit = vwrq->value;
-		else if (vwrq->flags & IW_RETRY_LONG)
-			llimit = vwrq->value;
-		else {
-			/* we are asked to set both */
-			slimit = vwrq->value;
-			llimit = vwrq->value;
-		}
-	}
-	if (vwrq->flags & IW_RETRY_LIFETIME)
-		/* Wireless tools use us unit while the device uses 1024 us unit */
-		lifetime = vwrq->value / 1024;
-
-	/* now set what is requested */
-	if (slimit)
-		rvalue =
-		    mgt_set_request(priv, DOT11_OID_SHORTRETRIES, 0, &slimit);
-	if (llimit)
-		rvalue |=
-		    mgt_set_request(priv, DOT11_OID_LONGRETRIES, 0, &llimit);
-	if (lifetime)
-		rvalue |=
-		    mgt_set_request(priv, DOT11_OID_MAXTXLIFETIME, 0,
-				    &lifetime);
-	return rvalue;
-}
-
-static int
-prism54_get_retry(struct net_device *ndev, struct iw_request_info *info,
-		  struct iw_param *vwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	union oid_res_t r;
-	int rvalue = 0;
-	vwrq->disabled = 0;	/* It cannot be disabled */
-
-	if ((vwrq->flags & IW_RETRY_TYPE) == IW_RETRY_LIFETIME) {
-		/* we are asked for the life time */
-		rvalue =
-		    mgt_get_request(priv, DOT11_OID_MAXTXLIFETIME, 0, NULL, &r);
-		vwrq->value = r.u * 1024;
-		vwrq->flags = IW_RETRY_LIFETIME;
-	} else if ((vwrq->flags & IW_RETRY_LONG)) {
-		/* we are asked for the long retry limit */
-		rvalue |=
-		    mgt_get_request(priv, DOT11_OID_LONGRETRIES, 0, NULL, &r);
-		vwrq->value = r.u;
-		vwrq->flags = IW_RETRY_LIMIT | IW_RETRY_LONG;
-	} else {
-		/* default. get the  short retry limit */
-		rvalue |=
-		    mgt_get_request(priv, DOT11_OID_SHORTRETRIES, 0, NULL, &r);
-		vwrq->value = r.u;
-		vwrq->flags = IW_RETRY_LIMIT | IW_RETRY_SHORT;
-	}
-
-	return rvalue;
-}
-
-static int
-prism54_set_encode(struct net_device *ndev, struct iw_request_info *info,
-		   struct iw_point *dwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	int rvalue = 0, force = 0;
-	int authen = DOT11_AUTH_OS, invoke = 0, exunencrypt = 0;
-	union oid_res_t r;
-
-	/* with the new API, it's impossible to get a NULL pointer.
-	 * New version of iwconfig set the IW_ENCODE_NOKEY flag
-	 * when no key is given, but older versions don't. */
-
-	if (dwrq->length > 0) {
-		/* we have a key to set */
-		int index = (dwrq->flags & IW_ENCODE_INDEX) - 1;
-		int current_index;
-		struct obj_key key = { DOT11_PRIV_WEP, 0, "" };
-
-		/* get the current key index */
-		rvalue = mgt_get_request(priv, DOT11_OID_DEFKEYID, 0, NULL, &r);
-		current_index = r.u;
-		/* Verify that the key is not marked as invalid */
-		if (!(dwrq->flags & IW_ENCODE_NOKEY)) {
-			if (dwrq->length > KEY_SIZE_TKIP) {
-				/* User-provided key data too big */
-				return -EINVAL;
-			}
-			if (dwrq->length > KEY_SIZE_WEP104) {
-				/* WPA-PSK TKIP */
-				key.type = DOT11_PRIV_TKIP;
-				key.length = KEY_SIZE_TKIP;
-			} else if (dwrq->length > KEY_SIZE_WEP40) {
-				/* WEP 104/128 */
-				key.length = KEY_SIZE_WEP104;
-			} else {
-				/* WEP 40/64 */
-				key.length = KEY_SIZE_WEP40;
-			}
-			memset(key.key, 0, sizeof (key.key));
-			memcpy(key.key, extra, dwrq->length);
-
-			if ((index < 0) || (index > 3))
-				/* no index provided use the current one */
-				index = current_index;
-
-			/* now send the key to the card  */
-			rvalue |=
-			    mgt_set_request(priv, DOT11_OID_DEFKEYX, index,
-					    &key);
-		}
-		/*
-		 * If a valid key is set, encryption should be enabled
-		 * (user may turn it off later).
-		 * This is also how "iwconfig ethX key on" works
-		 */
-		if ((index == current_index) && (key.length > 0))
-			force = 1;
-	} else {
-		int index = (dwrq->flags & IW_ENCODE_INDEX) - 1;
-		if ((index >= 0) && (index <= 3)) {
-			/* we want to set the key index */
-			rvalue |=
-			    mgt_set_request(priv, DOT11_OID_DEFKEYID, 0,
-					    &index);
-		} else {
-			if (!(dwrq->flags & IW_ENCODE_MODE)) {
-				/* we cannot do anything. Complain. */
-				return -EINVAL;
-			}
-		}
-	}
-	/* now read the flags */
-	if (dwrq->flags & IW_ENCODE_DISABLED) {
-		/* Encoding disabled,
-		 * authen = DOT11_AUTH_OS;
-		 * invoke = 0;
-		 * exunencrypt = 0; */
-	}
-	if (dwrq->flags & IW_ENCODE_OPEN)
-		/* Encode but accept non-encoded packets. No auth */
-		invoke = 1;
-	if ((dwrq->flags & IW_ENCODE_RESTRICTED) || force) {
-		/* Refuse non-encoded packets. Auth */
-		authen = DOT11_AUTH_BOTH;
-		invoke = 1;
-		exunencrypt = 1;
-	}
-	/* do the change if requested  */
-	if ((dwrq->flags & IW_ENCODE_MODE) || force) {
-		rvalue |=
-		    mgt_set_request(priv, DOT11_OID_AUTHENABLE, 0, &authen);
-		rvalue |=
-		    mgt_set_request(priv, DOT11_OID_PRIVACYINVOKED, 0, &invoke);
-		rvalue |=
-		    mgt_set_request(priv, DOT11_OID_EXUNENCRYPTED, 0,
-				    &exunencrypt);
-	}
-	return rvalue;
-}
-
-static int
-prism54_get_encode(struct net_device *ndev, struct iw_request_info *info,
-		   struct iw_point *dwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct obj_key *key;
-	u32 devindex, index = (dwrq->flags & IW_ENCODE_INDEX) - 1;
-	u32 authen = 0, invoke = 0, exunencrypt = 0;
-	int rvalue;
-	union oid_res_t r;
-
-	/* first get the flags */
-	rvalue = mgt_get_request(priv, DOT11_OID_AUTHENABLE, 0, NULL, &r);
-	authen = r.u;
-	rvalue |= mgt_get_request(priv, DOT11_OID_PRIVACYINVOKED, 0, NULL, &r);
-	invoke = r.u;
-	rvalue |= mgt_get_request(priv, DOT11_OID_EXUNENCRYPTED, 0, NULL, &r);
-	exunencrypt = r.u;
-
-	if (invoke && (authen == DOT11_AUTH_BOTH) && exunencrypt)
-		dwrq->flags = IW_ENCODE_RESTRICTED;
-	else if ((authen == DOT11_AUTH_OS) && !exunencrypt) {
-		if (invoke)
-			dwrq->flags = IW_ENCODE_OPEN;
-		else
-			dwrq->flags = IW_ENCODE_DISABLED;
-	} else
-		/* The card should not work in this state */
-		dwrq->flags = 0;
-
-	/* get the current device key index */
-	rvalue |= mgt_get_request(priv, DOT11_OID_DEFKEYID, 0, NULL, &r);
-	devindex = r.u;
-	/* Now get the key, return it */
-	if (index == -1 || index > 3)
-		/* no index provided, use the current one */
-		index = devindex;
-	rvalue |= mgt_get_request(priv, DOT11_OID_DEFKEYX, index, NULL, &r);
-	key = r.ptr;
-	dwrq->length = key->length;
-	memcpy(extra, key->key, dwrq->length);
-	kfree(key);
-	/* return the used key index */
-	dwrq->flags |= devindex + 1;
-
-	return rvalue;
-}
-
-static int
-prism54_get_txpower(struct net_device *ndev, struct iw_request_info *info,
-		    struct iw_param *vwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	union oid_res_t r;
-	int rvalue;
-
-	rvalue = mgt_get_request(priv, OID_INL_OUTPUTPOWER, 0, NULL, &r);
-	/* intersil firmware operates in 0.25 dBm (1/4 dBm) */
-	vwrq->value = (s32) r.u / 4;
-	vwrq->fixed = 1;
-	/* radio is not turned of
-	 * btw: how is possible to turn off only the radio
-	 */
-	vwrq->disabled = 0;
-
-	return rvalue;
-}
-
-static int
-prism54_set_txpower(struct net_device *ndev, struct iw_request_info *info,
-		    struct iw_param *vwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	s32 u = vwrq->value;
-
-	/* intersil firmware operates in 0.25 dBm (1/4) */
-	u *= 4;
-	if (vwrq->disabled) {
-		/* don't know how to disable radio */
-		printk(KERN_DEBUG
-		       "%s: %s() disabling radio is not yet supported.\n",
-		       priv->ndev->name, __func__);
-		return -ENOTSUPP;
-	} else if (vwrq->fixed)
-		/* currently only fixed value is supported */
-		return mgt_set_request(priv, OID_INL_OUTPUTPOWER, 0, &u);
-	else {
-		printk(KERN_DEBUG
-		       "%s: %s() auto power will be implemented later.\n",
-		       priv->ndev->name, __func__);
-		return -ENOTSUPP;
-	}
-}
-
-static int prism54_set_genie(struct net_device *ndev,
-			     struct iw_request_info *info,
-			     struct iw_point *data, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	int alen, ret = 0;
-	struct obj_attachment *attach;
-
-	if (data->length > MAX_WPA_IE_LEN ||
-	    (data->length && extra == NULL))
-		return -EINVAL;
-
-	memcpy(priv->wpa_ie, extra, data->length);
-	priv->wpa_ie_len = data->length;
-
-	alen = sizeof(*attach) + priv->wpa_ie_len;
-	attach = kzalloc(alen, GFP_KERNEL);
-	if (attach == NULL)
-		return -ENOMEM;
-
-#define WLAN_FC_TYPE_MGMT 0
-#define WLAN_FC_STYPE_ASSOC_REQ 0
-#define WLAN_FC_STYPE_REASSOC_REQ 2
-
-	/* Note: endianness is covered by mgt_set_varlen */
-	attach->type = (WLAN_FC_TYPE_MGMT << 2) |
-               (WLAN_FC_STYPE_ASSOC_REQ << 4);
-	attach->id = -1;
-	attach->size = priv->wpa_ie_len;
-	memcpy(attach->data, extra, priv->wpa_ie_len);
-
-	ret = mgt_set_varlen(priv, DOT11_OID_ATTACHMENT, attach,
-		priv->wpa_ie_len);
-	if (ret == 0) {
-		attach->type = (WLAN_FC_TYPE_MGMT << 2) |
-			(WLAN_FC_STYPE_REASSOC_REQ << 4);
-
-		ret = mgt_set_varlen(priv, DOT11_OID_ATTACHMENT, attach,
-			priv->wpa_ie_len);
-		if (ret == 0)
-			printk(KERN_DEBUG "%s: WPA IE Attachment was set\n",
-				ndev->name);
-	}
-
-	kfree(attach);
-	return ret;
-}
-
-
-static int prism54_get_genie(struct net_device *ndev,
-			     struct iw_request_info *info,
-			     struct iw_point *data, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	int len = priv->wpa_ie_len;
-
-	if (len <= 0) {
-		data->length = 0;
-		return 0;
-	}
-
-	if (data->length < len)
-		return -E2BIG;
-
-	data->length = len;
-	memcpy(extra, priv->wpa_ie, len);
-
-	return 0;
-}
-
-static int prism54_set_auth(struct net_device *ndev,
-			       struct iw_request_info *info,
-			       union iwreq_data *wrqu, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct iw_param *param = &wrqu->param;
-	u32 mlmelevel = 0, authen = 0, dot1x = 0;
-	u32 exunencrypt = 0, privinvoked = 0, wpa = 0;
-	u32 old_wpa;
-	int ret = 0;
-	union oid_res_t r;
-
-	if (islpci_get_state(priv) < PRV_STATE_INIT)
-		return 0;
-
-	/* first get the flags */
-	down_write(&priv->mib_sem);
-	wpa = old_wpa = priv->wpa;
-	up_write(&priv->mib_sem);
-	ret = mgt_get_request(priv, DOT11_OID_AUTHENABLE, 0, NULL, &r);
-	authen = r.u;
-	ret = mgt_get_request(priv, DOT11_OID_PRIVACYINVOKED, 0, NULL, &r);
-	privinvoked = r.u;
-	ret = mgt_get_request(priv, DOT11_OID_EXUNENCRYPTED, 0, NULL, &r);
-	exunencrypt = r.u;
-	ret = mgt_get_request(priv, DOT11_OID_DOT1XENABLE, 0, NULL, &r);
-	dot1x = r.u;
-	ret = mgt_get_request(priv, DOT11_OID_MLMEAUTOLEVEL, 0, NULL, &r);
-	mlmelevel = r.u;
-
-	if (ret < 0)
-		goto out;
-
-	switch (param->flags & IW_AUTH_INDEX) {
-	case IW_AUTH_CIPHER_PAIRWISE:
-	case IW_AUTH_CIPHER_GROUP:
-	case IW_AUTH_KEY_MGMT:
-		break;
-
-	case IW_AUTH_WPA_ENABLED:
-		/* Do the same thing as IW_AUTH_WPA_VERSION */
-		if (param->value) {
-			wpa = 1;
-			privinvoked = 1; /* For privacy invoked */
-			exunencrypt = 1; /* Filter out all unencrypted frames */
-			dot1x = 0x01; /* To enable eap filter */
-			mlmelevel = DOT11_MLME_EXTENDED;
-			authen = DOT11_AUTH_OS; /* Only WEP uses _SK and _BOTH */
-		} else {
-			wpa = 0;
-			privinvoked = 0;
-			exunencrypt = 0; /* Do not filter un-encrypted data */
-			dot1x = 0;
-			mlmelevel = DOT11_MLME_AUTO;
-		}
-		break;
-
-	case IW_AUTH_WPA_VERSION:
-		if (param->value & IW_AUTH_WPA_VERSION_DISABLED) {
-			wpa = 0;
-			privinvoked = 0;
-			exunencrypt = 0; /* Do not filter un-encrypted data */
-			dot1x = 0;
-			mlmelevel = DOT11_MLME_AUTO;
-		} else {
-			if (param->value & IW_AUTH_WPA_VERSION_WPA)
-				wpa = 1;
-			else if (param->value & IW_AUTH_WPA_VERSION_WPA2)
-				wpa = 2;
-			privinvoked = 1; /* For privacy invoked */
-			exunencrypt = 1; /* Filter out all unencrypted frames */
-			dot1x = 0x01; /* To enable eap filter */
-			mlmelevel = DOT11_MLME_EXTENDED;
-			authen = DOT11_AUTH_OS; /* Only WEP uses _SK and _BOTH */
-		}
-		break;
-
-	case IW_AUTH_RX_UNENCRYPTED_EAPOL:
-		/* dot1x should be the opposite of RX_UNENCRYPTED_EAPOL;
-		 * turn off dot1x when allowing receipt of unencrypted EAPOL
-		 * frames, turn on dot1x when receipt should be disallowed
-		 */
-		dot1x = param->value ? 0 : 0x01;
-		break;
-
-	case IW_AUTH_PRIVACY_INVOKED:
-		privinvoked = param->value ? 1 : 0;
-		break;
-
-	case IW_AUTH_DROP_UNENCRYPTED:
-		exunencrypt = param->value ? 1 : 0;
-		break;
-
-	case IW_AUTH_80211_AUTH_ALG:
-		if (param->value & IW_AUTH_ALG_SHARED_KEY) {
-			/* Only WEP uses _SK and _BOTH */
-			if (wpa > 0) {
-				ret = -EINVAL;
-				goto out;
-			}
-			authen = DOT11_AUTH_SK;
-		} else if (param->value & IW_AUTH_ALG_OPEN_SYSTEM) {
-			authen = DOT11_AUTH_OS;
-		} else {
-			ret = -EINVAL;
-			goto out;
-		}
-		break;
-
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	/* Set all the values */
-	down_write(&priv->mib_sem);
-	priv->wpa = wpa;
-	up_write(&priv->mib_sem);
-	mgt_set_request(priv, DOT11_OID_AUTHENABLE, 0, &authen);
-	mgt_set_request(priv, DOT11_OID_PRIVACYINVOKED, 0, &privinvoked);
-	mgt_set_request(priv, DOT11_OID_EXUNENCRYPTED, 0, &exunencrypt);
-	mgt_set_request(priv, DOT11_OID_DOT1XENABLE, 0, &dot1x);
-	mgt_set_request(priv, DOT11_OID_MLMEAUTOLEVEL, 0, &mlmelevel);
-
-out:
-	return ret;
-}
-
-static int prism54_get_auth(struct net_device *ndev,
-			    struct iw_request_info *info,
-			    union iwreq_data *wrqu, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct iw_param *param = &wrqu->param;
-	u32 wpa = 0;
-	int ret = 0;
-	union oid_res_t r;
-
-	if (islpci_get_state(priv) < PRV_STATE_INIT)
-		return 0;
-
-	/* first get the flags */
-	down_write(&priv->mib_sem);
-	wpa = priv->wpa;
-	up_write(&priv->mib_sem);
-
-	switch (param->flags & IW_AUTH_INDEX) {
-	case IW_AUTH_CIPHER_PAIRWISE:
-	case IW_AUTH_CIPHER_GROUP:
-	case IW_AUTH_KEY_MGMT:
-		/*
-		 * wpa_supplicant will control these internally
-		 */
-		ret = -EOPNOTSUPP;
-		break;
-
-	case IW_AUTH_WPA_VERSION:
-		switch (wpa) {
-		case 1:
-			param->value = IW_AUTH_WPA_VERSION_WPA;
-			break;
-		case 2:
-			param->value = IW_AUTH_WPA_VERSION_WPA2;
-			break;
-		case 0:
-		default:
-			param->value = IW_AUTH_WPA_VERSION_DISABLED;
-			break;
-		}
-		break;
-
-	case IW_AUTH_DROP_UNENCRYPTED:
-		ret = mgt_get_request(priv, DOT11_OID_EXUNENCRYPTED, 0, NULL, &r);
-		if (ret >= 0)
-			param->value = r.u > 0 ? 1 : 0;
-		break;
-
-	case IW_AUTH_80211_AUTH_ALG:
-		ret = mgt_get_request(priv, DOT11_OID_AUTHENABLE, 0, NULL, &r);
-		if (ret >= 0) {
-			switch (r.u) {
-			case DOT11_AUTH_OS:
-				param->value = IW_AUTH_ALG_OPEN_SYSTEM;
-				break;
-			case DOT11_AUTH_BOTH:
-			case DOT11_AUTH_SK:
-				param->value = IW_AUTH_ALG_SHARED_KEY;
-				break;
-			case DOT11_AUTH_NONE:
-			default:
-				param->value = 0;
-				break;
-			}
-		}
-		break;
-
-	case IW_AUTH_WPA_ENABLED:
-		param->value = wpa > 0 ? 1 : 0;
-		break;
-
-	case IW_AUTH_RX_UNENCRYPTED_EAPOL:
-		ret = mgt_get_request(priv, DOT11_OID_DOT1XENABLE, 0, NULL, &r);
-		if (ret >= 0)
-			param->value = r.u > 0 ? 1 : 0;
-		break;
-
-	case IW_AUTH_PRIVACY_INVOKED:
-		ret = mgt_get_request(priv, DOT11_OID_PRIVACYINVOKED, 0, NULL, &r);
-		if (ret >= 0)
-			param->value = r.u > 0 ? 1 : 0;
-		break;
-
-	default:
-		return -EOPNOTSUPP;
-	}
-	return ret;
-}
-
-static int prism54_set_encodeext(struct net_device *ndev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu,
-				 char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct iw_point *encoding = &wrqu->encoding;
-	struct iw_encode_ext *ext = (struct iw_encode_ext *)extra;
-	int idx, alg = ext->alg, set_key = 1;
-	union oid_res_t r;
-	int authen = DOT11_AUTH_OS, invoke = 0, exunencrypt = 0;
-	int ret = 0;
-
-	if (islpci_get_state(priv) < PRV_STATE_INIT)
-		return 0;
-
-	/* Determine and validate the key index */
-	idx = (encoding->flags & IW_ENCODE_INDEX) - 1;
-	if (idx) {
-		if (idx < 0 || idx > 3)
-			return -EINVAL;
-	} else {
-		ret = mgt_get_request(priv, DOT11_OID_DEFKEYID, 0, NULL, &r);
-		if (ret < 0)
-			goto out;
-		idx = r.u;
-	}
-
-	if (encoding->flags & IW_ENCODE_DISABLED)
-		alg = IW_ENCODE_ALG_NONE;
-
-	if (ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY) {
-		/* Only set transmit key index here, actual
-		 * key is set below if needed.
-		 */
-		ret = mgt_set_request(priv, DOT11_OID_DEFKEYID, 0, &idx);
-		set_key = ext->key_len > 0 ? 1 : 0;
-	}
-
-	if (set_key) {
-		struct obj_key key = { DOT11_PRIV_WEP, 0, "" };
-		switch (alg) {
-		case IW_ENCODE_ALG_NONE:
-			break;
-		case IW_ENCODE_ALG_WEP:
-			if (ext->key_len > KEY_SIZE_WEP104) {
-				ret = -EINVAL;
-				goto out;
-			}
-			if (ext->key_len > KEY_SIZE_WEP40)
-				key.length = KEY_SIZE_WEP104;
-			else
-				key.length = KEY_SIZE_WEP40;
-			break;
-		case IW_ENCODE_ALG_TKIP:
-			if (ext->key_len > KEY_SIZE_TKIP) {
-				ret = -EINVAL;
-				goto out;
-			}
-			key.type = DOT11_PRIV_TKIP;
-			key.length = KEY_SIZE_TKIP;
-			break;
-		default:
-			return -EINVAL;
-		}
-
-		if (key.length) {
-			memset(key.key, 0, sizeof(key.key));
-			memcpy(key.key, ext->key, ext->key_len);
-			ret = mgt_set_request(priv, DOT11_OID_DEFKEYX, idx,
-					    &key);
-			if (ret < 0)
-				goto out;
-		}
-	}
-
-	/* Read the flags */
-	if (encoding->flags & IW_ENCODE_DISABLED) {
-		/* Encoding disabled,
-		 * authen = DOT11_AUTH_OS;
-		 * invoke = 0;
-		 * exunencrypt = 0; */
-	}
-	if (encoding->flags & IW_ENCODE_OPEN) {
-		/* Encode but accept non-encoded packets. No auth */
-		invoke = 1;
-	}
-	if (encoding->flags & IW_ENCODE_RESTRICTED) {
-		/* Refuse non-encoded packets. Auth */
-		authen = DOT11_AUTH_BOTH;
-		invoke = 1;
-		exunencrypt = 1;
-	}
-
-	/* do the change if requested  */
-	if (encoding->flags & IW_ENCODE_MODE) {
-		ret = mgt_set_request(priv, DOT11_OID_AUTHENABLE, 0,
-				      &authen);
-		ret = mgt_set_request(priv, DOT11_OID_PRIVACYINVOKED, 0,
-				      &invoke);
-		ret = mgt_set_request(priv, DOT11_OID_EXUNENCRYPTED, 0,
-				      &exunencrypt);
-	}
-
-out:
-	return ret;
-}
-
-
-static int prism54_get_encodeext(struct net_device *ndev,
-				 struct iw_request_info *info,
-				 union iwreq_data *wrqu,
-				 char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct iw_point *encoding = &wrqu->encoding;
-	struct iw_encode_ext *ext = (struct iw_encode_ext *)extra;
-	int idx, max_key_len;
-	union oid_res_t r;
-	int authen = DOT11_AUTH_OS, invoke = 0, exunencrypt = 0, wpa = 0;
-	int ret = 0;
-
-	if (islpci_get_state(priv) < PRV_STATE_INIT)
-		return 0;
-
-	/* first get the flags */
-	ret = mgt_get_request(priv, DOT11_OID_AUTHENABLE, 0, NULL, &r);
-	authen = r.u;
-	ret = mgt_get_request(priv, DOT11_OID_PRIVACYINVOKED, 0, NULL, &r);
-	invoke = r.u;
-	ret = mgt_get_request(priv, DOT11_OID_EXUNENCRYPTED, 0, NULL, &r);
-	exunencrypt = r.u;
-	if (ret < 0)
-		goto out;
-
-	max_key_len = encoding->length - sizeof(*ext);
-	if (max_key_len < 0)
-		return -EINVAL;
-
-	idx = (encoding->flags & IW_ENCODE_INDEX) - 1;
-	if (idx) {
-		if (idx < 0 || idx > 3)
-			return -EINVAL;
-	} else {
-		ret = mgt_get_request(priv, DOT11_OID_DEFKEYID, 0, NULL, &r);
-		if (ret < 0)
-			goto out;
-		idx = r.u;
-	}
-
-	encoding->flags = idx + 1;
-	memset(ext, 0, sizeof(*ext));
-
-	switch (authen) {
-	case DOT11_AUTH_BOTH:
-	case DOT11_AUTH_SK:
-		wrqu->encoding.flags |= IW_ENCODE_RESTRICTED;
-		fallthrough;
-	case DOT11_AUTH_OS:
-	default:
-		wrqu->encoding.flags |= IW_ENCODE_OPEN;
-		break;
-	}
-
-	down_write(&priv->mib_sem);
-	wpa = priv->wpa;
-	up_write(&priv->mib_sem);
-
-	if (authen == DOT11_AUTH_OS && !exunencrypt && !invoke && !wpa) {
-		/* No encryption */
-		ext->alg = IW_ENCODE_ALG_NONE;
-		ext->key_len = 0;
-		wrqu->encoding.flags |= IW_ENCODE_DISABLED;
-	} else {
-		struct obj_key *key;
-
-		ret = mgt_get_request(priv, DOT11_OID_DEFKEYX, idx, NULL, &r);
-		if (ret < 0)
-			goto out;
-		key = r.ptr;
-		if (max_key_len < key->length) {
-			ret = -E2BIG;
-			goto out;
-		}
-		memcpy(ext->key, key->key, key->length);
-		ext->key_len = key->length;
-
-		switch (key->type) {
-		case DOT11_PRIV_TKIP:
-			ext->alg = IW_ENCODE_ALG_TKIP;
-			break;
-		default:
-		case DOT11_PRIV_WEP:
-			ext->alg = IW_ENCODE_ALG_WEP;
-			break;
-		}
-		wrqu->encoding.flags |= IW_ENCODE_ENABLED;
-	}
-
-out:
-	return ret;
-}
-
-
-static int
-prism54_reset(struct net_device *ndev, struct iw_request_info *info,
-	      __u32 * uwrq, char *extra)
-{
-	islpci_reset(netdev_priv(ndev), 0);
-
-	return 0;
-}
-
-static int
-prism54_get_oid(struct net_device *ndev, struct iw_request_info *info,
-		struct iw_point *dwrq, char *extra)
-{
-	union oid_res_t r;
-	int rvalue;
-	enum oid_num_t n = dwrq->flags;
-
-	rvalue = mgt_get_request(netdev_priv(ndev), n, 0, NULL, &r);
-	dwrq->length = mgt_response_to_str(n, &r, extra);
-	if ((isl_oid[n].flags & OID_FLAG_TYPE) != OID_TYPE_U32)
-		kfree(r.ptr);
-	return rvalue;
-}
-
-static int
-prism54_set_u32(struct net_device *ndev, struct iw_request_info *info,
-		__u32 * uwrq, char *extra)
-{
-	u32 oid = uwrq[0], u = uwrq[1];
-
-	return mgt_set_request(netdev_priv(ndev), oid, 0, &u);
-}
-
-static int
-prism54_set_raw(struct net_device *ndev, struct iw_request_info *info,
-		struct iw_point *dwrq, char *extra)
-{
-	u32 oid = dwrq->flags;
-
-	return mgt_set_request(netdev_priv(ndev), oid, 0, extra);
-}
-
-void
-prism54_acl_init(struct islpci_acl *acl)
-{
-	mutex_init(&acl->lock);
-	INIT_LIST_HEAD(&acl->mac_list);
-	acl->size = 0;
-	acl->policy = MAC_POLICY_OPEN;
-}
-
-static void
-prism54_clear_mac(struct islpci_acl *acl)
-{
-	struct list_head *ptr, *next;
-	struct mac_entry *entry;
-
-	mutex_lock(&acl->lock);
-
-	if (acl->size == 0) {
-		mutex_unlock(&acl->lock);
-		return;
-	}
-
-	for (ptr = acl->mac_list.next, next = ptr->next;
-	     ptr != &acl->mac_list; ptr = next, next = ptr->next) {
-		entry = list_entry(ptr, struct mac_entry, _list);
-		list_del(ptr);
-		kfree(entry);
-	}
-	acl->size = 0;
-	mutex_unlock(&acl->lock);
-}
-
-void
-prism54_acl_clean(struct islpci_acl *acl)
-{
-	prism54_clear_mac(acl);
-}
-
-static int
-prism54_add_mac(struct net_device *ndev, struct iw_request_info *info,
-		struct sockaddr *awrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct islpci_acl *acl = &priv->acl;
-	struct mac_entry *entry;
-	struct sockaddr *addr = (struct sockaddr *) extra;
-
-	if (addr->sa_family != ARPHRD_ETHER)
-		return -EOPNOTSUPP;
-
-	entry = kmalloc(sizeof (struct mac_entry), GFP_KERNEL);
-	if (entry == NULL)
-		return -ENOMEM;
-
-	memcpy(entry->addr, addr->sa_data, ETH_ALEN);
-
-	if (mutex_lock_interruptible(&acl->lock)) {
-		kfree(entry);
-		return -ERESTARTSYS;
-	}
-	list_add_tail(&entry->_list, &acl->mac_list);
-	acl->size++;
-	mutex_unlock(&acl->lock);
-
-	return 0;
-}
-
-static int
-prism54_del_mac(struct net_device *ndev, struct iw_request_info *info,
-		struct sockaddr *awrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct islpci_acl *acl = &priv->acl;
-	struct mac_entry *entry;
-	struct sockaddr *addr = (struct sockaddr *) extra;
-
-	if (addr->sa_family != ARPHRD_ETHER)
-		return -EOPNOTSUPP;
-
-	if (mutex_lock_interruptible(&acl->lock))
-		return -ERESTARTSYS;
-	list_for_each_entry(entry, &acl->mac_list, _list) {
-		if (ether_addr_equal(entry->addr, addr->sa_data)) {
-			list_del(&entry->_list);
-			acl->size--;
-			kfree(entry);
-			mutex_unlock(&acl->lock);
-			return 0;
-		}
-	}
-	mutex_unlock(&acl->lock);
-	return -EINVAL;
-}
-
-static int
-prism54_get_mac(struct net_device *ndev, struct iw_request_info *info,
-		struct iw_point *dwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct islpci_acl *acl = &priv->acl;
-	struct mac_entry *entry;
-	struct sockaddr *dst = (struct sockaddr *) extra;
-
-	dwrq->length = 0;
-
-	if (mutex_lock_interruptible(&acl->lock))
-		return -ERESTARTSYS;
-
-	list_for_each_entry(entry, &acl->mac_list, _list) {
-		memcpy(dst->sa_data, entry->addr, ETH_ALEN);
-		dst->sa_family = ARPHRD_ETHER;
-		dwrq->length++;
-		dst++;
-	}
-	mutex_unlock(&acl->lock);
-	return 0;
-}
-
-/* Setting policy also clears the MAC acl, even if we don't change the default
- * policy
- */
-
-static int
-prism54_set_policy(struct net_device *ndev, struct iw_request_info *info,
-		   __u32 * uwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct islpci_acl *acl = &priv->acl;
-	u32 mlmeautolevel;
-
-	prism54_clear_mac(acl);
-
-	if ((*uwrq < MAC_POLICY_OPEN) || (*uwrq > MAC_POLICY_REJECT))
-		return -EINVAL;
-
-	down_write(&priv->mib_sem);
-
-	acl->policy = *uwrq;
-
-	/* the ACL code needs an intermediate mlmeautolevel */
-	if ((priv->iw_mode == IW_MODE_MASTER) &&
-	    (acl->policy != MAC_POLICY_OPEN))
-		mlmeautolevel = DOT11_MLME_INTERMEDIATE;
-	else
-		mlmeautolevel = CARD_DEFAULT_MLME_MODE;
-	if (priv->wpa)
-		mlmeautolevel = DOT11_MLME_EXTENDED;
-	mgt_set(priv, DOT11_OID_MLMEAUTOLEVEL, &mlmeautolevel);
-	/* restart the card with our new policy */
-	if (mgt_commit(priv)) {
-		up_write(&priv->mib_sem);
-		return -EIO;
-	}
-	up_write(&priv->mib_sem);
-
-	return 0;
-}
-
-static int
-prism54_get_policy(struct net_device *ndev, struct iw_request_info *info,
-		   __u32 * uwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct islpci_acl *acl = &priv->acl;
-
-	*uwrq = acl->policy;
-
-	return 0;
-}
-
-/* Return 1 only if client should be accepted. */
-
-static int
-prism54_mac_accept(struct islpci_acl *acl, char *mac)
-{
-	struct mac_entry *entry;
-	int res = 0;
-
-	if (mutex_lock_interruptible(&acl->lock))
-		return -ERESTARTSYS;
-
-	if (acl->policy == MAC_POLICY_OPEN) {
-		mutex_unlock(&acl->lock);
-		return 1;
-	}
-
-	list_for_each_entry(entry, &acl->mac_list, _list) {
-		if (memcmp(entry->addr, mac, ETH_ALEN) == 0) {
-			res = 1;
-			break;
-		}
-	}
-	res = (acl->policy == MAC_POLICY_ACCEPT) ? !res : res;
-	mutex_unlock(&acl->lock);
-
-	return res;
-}
-
-static int
-prism54_kick_all(struct net_device *ndev, struct iw_request_info *info,
-		 struct iw_point *dwrq, char *extra)
-{
-	struct obj_mlme *mlme;
-	int rvalue;
-
-	mlme = kmalloc(sizeof (struct obj_mlme), GFP_KERNEL);
-	if (mlme == NULL)
-		return -ENOMEM;
-
-	/* Tell the card to kick every client */
-	mlme->id = 0;
-	rvalue =
-	    mgt_set_request(netdev_priv(ndev), DOT11_OID_DISASSOCIATE, 0, mlme);
-	kfree(mlme);
-
-	return rvalue;
-}
-
-static int
-prism54_kick_mac(struct net_device *ndev, struct iw_request_info *info,
-		 struct sockaddr *awrq, char *extra)
-{
-	struct obj_mlme *mlme;
-	struct sockaddr *addr = (struct sockaddr *) extra;
-	int rvalue;
-
-	if (addr->sa_family != ARPHRD_ETHER)
-		return -EOPNOTSUPP;
-
-	mlme = kmalloc(sizeof (struct obj_mlme), GFP_KERNEL);
-	if (mlme == NULL)
-		return -ENOMEM;
-
-	/* Tell the card to only kick the corresponding bastard */
-	memcpy(mlme->address, addr->sa_data, ETH_ALEN);
-	mlme->id = -1;
-	rvalue =
-	    mgt_set_request(netdev_priv(ndev), DOT11_OID_DISASSOCIATE, 0, mlme);
-
-	kfree(mlme);
-
-	return rvalue;
-}
-
-/* Translate a TRAP oid into a wireless event. Called in islpci_mgt_receive. */
-
-static void
-format_event(islpci_private *priv, char *dest, const char *str,
-	     const struct obj_mlme *mlme, u16 *length, int error)
-{
-	int n = snprintf(dest, IW_CUSTOM_MAX,
-			 "%s %s %pM %s (%2.2X)",
-			 str,
-			 ((priv->iw_mode == IW_MODE_MASTER) ? "from" : "to"),
-			 mlme->address,
-			 (error ? (mlme->code ? " : REJECTED " : " : ACCEPTED ")
-			  : ""), mlme->code);
-	WARN_ON(n >= IW_CUSTOM_MAX);
-	*length = n;
-}
-
-static void
-send_formatted_event(islpci_private *priv, const char *str,
-		     const struct obj_mlme *mlme, int error)
-{
-	union iwreq_data wrqu;
-	char *memptr;
-
-	memptr = kmalloc(IW_CUSTOM_MAX, GFP_KERNEL);
-	if (!memptr)
-		return;
-	wrqu.data.pointer = memptr;
-	wrqu.data.length = 0;
-	format_event(priv, memptr, str, mlme, &wrqu.data.length,
-		     error);
-	wireless_send_event(priv->ndev, IWEVCUSTOM, &wrqu, memptr);
-	kfree(memptr);
-}
-
-static void
-send_simple_event(islpci_private *priv, const char *str)
-{
-	union iwreq_data wrqu;
-	char *memptr;
-	int n = strlen(str);
-
-	memptr = kmalloc(IW_CUSTOM_MAX, GFP_KERNEL);
-	if (!memptr)
-		return;
-	BUG_ON(n >= IW_CUSTOM_MAX);
-	wrqu.data.pointer = memptr;
-	wrqu.data.length = n;
-	strcpy(memptr, str);
-	wireless_send_event(priv->ndev, IWEVCUSTOM, &wrqu, memptr);
-	kfree(memptr);
-}
-
-static void
-link_changed(struct net_device *ndev, u32 bitrate)
-{
-	islpci_private *priv = netdev_priv(ndev);
-
-	if (bitrate) {
-		netif_carrier_on(ndev);
-		if (priv->iw_mode == IW_MODE_INFRA) {
-			union iwreq_data uwrq;
-			prism54_get_wap(ndev, NULL, (struct sockaddr *) &uwrq,
-					NULL);
-			wireless_send_event(ndev, SIOCGIWAP, &uwrq, NULL);
-		} else
-			send_simple_event(netdev_priv(ndev),
-					  "Link established");
-	} else {
-		netif_carrier_off(ndev);
-		send_simple_event(netdev_priv(ndev), "Link lost");
-	}
-}
-
-/* Beacon/ProbeResp payload header */
-struct ieee80211_beacon_phdr {
-	u8 timestamp[8];
-	u16 beacon_int;
-	u16 capab_info;
-} __packed;
-
-#define WLAN_EID_GENERIC 0xdd
-static u8 wpa_oid[4] = { 0x00, 0x50, 0xf2, 1 };
-
-static void
-prism54_wpa_bss_ie_add(islpci_private *priv, u8 *bssid,
-		       u8 *wpa_ie, size_t wpa_ie_len)
-{
-	struct list_head *ptr;
-	struct islpci_bss_wpa_ie *bss = NULL;
-
-	if (wpa_ie_len > MAX_WPA_IE_LEN)
-		wpa_ie_len = MAX_WPA_IE_LEN;
-
-	mutex_lock(&priv->wpa_lock);
-
-	/* try to use existing entry */
-	list_for_each(ptr, &priv->bss_wpa_list) {
-		bss = list_entry(ptr, struct islpci_bss_wpa_ie, list);
-		if (memcmp(bss->bssid, bssid, ETH_ALEN) == 0) {
-			list_move(&bss->list, &priv->bss_wpa_list);
-			break;
-		}
-		bss = NULL;
-	}
-
-	if (bss == NULL) {
-		/* add a new BSS entry; if max number of entries is already
-		 * reached, replace the least recently updated */
-		if (priv->num_bss_wpa >= MAX_BSS_WPA_IE_COUNT) {
-			bss = list_entry(priv->bss_wpa_list.prev,
-					 struct islpci_bss_wpa_ie, list);
-			list_del(&bss->list);
-		} else {
-			bss = kzalloc(sizeof (*bss), GFP_ATOMIC);
-			if (bss != NULL)
-				priv->num_bss_wpa++;
-		}
-		if (bss != NULL) {
-			memcpy(bss->bssid, bssid, ETH_ALEN);
-			list_add(&bss->list, &priv->bss_wpa_list);
-		}
-	}
-
-	if (bss != NULL) {
-		memcpy(bss->wpa_ie, wpa_ie, wpa_ie_len);
-		bss->wpa_ie_len = wpa_ie_len;
-		bss->last_update = jiffies;
-	} else {
-		printk(KERN_DEBUG "Failed to add BSS WPA entry for "
-		       "%pM\n", bssid);
-	}
-
-	/* expire old entries from WPA list */
-	while (priv->num_bss_wpa > 0) {
-		bss = list_entry(priv->bss_wpa_list.prev,
-				 struct islpci_bss_wpa_ie, list);
-		if (!time_after(jiffies, bss->last_update + 60 * HZ))
-			break;
-
-		list_del(&bss->list);
-		priv->num_bss_wpa--;
-		kfree(bss);
-	}
-
-	mutex_unlock(&priv->wpa_lock);
-}
-
-static size_t
-prism54_wpa_bss_ie_get(islpci_private *priv, u8 *bssid, u8 *wpa_ie)
-{
-	struct list_head *ptr;
-	struct islpci_bss_wpa_ie *bss = NULL;
-	size_t len = 0;
-
-	mutex_lock(&priv->wpa_lock);
-
-	list_for_each(ptr, &priv->bss_wpa_list) {
-		bss = list_entry(ptr, struct islpci_bss_wpa_ie, list);
-		if (memcmp(bss->bssid, bssid, ETH_ALEN) == 0)
-			break;
-		bss = NULL;
-	}
-	if (bss) {
-		len = bss->wpa_ie_len;
-		memcpy(wpa_ie, bss->wpa_ie, len);
-	}
-	mutex_unlock(&priv->wpa_lock);
-
-	return len;
-}
-
-void
-prism54_wpa_bss_ie_init(islpci_private *priv)
-{
-	INIT_LIST_HEAD(&priv->bss_wpa_list);
-	mutex_init(&priv->wpa_lock);
-}
-
-void
-prism54_wpa_bss_ie_clean(islpci_private *priv)
-{
-	struct islpci_bss_wpa_ie *bss, *n;
-
-	list_for_each_entry_safe(bss, n, &priv->bss_wpa_list, list) {
-		kfree(bss);
-	}
-}
-
-static void
-prism54_process_bss_data(islpci_private *priv, u32 oid, u8 *addr,
-			 u8 *payload, size_t len)
-{
-	struct ieee80211_beacon_phdr *hdr;
-	u8 *pos, *end;
-
-	if (!priv->wpa)
-		return;
-
-	hdr = (struct ieee80211_beacon_phdr *) payload;
-	pos = (u8 *) (hdr + 1);
-	end = payload + len;
-	while (pos < end) {
-		if (pos + 2 + pos[1] > end) {
-			printk(KERN_DEBUG "Parsing Beacon/ProbeResp failed "
-			       "for %pM\n", addr);
-			return;
-		}
-		if (pos[0] == WLAN_EID_GENERIC && pos[1] >= 4 &&
-		    memcmp(pos + 2, wpa_oid, 4) == 0) {
-			prism54_wpa_bss_ie_add(priv, addr, pos, pos[1] + 2);
-			return;
-		}
-		pos += 2 + pos[1];
-	}
-}
-
-static void
-handle_request(islpci_private *priv, struct obj_mlme *mlme, enum oid_num_t oid)
-{
-	if (((mlme->state == DOT11_STATE_AUTHING) ||
-	     (mlme->state == DOT11_STATE_ASSOCING))
-	    && mgt_mlme_answer(priv)) {
-		/* Someone is requesting auth and we must respond. Just send back
-		 * the trap with error code set accordingly.
-		 */
-		mlme->code = prism54_mac_accept(&priv->acl,
-						mlme->address) ? 0 : 1;
-		mgt_set_request(priv, oid, 0, mlme);
-	}
-}
-
-static int
-prism54_process_trap_helper(islpci_private *priv, enum oid_num_t oid,
-			    char *data)
-{
-	struct obj_mlme *mlme = (struct obj_mlme *) data;
-	struct obj_mlmeex *mlmeex = (struct obj_mlmeex *) data;
-	struct obj_mlmeex *confirm;
-	u8 wpa_ie[MAX_WPA_IE_LEN];
-	int wpa_ie_len;
-	size_t len = 0; /* u16, better? */
-	u8 *payload = NULL, *pos = NULL;
-	int ret;
-
-	/* I think all trapable objects are listed here.
-	 * Some oids have a EX version. The difference is that they are emitted
-	 * in DOT11_MLME_EXTENDED mode (set with DOT11_OID_MLMEAUTOLEVEL)
-	 * with more info.
-	 * The few events already defined by the wireless tools are not really
-	 * suited. We use the more flexible custom event facility.
-	 */
-
-	if (oid >= DOT11_OID_BEACON) {
-		len = mlmeex->size;
-		payload = pos = mlmeex->data;
-	}
-
-	/* I fear prism54_process_bss_data won't work with big endian data */
-	if ((oid == DOT11_OID_BEACON) || (oid == DOT11_OID_PROBE))
-		prism54_process_bss_data(priv, oid, mlmeex->address,
-					 payload, len);
-
-	mgt_le_to_cpu(isl_oid[oid].flags & OID_FLAG_TYPE, (void *) mlme);
-
-	switch (oid) {
-
-	case GEN_OID_LINKSTATE:
-		link_changed(priv->ndev, (u32) *data);
-		break;
-
-	case DOT11_OID_MICFAILURE:
-		send_simple_event(priv, "Mic failure");
-		break;
-
-	case DOT11_OID_DEAUTHENTICATE:
-		send_formatted_event(priv, "DeAuthenticate request", mlme, 0);
-		break;
-
-	case DOT11_OID_AUTHENTICATE:
-		handle_request(priv, mlme, oid);
-		send_formatted_event(priv, "Authenticate request", mlme, 1);
-		break;
-
-	case DOT11_OID_DISASSOCIATE:
-		send_formatted_event(priv, "Disassociate request", mlme, 0);
-		break;
-
-	case DOT11_OID_ASSOCIATE:
-		handle_request(priv, mlme, oid);
-		send_formatted_event(priv, "Associate request", mlme, 1);
-		break;
-
-	case DOT11_OID_REASSOCIATE:
-		handle_request(priv, mlme, oid);
-		send_formatted_event(priv, "ReAssociate request", mlme, 1);
-		break;
-
-	case DOT11_OID_BEACON:
-		send_formatted_event(priv,
-				     "Received a beacon from an unknown AP",
-				     mlme, 0);
-		break;
-
-	case DOT11_OID_PROBE:
-		/* we received a probe from a client. */
-		send_formatted_event(priv, "Received a probe from client", mlme,
-				     0);
-		break;
-
-		/* Note : "mlme" is actually a "struct obj_mlmeex *" here, but this
-		 * is backward compatible layout-wise with "struct obj_mlme".
-		 */
-
-	case DOT11_OID_DEAUTHENTICATEEX:
-		send_formatted_event(priv, "DeAuthenticate request", mlme, 0);
-		break;
-
-	case DOT11_OID_AUTHENTICATEEX:
-		handle_request(priv, mlme, oid);
-		send_formatted_event(priv, "Authenticate request (ex)", mlme, 1);
-
-		if (priv->iw_mode != IW_MODE_MASTER
-				&& mlmeex->state != DOT11_STATE_AUTHING)
-			break;
-
-		confirm = kmalloc(sizeof(struct obj_mlmeex) + 6, GFP_ATOMIC);
-
-		if (!confirm)
-			break;
-
-		memcpy(&confirm->address, mlmeex->address, ETH_ALEN);
-		printk(KERN_DEBUG "Authenticate from: address:\t%pM\n",
-		       mlmeex->address);
-		confirm->id = -1; /* or mlmeex->id ? */
-		confirm->state = 0; /* not used */
-		confirm->code = 0;
-		confirm->size = 6;
-		confirm->data[0] = 0x00;
-		confirm->data[1] = 0x00;
-		confirm->data[2] = 0x02;
-		confirm->data[3] = 0x00;
-		confirm->data[4] = 0x00;
-		confirm->data[5] = 0x00;
-
-		ret = mgt_set_varlen(priv, DOT11_OID_ASSOCIATEEX, confirm, 6);
-
-		kfree(confirm);
-		if (ret)
-			return ret;
-		break;
-
-	case DOT11_OID_DISASSOCIATEEX:
-		send_formatted_event(priv, "Disassociate request (ex)", mlme, 0);
-		break;
-
-	case DOT11_OID_ASSOCIATEEX:
-		handle_request(priv, mlme, oid);
-		send_formatted_event(priv, "Associate request (ex)", mlme, 1);
-
-		if (priv->iw_mode != IW_MODE_MASTER
-				&& mlmeex->state != DOT11_STATE_ASSOCING)
-			break;
-
-		confirm = kmalloc(sizeof(struct obj_mlmeex), GFP_ATOMIC);
-
-		if (!confirm)
-			break;
-
-		memcpy(&confirm->address, mlmeex->address, ETH_ALEN);
-
-		confirm->id = ((struct obj_mlmeex *)mlme)->id;
-		confirm->state = 0; /* not used */
-		confirm->code = 0;
-
-		wpa_ie_len = prism54_wpa_bss_ie_get(priv, mlmeex->address, wpa_ie);
-
-		if (!wpa_ie_len) {
-			printk(KERN_DEBUG "No WPA IE found from address:\t%pM\n",
-			       mlmeex->address);
-			kfree(confirm);
-			break;
-		}
-
-		confirm->size = wpa_ie_len;
-		memcpy(&confirm->data, wpa_ie, wpa_ie_len);
-
-		mgt_set_varlen(priv, oid, confirm, wpa_ie_len);
-
-		kfree(confirm);
-
-		break;
-
-	case DOT11_OID_REASSOCIATEEX:
-		handle_request(priv, mlme, oid);
-		send_formatted_event(priv, "Reassociate request (ex)", mlme, 1);
-
-		if (priv->iw_mode != IW_MODE_MASTER
-				&& mlmeex->state != DOT11_STATE_ASSOCING)
-			break;
-
-		confirm = kmalloc(sizeof(struct obj_mlmeex), GFP_ATOMIC);
-
-		if (!confirm)
-			break;
-
-		memcpy(&confirm->address, mlmeex->address, ETH_ALEN);
-
-		confirm->id = mlmeex->id;
-		confirm->state = 0; /* not used */
-		confirm->code = 0;
-
-		wpa_ie_len = prism54_wpa_bss_ie_get(priv, mlmeex->address, wpa_ie);
-
-		if (!wpa_ie_len) {
-			printk(KERN_DEBUG "No WPA IE found from address:\t%pM\n",
-			       mlmeex->address);
-			kfree(confirm);
-			break;
-		}
-
-		confirm->size = wpa_ie_len;
-		memcpy(&confirm->data, wpa_ie, wpa_ie_len);
-
-		mgt_set_varlen(priv, oid, confirm, wpa_ie_len);
-
-		kfree(confirm);
-
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-/*
- * Process a device trap.  This is called via schedule_work(), outside of
- * interrupt context, no locks held.
- */
-void
-prism54_process_trap(struct work_struct *work)
-{
-	struct islpci_mgmtframe *frame =
-		container_of(work, struct islpci_mgmtframe, ws);
-	struct net_device *ndev = frame->ndev;
-	enum oid_num_t n = mgt_oidtonum(frame->header->oid);
-
-	if (n != OID_NUM_LAST)
-		prism54_process_trap_helper(netdev_priv(ndev), n, frame->data);
-	islpci_mgt_release(frame);
-}
-
-int
-prism54_set_mac_address(struct net_device *ndev, void *addr)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	int ret;
-
-	if (ndev->addr_len != 6)
-		return -EINVAL;
-	ret = mgt_set_request(priv, GEN_OID_MACADDRESS, 0,
-			      &((struct sockaddr *) addr)->sa_data);
-	if (!ret)
-		memcpy(priv->ndev->dev_addr,
-		       &((struct sockaddr *) addr)->sa_data, ETH_ALEN);
-
-	return ret;
-}
-
-#define PRISM54_SET_WPA			SIOCIWFIRSTPRIV+12
-
-static int
-prism54_set_wpa(struct net_device *ndev, struct iw_request_info *info,
-		__u32 * uwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	u32 mlme, authen, dot1x, filter, wep;
-
-	if (islpci_get_state(priv) < PRV_STATE_INIT)
-		return 0;
-
-	wep = 1; /* For privacy invoked */
-	filter = 1; /* Filter out all unencrypted frames */
-	dot1x = 0x01; /* To enable eap filter */
-	mlme = DOT11_MLME_EXTENDED;
-	authen = DOT11_AUTH_OS; /* Only WEP uses _SK and _BOTH */
-
-	down_write(&priv->mib_sem);
-	priv->wpa = *uwrq;
-
-	switch (priv->wpa) {
-		default:
-		case 0: /* Clears/disables WPA and friends */
-			wep = 0;
-			filter = 0; /* Do not filter un-encrypted data */
-			dot1x = 0;
-			mlme = DOT11_MLME_AUTO;
-			printk("%s: Disabling WPA\n", ndev->name);
-			break;
-		case 2:
-		case 1: /* WPA */
-			printk("%s: Enabling WPA\n", ndev->name);
-			break;
-	}
-	up_write(&priv->mib_sem);
-
-	mgt_set_request(priv, DOT11_OID_AUTHENABLE, 0, &authen);
-	mgt_set_request(priv, DOT11_OID_PRIVACYINVOKED, 0, &wep);
-	mgt_set_request(priv, DOT11_OID_EXUNENCRYPTED, 0, &filter);
-	mgt_set_request(priv, DOT11_OID_DOT1XENABLE, 0, &dot1x);
-	mgt_set_request(priv, DOT11_OID_MLMEAUTOLEVEL, 0, &mlme);
-
-	return 0;
-}
-
-static int
-prism54_get_wpa(struct net_device *ndev, struct iw_request_info *info,
-		__u32 * uwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	*uwrq = priv->wpa;
-	return 0;
-}
-
-static int
-prism54_set_prismhdr(struct net_device *ndev, struct iw_request_info *info,
-		     __u32 * uwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	priv->monitor_type =
-	    (*uwrq ? ARPHRD_IEEE80211_PRISM : ARPHRD_IEEE80211);
-	if (priv->iw_mode == IW_MODE_MONITOR)
-		priv->ndev->type = priv->monitor_type;
-
-	return 0;
-}
-
-static int
-prism54_get_prismhdr(struct net_device *ndev, struct iw_request_info *info,
-		     __u32 * uwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	*uwrq = (priv->monitor_type == ARPHRD_IEEE80211_PRISM);
-	return 0;
-}
-
-static int
-prism54_debug_oid(struct net_device *ndev, struct iw_request_info *info,
-		  __u32 * uwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-
-	priv->priv_oid = *uwrq;
-	printk("%s: oid 0x%08X\n", ndev->name, *uwrq);
-
-	return 0;
-}
-
-static int
-prism54_debug_get_oid(struct net_device *ndev, struct iw_request_info *info,
-		      struct iw_point *data, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct islpci_mgmtframe *response;
-	int ret = -EIO;
-
-	printk("%s: get_oid 0x%08X\n", ndev->name, priv->priv_oid);
-	data->length = 0;
-
-	if (islpci_get_state(priv) >= PRV_STATE_INIT) {
-		ret =
-		    islpci_mgt_transaction(priv->ndev, PIMFOR_OP_GET,
-					   priv->priv_oid, extra, 256,
-					   &response);
-		printk("%s: ret: %i\n", ndev->name, ret);
-		if (ret || !response
-		    || response->header->operation == PIMFOR_OP_ERROR) {
-			if (response) {
-				islpci_mgt_release(response);
-			}
-			printk("%s: EIO\n", ndev->name);
-			ret = -EIO;
-		}
-		if (!ret) {
-			data->length = response->header->length;
-			memcpy(extra, response->data, data->length);
-			islpci_mgt_release(response);
-			printk("%s: len: %i\n", ndev->name, data->length);
-		}
-	}
-
-	return ret;
-}
-
-static int
-prism54_debug_set_oid(struct net_device *ndev, struct iw_request_info *info,
-		      struct iw_point *data, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	struct islpci_mgmtframe *response;
-	int ret = 0, response_op = PIMFOR_OP_ERROR;
-
-	printk("%s: set_oid 0x%08X\tlen: %d\n", ndev->name, priv->priv_oid,
-	       data->length);
-
-	if (islpci_get_state(priv) >= PRV_STATE_INIT) {
-		ret =
-		    islpci_mgt_transaction(priv->ndev, PIMFOR_OP_SET,
-					   priv->priv_oid, extra, data->length,
-					   &response);
-		printk("%s: ret: %i\n", ndev->name, ret);
-		if (ret || !response
-		    || response->header->operation == PIMFOR_OP_ERROR) {
-			if (response) {
-				islpci_mgt_release(response);
-			}
-			printk("%s: EIO\n", ndev->name);
-			ret = -EIO;
-		}
-		if (!ret) {
-			response_op = response->header->operation;
-			printk("%s: response_op: %i\n", ndev->name,
-			       response_op);
-			islpci_mgt_release(response);
-		}
-	}
-
-	return (ret ? ret : -EINPROGRESS);
-}
-
-static int
-prism54_set_spy(struct net_device *ndev,
-		struct iw_request_info *info,
-		union iwreq_data *uwrq, char *extra)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	u32 u;
-	enum oid_num_t oid = OID_INL_CONFIG;
-
-	down_write(&priv->mib_sem);
-	mgt_get(priv, OID_INL_CONFIG, &u);
-
-	if ((uwrq->data.length == 0) && (priv->spy_data.spy_number > 0))
-		/* disable spy */
-		u &= ~INL_CONFIG_RXANNEX;
-	else if ((uwrq->data.length > 0) && (priv->spy_data.spy_number == 0))
-		/* enable spy */
-		u |= INL_CONFIG_RXANNEX;
-
-	mgt_set(priv, OID_INL_CONFIG, &u);
-	mgt_commit_list(priv, &oid, 1);
-	up_write(&priv->mib_sem);
-
-	return iw_handler_set_spy(ndev, info, uwrq, extra);
-}
-
-static const iw_handler prism54_handler[] = {
-	(iw_handler) prism54_commit,	/* SIOCSIWCOMMIT */
-	(iw_handler) prism54_get_name,	/* SIOCGIWNAME */
-	(iw_handler) NULL,	/* SIOCSIWNWID */
-	(iw_handler) NULL,	/* SIOCGIWNWID */
-	(iw_handler) prism54_set_freq,	/* SIOCSIWFREQ */
-	(iw_handler) prism54_get_freq,	/* SIOCGIWFREQ */
-	(iw_handler) prism54_set_mode,	/* SIOCSIWMODE */
-	(iw_handler) prism54_get_mode,	/* SIOCGIWMODE */
-	(iw_handler) prism54_set_sens,	/* SIOCSIWSENS */
-	(iw_handler) prism54_get_sens,	/* SIOCGIWSENS */
-	(iw_handler) NULL,	/* SIOCSIWRANGE */
-	(iw_handler) prism54_get_range,	/* SIOCGIWRANGE */
-	(iw_handler) NULL,	/* SIOCSIWPRIV */
-	(iw_handler) NULL,	/* SIOCGIWPRIV */
-	(iw_handler) NULL,	/* SIOCSIWSTATS */
-	(iw_handler) NULL,	/* SIOCGIWSTATS */
-	prism54_set_spy,	/* SIOCSIWSPY */
-	iw_handler_get_spy,	/* SIOCGIWSPY */
-	iw_handler_set_thrspy,	/* SIOCSIWTHRSPY */
-	iw_handler_get_thrspy,	/* SIOCGIWTHRSPY */
-	(iw_handler) prism54_set_wap,	/* SIOCSIWAP */
-	(iw_handler) prism54_get_wap,	/* SIOCGIWAP */
-	(iw_handler) NULL,	/* -- hole -- */
-	(iw_handler) NULL,	/* SIOCGIWAPLIST deprecated */
-	(iw_handler) prism54_set_scan,	/* SIOCSIWSCAN */
-	(iw_handler) prism54_get_scan,	/* SIOCGIWSCAN */
-	(iw_handler) prism54_set_essid,	/* SIOCSIWESSID */
-	(iw_handler) prism54_get_essid,	/* SIOCGIWESSID */
-	(iw_handler) prism54_set_nick,	/* SIOCSIWNICKN */
-	(iw_handler) prism54_get_nick,	/* SIOCGIWNICKN */
-	(iw_handler) NULL,	/* -- hole -- */
-	(iw_handler) NULL,	/* -- hole -- */
-	(iw_handler) prism54_set_rate,	/* SIOCSIWRATE */
-	(iw_handler) prism54_get_rate,	/* SIOCGIWRATE */
-	(iw_handler) prism54_set_rts,	/* SIOCSIWRTS */
-	(iw_handler) prism54_get_rts,	/* SIOCGIWRTS */
-	(iw_handler) prism54_set_frag,	/* SIOCSIWFRAG */
-	(iw_handler) prism54_get_frag,	/* SIOCGIWFRAG */
-	(iw_handler) prism54_set_txpower,	/* SIOCSIWTXPOW */
-	(iw_handler) prism54_get_txpower,	/* SIOCGIWTXPOW */
-	(iw_handler) prism54_set_retry,	/* SIOCSIWRETRY */
-	(iw_handler) prism54_get_retry,	/* SIOCGIWRETRY */
-	(iw_handler) prism54_set_encode,	/* SIOCSIWENCODE */
-	(iw_handler) prism54_get_encode,	/* SIOCGIWENCODE */
-	(iw_handler) NULL,	/* SIOCSIWPOWER */
-	(iw_handler) NULL,	/* SIOCGIWPOWER */
-	NULL,			/* -- hole -- */
-	NULL,			/* -- hole -- */
-	(iw_handler) prism54_set_genie,	/* SIOCSIWGENIE */
-	(iw_handler) prism54_get_genie,	/* SIOCGIWGENIE */
-	(iw_handler) prism54_set_auth,	/* SIOCSIWAUTH */
-	(iw_handler) prism54_get_auth,	/* SIOCGIWAUTH */
-	(iw_handler) prism54_set_encodeext, /* SIOCSIWENCODEEXT */
-	(iw_handler) prism54_get_encodeext, /* SIOCGIWENCODEEXT */
-	NULL,			/* SIOCSIWPMKSA */
-};
-
-/* The low order bit identify a SET (0) or a GET (1) ioctl.  */
-
-#define PRISM54_RESET		SIOCIWFIRSTPRIV
-#define PRISM54_GET_POLICY	SIOCIWFIRSTPRIV+1
-#define PRISM54_SET_POLICY	SIOCIWFIRSTPRIV+2
-#define PRISM54_GET_MAC		SIOCIWFIRSTPRIV+3
-#define PRISM54_ADD_MAC		SIOCIWFIRSTPRIV+4
-
-#define PRISM54_DEL_MAC		SIOCIWFIRSTPRIV+6
-
-#define PRISM54_KICK_MAC	SIOCIWFIRSTPRIV+8
-
-#define PRISM54_KICK_ALL	SIOCIWFIRSTPRIV+10
-
-#define PRISM54_GET_WPA		SIOCIWFIRSTPRIV+11
-#define PRISM54_SET_WPA		SIOCIWFIRSTPRIV+12
-
-#define PRISM54_DBG_OID		SIOCIWFIRSTPRIV+14
-#define PRISM54_DBG_GET_OID	SIOCIWFIRSTPRIV+15
-#define PRISM54_DBG_SET_OID	SIOCIWFIRSTPRIV+16
-
-#define PRISM54_GET_OID		SIOCIWFIRSTPRIV+17
-#define PRISM54_SET_OID_U32	SIOCIWFIRSTPRIV+18
-#define	PRISM54_SET_OID_STR	SIOCIWFIRSTPRIV+20
-#define	PRISM54_SET_OID_ADDR	SIOCIWFIRSTPRIV+22
-
-#define PRISM54_GET_PRISMHDR	SIOCIWFIRSTPRIV+23
-#define PRISM54_SET_PRISMHDR	SIOCIWFIRSTPRIV+24
-
-#define IWPRIV_SET_U32(n,x)	{ n, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "s_"x }
-#define IWPRIV_SET_SSID(n,x)	{ n, IW_PRIV_TYPE_CHAR | IW_PRIV_SIZE_FIXED | 1, 0, "s_"x }
-#define IWPRIV_SET_ADDR(n,x)	{ n, IW_PRIV_TYPE_ADDR | IW_PRIV_SIZE_FIXED | 1, 0, "s_"x }
-#define IWPRIV_GET(n,x)	{ n, 0, IW_PRIV_TYPE_CHAR | IW_PRIV_SIZE_FIXED | PRIV_STR_SIZE, "g_"x }
-
-#define IWPRIV_U32(n,x)		IWPRIV_SET_U32(n,x), IWPRIV_GET(n,x)
-#define IWPRIV_SSID(n,x)	IWPRIV_SET_SSID(n,x), IWPRIV_GET(n,x)
-#define IWPRIV_ADDR(n,x)	IWPRIV_SET_ADDR(n,x), IWPRIV_GET(n,x)
-
-/* Note : limited to 128 private ioctls (wireless tools 26) */
-
-static const struct iw_priv_args prism54_private_args[] = {
-/*{ cmd, set_args, get_args, name } */
-	{PRISM54_RESET, 0, 0, "reset"},
-	{PRISM54_GET_PRISMHDR, 0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-	 "get_prismhdr"},
-	{PRISM54_SET_PRISMHDR, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0,
-	 "set_prismhdr"},
-	{PRISM54_GET_POLICY, 0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-	 "getPolicy"},
-	{PRISM54_SET_POLICY, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0,
-	 "setPolicy"},
-	{PRISM54_GET_MAC, 0, IW_PRIV_TYPE_ADDR | 64, "getMac"},
-	{PRISM54_ADD_MAC, IW_PRIV_TYPE_ADDR | IW_PRIV_SIZE_FIXED | 1, 0,
-	 "addMac"},
-	{PRISM54_DEL_MAC, IW_PRIV_TYPE_ADDR | IW_PRIV_SIZE_FIXED | 1, 0,
-	 "delMac"},
-	{PRISM54_KICK_MAC, IW_PRIV_TYPE_ADDR | IW_PRIV_SIZE_FIXED | 1, 0,
-	 "kickMac"},
-	{PRISM54_KICK_ALL, 0, 0, "kickAll"},
-	{PRISM54_GET_WPA, 0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1,
-	 "get_wpa"},
-	{PRISM54_SET_WPA, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0,
-	 "set_wpa"},
-	{PRISM54_DBG_OID, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0,
-	 "dbg_oid"},
-	{PRISM54_DBG_GET_OID, 0, IW_PRIV_TYPE_BYTE | 256, "dbg_get_oid"},
-	{PRISM54_DBG_SET_OID, IW_PRIV_TYPE_BYTE | 256, 0, "dbg_set_oid"},
-	/* --- sub-ioctls handlers --- */
-	{PRISM54_GET_OID,
-	 0, IW_PRIV_TYPE_CHAR | IW_PRIV_SIZE_FIXED | PRIV_STR_SIZE, ""},
-	{PRISM54_SET_OID_U32,
-	 IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, ""},
-	{PRISM54_SET_OID_STR,
-	 IW_PRIV_TYPE_CHAR | IW_PRIV_SIZE_FIXED | 1, 0, ""},
-	{PRISM54_SET_OID_ADDR,
-	 IW_PRIV_TYPE_ADDR | IW_PRIV_SIZE_FIXED | 1, 0, ""},
-	/* --- sub-ioctls definitions --- */
-	IWPRIV_ADDR(GEN_OID_MACADDRESS, "addr"),
-	IWPRIV_GET(GEN_OID_LINKSTATE, "linkstate"),
-	IWPRIV_U32(DOT11_OID_BSSTYPE, "bsstype"),
-	IWPRIV_ADDR(DOT11_OID_BSSID, "bssid"),
-	IWPRIV_U32(DOT11_OID_STATE, "state"),
-	IWPRIV_U32(DOT11_OID_AID, "aid"),
-
-	IWPRIV_SSID(DOT11_OID_SSIDOVERRIDE, "ssidoverride"),
-
-	IWPRIV_U32(DOT11_OID_MEDIUMLIMIT, "medlimit"),
-	IWPRIV_U32(DOT11_OID_BEACONPERIOD, "beacon"),
-	IWPRIV_U32(DOT11_OID_DTIMPERIOD, "dtimperiod"),
-
-	IWPRIV_U32(DOT11_OID_AUTHENABLE, "authenable"),
-	IWPRIV_U32(DOT11_OID_PRIVACYINVOKED, "privinvok"),
-	IWPRIV_U32(DOT11_OID_EXUNENCRYPTED, "exunencrypt"),
-
-	IWPRIV_U32(DOT11_OID_REKEYTHRESHOLD, "rekeythresh"),
-
-	IWPRIV_U32(DOT11_OID_MAXTXLIFETIME, "maxtxlife"),
-	IWPRIV_U32(DOT11_OID_MAXRXLIFETIME, "maxrxlife"),
-	IWPRIV_U32(DOT11_OID_ALOFT_FIXEDRATE, "fixedrate"),
-	IWPRIV_U32(DOT11_OID_MAXFRAMEBURST, "frameburst"),
-	IWPRIV_U32(DOT11_OID_PSM, "psm"),
-
-	IWPRIV_U32(DOT11_OID_BRIDGELOCAL, "bridge"),
-	IWPRIV_U32(DOT11_OID_CLIENTS, "clients"),
-	IWPRIV_U32(DOT11_OID_CLIENTSASSOCIATED, "clientassoc"),
-	IWPRIV_U32(DOT11_OID_DOT1XENABLE, "dot1xenable"),
-	IWPRIV_U32(DOT11_OID_ANTENNARX, "rxant"),
-	IWPRIV_U32(DOT11_OID_ANTENNATX, "txant"),
-	IWPRIV_U32(DOT11_OID_ANTENNADIVERSITY, "antdivers"),
-	IWPRIV_U32(DOT11_OID_EDTHRESHOLD, "edthresh"),
-	IWPRIV_U32(DOT11_OID_PREAMBLESETTINGS, "preamble"),
-	IWPRIV_GET(DOT11_OID_RATES, "rates"),
-	IWPRIV_U32(DOT11_OID_OUTPUTPOWER, ".11outpower"),
-	IWPRIV_GET(DOT11_OID_SUPPORTEDRATES, "supprates"),
-	IWPRIV_GET(DOT11_OID_SUPPORTEDFREQUENCIES, "suppfreq"),
-
-	IWPRIV_U32(DOT11_OID_NOISEFLOOR, "noisefloor"),
-	IWPRIV_GET(DOT11_OID_FREQUENCYACTIVITY, "freqactivity"),
-	IWPRIV_U32(DOT11_OID_NONERPPROTECTION, "nonerpprotec"),
-	IWPRIV_U32(DOT11_OID_PROFILES, "profile"),
-	IWPRIV_GET(DOT11_OID_EXTENDEDRATES, "extrates"),
-	IWPRIV_U32(DOT11_OID_MLMEAUTOLEVEL, "mlmelevel"),
-
-	IWPRIV_GET(DOT11_OID_BSSS, "bsss"),
-	IWPRIV_GET(DOT11_OID_BSSLIST, "bsslist"),
-	IWPRIV_U32(OID_INL_MODE, "mode"),
-	IWPRIV_U32(OID_INL_CONFIG, "config"),
-	IWPRIV_U32(OID_INL_DOT11D_CONFORMANCE, ".11dconform"),
-	IWPRIV_GET(OID_INL_PHYCAPABILITIES, "phycapa"),
-	IWPRIV_U32(OID_INL_OUTPUTPOWER, "outpower"),
-};
-
-static const iw_handler prism54_private_handler[] = {
-	(iw_handler) prism54_reset,
-	(iw_handler) prism54_get_policy,
-	(iw_handler) prism54_set_policy,
-	(iw_handler) prism54_get_mac,
-	(iw_handler) prism54_add_mac,
-	(iw_handler) NULL,
-	(iw_handler) prism54_del_mac,
-	(iw_handler) NULL,
-	(iw_handler) prism54_kick_mac,
-	(iw_handler) NULL,
-	(iw_handler) prism54_kick_all,
-	(iw_handler) prism54_get_wpa,
-	(iw_handler) prism54_set_wpa,
-	(iw_handler) NULL,
-	(iw_handler) prism54_debug_oid,
-	(iw_handler) prism54_debug_get_oid,
-	(iw_handler) prism54_debug_set_oid,
-	(iw_handler) prism54_get_oid,
-	(iw_handler) prism54_set_u32,
-	(iw_handler) NULL,
-	(iw_handler) prism54_set_raw,
-	(iw_handler) NULL,
-	(iw_handler) prism54_set_raw,
-	(iw_handler) prism54_get_prismhdr,
-	(iw_handler) prism54_set_prismhdr,
-};
-
-const struct iw_handler_def prism54_handler_def = {
-	.num_standard = ARRAY_SIZE(prism54_handler),
-	.num_private = ARRAY_SIZE(prism54_private_handler),
-	.num_private_args = ARRAY_SIZE(prism54_private_args),
-	.standard = (iw_handler *) prism54_handler,
-	.private = (iw_handler *) prism54_private_handler,
-	.private_args = (struct iw_priv_args *) prism54_private_args,
-	.get_wireless_stats = prism54_get_wireless_stats,
-};
diff --git a/drivers/net/wireless/intersil/prism54/isl_ioctl.h b/drivers/net/wireless/intersil/prism54/isl_ioctl.h
deleted file mode 100644
index 3f85fd75ac19..000000000000
--- a/drivers/net/wireless/intersil/prism54/isl_ioctl.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  Copyright (C) 2002 Intersil Americas Inc.
- *            (C) 2003 Aurelien Alleaume <slts@free.fr>
- *            (C) 2003 Luis R. Rodriguez <mcgrof@ruslug.rutgers.edu>
- */
-
-#ifndef _ISL_IOCTL_H
-#define _ISL_IOCTL_H
-
-#include "islpci_mgt.h"
-#include "islpci_dev.h"
-
-#include <net/iw_handler.h>	/* New driver API */
-
-#define SUPPORTED_WIRELESS_EXT                  19
-
-void prism54_mib_init(islpci_private *);
-
-struct iw_statistics *prism54_get_wireless_stats(struct net_device *);
-void prism54_update_stats(struct work_struct *);
-
-void prism54_acl_init(struct islpci_acl *);
-void prism54_acl_clean(struct islpci_acl *);
-
-void prism54_process_trap(struct work_struct *);
-
-void prism54_wpa_bss_ie_init(islpci_private *priv);
-void prism54_wpa_bss_ie_clean(islpci_private *priv);
-
-int prism54_set_mac_address(struct net_device *, void *);
-
-extern const struct iw_handler_def prism54_handler_def;
-
-#endif				/* _ISL_IOCTL_H */
diff --git a/drivers/net/wireless/intersil/prism54/isl_oid.h b/drivers/net/wireless/intersil/prism54/isl_oid.h
deleted file mode 100644
index b889bb73a485..000000000000
--- a/drivers/net/wireless/intersil/prism54/isl_oid.h
+++ /dev/null
@@ -1,492 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  Copyright (C) 2003 Herbert Valerio Riedel <hvr@gnu.org>
- *  Copyright (C) 2004 Luis R. Rodriguez <mcgrof@ruslug.rutgers.edu>
- *  Copyright (C) 2004 Aurelien Alleaume <slts@free.fr>
- */
-
-#if !defined(_ISL_OID_H)
-#define _ISL_OID_H
-
-/*
- * MIB related constant and structure definitions for communicating
- * with the device firmware
- */
-
-struct obj_ssid {
-	u8 length;
-	char octets[33];
-} __packed;
-
-struct obj_key {
-	u8 type;		/* dot11_priv_t */
-	u8 length;
-	char key[32];
-} __packed;
-
-struct obj_mlme {
-	u8 address[6];
-	u16 id;
-	u16 state;
-	u16 code;
-} __packed;
-
-struct obj_mlmeex {
-	u8 address[6];
-	u16 id;
-	u16 state;
-	u16 code;
-	u16 size;
-	u8 data[];
-} __packed;
-
-struct obj_buffer {
-	u32 size;
-	u32 addr;		/* 32bit bus address */
-} __packed;
-
-struct obj_bss {
-	u8 address[6];
-	int:16;			/* padding */
-
-	char state;
-	char reserved;
-	short age;
-
-	char quality;
-	char rssi;
-
-	struct obj_ssid ssid;
-	short channel;
-	char beacon_period;
-	char dtim_period;
-	short capinfo;
-	short rates;
-	short basic_rates;
-	int:16;			/* padding */
-} __packed;
-
-struct obj_bsslist {
-	u32 nr;
-	struct obj_bss bsslist[];
-} __packed;
-
-struct obj_frequencies {
-	u16 nr;
-	u16 mhz[];
-} __packed;
-
-struct obj_attachment {
-	char type;
-	char reserved;
-	short id;
-	short size;
-	char data[];
-} __packed;
-
-/*
- * in case everything's ok, the inlined function below will be
- * optimized away by the compiler...
- */
-static inline void
-__bug_on_wrong_struct_sizes(void)
-{
-	BUILD_BUG_ON(sizeof (struct obj_ssid) != 34);
-	BUILD_BUG_ON(sizeof (struct obj_key) != 34);
-	BUILD_BUG_ON(sizeof (struct obj_mlme) != 12);
-	BUILD_BUG_ON(sizeof (struct obj_mlmeex) != 14);
-	BUILD_BUG_ON(sizeof (struct obj_buffer) != 8);
-	BUILD_BUG_ON(sizeof (struct obj_bss) != 60);
-	BUILD_BUG_ON(sizeof (struct obj_bsslist) != 4);
-	BUILD_BUG_ON(sizeof (struct obj_frequencies) != 2);
-}
-
-enum dot11_state_t {
-	DOT11_STATE_NONE = 0,
-	DOT11_STATE_AUTHING = 1,
-	DOT11_STATE_AUTH = 2,
-	DOT11_STATE_ASSOCING = 3,
-
-	DOT11_STATE_ASSOC = 5,
-	DOT11_STATE_IBSS = 6,
-	DOT11_STATE_WDS = 7
-};
-
-enum dot11_bsstype_t {
-	DOT11_BSSTYPE_NONE = 0,
-	DOT11_BSSTYPE_INFRA = 1,
-	DOT11_BSSTYPE_IBSS = 2,
-	DOT11_BSSTYPE_ANY = 3
-};
-
-enum dot11_auth_t {
-	DOT11_AUTH_NONE = 0,
-	DOT11_AUTH_OS = 1,
-	DOT11_AUTH_SK = 2,
-	DOT11_AUTH_BOTH = 3
-};
-
-enum dot11_mlme_t {
-	DOT11_MLME_AUTO = 0,
-	DOT11_MLME_INTERMEDIATE = 1,
-	DOT11_MLME_EXTENDED = 2
-};
-
-enum dot11_priv_t {
-	DOT11_PRIV_WEP = 0,
-	DOT11_PRIV_TKIP = 1
-};
-
-/* Prism "Nitro" / Frameburst / "Packet Frame Grouping"
- * Value is in microseconds. Represents the # microseconds
- * the firmware will take to group frames before sending out then out
- * together with a CSMA contention. Without this all frames are
- * sent with a CSMA contention.
- * Bibliography:
- * https://www.hpl.hp.com/personal/Jean_Tourrilhes/Papers/Packet.Frame.Grouping.html
- */
-enum dot11_maxframeburst_t {
-	/* Values for DOT11_OID_MAXFRAMEBURST */
-	DOT11_MAXFRAMEBURST_OFF = 0, /* Card firmware default */
-	DOT11_MAXFRAMEBURST_MIXED_SAFE = 650, /* 802.11 a,b,g safe */
-	DOT11_MAXFRAMEBURST_IDEAL = 1300, /* Theoretical ideal level */
-	DOT11_MAXFRAMEBURST_MAX = 5000, /* Use this as max,
-		* Note: firmware allows for greater values. This is a
-		* recommended max. I'll update this as I find
-		* out what the real MAX is. Also note that you don't necessarily
-		* get better results with a greater value here.
-		*/
-};
-
-/* Support for 802.11 long and short frame preambles.
- * Long	 preamble uses 128-bit sync field, 8-bit  CRC
- * Short preamble uses 56-bit  sync field, 16-bit CRC
- *
- * 802.11a -- not sure, both optionally ?
- * 802.11b supports long and optionally short
- * 802.11g supports both */
-enum dot11_preamblesettings_t {
-	DOT11_PREAMBLESETTING_LONG = 0,
-		/* Allows *only* long 802.11 preambles */
-	DOT11_PREAMBLESETTING_SHORT = 1,
-		/* Allows *only* short 802.11 preambles */
-	DOT11_PREAMBLESETTING_DYNAMIC = 2
-		/* AutomatiGically set */
-};
-
-/* Support for 802.11 slot timing (time between packets).
- *
- * Long uses 802.11a slot timing  (9 usec ?)
- * Short uses 802.11b slot timing (20 use ?) */
-enum dot11_slotsettings_t {
-	DOT11_SLOTSETTINGS_LONG = 0,
-		/* Allows *only* long 802.11b slot timing */
-	DOT11_SLOTSETTINGS_SHORT = 1,
-		/* Allows *only* long 802.11a slot timing */
-	DOT11_SLOTSETTINGS_DYNAMIC = 2
-		/* AutomatiGically set */
-};
-
-/* All you need to know, ERP is "Extended Rate PHY".
- * An Extended Rate PHY (ERP) STA or AP shall support three different
- * preamble and header formats:
- * Long  preamble (refer to above)
- * Short preamble (refer to above)
- * OFDM  preamble ( ? )
- *
- * I'm assuming here Protection tells the AP
- * to be careful, a STA which cannot handle the long pre-amble
- * has joined.
- */
-enum do11_nonerpstatus_t {
-	DOT11_ERPSTAT_NONEPRESENT = 0,
-	DOT11_ERPSTAT_USEPROTECTION = 1
-};
-
-/* (ERP is "Extended Rate PHY") Way to read NONERP is NON-ERP-*
- * The key here is DOT11 NON ERP NEVER protects against
- * NON ERP STA's. You *don't* want this unless
- * you know what you are doing. It means you will only
- * get Extended Rate capabilities */
-enum dot11_nonerpprotection_t {
-	DOT11_NONERP_NEVER = 0,
-	DOT11_NONERP_ALWAYS = 1,
-	DOT11_NONERP_DYNAMIC = 2
-};
-
-/* Preset OID configuration for 802.11 modes
- * Note: DOT11_OID_CW[MIN|MAX] hold the values of the
- * DCS MIN|MAX backoff used */
-enum dot11_profile_t { /* And set/allowed values */
-	/* Allowed values for DOT11_OID_PROFILES */
-	DOT11_PROFILE_B_ONLY = 0,
-		/* DOT11_OID_RATES: 1, 2, 5.5, 11Mbps
-		 * DOT11_OID_PREAMBLESETTINGS: DOT11_PREAMBLESETTING_DYNAMIC
-		 * DOT11_OID_CWMIN: 31
-		 * DOT11_OID_NONEPROTECTION: DOT11_NOERP_DYNAMIC
-		 * DOT11_OID_SLOTSETTINGS: DOT11_SLOTSETTINGS_LONG
-		 */
-	DOT11_PROFILE_MIXED_G_WIFI = 1,
-		/* DOT11_OID_RATES: 1, 2, 5.5, 11, 6, 9, 12, 18, 24, 36, 48, 54Mbs
-		 * DOT11_OID_PREAMBLESETTINGS: DOT11_PREAMBLESETTING_DYNAMIC
-		 * DOT11_OID_CWMIN: 15
-		 * DOT11_OID_NONEPROTECTION: DOT11_NOERP_DYNAMIC
-		 * DOT11_OID_SLOTSETTINGS: DOT11_SLOTSETTINGS_DYNAMIC
-		 */
-	DOT11_PROFILE_MIXED_LONG = 2, /* "Long range" */
-		/* Same as Profile MIXED_G_WIFI */
-	DOT11_PROFILE_G_ONLY = 3,
-		/* Same as Profile MIXED_G_WIFI */
-	DOT11_PROFILE_TEST = 4,
-		/* Same as Profile MIXED_G_WIFI except:
-		 * DOT11_OID_PREAMBLESETTINGS: DOT11_PREAMBLESETTING_SHORT
-		 * DOT11_OID_NONEPROTECTION: DOT11_NOERP_NEVER
-		 * DOT11_OID_SLOTSETTINGS: DOT11_SLOTSETTINGS_SHORT
-		 */
-	DOT11_PROFILE_B_WIFI = 5,
-		/* Same as Profile B_ONLY */
-	DOT11_PROFILE_A_ONLY = 6,
-		/* Same as Profile MIXED_G_WIFI except:
-		 * DOT11_OID_RATES: 6, 9, 12, 18, 24, 36, 48, 54Mbs
-		 */
-	DOT11_PROFILE_MIXED_SHORT = 7
-		/* Same as MIXED_G_WIFI */
-};
-
-
-/* The dot11d conformance level configures the 802.11d conformance levels.
- * The following conformance levels exist:*/
-enum oid_inl_conformance_t {
-	OID_INL_CONFORMANCE_NONE = 0,	/* Perform active scanning */
-	OID_INL_CONFORMANCE_STRICT = 1,	/* Strictly adhere to 802.11d */
-	OID_INL_CONFORMANCE_FLEXIBLE = 2,	/* Use passed 802.11d info to
-		* determine channel AND/OR just make assumption that active
-		* channels are valid  channels */
-};
-
-enum oid_inl_mode_t {
-	INL_MODE_NONE = -1,
-	INL_MODE_PROMISCUOUS = 0,
-	INL_MODE_CLIENT = 1,
-	INL_MODE_AP = 2,
-	INL_MODE_SNIFFER = 3
-};
-
-enum oid_inl_config_t {
-	INL_CONFIG_NOTHING = 0x00,
-	INL_CONFIG_MANUALRUN = 0x01,
-	INL_CONFIG_FRAMETRAP = 0x02,
-	INL_CONFIG_RXANNEX = 0x04,
-	INL_CONFIG_TXANNEX = 0x08,
-	INL_CONFIG_WDS = 0x10
-};
-
-enum oid_inl_phycap_t {
-	INL_PHYCAP_2400MHZ = 1,
-	INL_PHYCAP_5000MHZ = 2,
-	INL_PHYCAP_FAA = 0x80000000,	/* Means card supports the FAA switch */
-};
-
-
-enum oid_num_t {
-	GEN_OID_MACADDRESS = 0,
-	GEN_OID_LINKSTATE,
-	GEN_OID_WATCHDOG,
-	GEN_OID_MIBOP,
-	GEN_OID_OPTIONS,
-	GEN_OID_LEDCONFIG,
-
-	/* 802.11 */
-	DOT11_OID_BSSTYPE,
-	DOT11_OID_BSSID,
-	DOT11_OID_SSID,
-	DOT11_OID_STATE,
-	DOT11_OID_AID,
-	DOT11_OID_COUNTRYSTRING,
-	DOT11_OID_SSIDOVERRIDE,
-
-	DOT11_OID_MEDIUMLIMIT,
-	DOT11_OID_BEACONPERIOD,
-	DOT11_OID_DTIMPERIOD,
-	DOT11_OID_ATIMWINDOW,
-	DOT11_OID_LISTENINTERVAL,
-	DOT11_OID_CFPPERIOD,
-	DOT11_OID_CFPDURATION,
-
-	DOT11_OID_AUTHENABLE,
-	DOT11_OID_PRIVACYINVOKED,
-	DOT11_OID_EXUNENCRYPTED,
-	DOT11_OID_DEFKEYID,
-	DOT11_OID_DEFKEYX,	/* DOT11_OID_DEFKEY1,...DOT11_OID_DEFKEY4 */
-	DOT11_OID_STAKEY,
-	DOT11_OID_REKEYTHRESHOLD,
-	DOT11_OID_STASC,
-
-	DOT11_OID_PRIVTXREJECTED,
-	DOT11_OID_PRIVRXPLAIN,
-	DOT11_OID_PRIVRXFAILED,
-	DOT11_OID_PRIVRXNOKEY,
-
-	DOT11_OID_RTSTHRESH,
-	DOT11_OID_FRAGTHRESH,
-	DOT11_OID_SHORTRETRIES,
-	DOT11_OID_LONGRETRIES,
-	DOT11_OID_MAXTXLIFETIME,
-	DOT11_OID_MAXRXLIFETIME,
-	DOT11_OID_AUTHRESPTIMEOUT,
-	DOT11_OID_ASSOCRESPTIMEOUT,
-
-	DOT11_OID_ALOFT_TABLE,
-	DOT11_OID_ALOFT_CTRL_TABLE,
-	DOT11_OID_ALOFT_RETREAT,
-	DOT11_OID_ALOFT_PROGRESS,
-	DOT11_OID_ALOFT_FIXEDRATE,
-	DOT11_OID_ALOFT_RSSIGRAPH,
-	DOT11_OID_ALOFT_CONFIG,
-
-	DOT11_OID_VDCFX,
-	DOT11_OID_MAXFRAMEBURST,
-
-	DOT11_OID_PSM,
-	DOT11_OID_CAMTIMEOUT,
-	DOT11_OID_RECEIVEDTIMS,
-	DOT11_OID_ROAMPREFERENCE,
-
-	DOT11_OID_BRIDGELOCAL,
-	DOT11_OID_CLIENTS,
-	DOT11_OID_CLIENTSASSOCIATED,
-	DOT11_OID_CLIENTX,	/* DOT11_OID_CLIENTX,...DOT11_OID_CLIENT2007 */
-
-	DOT11_OID_CLIENTFIND,
-	DOT11_OID_WDSLINKADD,
-	DOT11_OID_WDSLINKREMOVE,
-	DOT11_OID_EAPAUTHSTA,
-	DOT11_OID_EAPUNAUTHSTA,
-	DOT11_OID_DOT1XENABLE,
-	DOT11_OID_MICFAILURE,
-	DOT11_OID_REKEYINDICATE,
-
-	DOT11_OID_MPDUTXSUCCESSFUL,
-	DOT11_OID_MPDUTXONERETRY,
-	DOT11_OID_MPDUTXMULTIPLERETRIES,
-	DOT11_OID_MPDUTXFAILED,
-	DOT11_OID_MPDURXSUCCESSFUL,
-	DOT11_OID_MPDURXDUPS,
-	DOT11_OID_RTSSUCCESSFUL,
-	DOT11_OID_RTSFAILED,
-	DOT11_OID_ACKFAILED,
-	DOT11_OID_FRAMERECEIVES,
-	DOT11_OID_FRAMEERRORS,
-	DOT11_OID_FRAMEABORTS,
-	DOT11_OID_FRAMEABORTSPHY,
-
-	DOT11_OID_SLOTTIME,
-	DOT11_OID_CWMIN, /* MIN DCS backoff */
-	DOT11_OID_CWMAX, /* MAX DCS backoff */
-	DOT11_OID_ACKWINDOW,
-	DOT11_OID_ANTENNARX,
-	DOT11_OID_ANTENNATX,
-	DOT11_OID_ANTENNADIVERSITY,
-	DOT11_OID_CHANNEL,
-	DOT11_OID_EDTHRESHOLD,
-	DOT11_OID_PREAMBLESETTINGS,
-	DOT11_OID_RATES,
-	DOT11_OID_CCAMODESUPPORTED,
-	DOT11_OID_CCAMODE,
-	DOT11_OID_RSSIVECTOR,
-	DOT11_OID_OUTPUTPOWERTABLE,
-	DOT11_OID_OUTPUTPOWER,
-	DOT11_OID_SUPPORTEDRATES,
-	DOT11_OID_FREQUENCY,
-	DOT11_OID_SUPPORTEDFREQUENCIES,
-	DOT11_OID_NOISEFLOOR,
-	DOT11_OID_FREQUENCYACTIVITY,
-	DOT11_OID_IQCALIBRATIONTABLE,
-	DOT11_OID_NONERPPROTECTION,
-	DOT11_OID_SLOTSETTINGS,
-	DOT11_OID_NONERPTIMEOUT,
-	DOT11_OID_PROFILES,
-	DOT11_OID_EXTENDEDRATES,
-
-	DOT11_OID_DEAUTHENTICATE,
-	DOT11_OID_AUTHENTICATE,
-	DOT11_OID_DISASSOCIATE,
-	DOT11_OID_ASSOCIATE,
-	DOT11_OID_SCAN,
-	DOT11_OID_BEACON,
-	DOT11_OID_PROBE,
-	DOT11_OID_DEAUTHENTICATEEX,
-	DOT11_OID_AUTHENTICATEEX,
-	DOT11_OID_DISASSOCIATEEX,
-	DOT11_OID_ASSOCIATEEX,
-	DOT11_OID_REASSOCIATE,
-	DOT11_OID_REASSOCIATEEX,
-
-	DOT11_OID_NONERPSTATUS,
-
-	DOT11_OID_STATIMEOUT,
-	DOT11_OID_MLMEAUTOLEVEL,
-	DOT11_OID_BSSTIMEOUT,
-	DOT11_OID_ATTACHMENT,
-	DOT11_OID_PSMBUFFER,
-
-	DOT11_OID_BSSS,
-	DOT11_OID_BSSX,		/*DOT11_OID_BSS1,...,DOT11_OID_BSS64 */
-	DOT11_OID_BSSFIND,
-	DOT11_OID_BSSLIST,
-
-	OID_INL_TUNNEL,
-	OID_INL_MEMADDR,
-	OID_INL_MEMORY,
-	OID_INL_MODE,
-	OID_INL_COMPONENT_NR,
-	OID_INL_VERSION,
-	OID_INL_INTERFACE_ID,
-	OID_INL_COMPONENT_ID,
-	OID_INL_CONFIG,
-	OID_INL_DOT11D_CONFORMANCE,
-	OID_INL_PHYCAPABILITIES,
-	OID_INL_OUTPUTPOWER,
-
-	OID_NUM_LAST
-};
-
-#define OID_FLAG_CACHED		0x80
-#define OID_FLAG_TYPE		0x7f
-
-#define OID_TYPE_U32		0x01
-#define OID_TYPE_SSID		0x02
-#define OID_TYPE_KEY		0x03
-#define OID_TYPE_BUFFER		0x04
-#define OID_TYPE_BSS		0x05
-#define OID_TYPE_BSSLIST	0x06
-#define OID_TYPE_FREQUENCIES	0x07
-#define OID_TYPE_MLME		0x08
-#define OID_TYPE_MLMEEX		0x09
-#define OID_TYPE_ADDR		0x0A
-#define OID_TYPE_RAW		0x0B
-#define OID_TYPE_ATTACH		0x0C
-
-/* OID_TYPE_MLMEEX is special because of a variable size field when sending.
- * Not yet implemented (not used in driver anyway).
- */
-
-struct oid_t {
-	enum oid_num_t oid;
-	short range;		/* to define a range of oid */
-	short size;		/* max size of the associated data */
-	char flags;
-};
-
-union oid_res_t {
-	void *ptr;
-	u32 u;
-};
-
-#define	IWMAX_BITRATES	20
-#define	IWMAX_BSS	24
-#define IWMAX_FREQ	30
-#define PRIV_STR_SIZE	1024
-
-#endif				/* !defined(_ISL_OID_H) */
-/* EOF */
diff --git a/drivers/net/wireless/intersil/prism54/islpci_dev.c b/drivers/net/wireless/intersil/prism54/islpci_dev.c
deleted file mode 100644
index 8eb6d5e4bd57..000000000000
--- a/drivers/net/wireless/intersil/prism54/islpci_dev.c
+++ /dev/null
@@ -1,951 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  Copyright (C) 2002 Intersil Americas Inc.
- *  Copyright (C) 2003 Herbert Valerio Riedel <hvr@gnu.org>
- *  Copyright (C) 2003 Luis R. Rodriguez <mcgrof@ruslug.rutgers.edu>
- */
-
-#include <linux/hardirq.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-
-#include <linux/netdevice.h>
-#include <linux/ethtool.h>
-#include <linux/pci.h>
-#include <linux/sched.h>
-#include <linux/etherdevice.h>
-#include <linux/delay.h>
-#include <linux/if_arp.h>
-
-#include <asm/io.h>
-
-#include "prismcompat.h"
-#include "isl_38xx.h"
-#include "isl_ioctl.h"
-#include "islpci_dev.h"
-#include "islpci_mgt.h"
-#include "islpci_eth.h"
-#include "oid_mgt.h"
-
-#define ISL3877_IMAGE_FILE	"isl3877"
-#define ISL3886_IMAGE_FILE	"isl3886"
-#define ISL3890_IMAGE_FILE	"isl3890"
-MODULE_FIRMWARE(ISL3877_IMAGE_FILE);
-MODULE_FIRMWARE(ISL3886_IMAGE_FILE);
-MODULE_FIRMWARE(ISL3890_IMAGE_FILE);
-
-static int prism54_bring_down(islpci_private *);
-static int islpci_alloc_memory(islpci_private *);
-
-/* Temporary dummy MAC address to use until firmware is loaded.
- * The idea there is that some tools (such as nameif) may query
- * the MAC address before the netdev is 'open'. By using a valid
- * OUI prefix, they can process the netdev properly.
- * Of course, this is not the final/real MAC address. It doesn't
- * matter, as you are suppose to be able to change it anytime via
- * ndev->set_mac_address. Jean II */
-static const unsigned char	dummy_mac[6] = { 0x00, 0x30, 0xB4, 0x00, 0x00, 0x00 };
-
-static int
-isl_upload_firmware(islpci_private *priv)
-{
-	u32 reg, rc;
-	void __iomem *device_base = priv->device_base;
-
-	/* clear the RAMBoot and the Reset bit */
-	reg = readl(device_base + ISL38XX_CTRL_STAT_REG);
-	reg &= ~ISL38XX_CTRL_STAT_RESET;
-	reg &= ~ISL38XX_CTRL_STAT_RAMBOOT;
-	writel(reg, device_base + ISL38XX_CTRL_STAT_REG);
-	wmb();
-	udelay(ISL38XX_WRITEIO_DELAY);
-
-	/* set the Reset bit without reading the register ! */
-	reg |= ISL38XX_CTRL_STAT_RESET;
-	writel(reg, device_base + ISL38XX_CTRL_STAT_REG);
-	wmb();
-	udelay(ISL38XX_WRITEIO_DELAY);
-
-	/* clear the Reset bit */
-	reg &= ~ISL38XX_CTRL_STAT_RESET;
-	writel(reg, device_base + ISL38XX_CTRL_STAT_REG);
-	wmb();
-
-	/* wait a while for the device to reboot */
-	mdelay(50);
-
-	{
-		const struct firmware *fw_entry = NULL;
-		long fw_len;
-		const u32 *fw_ptr;
-
-		rc = request_firmware(&fw_entry, priv->firmware, PRISM_FW_PDEV);
-		if (rc) {
-			printk(KERN_ERR
-			       "%s: request_firmware() failed for '%s'\n",
-			       "prism54", priv->firmware);
-			return rc;
-		}
-		/* prepare the Direct Memory Base register */
-		reg = ISL38XX_DEV_FIRMWARE_ADDRES;
-
-		fw_ptr = (u32 *) fw_entry->data;
-		fw_len = fw_entry->size;
-
-		if (fw_len % 4) {
-			printk(KERN_ERR
-			       "%s: firmware '%s' size is not multiple of 32bit, aborting!\n",
-			       "prism54", priv->firmware);
-			release_firmware(fw_entry);
-			return -EILSEQ; /* Illegal byte sequence  */;
-		}
-
-		while (fw_len > 0) {
-			long _fw_len =
-			    (fw_len >
-			     ISL38XX_MEMORY_WINDOW_SIZE) ?
-			    ISL38XX_MEMORY_WINDOW_SIZE : fw_len;
-			u32 __iomem *dev_fw_ptr = device_base + ISL38XX_DIRECT_MEM_WIN;
-
-			/* set the card's base address for writing the data */
-			isl38xx_w32_flush(device_base, reg,
-					  ISL38XX_DIR_MEM_BASE_REG);
-			wmb();	/* be paranoid */
-
-			/* increment the write address for next iteration */
-			reg += _fw_len;
-			fw_len -= _fw_len;
-
-			/* write the data to the Direct Memory Window 32bit-wise */
-			/* memcpy_toio() doesn't guarantee 32bit writes :-| */
-			while (_fw_len > 0) {
-				/* use non-swapping writel() */
-				__raw_writel(*fw_ptr, dev_fw_ptr);
-				fw_ptr++, dev_fw_ptr++;
-				_fw_len -= 4;
-			}
-
-			/* flush PCI posting */
-			(void) readl(device_base + ISL38XX_PCI_POSTING_FLUSH);
-			wmb();	/* be paranoid again */
-
-			BUG_ON(_fw_len != 0);
-		}
-
-		BUG_ON(fw_len != 0);
-
-		/* Firmware version is at offset 40 (also for "newmac") */
-		printk(KERN_DEBUG "%s: firmware version: %.8s\n",
-		       priv->ndev->name, fw_entry->data + 40);
-
-		release_firmware(fw_entry);
-	}
-
-	/* now reset the device
-	 * clear the Reset & ClkRun bit, set the RAMBoot bit */
-	reg = readl(device_base + ISL38XX_CTRL_STAT_REG);
-	reg &= ~ISL38XX_CTRL_STAT_CLKRUN;
-	reg &= ~ISL38XX_CTRL_STAT_RESET;
-	reg |= ISL38XX_CTRL_STAT_RAMBOOT;
-	isl38xx_w32_flush(device_base, reg, ISL38XX_CTRL_STAT_REG);
-	wmb();
-	udelay(ISL38XX_WRITEIO_DELAY);
-
-	/* set the reset bit latches the host override and RAMBoot bits
-	 * into the device for operation when the reset bit is reset */
-	reg |= ISL38XX_CTRL_STAT_RESET;
-	writel(reg, device_base + ISL38XX_CTRL_STAT_REG);
-	/* don't do flush PCI posting here! */
-	wmb();
-	udelay(ISL38XX_WRITEIO_DELAY);
-
-	/* clear the reset bit should start the whole circus */
-	reg &= ~ISL38XX_CTRL_STAT_RESET;
-	writel(reg, device_base + ISL38XX_CTRL_STAT_REG);
-	/* don't do flush PCI posting here! */
-	wmb();
-	udelay(ISL38XX_WRITEIO_DELAY);
-
-	return 0;
-}
-
-/******************************************************************************
-    Device Interrupt Handler
-******************************************************************************/
-
-irqreturn_t
-islpci_interrupt(int irq, void *config)
-{
-	u32 reg;
-	islpci_private *priv = config;
-	struct net_device *ndev = priv->ndev;
-	void __iomem *device = priv->device_base;
-	int powerstate = ISL38XX_PSM_POWERSAVE_STATE;
-
-	/* lock the interrupt handler */
-	spin_lock(&priv->slock);
-
-	/* received an interrupt request on a shared IRQ line
-	 * first check whether the device is in sleep mode */
-	reg = readl(device + ISL38XX_CTRL_STAT_REG);
-	if (reg & ISL38XX_CTRL_STAT_SLEEPMODE)
-		/* device is in sleep mode, IRQ was generated by someone else */
-	{
-#if VERBOSE > SHOW_ERROR_MESSAGES
-		DEBUG(SHOW_TRACING, "Assuming someone else called the IRQ\n");
-#endif
-		spin_unlock(&priv->slock);
-		return IRQ_NONE;
-	}
-
-
-	/* check whether there is any source of interrupt on the device */
-	reg = readl(device + ISL38XX_INT_IDENT_REG);
-
-	/* also check the contents of the Interrupt Enable Register, because this
-	 * will filter out interrupt sources from other devices on the same irq ! */
-	reg &= readl(device + ISL38XX_INT_EN_REG);
-	reg &= ISL38XX_INT_SOURCES;
-
-	if (reg != 0) {
-		if (islpci_get_state(priv) != PRV_STATE_SLEEP)
-			powerstate = ISL38XX_PSM_ACTIVE_STATE;
-
-		/* reset the request bits in the Identification register */
-		isl38xx_w32_flush(device, reg, ISL38XX_INT_ACK_REG);
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-		DEBUG(SHOW_FUNCTION_CALLS,
-		      "IRQ: Identification register 0x%p 0x%x\n", device, reg);
-#endif
-
-		/* check for each bit in the register separately */
-		if (reg & ISL38XX_INT_IDENT_UPDATE) {
-#if VERBOSE > SHOW_ERROR_MESSAGES
-			/* Queue has been updated */
-			DEBUG(SHOW_TRACING, "IRQ: Update flag\n");
-
-			DEBUG(SHOW_QUEUE_INDEXES,
-			      "CB drv Qs: [%i][%i][%i][%i][%i][%i]\n",
-			      le32_to_cpu(priv->control_block->
-					  driver_curr_frag[0]),
-			      le32_to_cpu(priv->control_block->
-					  driver_curr_frag[1]),
-			      le32_to_cpu(priv->control_block->
-					  driver_curr_frag[2]),
-			      le32_to_cpu(priv->control_block->
-					  driver_curr_frag[3]),
-			      le32_to_cpu(priv->control_block->
-					  driver_curr_frag[4]),
-			      le32_to_cpu(priv->control_block->
-					  driver_curr_frag[5])
-			    );
-
-			DEBUG(SHOW_QUEUE_INDEXES,
-			      "CB dev Qs: [%i][%i][%i][%i][%i][%i]\n",
-			      le32_to_cpu(priv->control_block->
-					  device_curr_frag[0]),
-			      le32_to_cpu(priv->control_block->
-					  device_curr_frag[1]),
-			      le32_to_cpu(priv->control_block->
-					  device_curr_frag[2]),
-			      le32_to_cpu(priv->control_block->
-					  device_curr_frag[3]),
-			      le32_to_cpu(priv->control_block->
-					  device_curr_frag[4]),
-			      le32_to_cpu(priv->control_block->
-					  device_curr_frag[5])
-			    );
-#endif
-
-			/* cleanup the data low transmit queue */
-			islpci_eth_cleanup_transmit(priv, priv->control_block);
-
-			/* device is in active state, update the
-			 * powerstate flag if necessary */
-			powerstate = ISL38XX_PSM_ACTIVE_STATE;
-
-			/* check all three queues in priority order
-			 * call the PIMFOR receive function until the
-			 * queue is empty */
-			if (isl38xx_in_queue(priv->control_block,
-						ISL38XX_CB_RX_MGMTQ) != 0) {
-#if VERBOSE > SHOW_ERROR_MESSAGES
-				DEBUG(SHOW_TRACING,
-				      "Received frame in Management Queue\n");
-#endif
-				islpci_mgt_receive(ndev);
-
-				islpci_mgt_cleanup_transmit(ndev);
-
-				/* Refill slots in receive queue */
-				islpci_mgmt_rx_fill(ndev);
-
-				/* no need to trigger the device, next
-                                   islpci_mgt_transaction does it */
-			}
-
-			while (isl38xx_in_queue(priv->control_block,
-						ISL38XX_CB_RX_DATA_LQ) != 0) {
-#if VERBOSE > SHOW_ERROR_MESSAGES
-				DEBUG(SHOW_TRACING,
-				      "Received frame in Data Low Queue\n");
-#endif
-				islpci_eth_receive(priv);
-			}
-
-			/* check whether the data transmit queues were full */
-			if (priv->data_low_tx_full) {
-				/* check whether the transmit is not full anymore */
-				if (ISL38XX_CB_TX_QSIZE -
-				    isl38xx_in_queue(priv->control_block,
-						     ISL38XX_CB_TX_DATA_LQ) >=
-				    ISL38XX_MIN_QTHRESHOLD) {
-					/* nope, the driver is ready for more network frames */
-					netif_wake_queue(priv->ndev);
-
-					/* reset the full flag */
-					priv->data_low_tx_full = 0;
-				}
-			}
-		}
-
-		if (reg & ISL38XX_INT_IDENT_INIT) {
-			/* Device has been initialized */
-#if VERBOSE > SHOW_ERROR_MESSAGES
-			DEBUG(SHOW_TRACING,
-			      "IRQ: Init flag, device initialized\n");
-#endif
-			wake_up(&priv->reset_done);
-		}
-
-		if (reg & ISL38XX_INT_IDENT_SLEEP) {
-			/* Device intends to move to powersave state */
-#if VERBOSE > SHOW_ERROR_MESSAGES
-			DEBUG(SHOW_TRACING, "IRQ: Sleep flag\n");
-#endif
-			isl38xx_handle_sleep_request(priv->control_block,
-						     &powerstate,
-						     priv->device_base);
-		}
-
-		if (reg & ISL38XX_INT_IDENT_WAKEUP) {
-			/* Device has been woken up to active state */
-#if VERBOSE > SHOW_ERROR_MESSAGES
-			DEBUG(SHOW_TRACING, "IRQ: Wakeup flag\n");
-#endif
-
-			isl38xx_handle_wakeup(priv->control_block,
-					      &powerstate, priv->device_base);
-		}
-	} else {
-#if VERBOSE > SHOW_ERROR_MESSAGES
-		DEBUG(SHOW_TRACING, "Assuming someone else called the IRQ\n");
-#endif
-		spin_unlock(&priv->slock);
-		return IRQ_NONE;
-	}
-
-	/* sleep -> ready */
-	if (islpci_get_state(priv) == PRV_STATE_SLEEP
-	    && powerstate == ISL38XX_PSM_ACTIVE_STATE)
-		islpci_set_state(priv, PRV_STATE_READY);
-
-	/* !sleep -> sleep */
-	if (islpci_get_state(priv) != PRV_STATE_SLEEP
-	    && powerstate == ISL38XX_PSM_POWERSAVE_STATE)
-		islpci_set_state(priv, PRV_STATE_SLEEP);
-
-	/* unlock the interrupt handler */
-	spin_unlock(&priv->slock);
-
-	return IRQ_HANDLED;
-}
-
-/******************************************************************************
-    Network Interface Control & Statistical functions
-******************************************************************************/
-static int
-islpci_open(struct net_device *ndev)
-{
-	u32 rc;
-	islpci_private *priv = netdev_priv(ndev);
-
-	/* reset data structures, upload firmware and reset device */
-	rc = islpci_reset(priv,1);
-	if (rc) {
-		prism54_bring_down(priv);
-		return rc; /* Returns informative message */
-	}
-
-	netif_start_queue(ndev);
-
-	/* Turn off carrier if in STA or Ad-hoc mode. It will be turned on
-	 * once the firmware receives a trap of being associated
-	 * (GEN_OID_LINKSTATE). In other modes (AP or WDS or monitor) we
-	 * should just leave the carrier on as its expected the firmware
-	 * won't send us a trigger. */
-	if (priv->iw_mode == IW_MODE_INFRA || priv->iw_mode == IW_MODE_ADHOC)
-		netif_carrier_off(ndev);
-	else
-		netif_carrier_on(ndev);
-
-	return 0;
-}
-
-static int
-islpci_close(struct net_device *ndev)
-{
-	islpci_private *priv = netdev_priv(ndev);
-
-	printk(KERN_DEBUG "%s: islpci_close ()\n", ndev->name);
-
-	netif_stop_queue(ndev);
-
-	return prism54_bring_down(priv);
-}
-
-static int
-prism54_bring_down(islpci_private *priv)
-{
-	void __iomem *device_base = priv->device_base;
-	u32 reg;
-	/* we are going to shutdown the device */
-	islpci_set_state(priv, PRV_STATE_PREBOOT);
-
-	/* disable all device interrupts in case they weren't */
-	isl38xx_disable_interrupts(priv->device_base);
-
-	/* For safety reasons, we may want to ensure that no DMA transfer is
-	 * currently in progress by emptying the TX and RX queues. */
-
-	/* wait until interrupts have finished executing on other CPUs */
-	synchronize_irq(priv->pdev->irq);
-
-	reg = readl(device_base + ISL38XX_CTRL_STAT_REG);
-	reg &= ~(ISL38XX_CTRL_STAT_RESET | ISL38XX_CTRL_STAT_RAMBOOT);
-	writel(reg, device_base + ISL38XX_CTRL_STAT_REG);
-	wmb();
-	udelay(ISL38XX_WRITEIO_DELAY);
-
-	reg |= ISL38XX_CTRL_STAT_RESET;
-	writel(reg, device_base + ISL38XX_CTRL_STAT_REG);
-	wmb();
-	udelay(ISL38XX_WRITEIO_DELAY);
-
-	/* clear the Reset bit */
-	reg &= ~ISL38XX_CTRL_STAT_RESET;
-	writel(reg, device_base + ISL38XX_CTRL_STAT_REG);
-	wmb();
-
-	/* wait a while for the device to reset */
-	schedule_timeout_uninterruptible(msecs_to_jiffies(50));
-
-	return 0;
-}
-
-static int
-islpci_upload_fw(islpci_private *priv)
-{
-	islpci_state_t old_state;
-	u32 rc;
-
-	old_state = islpci_set_state(priv, PRV_STATE_BOOT);
-
-	printk(KERN_DEBUG "%s: uploading firmware...\n", priv->ndev->name);
-
-	rc = isl_upload_firmware(priv);
-	if (rc) {
-		/* error uploading the firmware */
-		printk(KERN_ERR "%s: could not upload firmware ('%s')\n",
-		       priv->ndev->name, priv->firmware);
-
-		islpci_set_state(priv, old_state);
-		return rc;
-	}
-
-	printk(KERN_DEBUG "%s: firmware upload complete\n",
-	       priv->ndev->name);
-
-	islpci_set_state(priv, PRV_STATE_POSTBOOT);
-
-	return 0;
-}
-
-static int
-islpci_reset_if(islpci_private *priv)
-{
-	long remaining;
-	int result = -ETIME;
-	int count;
-
-	DEFINE_WAIT(wait);
-	prepare_to_wait(&priv->reset_done, &wait, TASK_UNINTERRUPTIBLE);
-
-	/* now the last step is to reset the interface */
-	isl38xx_interface_reset(priv->device_base, priv->device_host_address);
-	islpci_set_state(priv, PRV_STATE_PREINIT);
-
-        for(count = 0; count < 2 && result; count++) {
-		/* The software reset acknowledge needs about 220 msec here.
-		 * Be conservative and wait for up to one second. */
-
-		remaining = schedule_timeout_uninterruptible(HZ);
-
-		if(remaining > 0) {
-			result = 0;
-			break;
-		}
-
-		/* If we're here it's because our IRQ hasn't yet gone through.
-		 * Retry a bit more...
-		 */
-		printk(KERN_ERR "%s: no 'reset complete' IRQ seen - retrying\n",
-			priv->ndev->name);
-	}
-
-	finish_wait(&priv->reset_done, &wait);
-
-	if (result) {
-		printk(KERN_ERR "%s: interface reset failure\n", priv->ndev->name);
-		return result;
-	}
-
-	islpci_set_state(priv, PRV_STATE_INIT);
-
-	/* Now that the device is 100% up, let's allow
-	 * for the other interrupts --
-	 * NOTE: this is not *yet* true since we've only allowed the
-	 * INIT interrupt on the IRQ line. We can perhaps poll
-	 * the IRQ line until we know for sure the reset went through */
-	isl38xx_enable_common_interrupts(priv->device_base);
-
-	down_write(&priv->mib_sem);
-	result = mgt_commit(priv);
-	if (result) {
-		printk(KERN_ERR "%s: interface reset failure\n", priv->ndev->name);
-		up_write(&priv->mib_sem);
-		return result;
-	}
-	up_write(&priv->mib_sem);
-
-	islpci_set_state(priv, PRV_STATE_READY);
-
-	printk(KERN_DEBUG "%s: interface reset complete\n", priv->ndev->name);
-	return 0;
-}
-
-int
-islpci_reset(islpci_private *priv, int reload_firmware)
-{
-	isl38xx_control_block *cb =    /* volatile not needed */
-		(isl38xx_control_block *) priv->control_block;
-	unsigned counter;
-	int rc;
-
-	if (reload_firmware)
-		islpci_set_state(priv, PRV_STATE_PREBOOT);
-	else
-		islpci_set_state(priv, PRV_STATE_POSTBOOT);
-
-	printk(KERN_DEBUG "%s: resetting device...\n", priv->ndev->name);
-
-	/* disable all device interrupts in case they weren't */
-	isl38xx_disable_interrupts(priv->device_base);
-
-	/* flush all management queues */
-	priv->index_mgmt_tx = 0;
-	priv->index_mgmt_rx = 0;
-
-	/* clear the indexes in the frame pointer */
-	for (counter = 0; counter < ISL38XX_CB_QCOUNT; counter++) {
-		cb->driver_curr_frag[counter] = cpu_to_le32(0);
-		cb->device_curr_frag[counter] = cpu_to_le32(0);
-	}
-
-	/* reset the mgmt receive queue */
-	for (counter = 0; counter < ISL38XX_CB_MGMT_QSIZE; counter++) {
-		isl38xx_fragment *frag = &cb->rx_data_mgmt[counter];
-		frag->size = cpu_to_le16(MGMT_FRAME_SIZE);
-		frag->flags = 0;
-		frag->address = cpu_to_le32(priv->mgmt_rx[counter].pci_addr);
-	}
-
-	for (counter = 0; counter < ISL38XX_CB_RX_QSIZE; counter++) {
-		cb->rx_data_low[counter].address =
-		    cpu_to_le32((u32) priv->pci_map_rx_address[counter]);
-	}
-
-	/* since the receive queues are filled with empty fragments, now we can
-	 * set the corresponding indexes in the Control Block */
-	priv->control_block->driver_curr_frag[ISL38XX_CB_RX_DATA_LQ] =
-	    cpu_to_le32(ISL38XX_CB_RX_QSIZE);
-	priv->control_block->driver_curr_frag[ISL38XX_CB_RX_MGMTQ] =
-	    cpu_to_le32(ISL38XX_CB_MGMT_QSIZE);
-
-	/* reset the remaining real index registers and full flags */
-	priv->free_data_rx = 0;
-	priv->free_data_tx = 0;
-	priv->data_low_tx_full = 0;
-
-	if (reload_firmware) { /* Should we load the firmware ? */
-	/* now that the data structures are cleaned up, upload
-	 * firmware and reset interface */
-		rc = islpci_upload_fw(priv);
-		if (rc) {
-			printk(KERN_ERR "%s: islpci_reset: failure\n",
-				priv->ndev->name);
-			return rc;
-		}
-	}
-
-	/* finally reset interface */
-	rc = islpci_reset_if(priv);
-	if (rc)
-		printk(KERN_ERR "prism54: Your card/socket may be faulty, or IRQ line too busy :(\n");
-	return rc;
-}
-
-/******************************************************************************
-    Network device configuration functions
-******************************************************************************/
-static int
-islpci_alloc_memory(islpci_private *priv)
-{
-	int counter;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	printk(KERN_DEBUG "islpci_alloc_memory\n");
-#endif
-
-	/* remap the PCI device base address to accessible */
-	if (!(priv->device_base =
-	      ioremap(pci_resource_start(priv->pdev, 0),
-		      ISL38XX_PCI_MEM_SIZE))) {
-		/* error in remapping the PCI device memory address range */
-		printk(KERN_ERR "PCI memory remapping failed\n");
-		return -1;
-	}
-
-	/* memory layout for consistent DMA region:
-	 *
-	 * Area 1: Control Block for the device interface
-	 * Area 2: Power Save Mode Buffer for temporary frame storage. Be aware that
-	 *         the number of supported stations in the AP determines the minimal
-	 *         size of the buffer !
-	 */
-
-	/* perform the allocation */
-	priv->driver_mem_address = dma_alloc_coherent(&priv->pdev->dev,
-						      HOST_MEM_BLOCK,
-						      &priv->device_host_address,
-						      GFP_KERNEL);
-
-	if (!priv->driver_mem_address) {
-		/* error allocating the block of PCI memory */
-		printk(KERN_ERR "%s: could not allocate DMA memory, aborting!",
-		       "prism54");
-		return -1;
-	}
-
-	/* assign the Control Block to the first address of the allocated area */
-	priv->control_block =
-	    (isl38xx_control_block *) priv->driver_mem_address;
-
-	/* set the Power Save Buffer pointer directly behind the CB */
-	priv->device_psm_buffer =
-		priv->device_host_address + CONTROL_BLOCK_SIZE;
-
-	/* make sure all buffer pointers are initialized */
-	for (counter = 0; counter < ISL38XX_CB_QCOUNT; counter++) {
-		priv->control_block->driver_curr_frag[counter] = cpu_to_le32(0);
-		priv->control_block->device_curr_frag[counter] = cpu_to_le32(0);
-	}
-
-	priv->index_mgmt_rx = 0;
-	memset(priv->mgmt_rx, 0, sizeof(priv->mgmt_rx));
-	memset(priv->mgmt_tx, 0, sizeof(priv->mgmt_tx));
-
-	/* allocate rx queue for management frames */
-	if (islpci_mgmt_rx_fill(priv->ndev) < 0)
-		goto out_free;
-
-	/* now get the data rx skb's */
-	memset(priv->data_low_rx, 0, sizeof (priv->data_low_rx));
-	memset(priv->pci_map_rx_address, 0, sizeof (priv->pci_map_rx_address));
-
-	for (counter = 0; counter < ISL38XX_CB_RX_QSIZE; counter++) {
-		struct sk_buff *skb;
-
-		/* allocate an sk_buff for received data frames storage
-		 * each frame on receive size consists of 1 fragment
-		 * include any required allignment operations */
-		if (!(skb = dev_alloc_skb(MAX_FRAGMENT_SIZE_RX + 2))) {
-			/* error allocating an sk_buff structure elements */
-			printk(KERN_ERR "Error allocating skb.\n");
-			skb = NULL;
-			goto out_free;
-		}
-		skb_reserve(skb, (4 - (long) skb->data) & 0x03);
-		/* add the new allocated sk_buff to the buffer array */
-		priv->data_low_rx[counter] = skb;
-
-		/* map the allocated skb data area to pci */
-		priv->pci_map_rx_address[counter] =
-		    dma_map_single(&priv->pdev->dev, (void *)skb->data,
-				   MAX_FRAGMENT_SIZE_RX + 2, DMA_FROM_DEVICE);
-		if (dma_mapping_error(&priv->pdev->dev, priv->pci_map_rx_address[counter])) {
-			priv->pci_map_rx_address[counter] = 0;
-			/* error mapping the buffer to device
-			   accessible memory address */
-			printk(KERN_ERR "failed to map skb DMA'able\n");
-			goto out_free;
-		}
-	}
-
-	prism54_acl_init(&priv->acl);
-	prism54_wpa_bss_ie_init(priv);
-	if (mgt_init(priv))
-		goto out_free;
-
-	return 0;
- out_free:
-	islpci_free_memory(priv);
-	return -1;
-}
-
-int
-islpci_free_memory(islpci_private *priv)
-{
-	int counter;
-
-	if (priv->device_base)
-		iounmap(priv->device_base);
-	priv->device_base = NULL;
-
-	/* free consistent DMA area... */
-	if (priv->driver_mem_address)
-		dma_free_coherent(&priv->pdev->dev, HOST_MEM_BLOCK,
-				  priv->driver_mem_address,
-				  priv->device_host_address);
-
-	/* clear some dangling pointers */
-	priv->driver_mem_address = NULL;
-	priv->device_host_address = 0;
-	priv->device_psm_buffer = 0;
-	priv->control_block = NULL;
-
-        /* clean up mgmt rx buffers */
-        for (counter = 0; counter < ISL38XX_CB_MGMT_QSIZE; counter++) {
-		struct islpci_membuf *buf = &priv->mgmt_rx[counter];
-		if (buf->pci_addr)
-			dma_unmap_single(&priv->pdev->dev, buf->pci_addr,
-					 buf->size, DMA_FROM_DEVICE);
-		buf->pci_addr = 0;
-		kfree(buf->mem);
-		buf->size = 0;
-		buf->mem = NULL;
-        }
-
-	/* clean up data rx buffers */
-	for (counter = 0; counter < ISL38XX_CB_RX_QSIZE; counter++) {
-		if (priv->pci_map_rx_address[counter])
-			dma_unmap_single(&priv->pdev->dev,
-					 priv->pci_map_rx_address[counter],
-					 MAX_FRAGMENT_SIZE_RX + 2,
-					 DMA_FROM_DEVICE);
-		priv->pci_map_rx_address[counter] = 0;
-
-		if (priv->data_low_rx[counter])
-			dev_kfree_skb(priv->data_low_rx[counter]);
-		priv->data_low_rx[counter] = NULL;
-	}
-
-	/* Free the access control list and the WPA list */
-	prism54_acl_clean(&priv->acl);
-	prism54_wpa_bss_ie_clean(priv);
-	mgt_clean(priv);
-
-	return 0;
-}
-
-#if 0
-static void
-islpci_set_multicast_list(struct net_device *dev)
-{
-	/* put device into promisc mode and let network layer handle it */
-}
-#endif
-
-static void islpci_ethtool_get_drvinfo(struct net_device *dev,
-                                       struct ethtool_drvinfo *info)
-{
-	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
-	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
-}
-
-static const struct ethtool_ops islpci_ethtool_ops = {
-	.get_drvinfo = islpci_ethtool_get_drvinfo,
-};
-
-static const struct net_device_ops islpci_netdev_ops = {
-	.ndo_open 		= islpci_open,
-	.ndo_stop		= islpci_close,
-	.ndo_start_xmit		= islpci_eth_transmit,
-	.ndo_tx_timeout		= islpci_eth_tx_timeout,
-	.ndo_set_mac_address 	= prism54_set_mac_address,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-static struct device_type wlan_type = {
-	.name	= "wlan",
-};
-
-struct net_device *
-islpci_setup(struct pci_dev *pdev)
-{
-	islpci_private *priv;
-	struct net_device *ndev = alloc_etherdev(sizeof (islpci_private));
-
-	if (!ndev)
-		return ndev;
-
-	pci_set_drvdata(pdev, ndev);
-	SET_NETDEV_DEV(ndev, &pdev->dev);
-	SET_NETDEV_DEVTYPE(ndev, &wlan_type);
-
-	/* setup the structure members */
-	ndev->base_addr = pci_resource_start(pdev, 0);
-	ndev->irq = pdev->irq;
-
-	/* initialize the function pointers */
-	ndev->netdev_ops = &islpci_netdev_ops;
-	ndev->wireless_handlers = &prism54_handler_def;
-	ndev->ethtool_ops = &islpci_ethtool_ops;
-
-	/* ndev->set_multicast_list = &islpci_set_multicast_list; */
-	ndev->addr_len = ETH_ALEN;
-	/* Get a non-zero dummy MAC address for nameif. Jean II */
-	memcpy(ndev->dev_addr, dummy_mac, ETH_ALEN);
-
-	ndev->watchdog_timeo = ISLPCI_TX_TIMEOUT;
-
-	/* allocate a private device structure to the network device  */
-	priv = netdev_priv(ndev);
-	priv->ndev = ndev;
-	priv->pdev = pdev;
-	priv->monitor_type = ARPHRD_IEEE80211;
-	priv->ndev->type = (priv->iw_mode == IW_MODE_MONITOR) ?
-		priv->monitor_type : ARPHRD_ETHER;
-
-	/* Add pointers to enable iwspy support. */
-	priv->wireless_data.spy_data = &priv->spy_data;
-	ndev->wireless_data = &priv->wireless_data;
-
-	/* save the start and end address of the PCI memory area */
-	ndev->mem_start = (unsigned long) priv->device_base;
-	ndev->mem_end = ndev->mem_start + ISL38XX_PCI_MEM_SIZE;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_TRACING, "PCI Memory remapped to 0x%p\n", priv->device_base);
-#endif
-
-	init_waitqueue_head(&priv->reset_done);
-
-	/* init the queue read locks, process wait counter */
-	mutex_init(&priv->mgmt_lock);
-	priv->mgmt_received = NULL;
-	init_waitqueue_head(&priv->mgmt_wqueue);
-	mutex_init(&priv->stats_lock);
-	spin_lock_init(&priv->slock);
-
-	/* init state machine with off#1 state */
-	priv->state = PRV_STATE_OFF;
-	priv->state_off = 1;
-
-	/* initialize workqueue's */
-	INIT_WORK(&priv->stats_work, prism54_update_stats);
-	priv->stats_timestamp = 0;
-
-	INIT_WORK(&priv->reset_task, islpci_do_reset_and_wake);
-	priv->reset_task_pending = 0;
-
-	/* allocate various memory areas */
-	if (islpci_alloc_memory(priv))
-		goto do_free_netdev;
-
-	/* select the firmware file depending on the device id */
-	switch (pdev->device) {
-	case 0x3877:
-		strcpy(priv->firmware, ISL3877_IMAGE_FILE);
-		break;
-
-	case 0x3886:
-		strcpy(priv->firmware, ISL3886_IMAGE_FILE);
-		break;
-
-	default:
-		strcpy(priv->firmware, ISL3890_IMAGE_FILE);
-		break;
-	}
-
-	if (register_netdev(ndev)) {
-		DEBUG(SHOW_ERROR_MESSAGES,
-		      "ERROR: register_netdev() failed\n");
-		goto do_islpci_free_memory;
-	}
-
-	return ndev;
-
-      do_islpci_free_memory:
-	islpci_free_memory(priv);
-      do_free_netdev:
-	free_netdev(ndev);
-	priv = NULL;
-	return NULL;
-}
-
-islpci_state_t
-islpci_set_state(islpci_private *priv, islpci_state_t new_state)
-{
-	islpci_state_t old_state;
-
-	/* lock */
-	old_state = priv->state;
-
-	/* this means either a race condition or some serious error in
-	 * the driver code */
-	switch (new_state) {
-	case PRV_STATE_OFF:
-		priv->state_off++;
-		fallthrough;
-	default:
-		priv->state = new_state;
-		break;
-
-	case PRV_STATE_PREBOOT:
-		/* there are actually many off-states, enumerated by
-		 * state_off */
-		if (old_state == PRV_STATE_OFF)
-			priv->state_off--;
-
-		/* only if hw_unavailable is zero now it means we either
-		 * were in off#1 state, or came here from
-		 * somewhere else */
-		if (!priv->state_off)
-			priv->state = new_state;
-		break;
-	}
-#if 0
-	printk(KERN_DEBUG "%s: state transition %d -> %d (off#%d)\n",
-	       priv->ndev->name, old_state, new_state, priv->state_off);
-#endif
-
-	/* invariants */
-	BUG_ON(priv->state_off < 0);
-	BUG_ON(priv->state_off && (priv->state != PRV_STATE_OFF));
-	BUG_ON(!priv->state_off && (priv->state == PRV_STATE_OFF));
-
-	/* unlock */
-	return old_state;
-}
diff --git a/drivers/net/wireless/intersil/prism54/islpci_dev.h b/drivers/net/wireless/intersil/prism54/islpci_dev.h
deleted file mode 100644
index 4753418dce62..000000000000
--- a/drivers/net/wireless/intersil/prism54/islpci_dev.h
+++ /dev/null
@@ -1,204 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  Copyright (C) 2002 Intersil Americas Inc.
- *  Copyright (C) 2003 Herbert Valerio Riedel <hvr@gnu.org>
- *  Copyright (C) 2003 Luis R. Rodriguez <mcgrof@ruslug.rutgers.edu>
- *  Copyright (C) 2003 Aurelien Alleaume <slts@free.fr>
- */
-
-#ifndef _ISLPCI_DEV_H
-#define _ISLPCI_DEV_H
-
-#include <linux/irqreturn.h>
-#include <linux/netdevice.h>
-#include <linux/wireless.h>
-#include <net/iw_handler.h>
-#include <linux/list.h>
-#include <linux/mutex.h>
-
-#include "isl_38xx.h"
-#include "isl_oid.h"
-#include "islpci_mgt.h"
-
-/* some states might not be superflous and may be removed when
-   design is finalized (hvr) */
-typedef enum {
-	PRV_STATE_OFF = 0,	/* this means hw_unavailable is != 0 */
-	PRV_STATE_PREBOOT,	/* we are in a pre-boot state (empty RAM) */
-	PRV_STATE_BOOT,		/* boot state (fw upload, run fw) */
-	PRV_STATE_POSTBOOT,	/* after boot state, need reset now */
-	PRV_STATE_PREINIT,	/* pre-init state */
-	PRV_STATE_INIT,		/* init state (restore MIB backup to device) */
-	PRV_STATE_READY,	/* driver&device are in operational state */
-	PRV_STATE_SLEEP		/* device in sleep mode */
-} islpci_state_t;
-
-/* ACL using MAC address */
-struct mac_entry {
-   struct list_head _list;
-   char addr[ETH_ALEN];
-};
-
-struct islpci_acl {
-   enum { MAC_POLICY_OPEN=0, MAC_POLICY_ACCEPT=1, MAC_POLICY_REJECT=2 } policy;
-   struct list_head mac_list;  /* a list of mac_entry */
-   int size;   /* size of queue */
-   struct mutex lock;   /* accessed in ioctls and trap_work */
-};
-
-struct islpci_membuf {
-	int size;                   /* size of memory */
-	void *mem;                  /* address of memory as seen by CPU */
-	dma_addr_t pci_addr;        /* address of memory as seen by device */
-};
-
-#define MAX_BSS_WPA_IE_COUNT 64
-#define MAX_WPA_IE_LEN 64
-struct islpci_bss_wpa_ie {
-	struct list_head list;
-	unsigned long last_update;
-	u8 bssid[ETH_ALEN];
-	u8 wpa_ie[MAX_WPA_IE_LEN];
-	size_t wpa_ie_len;
-
-};
-
-typedef struct {
-	spinlock_t slock;	/* generic spinlock; */
-
-	u32 priv_oid;
-
-	/* our mib cache */
-	u32 iw_mode;
-        struct rw_semaphore mib_sem;
-	void **mib;
-	char nickname[IW_ESSID_MAX_SIZE+1];
-
-	/* Take care of the wireless stats */
-	struct work_struct stats_work;
-	struct mutex stats_lock;
-	/* remember when we last updated the stats */
-	unsigned long stats_timestamp;
-	/* The first is accessed under semaphore locking.
-	 * The second is the clean one we return to iwconfig.
-	 */
-	struct iw_statistics local_iwstatistics;
-	struct iw_statistics iwstatistics;
-
-	struct iw_spy_data spy_data; /* iwspy support */
-
-	struct iw_public_data wireless_data;
-
-	int monitor_type; /* ARPHRD_IEEE80211 or ARPHRD_IEEE80211_PRISM */
-
-	struct islpci_acl acl;
-
-	/* PCI bus allocation & configuration members */
-	struct pci_dev *pdev;	/* PCI structure information */
-	char firmware[33];
-
-	void __iomem *device_base;	/* ioremapped device base address */
-
-	/* consistent DMA region */
-	void *driver_mem_address;	/* base DMA address */
-	dma_addr_t device_host_address;	/* base DMA address (bus address) */
-	dma_addr_t device_psm_buffer;	/* host memory for PSM buffering (bus address) */
-
-	/* our network_device structure  */
-	struct net_device *ndev;
-
-	/* device queue interface members */
-	struct isl38xx_cb *control_block;	/* device control block
-							   (== driver_mem_address!) */
-
-	/* Each queue has three indexes:
-	 *   free/index_mgmt/data_rx/tx (called index, see below),
-	 *   driver_curr_frag, and device_curr_frag (in the control block)
-	 * All indexes are ever-increasing, but interpreted modulo the
-	 * device queue size when used.
-	 *   index <= device_curr_frag <= driver_curr_frag  at all times
-	 * For rx queues, [index, device_curr_frag) contains fragments
-	 * that the interrupt processing needs to handle (owned by driver).
-	 * [device_curr_frag, driver_curr_frag) is the free space in the
-	 * rx queue, waiting for data (owned by device).  The driver
-	 * increments driver_curr_frag to indicate to the device that more
-	 * buffers are available.
-	 * If device_curr_frag == driver_curr_frag, no more rx buffers are
-	 * available, and the rx DMA engine of the device is halted.
-	 * For tx queues, [index, device_curr_frag) contains fragments
-	 * where tx is done; they need to be freed (owned by driver).
-	 * [device_curr_frag, driver_curr_frag) contains the frames
-	 * that are being transferred (owned by device).  The driver
-	 * increments driver_curr_frag to indicate that more tx work
-	 * needs to be done.
-	 */
-	u32 index_mgmt_rx;              /* real index mgmt rx queue */
-	u32 index_mgmt_tx;              /* read index mgmt tx queue */
-	u32 free_data_rx;	/* free pointer data rx queue */
-	u32 free_data_tx;	/* free pointer data tx queue */
-	u32 data_low_tx_full;	/* full detected flag */
-
-	/* frame memory buffers for the device queues */
-	struct islpci_membuf mgmt_tx[ISL38XX_CB_MGMT_QSIZE];
-	struct islpci_membuf mgmt_rx[ISL38XX_CB_MGMT_QSIZE];
-	struct sk_buff *data_low_tx[ISL38XX_CB_TX_QSIZE];
-	struct sk_buff *data_low_rx[ISL38XX_CB_RX_QSIZE];
-	dma_addr_t pci_map_tx_address[ISL38XX_CB_TX_QSIZE];
-	dma_addr_t pci_map_rx_address[ISL38XX_CB_RX_QSIZE];
-
-	/* wait for a reset interrupt */
-	wait_queue_head_t reset_done;
-
-	/* used by islpci_mgt_transaction */
-	struct mutex mgmt_lock; /* serialize access to mailbox and wqueue */
-	struct islpci_mgmtframe *mgmt_received;	  /* mbox for incoming frame */
-	wait_queue_head_t mgmt_wqueue;            /* waitqueue for mbox */
-
-	/* state machine */
-	islpci_state_t state;
-	int state_off;		/* enumeration of off-state, if 0 then
-				 * we're not in any off-state */
-
-	/* WPA stuff */
-	int wpa; /* WPA mode enabled */
-	struct list_head bss_wpa_list;
-	int num_bss_wpa;
-	struct mutex wpa_lock;
-	u8 wpa_ie[MAX_WPA_IE_LEN];
-	size_t wpa_ie_len;
-
-	struct work_struct reset_task;
-	int reset_task_pending;
-} islpci_private;
-
-static inline islpci_state_t
-islpci_get_state(islpci_private *priv)
-{
-	/* lock */
-	return priv->state;
-	/* unlock */
-}
-
-islpci_state_t islpci_set_state(islpci_private *priv, islpci_state_t new_state);
-
-#define ISLPCI_TX_TIMEOUT               (2*HZ)
-
-irqreturn_t islpci_interrupt(int, void *);
-
-int prism54_post_setup(islpci_private *, int);
-int islpci_reset(islpci_private *, int);
-
-static inline void
-islpci_trigger(islpci_private *priv)
-{
-	isl38xx_trigger_device(islpci_get_state(priv) == PRV_STATE_SLEEP,
-			       priv->device_base);
-}
-
-int islpci_free_memory(islpci_private *);
-struct net_device *islpci_setup(struct pci_dev *);
-
-#define DRV_NAME	"prism54"
-#define DRV_VERSION	"1.2"
-
-#endif				/* _ISLPCI_DEV_H */
diff --git a/drivers/net/wireless/intersil/prism54/islpci_eth.c b/drivers/net/wireless/intersil/prism54/islpci_eth.c
deleted file mode 100644
index 74dd65716afd..000000000000
--- a/drivers/net/wireless/intersil/prism54/islpci_eth.c
+++ /dev/null
@@ -1,489 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  Copyright (C) 2002 Intersil Americas Inc.
- *  Copyright (C) 2004 Aurelien Alleaume <slts@free.fr>
- */
-
-#include <linux/module.h>
-#include <linux/gfp.h>
-
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/if_arp.h>
-#include <asm/byteorder.h>
-
-#include "prismcompat.h"
-#include "isl_38xx.h"
-#include "islpci_eth.h"
-#include "islpci_mgt.h"
-#include "oid_mgt.h"
-
-/******************************************************************************
-    Network Interface functions
-******************************************************************************/
-void
-islpci_eth_cleanup_transmit(islpci_private *priv,
-			    isl38xx_control_block *control_block)
-{
-	struct sk_buff *skb;
-	u32 index;
-
-	/* compare the control block read pointer with the free pointer */
-	while (priv->free_data_tx !=
-	       le32_to_cpu(control_block->
-			   device_curr_frag[ISL38XX_CB_TX_DATA_LQ])) {
-		/* read the index of the first fragment to be freed */
-		index = priv->free_data_tx % ISL38XX_CB_TX_QSIZE;
-
-		/* check for holes in the arrays caused by multi fragment frames
-		 * searching for the last fragment of a frame */
-		if (priv->pci_map_tx_address[index]) {
-			/* entry is the last fragment of a frame
-			 * free the skb structure and unmap pci memory */
-			skb = priv->data_low_tx[index];
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-			DEBUG(SHOW_TRACING,
-			      "cleanup skb %p skb->data %p skb->len %u truesize %u\n",
-			      skb, skb->data, skb->len, skb->truesize);
-#endif
-
-			dma_unmap_single(&priv->pdev->dev,
-					 priv->pci_map_tx_address[index],
-					 skb->len, DMA_TO_DEVICE);
-			dev_kfree_skb_irq(skb);
-			skb = NULL;
-		}
-		/* increment the free data low queue pointer */
-		priv->free_data_tx++;
-	}
-}
-
-netdev_tx_t
-islpci_eth_transmit(struct sk_buff *skb, struct net_device *ndev)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	isl38xx_control_block *cb = priv->control_block;
-	u32 index;
-	dma_addr_t pci_map_address;
-	int frame_size;
-	isl38xx_fragment *fragment;
-	int offset;
-	struct sk_buff *newskb;
-	int newskb_offset;
-	unsigned long flags;
-	unsigned char wds_mac[6];
-	u32 curr_frag;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_FUNCTION_CALLS, "islpci_eth_transmit\n");
-#endif
-
-	/* lock the driver code */
-	spin_lock_irqsave(&priv->slock, flags);
-
-	/* check whether the destination queue has enough fragments for the frame */
-	curr_frag = le32_to_cpu(cb->driver_curr_frag[ISL38XX_CB_TX_DATA_LQ]);
-	if (unlikely(curr_frag - priv->free_data_tx >= ISL38XX_CB_TX_QSIZE)) {
-		printk(KERN_ERR "%s: transmit device queue full when awake\n",
-		       ndev->name);
-		netif_stop_queue(ndev);
-
-		/* trigger the device */
-		isl38xx_w32_flush(priv->device_base, ISL38XX_DEV_INT_UPDATE,
-				  ISL38XX_DEV_INT_REG);
-		udelay(ISL38XX_WRITEIO_DELAY);
-		goto drop_free;
-	}
-	/* Check alignment and WDS frame formatting. The start of the packet should
-	 * be aligned on a 4-byte boundary. If WDS is enabled add another 6 bytes
-	 * and add WDS address information */
-	if (likely(((long) skb->data & 0x03) | init_wds)) {
-		/* get the number of bytes to add and re-align */
-		offset = (4 - (long) skb->data) & 0x03;
-		offset += init_wds ? 6 : 0;
-
-		/* check whether the current skb can be used  */
-		if (!skb_cloned(skb) && (skb_tailroom(skb) >= offset)) {
-			unsigned char *src = skb->data;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-			DEBUG(SHOW_TRACING, "skb offset %i wds %i\n", offset,
-			      init_wds);
-#endif
-
-			/* align the buffer on 4-byte boundary */
-			skb_reserve(skb, (4 - (long) skb->data) & 0x03);
-			if (init_wds) {
-				/* wds requires an additional address field of 6 bytes */
-				skb_put(skb, 6);
-#ifdef ISLPCI_ETH_DEBUG
-				printk("islpci_eth_transmit:wds_mac\n");
-#endif
-				memmove(skb->data + 6, src, skb->len);
-				skb_copy_to_linear_data(skb, wds_mac, 6);
-			} else {
-				memmove(skb->data, src, skb->len);
-			}
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-			DEBUG(SHOW_TRACING, "memmove %p %p %i\n", skb->data,
-			      src, skb->len);
-#endif
-		} else {
-			newskb =
-			    dev_alloc_skb(init_wds ? skb->len + 6 : skb->len);
-			if (unlikely(newskb == NULL)) {
-				printk(KERN_ERR "%s: Cannot allocate skb\n",
-				       ndev->name);
-				goto drop_free;
-			}
-			newskb_offset = (4 - (long) newskb->data) & 0x03;
-
-			/* Check if newskb->data is aligned */
-			if (newskb_offset)
-				skb_reserve(newskb, newskb_offset);
-
-			skb_put(newskb, init_wds ? skb->len + 6 : skb->len);
-			if (init_wds) {
-				skb_copy_from_linear_data(skb,
-							  newskb->data + 6,
-							  skb->len);
-				skb_copy_to_linear_data(newskb, wds_mac, 6);
-#ifdef ISLPCI_ETH_DEBUG
-				printk("islpci_eth_transmit:wds_mac\n");
-#endif
-			} else
-				skb_copy_from_linear_data(skb, newskb->data,
-							  skb->len);
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-			DEBUG(SHOW_TRACING, "memcpy %p %p %i wds %i\n",
-			      newskb->data, skb->data, skb->len, init_wds);
-#endif
-
-			newskb->dev = skb->dev;
-			dev_kfree_skb_irq(skb);
-			skb = newskb;
-		}
-	}
-	/* display the buffer contents for debugging */
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_BUFFER_CONTENTS, "\ntx %p ", skb->data);
-	display_buffer((char *) skb->data, skb->len);
-#endif
-
-	/* map the skb buffer to pci memory for DMA operation */
-	pci_map_address = dma_map_single(&priv->pdev->dev, (void *)skb->data,
-					 skb->len, DMA_TO_DEVICE);
-	if (dma_mapping_error(&priv->pdev->dev, pci_map_address)) {
-		printk(KERN_WARNING "%s: cannot map buffer to PCI\n",
-		       ndev->name);
-		goto drop_free;
-	}
-	/* Place the fragment in the control block structure. */
-	index = curr_frag % ISL38XX_CB_TX_QSIZE;
-	fragment = &cb->tx_data_low[index];
-
-	priv->pci_map_tx_address[index] = pci_map_address;
-	/* store the skb address for future freeing  */
-	priv->data_low_tx[index] = skb;
-	/* set the proper fragment start address and size information */
-	frame_size = skb->len;
-	fragment->size = cpu_to_le16(frame_size);
-	fragment->flags = cpu_to_le16(0);	/* set to 1 if more fragments */
-	fragment->address = cpu_to_le32(pci_map_address);
-	curr_frag++;
-
-	/* The fragment address in the control block must have been
-	 * written before announcing the frame buffer to device. */
-	wmb();
-	cb->driver_curr_frag[ISL38XX_CB_TX_DATA_LQ] = cpu_to_le32(curr_frag);
-
-	if (curr_frag - priv->free_data_tx + ISL38XX_MIN_QTHRESHOLD
-	    > ISL38XX_CB_TX_QSIZE) {
-		/* stop sends from upper layers */
-		netif_stop_queue(ndev);
-
-		/* set the full flag for the transmission queue */
-		priv->data_low_tx_full = 1;
-	}
-
-	ndev->stats.tx_packets++;
-	ndev->stats.tx_bytes += skb->len;
-
-	/* trigger the device */
-	islpci_trigger(priv);
-
-	/* unlock the driver code */
-	spin_unlock_irqrestore(&priv->slock, flags);
-
-	return NETDEV_TX_OK;
-
-      drop_free:
-	ndev->stats.tx_dropped++;
-	spin_unlock_irqrestore(&priv->slock, flags);
-	dev_kfree_skb(skb);
-	return NETDEV_TX_OK;
-}
-
-static inline int
-islpci_monitor_rx(islpci_private *priv, struct sk_buff **skb)
-{
-	/* The card reports full 802.11 packets but with a 20 bytes
-	 * header and without the FCS. But there a is a bit that
-	 * indicates if the packet is corrupted :-) */
-	struct rfmon_header *hdr = (struct rfmon_header *) (*skb)->data;
-
-	if (hdr->flags & 0x01)
-		/* This one is bad. Drop it ! */
-		return -1;
-	if (priv->ndev->type == ARPHRD_IEEE80211_PRISM) {
-		struct avs_80211_1_header *avs;
-		/* extract the relevant data from the header */
-		u32 clock = le32_to_cpu(hdr->clock);
-		u8 rate = hdr->rate;
-		u16 freq = le16_to_cpu(hdr->freq);
-		u8 rssi = hdr->rssi;
-
-		skb_pull(*skb, sizeof (struct rfmon_header));
-
-		if (skb_headroom(*skb) < sizeof (struct avs_80211_1_header)) {
-			struct sk_buff *newskb = skb_copy_expand(*skb,
-								 sizeof (struct
-									 avs_80211_1_header),
-								 0, GFP_ATOMIC);
-			if (newskb) {
-				dev_kfree_skb_irq(*skb);
-				*skb = newskb;
-			} else
-				return -1;
-			/* This behavior is not very subtile... */
-		}
-
-		/* make room for the new header and fill it. */
-		avs = skb_push(*skb, sizeof(struct avs_80211_1_header));
-
-		avs->version = cpu_to_be32(P80211CAPTURE_VERSION);
-		avs->length = cpu_to_be32(sizeof (struct avs_80211_1_header));
-		avs->mactime = cpu_to_be64(clock);
-		avs->hosttime = cpu_to_be64(jiffies);
-		avs->phytype = cpu_to_be32(6);	/*OFDM: 6 for (g), 8 for (a) */
-		avs->channel = cpu_to_be32(channel_of_freq(freq));
-		avs->datarate = cpu_to_be32(rate * 5);
-		avs->antenna = cpu_to_be32(0);	/*unknown */
-		avs->priority = cpu_to_be32(0);	/*unknown */
-		avs->ssi_type = cpu_to_be32(3);	/*2: dBm, 3: raw RSSI */
-		avs->ssi_signal = cpu_to_be32(rssi & 0x7f);
-		avs->ssi_noise = cpu_to_be32(priv->local_iwstatistics.qual.noise);	/*better than 'undefined', I assume */
-		avs->preamble = cpu_to_be32(0);	/*unknown */
-		avs->encoding = cpu_to_be32(0);	/*unknown */
-	} else
-		skb_pull(*skb, sizeof (struct rfmon_header));
-
-	(*skb)->protocol = htons(ETH_P_802_2);
-	skb_reset_mac_header(*skb);
-	(*skb)->pkt_type = PACKET_OTHERHOST;
-
-	return 0;
-}
-
-int
-islpci_eth_receive(islpci_private *priv)
-{
-	struct net_device *ndev = priv->ndev;
-	isl38xx_control_block *control_block = priv->control_block;
-	struct sk_buff *skb;
-	u16 size;
-	u32 index, offset;
-	unsigned char *src;
-	int discard = 0;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_FUNCTION_CALLS, "islpci_eth_receive\n");
-#endif
-
-	/* the device has written an Ethernet frame in the data area
-	 * of the sk_buff without updating the structure, do it now */
-	index = priv->free_data_rx % ISL38XX_CB_RX_QSIZE;
-	size = le16_to_cpu(control_block->rx_data_low[index].size);
-	skb = priv->data_low_rx[index];
-	offset = ((unsigned long)
-		  le32_to_cpu(control_block->rx_data_low[index].address) -
-		  (unsigned long) skb->data) & 3;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_TRACING,
-	      "frq->addr %x skb->data %p skb->len %u offset %u truesize %u\n",
-	      control_block->rx_data_low[priv->free_data_rx].address, skb->data,
-	      skb->len, offset, skb->truesize);
-#endif
-
-	/* delete the streaming DMA mapping before processing the skb */
-	dma_unmap_single(&priv->pdev->dev, priv->pci_map_rx_address[index],
-			 MAX_FRAGMENT_SIZE_RX + 2, DMA_FROM_DEVICE);
-
-	/* update the skb structure and align the buffer */
-	skb_put(skb, size);
-	if (offset) {
-		/* shift the buffer allocation offset bytes to get the right frame */
-		skb_pull(skb, 2);
-		skb_put(skb, 2);
-	}
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	/* display the buffer contents for debugging */
-	DEBUG(SHOW_BUFFER_CONTENTS, "\nrx %p ", skb->data);
-	display_buffer((char *) skb->data, skb->len);
-#endif
-
-	/* check whether WDS is enabled and whether the data frame is a WDS frame */
-
-	if (init_wds) {
-		/* WDS enabled, check for the wds address on the first 6 bytes of the buffer */
-		src = skb->data + 6;
-		memmove(skb->data, src, skb->len - 6);
-		skb_trim(skb, skb->len - 6);
-	}
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_TRACING, "Fragment size %i in skb at %p\n", size, skb);
-	DEBUG(SHOW_TRACING, "Skb data at %p, length %i\n", skb->data, skb->len);
-
-	/* display the buffer contents for debugging */
-	DEBUG(SHOW_BUFFER_CONTENTS, "\nrx %p ", skb->data);
-	display_buffer((char *) skb->data, skb->len);
-#endif
-	/* take care of monitor mode and spy monitoring. */
-	if (unlikely(priv->iw_mode == IW_MODE_MONITOR)) {
-		skb->dev = ndev;
-		discard = islpci_monitor_rx(priv, &skb);
-	} else {
-		if (unlikely(skb->data[2 * ETH_ALEN] == 0)) {
-			/* The packet has a rx_annex. Read it for spy monitoring, Then
-			 * remove it, while keeping the 2 leading MAC addr.
-			 */
-			struct iw_quality wstats;
-			struct rx_annex_header *annex =
-			    (struct rx_annex_header *) skb->data;
-			wstats.level = annex->rfmon.rssi;
-			/* The noise value can be a bit outdated if nobody's
-			 * reading wireless stats... */
-			wstats.noise = priv->local_iwstatistics.qual.noise;
-			wstats.qual = wstats.level - wstats.noise;
-			wstats.updated = 0x07;
-			/* Update spy records */
-			wireless_spy_update(ndev, annex->addr2, &wstats);
-
-			skb_copy_from_linear_data(skb,
-						  (skb->data +
-						   sizeof(struct rfmon_header)),
-						  2 * ETH_ALEN);
-			skb_pull(skb, sizeof (struct rfmon_header));
-		}
-		skb->protocol = eth_type_trans(skb, ndev);
-	}
-	skb->ip_summed = CHECKSUM_NONE;
-	ndev->stats.rx_packets++;
-	ndev->stats.rx_bytes += size;
-
-	/* deliver the skb to the network layer */
-#ifdef ISLPCI_ETH_DEBUG
-	printk
-	    ("islpci_eth_receive:netif_rx %2.2X %2.2X %2.2X %2.2X %2.2X %2.2X\n",
-	     skb->data[0], skb->data[1], skb->data[2], skb->data[3],
-	     skb->data[4], skb->data[5]);
-#endif
-	if (unlikely(discard)) {
-		dev_kfree_skb_irq(skb);
-		skb = NULL;
-	} else
-		netif_rx(skb);
-
-	/* increment the read index for the rx data low queue */
-	priv->free_data_rx++;
-
-	/* add one or more sk_buff structures */
-	while (index =
-	       le32_to_cpu(control_block->
-			   driver_curr_frag[ISL38XX_CB_RX_DATA_LQ]),
-	       index - priv->free_data_rx < ISL38XX_CB_RX_QSIZE) {
-		/* allocate an sk_buff for received data frames storage
-		 * include any required allignment operations */
-		skb = dev_alloc_skb(MAX_FRAGMENT_SIZE_RX + 2);
-		if (unlikely(skb == NULL)) {
-			/* error allocating an sk_buff structure elements */
-			DEBUG(SHOW_ERROR_MESSAGES, "Error allocating skb\n");
-			break;
-		}
-		skb_reserve(skb, (4 - (long) skb->data) & 0x03);
-		/* store the new skb structure pointer */
-		index = index % ISL38XX_CB_RX_QSIZE;
-		priv->data_low_rx[index] = skb;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-		DEBUG(SHOW_TRACING,
-		      "new alloc skb %p skb->data %p skb->len %u index %u truesize %u\n",
-		      skb, skb->data, skb->len, index, skb->truesize);
-#endif
-
-		/* set the streaming DMA mapping for proper PCI bus operation */
-		priv->pci_map_rx_address[index] =
-		    dma_map_single(&priv->pdev->dev, (void *)skb->data,
-				   MAX_FRAGMENT_SIZE_RX + 2, DMA_FROM_DEVICE);
-		if (dma_mapping_error(&priv->pdev->dev, priv->pci_map_rx_address[index])) {
-			/* error mapping the buffer to device accessible memory address */
-			DEBUG(SHOW_ERROR_MESSAGES,
-			      "Error mapping DMA address\n");
-
-			/* free the skbuf structure before aborting */
-			dev_kfree_skb_irq(skb);
-			skb = NULL;
-			break;
-		}
-		/* update the fragment address */
-		control_block->rx_data_low[index].address =
-			cpu_to_le32((u32)priv->pci_map_rx_address[index]);
-		wmb();
-
-		/* increment the driver read pointer */
-		le32_add_cpu(&control_block->
-			     driver_curr_frag[ISL38XX_CB_RX_DATA_LQ], 1);
-	}
-
-	/* trigger the device */
-	islpci_trigger(priv);
-
-	return 0;
-}
-
-void
-islpci_do_reset_and_wake(struct work_struct *work)
-{
-	islpci_private *priv = container_of(work, islpci_private, reset_task);
-
-	islpci_reset(priv, 1);
-	priv->reset_task_pending = 0;
-	smp_wmb();
-	netif_wake_queue(priv->ndev);
-}
-
-void
-islpci_eth_tx_timeout(struct net_device *ndev, unsigned int txqueue)
-{
-	islpci_private *priv = netdev_priv(ndev);
-
-	/* increment the transmit error counter */
-	ndev->stats.tx_errors++;
-
-	if (!priv->reset_task_pending) {
-		printk(KERN_WARNING
-			"%s: tx_timeout, scheduling reset", ndev->name);
-		netif_stop_queue(ndev);
-		priv->reset_task_pending = 1;
-		schedule_work(&priv->reset_task);
-	} else {
-		printk(KERN_WARNING
-			"%s: tx_timeout, waiting for reset", ndev->name);
-	}
-}
diff --git a/drivers/net/wireless/intersil/prism54/islpci_eth.h b/drivers/net/wireless/intersil/prism54/islpci_eth.h
deleted file mode 100644
index e433ccdc526b..000000000000
--- a/drivers/net/wireless/intersil/prism54/islpci_eth.h
+++ /dev/null
@@ -1,59 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  Copyright (C) 2002 Intersil Americas Inc.
- */
-
-#ifndef _ISLPCI_ETH_H
-#define _ISLPCI_ETH_H
-
-#include "isl_38xx.h"
-#include "islpci_dev.h"
-
-struct rfmon_header {
-	__le16 unk0;		/* = 0x0000 */
-	__le16 length;		/* = 0x1400 */
-	__le32 clock;		/* 1MHz clock */
-	u8 flags;
-	u8 unk1;
-	u8 rate;
-	u8 unk2;
-	__le16 freq;
-	__le16 unk3;
-	u8 rssi;
-	u8 padding[3];
-} __packed;
-
-struct rx_annex_header {
-	u8 addr1[ETH_ALEN];
-	u8 addr2[ETH_ALEN];
-	struct rfmon_header rfmon;
-} __packed;
-
-/* wlan-ng (and hopefully others) AVS header, version one.  Fields in
- * network byte order. */
-#define P80211CAPTURE_VERSION 0x80211001
-
-struct avs_80211_1_header {
-	__be32 version;
-	__be32 length;
-	__be64 mactime;
-	__be64 hosttime;
-	__be32 phytype;
-	__be32 channel;
-	__be32 datarate;
-	__be32 antenna;
-	__be32 priority;
-	__be32 ssi_type;
-	__be32 ssi_signal;
-	__be32 ssi_noise;
-	__be32 preamble;
-	__be32 encoding;
-};
-
-void islpci_eth_cleanup_transmit(islpci_private *, isl38xx_control_block *);
-netdev_tx_t islpci_eth_transmit(struct sk_buff *, struct net_device *);
-int islpci_eth_receive(islpci_private *);
-void islpci_eth_tx_timeout(struct net_device *, unsigned int txqueue);
-void islpci_do_reset_and_wake(struct work_struct *);
-
-#endif				/* _ISL_GEN_H */
diff --git a/drivers/net/wireless/intersil/prism54/islpci_hotplug.c b/drivers/net/wireless/intersil/prism54/islpci_hotplug.c
deleted file mode 100644
index 31a1e61326ff..000000000000
--- a/drivers/net/wireless/intersil/prism54/islpci_hotplug.c
+++ /dev/null
@@ -1,316 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  Copyright (C) 2002 Intersil Americas Inc.
- *  Copyright (C) 2003 Herbert Valerio Riedel <hvr@gnu.org>
- */
-
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/init.h> /* For __init, __exit */
-#include <linux/dma-mapping.h>
-
-#include "prismcompat.h"
-#include "islpci_dev.h"
-#include "islpci_mgt.h"		/* for pc_debug */
-#include "isl_oid.h"
-
-MODULE_AUTHOR("[Intersil] R.Bastings and W.Termorshuizen, The prism54.org Development Team <prism54-devel@prism54.org>");
-MODULE_DESCRIPTION("The Prism54 802.11 Wireless LAN adapter");
-MODULE_LICENSE("GPL");
-
-static int	init_pcitm = 0;
-module_param(init_pcitm, int, 0);
-
-/* In this order: vendor, device, subvendor, subdevice, class, class_mask,
- * driver_data
- * If you have an update for this please contact prism54-devel@prism54.org
- * The latest list can be found at http://wireless.wiki.kernel.org/en/users/Drivers/p54
- */
-static const struct pci_device_id prism54_id_tbl[] = {
-	/* Intersil PRISM Duette/Prism GT Wireless LAN adapter */
-	{
-	 0x1260, 0x3890,
-	 PCI_ANY_ID, PCI_ANY_ID,
-	 0, 0, 0
-	},
-
-	/* 3COM 3CRWE154G72 Wireless LAN adapter */
-	{
-	 PCI_VDEVICE(3COM, 0x6001), 0
-	},
-
-	/* Intersil PRISM Indigo Wireless LAN adapter */
-	{
-	 0x1260, 0x3877,
-	 PCI_ANY_ID, PCI_ANY_ID,
-	 0, 0, 0
-	},
-
-	/* Intersil PRISM Javelin/Xbow Wireless LAN adapter */
-	{
-	 0x1260, 0x3886,
-	 PCI_ANY_ID, PCI_ANY_ID,
-	 0, 0, 0
-	},
-
-	/* End of list */
-	{0,0,0,0,0,0,0}
-};
-
-/* register the device with the Hotplug facilities of the kernel */
-MODULE_DEVICE_TABLE(pci, prism54_id_tbl);
-
-static int prism54_probe(struct pci_dev *, const struct pci_device_id *);
-static void prism54_remove(struct pci_dev *);
-static int __maybe_unused prism54_suspend(struct device *);
-static int __maybe_unused prism54_resume(struct device *);
-
-static SIMPLE_DEV_PM_OPS(prism54_pm_ops, prism54_suspend, prism54_resume);
-
-static struct pci_driver prism54_driver = {
-	.name = DRV_NAME,
-	.id_table = prism54_id_tbl,
-	.probe = prism54_probe,
-	.remove = prism54_remove,
-	.driver.pm = &prism54_pm_ops,
-};
-
-/******************************************************************************
-    Module initialization functions
-******************************************************************************/
-
-static int
-prism54_probe(struct pci_dev *pdev, const struct pci_device_id *id)
-{
-	struct net_device *ndev;
-	u8 latency_tmr;
-	u32 mem_addr;
-	islpci_private *priv;
-	int rvalue;
-
-	/* Enable the pci device */
-	if (pci_enable_device(pdev)) {
-		printk(KERN_ERR "%s: pci_enable_device() failed.\n", DRV_NAME);
-		return -ENODEV;
-	}
-
-	/* check whether the latency timer is set correctly */
-	pci_read_config_byte(pdev, PCI_LATENCY_TIMER, &latency_tmr);
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_TRACING, "latency timer: %x\n", latency_tmr);
-#endif
-	if (latency_tmr < PCIDEVICE_LATENCY_TIMER_MIN) {
-		/* set the latency timer */
-		pci_write_config_byte(pdev, PCI_LATENCY_TIMER,
-				      PCIDEVICE_LATENCY_TIMER_VAL);
-	}
-
-	/* enable PCI DMA */
-	if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) {
-		printk(KERN_ERR "%s: 32-bit PCI DMA not supported", DRV_NAME);
-		goto do_pci_disable_device;
-        }
-
-	/* 0x40 is the programmable timer to configure the response timeout (TRDY_TIMEOUT)
-	 * 0x41 is the programmable timer to configure the retry timeout (RETRY_TIMEOUT)
-	 *	The RETRY_TIMEOUT is used to set the number of retries that the core, as a
-	 *	Master, will perform before abandoning a cycle. The default value for
-	 *	RETRY_TIMEOUT is 0x80, which far exceeds the PCI 2.1 requirement for new
-	 *	devices. A write of zero to the RETRY_TIMEOUT register disables this
-	 *	function to allow use with any non-compliant legacy devices that may
-	 *	execute more retries.
-	 *
-	 *	Writing zero to both these two registers will disable both timeouts and
-	 *	*can* solve problems caused by devices that are slow to respond.
-	 *	Make this configurable - MSW
-	 */
-	if ( init_pcitm >= 0 ) {
-		pci_write_config_byte(pdev, 0x40, (u8)init_pcitm);
-		pci_write_config_byte(pdev, 0x41, (u8)init_pcitm);
-	} else {
-		printk(KERN_INFO "PCI TRDY/RETRY unchanged\n");
-	}
-
-	/* request the pci device I/O regions */
-	rvalue = pci_request_regions(pdev, DRV_NAME);
-	if (rvalue) {
-		printk(KERN_ERR "%s: pci_request_regions failure (rc=%d)\n",
-		       DRV_NAME, rvalue);
-		goto do_pci_disable_device;
-	}
-
-	/* check if the memory window is indeed set */
-	rvalue = pci_read_config_dword(pdev, PCI_BASE_ADDRESS_0, &mem_addr);
-	if (rvalue || !mem_addr) {
-		printk(KERN_ERR "%s: PCI device memory region not configured; fix your BIOS or CardBus bridge/drivers\n",
-		       DRV_NAME);
-		goto do_pci_release_regions;
-	}
-
-	/* enable PCI bus-mastering */
-	DEBUG(SHOW_TRACING, "%s: pci_set_master(pdev)\n", DRV_NAME);
-	pci_set_master(pdev);
-
-	/* enable MWI */
-	pci_try_set_mwi(pdev);
-
-	/* setup the network device interface and its structure */
-	if (!(ndev = islpci_setup(pdev))) {
-		/* error configuring the driver as a network device */
-		printk(KERN_ERR "%s: could not configure network device\n",
-		       DRV_NAME);
-		goto do_pci_clear_mwi;
-	}
-
-	priv = netdev_priv(ndev);
-	islpci_set_state(priv, PRV_STATE_PREBOOT); /* we are attempting to boot */
-
-	/* card is in unknown state yet, might have some interrupts pending */
-	isl38xx_disable_interrupts(priv->device_base);
-
-	/* request for the interrupt before uploading the firmware */
-	rvalue = request_irq(pdev->irq, islpci_interrupt,
-			     IRQF_SHARED, ndev->name, priv);
-
-	if (rvalue) {
-		/* error, could not hook the handler to the irq */
-		printk(KERN_ERR "%s: could not install IRQ handler\n",
-		       ndev->name);
-		goto do_unregister_netdev;
-	}
-
-	/* firmware upload is triggered in islpci_open */
-
-	return 0;
-
-      do_unregister_netdev:
-	unregister_netdev(ndev);
-	islpci_free_memory(priv);
-	free_netdev(ndev);
-	priv = NULL;
-      do_pci_clear_mwi:
-	pci_clear_mwi(pdev);
-      do_pci_release_regions:
-	pci_release_regions(pdev);
-      do_pci_disable_device:
-	pci_disable_device(pdev);
-	return -EIO;
-}
-
-/* set by cleanup_module */
-static volatile int __in_cleanup_module = 0;
-
-/* this one removes one(!!) instance only */
-static void
-prism54_remove(struct pci_dev *pdev)
-{
-	struct net_device *ndev = pci_get_drvdata(pdev);
-	islpci_private *priv = ndev ? netdev_priv(ndev) : NULL;
-	BUG_ON(!priv);
-
-	if (!__in_cleanup_module) {
-		printk(KERN_DEBUG "%s: hot unplug detected\n", ndev->name);
-		islpci_set_state(priv, PRV_STATE_OFF);
-	}
-
-	printk(KERN_DEBUG "%s: removing device\n", ndev->name);
-
-	unregister_netdev(ndev);
-
-	/* free the interrupt request */
-
-	if (islpci_get_state(priv) != PRV_STATE_OFF) {
-		isl38xx_disable_interrupts(priv->device_base);
-		islpci_set_state(priv, PRV_STATE_OFF);
-		/* This bellow causes a lockup at rmmod time. It might be
-		 * because some interrupts still linger after rmmod time,
-		 * see bug #17 */
-		/* pci_set_power_state(pdev, 3);*/	/* try to power-off */
-	}
-
-	free_irq(pdev->irq, priv);
-
-	/* free the PCI memory and unmap the remapped page */
-	islpci_free_memory(priv);
-
-	free_netdev(ndev);
-	priv = NULL;
-
-	pci_clear_mwi(pdev);
-
-	pci_release_regions(pdev);
-
-	pci_disable_device(pdev);
-}
-
-static int __maybe_unused
-prism54_suspend(struct device *dev)
-{
-	struct net_device *ndev = dev_get_drvdata(dev);
-	islpci_private *priv = ndev ? netdev_priv(ndev) : NULL;
-	BUG_ON(!priv);
-
-	/* tell the device not to trigger interrupts for now... */
-	isl38xx_disable_interrupts(priv->device_base);
-
-	/* from now on assume the hardware was already powered down
-	   and don't touch it anymore */
-	islpci_set_state(priv, PRV_STATE_OFF);
-
-	netif_stop_queue(ndev);
-	netif_device_detach(ndev);
-
-	return 0;
-}
-
-static int __maybe_unused
-prism54_resume(struct device *dev)
-{
-	struct net_device *ndev = dev_get_drvdata(dev);
-	islpci_private *priv = ndev ? netdev_priv(ndev) : NULL;
-
-	BUG_ON(!priv);
-
-	printk(KERN_NOTICE "%s: got resume request\n", ndev->name);
-
-	/* alright let's go into the PREBOOT state */
-	islpci_reset(priv, 1);
-
-	netif_device_attach(ndev);
-	netif_start_queue(ndev);
-
-	return 0;
-}
-
-static int __init
-prism54_module_init(void)
-{
-	printk(KERN_INFO "Loaded %s driver, version %s\n",
-	       DRV_NAME, DRV_VERSION);
-
-	__bug_on_wrong_struct_sizes ();
-
-	return pci_register_driver(&prism54_driver);
-}
-
-/* by the time prism54_module_exit() terminates, as a postcondition
- * all instances will have been destroyed by calls to
- * prism54_remove() */
-static void __exit
-prism54_module_exit(void)
-{
-	__in_cleanup_module = 1;
-
-	pci_unregister_driver(&prism54_driver);
-
-	printk(KERN_INFO "Unloaded %s driver\n", DRV_NAME);
-
-	__in_cleanup_module = 0;
-}
-
-/* register entry points */
-module_init(prism54_module_init);
-module_exit(prism54_module_exit);
-/* EOF */
diff --git a/drivers/net/wireless/intersil/prism54/islpci_mgt.c b/drivers/net/wireless/intersil/prism54/islpci_mgt.c
deleted file mode 100644
index 0c7fb76c7d1c..000000000000
--- a/drivers/net/wireless/intersil/prism54/islpci_mgt.c
+++ /dev/null
@@ -1,491 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  Copyright (C) 2002 Intersil Americas Inc.
- *  Copyright 2004 Jens Maurer <Jens.Maurer@gmx.net>
- */
-
-#include <linux/netdevice.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-
-#include <asm/io.h>
-#include <linux/if_arp.h>
-
-#include "prismcompat.h"
-#include "isl_38xx.h"
-#include "islpci_mgt.h"
-#include "isl_oid.h"		/* additional types and defs for isl38xx fw */
-#include "isl_ioctl.h"
-
-#include <net/iw_handler.h>
-
-/******************************************************************************
-        Global variable definition section
-******************************************************************************/
-int pc_debug = VERBOSE;
-module_param(pc_debug, int, 0);
-
-/******************************************************************************
-    Driver general functions
-******************************************************************************/
-#if VERBOSE > SHOW_ERROR_MESSAGES
-void
-display_buffer(char *buffer, int length)
-{
-	if ((pc_debug & SHOW_BUFFER_CONTENTS) == 0)
-		return;
-
-	while (length > 0) {
-		printk("[%02x]", *buffer & 255);
-		length--;
-		buffer++;
-	}
-
-	printk("\n");
-}
-#endif
-
-/*****************************************************************************
-    Queue handling for management frames
-******************************************************************************/
-
-/*
- * Helper function to create a PIMFOR management frame header.
- */
-static void
-pimfor_encode_header(int operation, u32 oid, u32 length, pimfor_header_t *h)
-{
-	h->version = PIMFOR_VERSION;
-	h->operation = operation;
-	h->device_id = PIMFOR_DEV_ID_MHLI_MIB;
-	h->flags = 0;
-	h->oid = cpu_to_be32(oid);
-	h->length = cpu_to_be32(length);
-}
-
-/*
- * Helper function to analyze a PIMFOR management frame header.
- */
-static pimfor_header_t *
-pimfor_decode_header(void *data, int len)
-{
-	pimfor_header_t *h = data;
-
-	while ((void *) h < data + len) {
-		if (h->flags & PIMFOR_FLAG_LITTLE_ENDIAN) {
-			le32_to_cpus(&h->oid);
-			le32_to_cpus(&h->length);
-		} else {
-			be32_to_cpus(&h->oid);
-			be32_to_cpus(&h->length);
-		}
-		if (h->oid != OID_INL_TUNNEL)
-			return h;
-		h++;
-	}
-	return NULL;
-}
-
-/*
- * Fill the receive queue for management frames with fresh buffers.
- */
-int
-islpci_mgmt_rx_fill(struct net_device *ndev)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	isl38xx_control_block *cb =	/* volatile not needed */
-	    (isl38xx_control_block *) priv->control_block;
-	u32 curr = le32_to_cpu(cb->driver_curr_frag[ISL38XX_CB_RX_MGMTQ]);
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_FUNCTION_CALLS, "islpci_mgmt_rx_fill\n");
-#endif
-
-	while (curr - priv->index_mgmt_rx < ISL38XX_CB_MGMT_QSIZE) {
-		u32 index = curr % ISL38XX_CB_MGMT_QSIZE;
-		struct islpci_membuf *buf = &priv->mgmt_rx[index];
-		isl38xx_fragment *frag = &cb->rx_data_mgmt[index];
-
-		if (buf->mem == NULL) {
-			buf->mem = kmalloc(MGMT_FRAME_SIZE, GFP_ATOMIC);
-			if (!buf->mem)
-				return -ENOMEM;
-			buf->size = MGMT_FRAME_SIZE;
-		}
-		if (buf->pci_addr == 0) {
-			buf->pci_addr = dma_map_single(&priv->pdev->dev,
-						       buf->mem,
-						       MGMT_FRAME_SIZE,
-						       DMA_FROM_DEVICE);
-			if (dma_mapping_error(&priv->pdev->dev, buf->pci_addr)) {
-				printk(KERN_WARNING
-				       "Failed to make memory DMA'able.\n");
-				return -ENOMEM;
-			}
-		}
-
-		/* be safe: always reset control block information */
-		frag->size = cpu_to_le16(MGMT_FRAME_SIZE);
-		frag->flags = 0;
-		frag->address = cpu_to_le32(buf->pci_addr);
-		curr++;
-
-		/* The fragment address in the control block must have
-		 * been written before announcing the frame buffer to
-		 * device */
-		wmb();
-		cb->driver_curr_frag[ISL38XX_CB_RX_MGMTQ] = cpu_to_le32(curr);
-	}
-	return 0;
-}
-
-/*
- * Create and transmit a management frame using "operation" and "oid",
- * with arguments data/length.
- * We either return an error and free the frame, or we return 0 and
- * islpci_mgt_cleanup_transmit() frees the frame in the tx-done
- * interrupt.
- */
-static int
-islpci_mgt_transmit(struct net_device *ndev, int operation, unsigned long oid,
-		    void *data, int length)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	isl38xx_control_block *cb =
-	    (isl38xx_control_block *) priv->control_block;
-	void *p;
-	int err = -EINVAL;
-	unsigned long flags;
-	isl38xx_fragment *frag;
-	struct islpci_membuf buf;
-	u32 curr_frag;
-	int index;
-	int frag_len = length + PIMFOR_HEADER_SIZE;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_FUNCTION_CALLS, "islpci_mgt_transmit\n");
-#endif
-
-	if (frag_len > MGMT_FRAME_SIZE) {
-		printk(KERN_DEBUG "%s: mgmt frame too large %d\n",
-		       ndev->name, frag_len);
-		goto error;
-	}
-
-	err = -ENOMEM;
-	p = buf.mem = kmalloc(frag_len, GFP_KERNEL);
-	if (!buf.mem)
-		goto error;
-
-	buf.size = frag_len;
-
-	/* create the header directly in the fragment data area */
-	pimfor_encode_header(operation, oid, length, (pimfor_header_t *) p);
-	p += PIMFOR_HEADER_SIZE;
-
-	if (data)
-		memcpy(p, data, length);
-	else
-		memset(p, 0, length);
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	{
-		pimfor_header_t *h = buf.mem;
-		DEBUG(SHOW_PIMFOR_FRAMES,
-		      "PIMFOR: op %i, oid 0x%08lx, device %i, flags 0x%x length 0x%x\n",
-		      h->operation, oid, h->device_id, h->flags, length);
-
-		/* display the buffer contents for debugging */
-		display_buffer((char *) h, sizeof (pimfor_header_t));
-		display_buffer(p, length);
-	}
-#endif
-
-	err = -ENOMEM;
-	buf.pci_addr = dma_map_single(&priv->pdev->dev, buf.mem, frag_len,
-				      DMA_TO_DEVICE);
-	if (dma_mapping_error(&priv->pdev->dev, buf.pci_addr)) {
-		printk(KERN_WARNING "%s: cannot map PCI memory for mgmt\n",
-		       ndev->name);
-		goto error_free;
-	}
-
-	/* Protect the control block modifications against interrupts. */
-	spin_lock_irqsave(&priv->slock, flags);
-	curr_frag = le32_to_cpu(cb->driver_curr_frag[ISL38XX_CB_TX_MGMTQ]);
-	if (curr_frag - priv->index_mgmt_tx >= ISL38XX_CB_MGMT_QSIZE) {
-		printk(KERN_WARNING "%s: mgmt tx queue is still full\n",
-		       ndev->name);
-		goto error_unlock;
-	}
-
-	/* commit the frame to the tx device queue */
-	index = curr_frag % ISL38XX_CB_MGMT_QSIZE;
-	priv->mgmt_tx[index] = buf;
-	frag = &cb->tx_data_mgmt[index];
-	frag->size = cpu_to_le16(frag_len);
-	frag->flags = 0;	/* for any other than the last fragment, set to 1 */
-	frag->address = cpu_to_le32(buf.pci_addr);
-
-	/* The fragment address in the control block must have
-	 * been written before announcing the frame buffer to
-	 * device */
-	wmb();
-	cb->driver_curr_frag[ISL38XX_CB_TX_MGMTQ] = cpu_to_le32(curr_frag + 1);
-	spin_unlock_irqrestore(&priv->slock, flags);
-
-	/* trigger the device */
-	islpci_trigger(priv);
-	return 0;
-
-      error_unlock:
-	spin_unlock_irqrestore(&priv->slock, flags);
-      error_free:
-	kfree(buf.mem);
-      error:
-	return err;
-}
-
-/*
- * Receive a management frame from the device.
- * This can be an arbitrary number of traps, and at most one response
- * frame for a previous request sent via islpci_mgt_transmit().
- */
-int
-islpci_mgt_receive(struct net_device *ndev)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	isl38xx_control_block *cb =
-	    (isl38xx_control_block *) priv->control_block;
-	u32 curr_frag;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_FUNCTION_CALLS, "islpci_mgt_receive\n");
-#endif
-
-	/* Only once per interrupt, determine fragment range to
-	 * process.  This avoids an endless loop (i.e. lockup) if
-	 * frames come in faster than we can process them. */
-	curr_frag = le32_to_cpu(cb->device_curr_frag[ISL38XX_CB_RX_MGMTQ]);
-	barrier();
-
-	for (; priv->index_mgmt_rx < curr_frag; priv->index_mgmt_rx++) {
-		pimfor_header_t *header;
-		u32 index = priv->index_mgmt_rx % ISL38XX_CB_MGMT_QSIZE;
-		struct islpci_membuf *buf = &priv->mgmt_rx[index];
-		u16 frag_len;
-		int size;
-		struct islpci_mgmtframe *frame;
-
-		/* I have no idea (and no documentation) if flags != 0
-		 * is possible.  Drop the frame, reuse the buffer. */
-		if (le16_to_cpu(cb->rx_data_mgmt[index].flags) != 0) {
-			printk(KERN_WARNING "%s: unknown flags 0x%04x\n",
-			       ndev->name,
-			       le16_to_cpu(cb->rx_data_mgmt[index].flags));
-			continue;
-		}
-
-		/* The device only returns the size of the header(s) here. */
-		frag_len = le16_to_cpu(cb->rx_data_mgmt[index].size);
-
-		/*
-		 * We appear to have no way to tell the device the
-		 * size of a receive buffer.  Thus, if this check
-		 * triggers, we likely have kernel heap corruption. */
-		if (frag_len > MGMT_FRAME_SIZE) {
-			printk(KERN_WARNING
-				"%s: Bogus packet size of %d (%#x).\n",
-				ndev->name, frag_len, frag_len);
-			frag_len = MGMT_FRAME_SIZE;
-		}
-
-		/* Ensure the results of device DMA are visible to the CPU. */
-		dma_sync_single_for_cpu(&priv->pdev->dev, buf->pci_addr,
-					buf->size, DMA_FROM_DEVICE);
-
-		/* Perform endianess conversion for PIMFOR header in-place. */
-		header = pimfor_decode_header(buf->mem, frag_len);
-		if (!header) {
-			printk(KERN_WARNING "%s: no PIMFOR header found\n",
-			       ndev->name);
-			continue;
-		}
-
-		/* The device ID from the PIMFOR packet received from
-		 * the MVC is always 0.  We forward a sensible device_id.
-		 * Not that anyone upstream would care... */
-		header->device_id = priv->ndev->ifindex;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-		DEBUG(SHOW_PIMFOR_FRAMES,
-		      "PIMFOR: op %i, oid 0x%08x, device %i, flags 0x%x length 0x%x\n",
-		      header->operation, header->oid, header->device_id,
-		      header->flags, header->length);
-
-		/* display the buffer contents for debugging */
-		display_buffer((char *) header, PIMFOR_HEADER_SIZE);
-		display_buffer((char *) header + PIMFOR_HEADER_SIZE,
-			       header->length);
-#endif
-
-		/* nobody sends these */
-		if (header->flags & PIMFOR_FLAG_APPLIC_ORIGIN) {
-			printk(KERN_DEBUG
-			       "%s: errant PIMFOR application frame\n",
-			       ndev->name);
-			continue;
-		}
-
-		/* Determine frame size, skipping OID_INL_TUNNEL headers. */
-		size = PIMFOR_HEADER_SIZE + header->length;
-		frame = kmalloc(sizeof(struct islpci_mgmtframe) + size,
-				GFP_ATOMIC);
-		if (!frame)
-			continue;
-
-		frame->ndev = ndev;
-		memcpy(&frame->buf, header, size);
-		frame->header = (pimfor_header_t *) frame->buf;
-		frame->data = frame->buf + PIMFOR_HEADER_SIZE;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-		DEBUG(SHOW_PIMFOR_FRAMES,
-		      "frame: header: %p, data: %p, size: %d\n",
-		      frame->header, frame->data, size);
-#endif
-
-		if (header->operation == PIMFOR_OP_TRAP) {
-#if VERBOSE > SHOW_ERROR_MESSAGES
-			printk(KERN_DEBUG
-			       "TRAP: oid 0x%x, device %i, flags 0x%x length %i\n",
-			       header->oid, header->device_id, header->flags,
-			       header->length);
-#endif
-
-			/* Create work to handle trap out of interrupt
-			 * context. */
-			INIT_WORK(&frame->ws, prism54_process_trap);
-			schedule_work(&frame->ws);
-
-		} else {
-			/* Signal the one waiting process that a response
-			 * has been received. */
-			if ((frame = xchg(&priv->mgmt_received, frame)) != NULL) {
-				printk(KERN_WARNING
-				       "%s: mgmt response not collected\n",
-				       ndev->name);
-				kfree(frame);
-			}
-#if VERBOSE > SHOW_ERROR_MESSAGES
-			DEBUG(SHOW_TRACING, "Wake up Mgmt Queue\n");
-#endif
-			wake_up(&priv->mgmt_wqueue);
-		}
-
-	}
-
-	return 0;
-}
-
-/*
- * Cleanup the transmit queue by freeing all frames handled by the device.
- */
-void
-islpci_mgt_cleanup_transmit(struct net_device *ndev)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	isl38xx_control_block *cb =	/* volatile not needed */
-	    (isl38xx_control_block *) priv->control_block;
-	u32 curr_frag;
-
-#if VERBOSE > SHOW_ERROR_MESSAGES
-	DEBUG(SHOW_FUNCTION_CALLS, "islpci_mgt_cleanup_transmit\n");
-#endif
-
-	/* Only once per cleanup, determine fragment range to
-	 * process.  This avoids an endless loop (i.e. lockup) if
-	 * the device became confused, incrementing device_curr_frag
-	 * rapidly. */
-	curr_frag = le32_to_cpu(cb->device_curr_frag[ISL38XX_CB_TX_MGMTQ]);
-	barrier();
-
-	for (; priv->index_mgmt_tx < curr_frag; priv->index_mgmt_tx++) {
-		int index = priv->index_mgmt_tx % ISL38XX_CB_MGMT_QSIZE;
-		struct islpci_membuf *buf = &priv->mgmt_tx[index];
-		dma_unmap_single(&priv->pdev->dev, buf->pci_addr, buf->size,
-				 DMA_TO_DEVICE);
-		buf->pci_addr = 0;
-		kfree(buf->mem);
-		buf->mem = NULL;
-		buf->size = 0;
-	}
-}
-
-/*
- * Perform one request-response transaction to the device.
- */
-int
-islpci_mgt_transaction(struct net_device *ndev,
-		       int operation, unsigned long oid,
-		       void *senddata, int sendlen,
-		       struct islpci_mgmtframe **recvframe)
-{
-	islpci_private *priv = netdev_priv(ndev);
-	const long wait_cycle_jiffies = msecs_to_jiffies(ISL38XX_WAIT_CYCLE * 10);
-	long timeout_left = ISL38XX_MAX_WAIT_CYCLES * wait_cycle_jiffies;
-	int err;
-	DEFINE_WAIT(wait);
-
-	*recvframe = NULL;
-
-	if (mutex_lock_interruptible(&priv->mgmt_lock))
-		return -ERESTARTSYS;
-
-	prepare_to_wait(&priv->mgmt_wqueue, &wait, TASK_UNINTERRUPTIBLE);
-	err = islpci_mgt_transmit(ndev, operation, oid, senddata, sendlen);
-	if (err)
-		goto out;
-
-	err = -ETIMEDOUT;
-	while (timeout_left > 0) {
-		int timeleft;
-		struct islpci_mgmtframe *frame;
-
-		timeleft = schedule_timeout_uninterruptible(wait_cycle_jiffies);
-		frame = xchg(&priv->mgmt_received, NULL);
-		if (frame) {
-			if (frame->header->oid == oid) {
-				*recvframe = frame;
-				err = 0;
-				goto out;
-			} else {
-				printk(KERN_DEBUG
-				       "%s: expecting oid 0x%x, received 0x%x.\n",
-				       ndev->name, (unsigned int) oid,
-				       frame->header->oid);
-				kfree(frame);
-				frame = NULL;
-			}
-		}
-		if (timeleft == 0) {
-			printk(KERN_DEBUG
-				"%s: timeout waiting for mgmt response %lu, "
-				"triggering device\n",
-				ndev->name, timeout_left);
-			islpci_trigger(priv);
-		}
-		timeout_left += timeleft - wait_cycle_jiffies;
-	}
-	printk(KERN_WARNING "%s: timeout waiting for mgmt response\n",
-	       ndev->name);
-
-	/* TODO: we should reset the device here */
- out:
-	finish_wait(&priv->mgmt_wqueue, &wait);
-	mutex_unlock(&priv->mgmt_lock);
-	return err;
-}
-
diff --git a/drivers/net/wireless/intersil/prism54/islpci_mgt.h b/drivers/net/wireless/intersil/prism54/islpci_mgt.h
deleted file mode 100644
index 1f87d0aea60c..000000000000
--- a/drivers/net/wireless/intersil/prism54/islpci_mgt.h
+++ /dev/null
@@ -1,126 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  Copyright (C) 2002 Intersil Americas Inc.
- *  Copyright (C) 2003 Luis R. Rodriguez <mcgrof@ruslug.rutgers.edu>
- */
-
-#ifndef _ISLPCI_MGT_H
-#define _ISLPCI_MGT_H
-
-#include <linux/wireless.h>
-#include <linux/skbuff.h>
-#include <linux/slab.h>
-
-/*
- *  Function definitions
- */
-
-#define K_DEBUG(f, m, args...) do { if(f & m) printk(KERN_DEBUG args); } while(0)
-#define DEBUG(f, args...) K_DEBUG(f, pc_debug, args)
-
-extern int pc_debug;
-#define init_wds 0	/* help compiler optimize away dead code */
-
-
-/* General driver definitions */
-#define PCIDEVICE_LATENCY_TIMER_MIN		0x40
-#define PCIDEVICE_LATENCY_TIMER_VAL		0x50
-
-/* Debugging verbose definitions */
-#define SHOW_NOTHING                            0x00	/* overrules everything */
-#define SHOW_ANYTHING                           0xFF
-#define SHOW_ERROR_MESSAGES                     0x01
-#define SHOW_TRAPS                              0x02
-#define SHOW_FUNCTION_CALLS                     0x04
-#define SHOW_TRACING                            0x08
-#define SHOW_QUEUE_INDEXES                      0x10
-#define SHOW_PIMFOR_FRAMES                      0x20
-#define SHOW_BUFFER_CONTENTS                    0x40
-#define VERBOSE                                 0x01
-
-/* Default card definitions */
-#define CARD_DEFAULT_CHANNEL                    6
-#define CARD_DEFAULT_MODE                       INL_MODE_CLIENT
-#define CARD_DEFAULT_IW_MODE			IW_MODE_INFRA
-#define CARD_DEFAULT_BSSTYPE                    DOT11_BSSTYPE_INFRA
-#define CARD_DEFAULT_CLIENT_SSID		""
-#define CARD_DEFAULT_AP_SSID			"default"
-#define CARD_DEFAULT_KEY1                       "default_key_1"
-#define CARD_DEFAULT_KEY2                       "default_key_2"
-#define CARD_DEFAULT_KEY3                       "default_key_3"
-#define CARD_DEFAULT_KEY4                       "default_key_4"
-#define CARD_DEFAULT_WEP                        0
-#define CARD_DEFAULT_FILTER                     0
-#define CARD_DEFAULT_WDS                        0
-#define	CARD_DEFAULT_AUTHEN                     DOT11_AUTH_OS
-#define	CARD_DEFAULT_DOT1X			0
-#define CARD_DEFAULT_MLME_MODE			DOT11_MLME_AUTO
-#define CARD_DEFAULT_CONFORMANCE                OID_INL_CONFORMANCE_NONE
-#define CARD_DEFAULT_PROFILE			DOT11_PROFILE_MIXED_G_WIFI
-#define CARD_DEFAULT_MAXFRAMEBURST		DOT11_MAXFRAMEBURST_MIXED_SAFE
-
-/* PIMFOR package definitions */
-#define PIMFOR_ETHERTYPE                        0x8828
-#define PIMFOR_HEADER_SIZE                      12
-#define PIMFOR_VERSION                          1
-#define PIMFOR_OP_GET                           0
-#define PIMFOR_OP_SET                           1
-#define PIMFOR_OP_RESPONSE                      2
-#define PIMFOR_OP_ERROR                         3
-#define PIMFOR_OP_TRAP                          4
-#define PIMFOR_OP_RESERVED                      5	/* till 255 */
-#define PIMFOR_DEV_ID_MHLI_MIB                  0
-#define PIMFOR_FLAG_APPLIC_ORIGIN               0x01
-#define PIMFOR_FLAG_LITTLE_ENDIAN               0x02
-
-void display_buffer(char *, int);
-
-/*
- *  Type definition section
- *
- *  the structure defines only the header allowing copyless
- *  frame handling
- */
-typedef struct {
-	u8 version;
-	u8 operation;
-	u32 oid;
-	u8 device_id;
-	u8 flags;
-	u32 length;
-} __packed
-pimfor_header_t;
-
-/* A received and interrupt-processed management frame, either for
- * schedule_work(prism54_process_trap) or for priv->mgmt_received,
- * processed by islpci_mgt_transaction(). */
-struct islpci_mgmtframe {
-	struct net_device *ndev;      /* pointer to network device */
-	pimfor_header_t *header;      /* payload header, points into buf */
-	void *data;		      /* payload ex header, points into buf */
-        struct work_struct ws;	      /* argument for schedule_work() */
-	char buf[];		      /* fragment buffer */
-};
-
-int
-islpci_mgt_receive(struct net_device *ndev);
-
-int
-islpci_mgmt_rx_fill(struct net_device *ndev);
-
-void
-islpci_mgt_cleanup_transmit(struct net_device *ndev);
-
-int
-islpci_mgt_transaction(struct net_device *ndev,
-                       int operation, unsigned long oid,
-		       void *senddata, int sendlen,
-		       struct islpci_mgmtframe **recvframe);
-
-static inline void
-islpci_mgt_release(struct islpci_mgmtframe *frame)
-{
-        kfree(frame);
-}
-
-#endif				/* _ISLPCI_MGT_H */
diff --git a/drivers/net/wireless/intersil/prism54/oid_mgt.c b/drivers/net/wireless/intersil/prism54/oid_mgt.c
deleted file mode 100644
index 9fd307ca4b6d..000000000000
--- a/drivers/net/wireless/intersil/prism54/oid_mgt.c
+++ /dev/null
@@ -1,889 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  Copyright (C) 2003,2004 Aurelien Alleaume <slts@free.fr>
- */
-
-#include <linux/kernel.h>
-#include <linux/slab.h>
-
-#include "prismcompat.h"
-#include "islpci_dev.h"
-#include "islpci_mgt.h"
-#include "isl_oid.h"
-#include "oid_mgt.h"
-#include "isl_ioctl.h"
-
-/* to convert between channel and freq */
-static const int frequency_list_bg[] = { 2412, 2417, 2422, 2427, 2432,
-	2437, 2442, 2447, 2452, 2457, 2462, 2467, 2472, 2484
-};
-
-int
-channel_of_freq(int f)
-{
-	int c = 0;
-
-	if ((f >= 2412) && (f <= 2484)) {
-		while ((c < 14) && (f != frequency_list_bg[c]))
-			c++;
-		return (c >= 14) ? 0 : ++c;
-	} else if ((f >= (int) 5000) && (f <= (int) 6000)) {
-		return ( (f - 5000) / 5 );
-	} else
-		return 0;
-}
-
-#define OID_STRUCT(name,oid,s,t) [name] = {oid, 0, sizeof(s), t}
-#define OID_STRUCT_C(name,oid,s,t) OID_STRUCT(name,oid,s,t | OID_FLAG_CACHED)
-#define OID_U32(name,oid) OID_STRUCT(name,oid,u32,OID_TYPE_U32)
-#define OID_U32_C(name,oid) OID_STRUCT_C(name,oid,u32,OID_TYPE_U32)
-#define OID_STRUCT_MLME(name,oid) OID_STRUCT(name,oid,struct obj_mlme,OID_TYPE_MLME)
-#define OID_STRUCT_MLMEEX(name,oid) OID_STRUCT(name,oid,struct obj_mlmeex,OID_TYPE_MLMEEX)
-
-#define OID_UNKNOWN(name,oid) OID_STRUCT(name,oid,0,0)
-
-struct oid_t isl_oid[] = {
-	OID_STRUCT(GEN_OID_MACADDRESS, 0x00000000, u8[6], OID_TYPE_ADDR),
-	OID_U32(GEN_OID_LINKSTATE, 0x00000001),
-	OID_UNKNOWN(GEN_OID_WATCHDOG, 0x00000002),
-	OID_UNKNOWN(GEN_OID_MIBOP, 0x00000003),
-	OID_UNKNOWN(GEN_OID_OPTIONS, 0x00000004),
-	OID_UNKNOWN(GEN_OID_LEDCONFIG, 0x00000005),
-
-	/* 802.11 */
-	OID_U32_C(DOT11_OID_BSSTYPE, 0x10000000),
-	OID_STRUCT_C(DOT11_OID_BSSID, 0x10000001, u8[6], OID_TYPE_RAW),
-	OID_STRUCT_C(DOT11_OID_SSID, 0x10000002, struct obj_ssid,
-		     OID_TYPE_SSID),
-	OID_U32(DOT11_OID_STATE, 0x10000003),
-	OID_U32(DOT11_OID_AID, 0x10000004),
-	OID_STRUCT(DOT11_OID_COUNTRYSTRING, 0x10000005, u8[4], OID_TYPE_RAW),
-	OID_STRUCT_C(DOT11_OID_SSIDOVERRIDE, 0x10000006, struct obj_ssid,
-		     OID_TYPE_SSID),
-
-	OID_U32(DOT11_OID_MEDIUMLIMIT, 0x11000000),
-	OID_U32_C(DOT11_OID_BEACONPERIOD, 0x11000001),
-	OID_U32(DOT11_OID_DTIMPERIOD, 0x11000002),
-	OID_U32(DOT11_OID_ATIMWINDOW, 0x11000003),
-	OID_U32(DOT11_OID_LISTENINTERVAL, 0x11000004),
-	OID_U32(DOT11_OID_CFPPERIOD, 0x11000005),
-	OID_U32(DOT11_OID_CFPDURATION, 0x11000006),
-
-	OID_U32_C(DOT11_OID_AUTHENABLE, 0x12000000),
-	OID_U32_C(DOT11_OID_PRIVACYINVOKED, 0x12000001),
-	OID_U32_C(DOT11_OID_EXUNENCRYPTED, 0x12000002),
-	OID_U32_C(DOT11_OID_DEFKEYID, 0x12000003),
-	[DOT11_OID_DEFKEYX] = {0x12000004, 3, sizeof (struct obj_key),
-			       OID_FLAG_CACHED | OID_TYPE_KEY},	/* DOT11_OID_DEFKEY1,...DOT11_OID_DEFKEY4 */
-	OID_UNKNOWN(DOT11_OID_STAKEY, 0x12000008),
-	OID_U32(DOT11_OID_REKEYTHRESHOLD, 0x12000009),
-	OID_UNKNOWN(DOT11_OID_STASC, 0x1200000a),
-
-	OID_U32(DOT11_OID_PRIVTXREJECTED, 0x1a000000),
-	OID_U32(DOT11_OID_PRIVRXPLAIN, 0x1a000001),
-	OID_U32(DOT11_OID_PRIVRXFAILED, 0x1a000002),
-	OID_U32(DOT11_OID_PRIVRXNOKEY, 0x1a000003),
-
-	OID_U32_C(DOT11_OID_RTSTHRESH, 0x13000000),
-	OID_U32_C(DOT11_OID_FRAGTHRESH, 0x13000001),
-	OID_U32_C(DOT11_OID_SHORTRETRIES, 0x13000002),
-	OID_U32_C(DOT11_OID_LONGRETRIES, 0x13000003),
-	OID_U32_C(DOT11_OID_MAXTXLIFETIME, 0x13000004),
-	OID_U32(DOT11_OID_MAXRXLIFETIME, 0x13000005),
-	OID_U32(DOT11_OID_AUTHRESPTIMEOUT, 0x13000006),
-	OID_U32(DOT11_OID_ASSOCRESPTIMEOUT, 0x13000007),
-
-	OID_UNKNOWN(DOT11_OID_ALOFT_TABLE, 0x1d000000),
-	OID_UNKNOWN(DOT11_OID_ALOFT_CTRL_TABLE, 0x1d000001),
-	OID_UNKNOWN(DOT11_OID_ALOFT_RETREAT, 0x1d000002),
-	OID_UNKNOWN(DOT11_OID_ALOFT_PROGRESS, 0x1d000003),
-	OID_U32(DOT11_OID_ALOFT_FIXEDRATE, 0x1d000004),
-	OID_UNKNOWN(DOT11_OID_ALOFT_RSSIGRAPH, 0x1d000005),
-	OID_UNKNOWN(DOT11_OID_ALOFT_CONFIG, 0x1d000006),
-
-	[DOT11_OID_VDCFX] = {0x1b000000, 7, 0, 0},
-	OID_U32(DOT11_OID_MAXFRAMEBURST, 0x1b000008),
-
-	OID_U32(DOT11_OID_PSM, 0x14000000),
-	OID_U32(DOT11_OID_CAMTIMEOUT, 0x14000001),
-	OID_U32(DOT11_OID_RECEIVEDTIMS, 0x14000002),
-	OID_U32(DOT11_OID_ROAMPREFERENCE, 0x14000003),
-
-	OID_U32(DOT11_OID_BRIDGELOCAL, 0x15000000),
-	OID_U32(DOT11_OID_CLIENTS, 0x15000001),
-	OID_U32(DOT11_OID_CLIENTSASSOCIATED, 0x15000002),
-	[DOT11_OID_CLIENTX] = {0x15000003, 2006, 0, 0},	/* DOT11_OID_CLIENTX,...DOT11_OID_CLIENT2007 */
-
-	OID_STRUCT(DOT11_OID_CLIENTFIND, 0x150007DB, u8[6], OID_TYPE_ADDR),
-	OID_STRUCT(DOT11_OID_WDSLINKADD, 0x150007DC, u8[6], OID_TYPE_ADDR),
-	OID_STRUCT(DOT11_OID_WDSLINKREMOVE, 0x150007DD, u8[6], OID_TYPE_ADDR),
-	OID_STRUCT(DOT11_OID_EAPAUTHSTA, 0x150007DE, u8[6], OID_TYPE_ADDR),
-	OID_STRUCT(DOT11_OID_EAPUNAUTHSTA, 0x150007DF, u8[6], OID_TYPE_ADDR),
-	OID_U32_C(DOT11_OID_DOT1XENABLE, 0x150007E0),
-	OID_UNKNOWN(DOT11_OID_MICFAILURE, 0x150007E1),
-	OID_UNKNOWN(DOT11_OID_REKEYINDICATE, 0x150007E2),
-
-	OID_U32(DOT11_OID_MPDUTXSUCCESSFUL, 0x16000000),
-	OID_U32(DOT11_OID_MPDUTXONERETRY, 0x16000001),
-	OID_U32(DOT11_OID_MPDUTXMULTIPLERETRIES, 0x16000002),
-	OID_U32(DOT11_OID_MPDUTXFAILED, 0x16000003),
-	OID_U32(DOT11_OID_MPDURXSUCCESSFUL, 0x16000004),
-	OID_U32(DOT11_OID_MPDURXDUPS, 0x16000005),
-	OID_U32(DOT11_OID_RTSSUCCESSFUL, 0x16000006),
-	OID_U32(DOT11_OID_RTSFAILED, 0x16000007),
-	OID_U32(DOT11_OID_ACKFAILED, 0x16000008),
-	OID_U32(DOT11_OID_FRAMERECEIVES, 0x16000009),
-	OID_U32(DOT11_OID_FRAMEERRORS, 0x1600000A),
-	OID_U32(DOT11_OID_FRAMEABORTS, 0x1600000B),
-	OID_U32(DOT11_OID_FRAMEABORTSPHY, 0x1600000C),
-
-	OID_U32(DOT11_OID_SLOTTIME, 0x17000000),
-	OID_U32(DOT11_OID_CWMIN, 0x17000001),
-	OID_U32(DOT11_OID_CWMAX, 0x17000002),
-	OID_U32(DOT11_OID_ACKWINDOW, 0x17000003),
-	OID_U32(DOT11_OID_ANTENNARX, 0x17000004),
-	OID_U32(DOT11_OID_ANTENNATX, 0x17000005),
-	OID_U32(DOT11_OID_ANTENNADIVERSITY, 0x17000006),
-	OID_U32_C(DOT11_OID_CHANNEL, 0x17000007),
-	OID_U32_C(DOT11_OID_EDTHRESHOLD, 0x17000008),
-	OID_U32(DOT11_OID_PREAMBLESETTINGS, 0x17000009),
-	OID_STRUCT(DOT11_OID_RATES, 0x1700000A, u8[IWMAX_BITRATES + 1],
-		   OID_TYPE_RAW),
-	OID_U32(DOT11_OID_CCAMODESUPPORTED, 0x1700000B),
-	OID_U32(DOT11_OID_CCAMODE, 0x1700000C),
-	OID_UNKNOWN(DOT11_OID_RSSIVECTOR, 0x1700000D),
-	OID_UNKNOWN(DOT11_OID_OUTPUTPOWERTABLE, 0x1700000E),
-	OID_U32(DOT11_OID_OUTPUTPOWER, 0x1700000F),
-	OID_STRUCT(DOT11_OID_SUPPORTEDRATES, 0x17000010,
-		   u8[IWMAX_BITRATES + 1], OID_TYPE_RAW),
-	OID_U32_C(DOT11_OID_FREQUENCY, 0x17000011),
-	[DOT11_OID_SUPPORTEDFREQUENCIES] =
-	    {0x17000012, 0, sizeof (struct obj_frequencies)
-	     + sizeof (u16) * IWMAX_FREQ, OID_TYPE_FREQUENCIES},
-
-	OID_U32(DOT11_OID_NOISEFLOOR, 0x17000013),
-	OID_STRUCT(DOT11_OID_FREQUENCYACTIVITY, 0x17000014, u8[IWMAX_FREQ + 1],
-		   OID_TYPE_RAW),
-	OID_UNKNOWN(DOT11_OID_IQCALIBRATIONTABLE, 0x17000015),
-	OID_U32(DOT11_OID_NONERPPROTECTION, 0x17000016),
-	OID_U32(DOT11_OID_SLOTSETTINGS, 0x17000017),
-	OID_U32(DOT11_OID_NONERPTIMEOUT, 0x17000018),
-	OID_U32(DOT11_OID_PROFILES, 0x17000019),
-	OID_STRUCT(DOT11_OID_EXTENDEDRATES, 0x17000020,
-		   u8[IWMAX_BITRATES + 1], OID_TYPE_RAW),
-
-	OID_STRUCT_MLME(DOT11_OID_DEAUTHENTICATE, 0x18000000),
-	OID_STRUCT_MLME(DOT11_OID_AUTHENTICATE, 0x18000001),
-	OID_STRUCT_MLME(DOT11_OID_DISASSOCIATE, 0x18000002),
-	OID_STRUCT_MLME(DOT11_OID_ASSOCIATE, 0x18000003),
-	OID_UNKNOWN(DOT11_OID_SCAN, 0x18000004),
-	OID_STRUCT_MLMEEX(DOT11_OID_BEACON, 0x18000005),
-	OID_STRUCT_MLMEEX(DOT11_OID_PROBE, 0x18000006),
-	OID_STRUCT_MLMEEX(DOT11_OID_DEAUTHENTICATEEX, 0x18000007),
-	OID_STRUCT_MLMEEX(DOT11_OID_AUTHENTICATEEX, 0x18000008),
-	OID_STRUCT_MLMEEX(DOT11_OID_DISASSOCIATEEX, 0x18000009),
-	OID_STRUCT_MLMEEX(DOT11_OID_ASSOCIATEEX, 0x1800000A),
-	OID_STRUCT_MLMEEX(DOT11_OID_REASSOCIATE, 0x1800000B),
-	OID_STRUCT_MLMEEX(DOT11_OID_REASSOCIATEEX, 0x1800000C),
-
-	OID_U32(DOT11_OID_NONERPSTATUS, 0x1E000000),
-
-	OID_U32(DOT11_OID_STATIMEOUT, 0x19000000),
-	OID_U32_C(DOT11_OID_MLMEAUTOLEVEL, 0x19000001),
-	OID_U32(DOT11_OID_BSSTIMEOUT, 0x19000002),
-	[DOT11_OID_ATTACHMENT] = {0x19000003, 0,
-		sizeof(struct obj_attachment), OID_TYPE_ATTACH},
-	OID_STRUCT_C(DOT11_OID_PSMBUFFER, 0x19000004, struct obj_buffer,
-		     OID_TYPE_BUFFER),
-
-	OID_U32(DOT11_OID_BSSS, 0x1C000000),
-	[DOT11_OID_BSSX] = {0x1C000001, 63, sizeof (struct obj_bss),
-			    OID_TYPE_BSS},	/*DOT11_OID_BSS1,...,DOT11_OID_BSS64 */
-	OID_STRUCT(DOT11_OID_BSSFIND, 0x1C000042, struct obj_bss, OID_TYPE_BSS),
-	[DOT11_OID_BSSLIST] = {0x1C000043, 0, sizeof (struct
-						      obj_bsslist) +
-			       sizeof (struct obj_bss[IWMAX_BSS]),
-			       OID_TYPE_BSSLIST},
-
-	OID_UNKNOWN(OID_INL_TUNNEL, 0xFF020000),
-	OID_UNKNOWN(OID_INL_MEMADDR, 0xFF020001),
-	OID_UNKNOWN(OID_INL_MEMORY, 0xFF020002),
-	OID_U32_C(OID_INL_MODE, 0xFF020003),
-	OID_UNKNOWN(OID_INL_COMPONENT_NR, 0xFF020004),
-	OID_STRUCT(OID_INL_VERSION, 0xFF020005, u8[8], OID_TYPE_RAW),
-	OID_UNKNOWN(OID_INL_INTERFACE_ID, 0xFF020006),
-	OID_UNKNOWN(OID_INL_COMPONENT_ID, 0xFF020007),
-	OID_U32_C(OID_INL_CONFIG, 0xFF020008),
-	OID_U32_C(OID_INL_DOT11D_CONFORMANCE, 0xFF02000C),
-	OID_U32(OID_INL_PHYCAPABILITIES, 0xFF02000D),
-	OID_U32_C(OID_INL_OUTPUTPOWER, 0xFF02000F),
-
-};
-
-int
-mgt_init(islpci_private *priv)
-{
-	int i;
-
-	priv->mib = kcalloc(OID_NUM_LAST, sizeof (void *), GFP_KERNEL);
-	if (!priv->mib)
-		return -ENOMEM;
-
-	/* Alloc the cache */
-	for (i = 0; i < OID_NUM_LAST; i++) {
-		if (isl_oid[i].flags & OID_FLAG_CACHED) {
-			priv->mib[i] = kcalloc(isl_oid[i].size,
-					       (isl_oid[i].range + 1),
-					       GFP_KERNEL);
-			if (!priv->mib[i])
-				return -ENOMEM;
-		} else
-			priv->mib[i] = NULL;
-	}
-
-	init_rwsem(&priv->mib_sem);
-	prism54_mib_init(priv);
-
-	return 0;
-}
-
-void
-mgt_clean(islpci_private *priv)
-{
-	int i;
-
-	if (!priv->mib)
-		return;
-	for (i = 0; i < OID_NUM_LAST; i++) {
-		kfree(priv->mib[i]);
-		priv->mib[i] = NULL;
-	}
-	kfree(priv->mib);
-	priv->mib = NULL;
-}
-
-void
-mgt_le_to_cpu(int type, void *data)
-{
-	switch (type) {
-	case OID_TYPE_U32:
-		*(u32 *) data = le32_to_cpu(*(u32 *) data);
-		break;
-	case OID_TYPE_BUFFER:{
-			struct obj_buffer *buff = data;
-			buff->size = le32_to_cpu(buff->size);
-			buff->addr = le32_to_cpu(buff->addr);
-			break;
-		}
-	case OID_TYPE_BSS:{
-			struct obj_bss *bss = data;
-			bss->age = le16_to_cpu(bss->age);
-			bss->channel = le16_to_cpu(bss->channel);
-			bss->capinfo = le16_to_cpu(bss->capinfo);
-			bss->rates = le16_to_cpu(bss->rates);
-			bss->basic_rates = le16_to_cpu(bss->basic_rates);
-			break;
-		}
-	case OID_TYPE_BSSLIST:{
-			struct obj_bsslist *list = data;
-			int i;
-			list->nr = le32_to_cpu(list->nr);
-			for (i = 0; i < list->nr; i++)
-				mgt_le_to_cpu(OID_TYPE_BSS, &list->bsslist[i]);
-			break;
-		}
-	case OID_TYPE_FREQUENCIES:{
-			struct obj_frequencies *freq = data;
-			int i;
-			freq->nr = le16_to_cpu(freq->nr);
-			for (i = 0; i < freq->nr; i++)
-				freq->mhz[i] = le16_to_cpu(freq->mhz[i]);
-			break;
-		}
-	case OID_TYPE_MLME:{
-			struct obj_mlme *mlme = data;
-			mlme->id = le16_to_cpu(mlme->id);
-			mlme->state = le16_to_cpu(mlme->state);
-			mlme->code = le16_to_cpu(mlme->code);
-			break;
-		}
-	case OID_TYPE_MLMEEX:{
-			struct obj_mlmeex *mlme = data;
-			mlme->id = le16_to_cpu(mlme->id);
-			mlme->state = le16_to_cpu(mlme->state);
-			mlme->code = le16_to_cpu(mlme->code);
-			mlme->size = le16_to_cpu(mlme->size);
-			break;
-		}
-	case OID_TYPE_ATTACH:{
-			struct obj_attachment *attach = data;
-			attach->id = le16_to_cpu(attach->id);
-			attach->size = le16_to_cpu(attach->size);
-			break;
-	}
-	case OID_TYPE_SSID:
-	case OID_TYPE_KEY:
-	case OID_TYPE_ADDR:
-	case OID_TYPE_RAW:
-		break;
-	default:
-		BUG();
-	}
-}
-
-static void
-mgt_cpu_to_le(int type, void *data)
-{
-	switch (type) {
-	case OID_TYPE_U32:
-		*(u32 *) data = cpu_to_le32(*(u32 *) data);
-		break;
-	case OID_TYPE_BUFFER:{
-			struct obj_buffer *buff = data;
-			buff->size = cpu_to_le32(buff->size);
-			buff->addr = cpu_to_le32(buff->addr);
-			break;
-		}
-	case OID_TYPE_BSS:{
-			struct obj_bss *bss = data;
-			bss->age = cpu_to_le16(bss->age);
-			bss->channel = cpu_to_le16(bss->channel);
-			bss->capinfo = cpu_to_le16(bss->capinfo);
-			bss->rates = cpu_to_le16(bss->rates);
-			bss->basic_rates = cpu_to_le16(bss->basic_rates);
-			break;
-		}
-	case OID_TYPE_BSSLIST:{
-			struct obj_bsslist *list = data;
-			int i;
-			list->nr = cpu_to_le32(list->nr);
-			for (i = 0; i < list->nr; i++)
-				mgt_cpu_to_le(OID_TYPE_BSS, &list->bsslist[i]);
-			break;
-		}
-	case OID_TYPE_FREQUENCIES:{
-			struct obj_frequencies *freq = data;
-			int i;
-			freq->nr = cpu_to_le16(freq->nr);
-			for (i = 0; i < freq->nr; i++)
-				freq->mhz[i] = cpu_to_le16(freq->mhz[i]);
-			break;
-		}
-	case OID_TYPE_MLME:{
-			struct obj_mlme *mlme = data;
-			mlme->id = cpu_to_le16(mlme->id);
-			mlme->state = cpu_to_le16(mlme->state);
-			mlme->code = cpu_to_le16(mlme->code);
-			break;
-		}
-	case OID_TYPE_MLMEEX:{
-			struct obj_mlmeex *mlme = data;
-			mlme->id = cpu_to_le16(mlme->id);
-			mlme->state = cpu_to_le16(mlme->state);
-			mlme->code = cpu_to_le16(mlme->code);
-			mlme->size = cpu_to_le16(mlme->size);
-			break;
-		}
-	case OID_TYPE_ATTACH:{
-			struct obj_attachment *attach = data;
-			attach->id = cpu_to_le16(attach->id);
-			attach->size = cpu_to_le16(attach->size);
-			break;
-	}
-	case OID_TYPE_SSID:
-	case OID_TYPE_KEY:
-	case OID_TYPE_ADDR:
-	case OID_TYPE_RAW:
-		break;
-	default:
-		BUG();
-	}
-}
-
-/* Note : data is modified during this function */
-
-int
-mgt_set_request(islpci_private *priv, enum oid_num_t n, int extra, void *data)
-{
-	int ret = 0;
-	struct islpci_mgmtframe *response = NULL;
-	int response_op = PIMFOR_OP_ERROR;
-	int dlen;
-	void *cache, *_data = data;
-	u32 oid;
-
-	BUG_ON(n >= OID_NUM_LAST);
-	BUG_ON(extra > isl_oid[n].range);
-
-	if (!priv->mib)
-		/* memory has been freed */
-		return -1;
-
-	dlen = isl_oid[n].size;
-	cache = priv->mib[n];
-	cache += (cache ? extra * dlen : 0);
-	oid = isl_oid[n].oid + extra;
-
-	if (_data == NULL)
-		/* we are requested to re-set a cached value */
-		_data = cache;
-	else
-		mgt_cpu_to_le(isl_oid[n].flags & OID_FLAG_TYPE, _data);
-	/* If we are going to write to the cache, we don't want anyone to read
-	 * it -> acquire write lock.
-	 * Else we could acquire a read lock to be sure we don't bother the
-	 * commit process (which takes a write lock). But I'm not sure if it's
-	 * needed.
-	 */
-	if (cache)
-		down_write(&priv->mib_sem);
-
-	if (islpci_get_state(priv) >= PRV_STATE_READY) {
-		ret = islpci_mgt_transaction(priv->ndev, PIMFOR_OP_SET, oid,
-					     _data, dlen, &response);
-		if (!ret) {
-			response_op = response->header->operation;
-			islpci_mgt_release(response);
-		}
-		if (ret || response_op == PIMFOR_OP_ERROR)
-			ret = -EIO;
-	} else if (!cache)
-		ret = -EIO;
-
-	if (cache) {
-		if (!ret && data)
-			memcpy(cache, _data, dlen);
-		up_write(&priv->mib_sem);
-	}
-
-	/* re-set given data to what it was */
-	if (data)
-		mgt_le_to_cpu(isl_oid[n].flags & OID_FLAG_TYPE, data);
-
-	return ret;
-}
-
-/* None of these are cached */
-int
-mgt_set_varlen(islpci_private *priv, enum oid_num_t n, void *data, int extra_len)
-{
-	int ret = 0;
-	struct islpci_mgmtframe *response;
-	int response_op = PIMFOR_OP_ERROR;
-	int dlen;
-	u32 oid;
-
-	BUG_ON(n >= OID_NUM_LAST);
-
-	dlen = isl_oid[n].size;
-	oid = isl_oid[n].oid;
-
-	mgt_cpu_to_le(isl_oid[n].flags & OID_FLAG_TYPE, data);
-
-	if (islpci_get_state(priv) >= PRV_STATE_READY) {
-		ret = islpci_mgt_transaction(priv->ndev, PIMFOR_OP_SET, oid,
-					     data, dlen + extra_len, &response);
-		if (!ret) {
-			response_op = response->header->operation;
-			islpci_mgt_release(response);
-		}
-		if (ret || response_op == PIMFOR_OP_ERROR)
-			ret = -EIO;
-	} else
-		ret = -EIO;
-
-	/* re-set given data to what it was */
-	if (data)
-		mgt_le_to_cpu(isl_oid[n].flags & OID_FLAG_TYPE, data);
-
-	return ret;
-}
-
-int
-mgt_get_request(islpci_private *priv, enum oid_num_t n, int extra, void *data,
-		union oid_res_t *res)
-{
-
-	int ret = -EIO;
-	int reslen = 0;
-	struct islpci_mgmtframe *response = NULL;
-
-	int dlen;
-	void *cache, *_res = NULL;
-	u32 oid;
-
-	BUG_ON(n >= OID_NUM_LAST);
-	BUG_ON(extra > isl_oid[n].range);
-
-	res->ptr = NULL;
-
-	if (!priv->mib)
-		/* memory has been freed */
-		return -1;
-
-	dlen = isl_oid[n].size;
-	cache = priv->mib[n];
-	cache += cache ? extra * dlen : 0;
-	oid = isl_oid[n].oid + extra;
-	reslen = dlen;
-
-	if (cache)
-		down_read(&priv->mib_sem);
-
-	if (islpci_get_state(priv) >= PRV_STATE_READY) {
-		ret = islpci_mgt_transaction(priv->ndev, PIMFOR_OP_GET,
-					     oid, data, dlen, &response);
-		if (ret || !response ||
-		    response->header->operation == PIMFOR_OP_ERROR) {
-			if (response)
-				islpci_mgt_release(response);
-			ret = -EIO;
-		}
-		if (!ret) {
-			_res = response->data;
-			reslen = response->header->length;
-		}
-	} else if (cache) {
-		_res = cache;
-		ret = 0;
-	}
-	if ((isl_oid[n].flags & OID_FLAG_TYPE) == OID_TYPE_U32)
-		res->u = ret ? 0 : le32_to_cpu(*(u32 *) _res);
-	else {
-		res->ptr = kmalloc(reslen, GFP_KERNEL);
-		BUG_ON(res->ptr == NULL);
-		if (ret)
-			memset(res->ptr, 0, reslen);
-		else {
-			memcpy(res->ptr, _res, reslen);
-			mgt_le_to_cpu(isl_oid[n].flags & OID_FLAG_TYPE,
-				      res->ptr);
-		}
-	}
-	if (cache)
-		up_read(&priv->mib_sem);
-
-	if (response && !ret)
-		islpci_mgt_release(response);
-
-	if (reslen > isl_oid[n].size)
-		printk(KERN_DEBUG
-		       "mgt_get_request(0x%x): received data length was bigger "
-		       "than expected (%d > %d). Memory is probably corrupted...",
-		       oid, reslen, isl_oid[n].size);
-
-	return ret;
-}
-
-/* lock outside */
-int
-mgt_commit_list(islpci_private *priv, enum oid_num_t *l, int n)
-{
-	int i, ret = 0;
-	struct islpci_mgmtframe *response;
-
-	for (i = 0; i < n; i++) {
-		struct oid_t *t = &(isl_oid[l[i]]);
-		void *data = priv->mib[l[i]];
-		int j = 0;
-		u32 oid = t->oid;
-		BUG_ON(data == NULL);
-		while (j <= t->range) {
-			int r = islpci_mgt_transaction(priv->ndev, PIMFOR_OP_SET,
-						      oid, data, t->size,
-						      &response);
-			if (response) {
-				r |= (response->header->operation == PIMFOR_OP_ERROR);
-				islpci_mgt_release(response);
-			}
-			if (r)
-				printk(KERN_ERR "%s: mgt_commit_list: failure. "
-					"oid=%08x err=%d\n",
-					priv->ndev->name, oid, r);
-			ret |= r;
-			j++;
-			oid++;
-			data += t->size;
-		}
-	}
-	return ret;
-}
-
-/* Lock outside */
-
-void
-mgt_set(islpci_private *priv, enum oid_num_t n, void *data)
-{
-	BUG_ON(n >= OID_NUM_LAST);
-	BUG_ON(priv->mib[n] == NULL);
-
-	memcpy(priv->mib[n], data, isl_oid[n].size);
-	mgt_cpu_to_le(isl_oid[n].flags & OID_FLAG_TYPE, priv->mib[n]);
-}
-
-void
-mgt_get(islpci_private *priv, enum oid_num_t n, void *res)
-{
-	BUG_ON(n >= OID_NUM_LAST);
-	BUG_ON(priv->mib[n] == NULL);
-	BUG_ON(res == NULL);
-
-	memcpy(res, priv->mib[n], isl_oid[n].size);
-	mgt_le_to_cpu(isl_oid[n].flags & OID_FLAG_TYPE, res);
-}
-
-/* Commits the cache. Lock outside. */
-
-static enum oid_num_t commit_part1[] = {
-	OID_INL_CONFIG,
-	OID_INL_MODE,
-	DOT11_OID_BSSTYPE,
-	DOT11_OID_CHANNEL,
-	DOT11_OID_MLMEAUTOLEVEL
-};
-
-static enum oid_num_t commit_part2[] = {
-	DOT11_OID_SSID,
-	DOT11_OID_PSMBUFFER,
-	DOT11_OID_AUTHENABLE,
-	DOT11_OID_PRIVACYINVOKED,
-	DOT11_OID_EXUNENCRYPTED,
-	DOT11_OID_DEFKEYX,	/* MULTIPLE */
-	DOT11_OID_DEFKEYID,
-	DOT11_OID_DOT1XENABLE,
-	OID_INL_DOT11D_CONFORMANCE,
-	/* Do not initialize this - fw < 1.0.4.3 rejects it
-	OID_INL_OUTPUTPOWER,
-	*/
-};
-
-/* update the MAC addr. */
-static int
-mgt_update_addr(islpci_private *priv)
-{
-	struct islpci_mgmtframe *res;
-	int ret;
-
-	ret = islpci_mgt_transaction(priv->ndev, PIMFOR_OP_GET,
-				     isl_oid[GEN_OID_MACADDRESS].oid, NULL,
-				     isl_oid[GEN_OID_MACADDRESS].size, &res);
-
-	if ((ret == 0) && res && (res->header->operation != PIMFOR_OP_ERROR))
-		memcpy(priv->ndev->dev_addr, res->data, ETH_ALEN);
-	else
-		ret = -EIO;
-	if (res)
-		islpci_mgt_release(res);
-
-	if (ret)
-		printk(KERN_ERR "%s: mgt_update_addr: failure\n", priv->ndev->name);
-	return ret;
-}
-
-int
-mgt_commit(islpci_private *priv)
-{
-	int rvalue;
-	enum oid_num_t u;
-
-	if (islpci_get_state(priv) < PRV_STATE_INIT)
-		return 0;
-
-	rvalue = mgt_commit_list(priv, commit_part1, ARRAY_SIZE(commit_part1));
-
-	if (priv->iw_mode != IW_MODE_MONITOR)
-		rvalue |= mgt_commit_list(priv, commit_part2, ARRAY_SIZE(commit_part2));
-
-	u = OID_INL_MODE;
-	rvalue |= mgt_commit_list(priv, &u, 1);
-	rvalue |= mgt_update_addr(priv);
-
-	if (rvalue) {
-		/* some request have failed. The device might be in an
-		   incoherent state. We should reset it ! */
-		printk(KERN_DEBUG "%s: mgt_commit: failure\n", priv->ndev->name);
-	}
-	return rvalue;
-}
-
-/* The following OIDs need to be "unlatched":
- *
- * MEDIUMLIMIT,BEACONPERIOD,DTIMPERIOD,ATIMWINDOW,LISTENINTERVAL
- * FREQUENCY,EXTENDEDRATES.
- *
- * The way to do this is to set ESSID. Note though that they may get
- * unlatch before though by setting another OID. */
-#if 0
-void
-mgt_unlatch_all(islpci_private *priv)
-{
-	u32 u;
-	int rvalue = 0;
-
-	if (islpci_get_state(priv) < PRV_STATE_INIT)
-		return;
-
-	u = DOT11_OID_SSID;
-	rvalue = mgt_commit_list(priv, &u, 1);
-	/* Necessary if in MANUAL RUN mode? */
-#if 0
-	u = OID_INL_MODE;
-	rvalue |= mgt_commit_list(priv, &u, 1);
-
-	u = DOT11_OID_MLMEAUTOLEVEL;
-	rvalue |= mgt_commit_list(priv, &u, 1);
-
-	u = OID_INL_MODE;
-	rvalue |= mgt_commit_list(priv, &u, 1);
-#endif
-
-	if (rvalue)
-		printk(KERN_DEBUG "%s: Unlatching OIDs failed\n", priv->ndev->name);
-}
-#endif
-
-/* This will tell you if you are allowed to answer a mlme(ex) request .*/
-
-int
-mgt_mlme_answer(islpci_private *priv)
-{
-	u32 mlmeautolevel;
-	/* Acquire a read lock because if we are in a mode change, it's
-	 * possible to answer true, while the card is leaving master to managed
-	 * mode. Answering to a mlme in this situation could hang the card.
-	 */
-	down_read(&priv->mib_sem);
-	mlmeautolevel =
-	    le32_to_cpu(*(u32 *) priv->mib[DOT11_OID_MLMEAUTOLEVEL]);
-	up_read(&priv->mib_sem);
-
-	return ((priv->iw_mode == IW_MODE_MASTER) &&
-		(mlmeautolevel >= DOT11_MLME_INTERMEDIATE));
-}
-
-enum oid_num_t
-mgt_oidtonum(u32 oid)
-{
-	int i;
-
-	for (i = 0; i < OID_NUM_LAST; i++)
-		if (isl_oid[i].oid == oid)
-			return i;
-
-	printk(KERN_DEBUG "looking for an unknown oid 0x%x", oid);
-
-	return OID_NUM_LAST;
-}
-
-int
-mgt_response_to_str(enum oid_num_t n, union oid_res_t *r, char *str)
-{
-	switch (isl_oid[n].flags & OID_FLAG_TYPE) {
-	case OID_TYPE_U32:
-		return scnprintf(str, PRIV_STR_SIZE, "%u\n", r->u);
-	case OID_TYPE_BUFFER:{
-			struct obj_buffer *buff = r->ptr;
-			return scnprintf(str, PRIV_STR_SIZE,
-					"size=%u\naddr=0x%X\n", buff->size,
-					buff->addr);
-		}
-		break;
-	case OID_TYPE_BSS:{
-			struct obj_bss *bss = r->ptr;
-			return scnprintf(str, PRIV_STR_SIZE,
-					"age=%u\nchannel=%u\n"
-					"capinfo=0x%X\nrates=0x%X\n"
-					"basic_rates=0x%X\n", bss->age,
-					bss->channel, bss->capinfo,
-					bss->rates, bss->basic_rates);
-		}
-		break;
-	case OID_TYPE_BSSLIST:{
-			struct obj_bsslist *list = r->ptr;
-			int i, k;
-			k = scnprintf(str, PRIV_STR_SIZE, "nr=%u\n", list->nr);
-			for (i = 0; i < list->nr; i++)
-				k += scnprintf(str + k, PRIV_STR_SIZE - k,
-					      "bss[%u] :\nage=%u\nchannel=%u\n"
-					      "capinfo=0x%X\nrates=0x%X\n"
-					      "basic_rates=0x%X\n",
-					      i, list->bsslist[i].age,
-					      list->bsslist[i].channel,
-					      list->bsslist[i].capinfo,
-					      list->bsslist[i].rates,
-					      list->bsslist[i].basic_rates);
-			return k;
-		}
-		break;
-	case OID_TYPE_FREQUENCIES:{
-			struct obj_frequencies *freq = r->ptr;
-			int i, t;
-			printk("nr : %u\n", freq->nr);
-			t = scnprintf(str, PRIV_STR_SIZE, "nr=%u\n", freq->nr);
-			for (i = 0; i < freq->nr; i++)
-				t += scnprintf(str + t, PRIV_STR_SIZE - t,
-					      "mhz[%u]=%u\n", i, freq->mhz[i]);
-			return t;
-		}
-		break;
-	case OID_TYPE_MLME:{
-			struct obj_mlme *mlme = r->ptr;
-			return scnprintf(str, PRIV_STR_SIZE,
-					"id=0x%X\nstate=0x%X\ncode=0x%X\n",
-					mlme->id, mlme->state, mlme->code);
-		}
-		break;
-	case OID_TYPE_MLMEEX:{
-			struct obj_mlmeex *mlme = r->ptr;
-			return scnprintf(str, PRIV_STR_SIZE,
-					"id=0x%X\nstate=0x%X\n"
-					"code=0x%X\nsize=0x%X\n", mlme->id,
-					mlme->state, mlme->code, mlme->size);
-		}
-		break;
-	case OID_TYPE_ATTACH:{
-			struct obj_attachment *attach = r->ptr;
-			return scnprintf(str, PRIV_STR_SIZE,
-					"id=%d\nsize=%d\n",
-					attach->id,
-					attach->size);
-		}
-		break;
-	case OID_TYPE_SSID:{
-			struct obj_ssid *ssid = r->ptr;
-			return scnprintf(str, PRIV_STR_SIZE,
-					"length=%u\noctets=%.*s\n",
-					ssid->length, ssid->length,
-					ssid->octets);
-		}
-		break;
-	case OID_TYPE_KEY:{
-			struct obj_key *key = r->ptr;
-			int t, i;
-			t = scnprintf(str, PRIV_STR_SIZE,
-				     "type=0x%X\nlength=0x%X\nkey=0x",
-				     key->type, key->length);
-			for (i = 0; i < key->length; i++)
-				t += scnprintf(str + t, PRIV_STR_SIZE - t,
-					      "%02X:", key->key[i]);
-			t += scnprintf(str + t, PRIV_STR_SIZE - t, "\n");
-			return t;
-		}
-		break;
-	case OID_TYPE_RAW:
-	case OID_TYPE_ADDR:{
-			unsigned char *buff = r->ptr;
-			int t, i;
-			t = scnprintf(str, PRIV_STR_SIZE, "hex data=");
-			for (i = 0; i < isl_oid[n].size; i++)
-				t += scnprintf(str + t, PRIV_STR_SIZE - t,
-					      "%02X:", buff[i]);
-			t += scnprintf(str + t, PRIV_STR_SIZE - t, "\n");
-			return t;
-		}
-		break;
-	default:
-		BUG();
-	}
-	return 0;
-}
diff --git a/drivers/net/wireless/intersil/prism54/oid_mgt.h b/drivers/net/wireless/intersil/prism54/oid_mgt.h
deleted file mode 100644
index a7dc9e24c0bf..000000000000
--- a/drivers/net/wireless/intersil/prism54/oid_mgt.h
+++ /dev/null
@@ -1,46 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  Copyright (C) 2003 Aurelien Alleaume <slts@free.fr>
- */
-
-#if !defined(_OID_MGT_H)
-#define _OID_MGT_H
-
-#include "isl_oid.h"
-#include "islpci_dev.h"
-
-extern struct oid_t isl_oid[];
-
-int mgt_init(islpci_private *);
-
-void mgt_clean(islpci_private *);
-
-/* I don't know where to put these 2 */
-extern const int frequency_list_a[];
-int channel_of_freq(int);
-
-void mgt_le_to_cpu(int, void *);
-
-int mgt_set_request(islpci_private *, enum oid_num_t, int, void *);
-int mgt_set_varlen(islpci_private *, enum oid_num_t, void *, int);
-
-
-int mgt_get_request(islpci_private *, enum oid_num_t, int, void *,
-		    union oid_res_t *);
-
-int mgt_commit_list(islpci_private *, enum oid_num_t *, int);
-
-void mgt_set(islpci_private *, enum oid_num_t, void *);
-
-void mgt_get(islpci_private *, enum oid_num_t, void *);
-
-int mgt_commit(islpci_private *);
-
-int mgt_mlme_answer(islpci_private *);
-
-enum oid_num_t mgt_oidtonum(u32 oid);
-
-int mgt_response_to_str(enum oid_num_t, union oid_res_t *, char *);
-
-#endif				/* !defined(_OID_MGT_H) */
-/* EOF */
diff --git a/drivers/net/wireless/intersil/prism54/prismcompat.h b/drivers/net/wireless/intersil/prism54/prismcompat.h
deleted file mode 100644
index c4489b66d07e..000000000000
--- a/drivers/net/wireless/intersil/prism54/prismcompat.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  (C) 2004 Margit Schubert-While <margitsw@t-online.de>
- */
-
-/*
- *	Compatibility header file to aid support of different kernel versions
- */
-
-#ifdef PRISM54_COMPAT24
-#include "prismcompat24.h"
-#else	/* PRISM54_COMPAT24 */
-
-#ifndef _PRISM_COMPAT_H
-#define _PRISM_COMPAT_H
-
-#include <linux/device.h>
-#include <linux/firmware.h>
-#include <linux/moduleparam.h>
-#include <linux/workqueue.h>
-#include <linux/compiler.h>
-
-#ifndef __iomem
-#define __iomem
-#endif
-
-#define PRISM_FW_PDEV		&priv->pdev->dev
-
-#endif				/* _PRISM_COMPAT_H */
-#endif				/* PRISM54_COMPAT24 */
diff --git a/drivers/net/wireless/marvell/libertas/ethtool.c b/drivers/net/wireless/marvell/libertas/ethtool.c
index 1bb8746a0b23..d8e4f29b690d 100644
--- a/drivers/net/wireless/marvell/libertas/ethtool.c
+++ b/drivers/net/wireless/marvell/libertas/ethtool.c
@@ -43,10 +43,8 @@ static int lbs_ethtool_get_eeprom(struct net_device *dev,
 	int ret;
 
 	if (eeprom->offset + eeprom->len > LBS_EEPROM_LEN ||
-	    eeprom->len > LBS_EEPROM_READ_LEN) {
-		ret = -EINVAL;
-		goto out;
-	}
+	    eeprom->len > LBS_EEPROM_READ_LEN)
+		return -EINVAL;
 
 	cmd.hdr.size = cpu_to_le16(sizeof(struct cmd_ds_802_11_eeprom_access) -
 		LBS_EEPROM_READ_LEN + eeprom->len);
@@ -57,8 +55,7 @@ static int lbs_ethtool_get_eeprom(struct net_device *dev,
 	if (!ret)
 		memcpy(bytes, cmd.value, eeprom->len);
 
-out:
-        return ret;
+	return ret;
 }
 
 static void lbs_ethtool_get_wol(struct net_device *dev,
diff --git a/drivers/net/wireless/marvell/mwifiex/Makefile b/drivers/net/wireless/marvell/mwifiex/Makefile
index 162d557b78af..2bd00f40958e 100644
--- a/drivers/net/wireless/marvell/mwifiex/Makefile
+++ b/drivers/net/wireless/marvell/mwifiex/Makefile
@@ -49,6 +49,7 @@ mwifiex_sdio-y += sdio.o
 obj-$(CONFIG_MWIFIEX_SDIO) += mwifiex_sdio.o
 
 mwifiex_pcie-y += pcie.o
+mwifiex_pcie-y += pcie_quirks.o
 obj-$(CONFIG_MWIFIEX_PCIE) += mwifiex_pcie.o
 
 mwifiex_usb-y += usb.o
diff --git a/drivers/net/wireless/marvell/mwifiex/cmdevt.c b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
index 3a11342a6bde..171a25742600 100644
--- a/drivers/net/wireless/marvell/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
@@ -187,7 +187,7 @@ static int mwifiex_dnld_cmd_to_fw(struct mwifiex_private *priv,
 	host_cmd = (struct host_cmd_ds_command *) (cmd_node->cmd_skb->data);
 
 	/* Sanity test */
-	if (host_cmd == NULL || host_cmd->size == 0) {
+	if (host_cmd->size == 0) {
 		mwifiex_dbg(adapter, ERROR,
 			    "DNLD_CMD: host_cmd is null\t"
 			    "or cmd size is 0, not sending\n");
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c
index 46517515ba72..c6ccce426b49 100644
--- a/drivers/net/wireless/marvell/mwifiex/pcie.c
+++ b/drivers/net/wireless/marvell/mwifiex/pcie.c
@@ -27,6 +27,7 @@
 #include "wmm.h"
 #include "11n.h"
 #include "pcie.h"
+#include "pcie_quirks.h"
 
 #define PCIE_VERSION	"1.0"
 #define DRV_NAME        "Marvell mwifiex PCIe"
@@ -410,6 +411,9 @@ static int mwifiex_pcie_probe(struct pci_dev *pdev,
 			return ret;
 	}
 
+	/* check quirks */
+	mwifiex_initialize_quirks(card);
+
 	if (mwifiex_add_card(card, &card->fw_done, &pcie_ops,
 			     MWIFIEX_PCIE, &pdev->dev)) {
 		pr_err("%s failed\n", __func__);
@@ -524,6 +528,13 @@ static void mwifiex_pcie_reset_prepare(struct pci_dev *pdev)
 	mwifiex_shutdown_sw(adapter);
 	clear_bit(MWIFIEX_IFACE_WORK_DEVICE_DUMP, &card->work_flags);
 	clear_bit(MWIFIEX_IFACE_WORK_CARD_RESET, &card->work_flags);
+
+	/* On MS Surface gen4+ devices FLR isn't effective to recover from
+	 * hangups, so we power-cycle the card instead.
+	 */
+	if (card->quirks & QUIRK_FW_RST_D3COLD)
+		mwifiex_pcie_reset_d3cold_quirk(pdev);
+
 	mwifiex_dbg(adapter, INFO, "%s, successful\n", __func__);
 
 	card->pci_reset_ongoing = true;
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.h b/drivers/net/wireless/marvell/mwifiex/pcie.h
index 5ed613d65709..981e330c77d7 100644
--- a/drivers/net/wireless/marvell/mwifiex/pcie.h
+++ b/drivers/net/wireless/marvell/mwifiex/pcie.h
@@ -244,6 +244,7 @@ struct pcie_service_card {
 	unsigned long work_flags;
 
 	bool pci_reset_ongoing;
+	unsigned long quirks;
 };
 
 static inline int
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie_quirks.c b/drivers/net/wireless/marvell/mwifiex/pcie_quirks.c
new file mode 100644
index 000000000000..0234cf3c2974
--- /dev/null
+++ b/drivers/net/wireless/marvell/mwifiex/pcie_quirks.c
@@ -0,0 +1,161 @@
+/*
+ * NXP Wireless LAN device driver: PCIE and platform specific quirks
+ *
+ * This software file (the "File") is distributed by NXP
+ * under the terms of the GNU General Public License Version 2, June 1991
+ * (the "License").  You may use, redistribute and/or modify this File in
+ * accordance with the terms and conditions of the License, a copy of which
+ * is available by writing to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA or on the
+ * worldwide web at http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt.
+ *
+ * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE
+ * ARE EXPRESSLY DISCLAIMED.  The License provides additional details about
+ * this warranty disclaimer.
+ */
+
+#include <linux/dmi.h>
+
+#include "pcie_quirks.h"
+
+/* quirk table based on DMI matching */
+static const struct dmi_system_id mwifiex_quirk_table[] = {
+	{
+		.ident = "Surface Pro 4",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Surface Pro 4"),
+		},
+		.driver_data = (void *)QUIRK_FW_RST_D3COLD,
+	},
+	{
+		.ident = "Surface Pro 5",
+		.matches = {
+			/* match for SKU here due to generic product name "Surface Pro" */
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "Surface_Pro_1796"),
+		},
+		.driver_data = (void *)QUIRK_FW_RST_D3COLD,
+	},
+	{
+		.ident = "Surface Pro 5 (LTE)",
+		.matches = {
+			/* match for SKU here due to generic product name "Surface Pro" */
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "Surface_Pro_1807"),
+		},
+		.driver_data = (void *)QUIRK_FW_RST_D3COLD,
+	},
+	{
+		.ident = "Surface Pro 6",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Surface Pro 6"),
+		},
+		.driver_data = (void *)QUIRK_FW_RST_D3COLD,
+	},
+	{
+		.ident = "Surface Book 1",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Surface Book"),
+		},
+		.driver_data = (void *)QUIRK_FW_RST_D3COLD,
+	},
+	{
+		.ident = "Surface Book 2",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Surface Book 2"),
+		},
+		.driver_data = (void *)QUIRK_FW_RST_D3COLD,
+	},
+	{
+		.ident = "Surface Laptop 1",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Surface Laptop"),
+		},
+		.driver_data = (void *)QUIRK_FW_RST_D3COLD,
+	},
+	{
+		.ident = "Surface Laptop 2",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Surface Laptop 2"),
+		},
+		.driver_data = (void *)QUIRK_FW_RST_D3COLD,
+	},
+	{}
+};
+
+void mwifiex_initialize_quirks(struct pcie_service_card *card)
+{
+	struct pci_dev *pdev = card->dev;
+	const struct dmi_system_id *dmi_id;
+
+	dmi_id = dmi_first_match(mwifiex_quirk_table);
+	if (dmi_id)
+		card->quirks = (uintptr_t)dmi_id->driver_data;
+
+	if (!card->quirks)
+		dev_info(&pdev->dev, "no quirks enabled\n");
+	if (card->quirks & QUIRK_FW_RST_D3COLD)
+		dev_info(&pdev->dev, "quirk reset_d3cold enabled\n");
+}
+
+static void mwifiex_pcie_set_power_d3cold(struct pci_dev *pdev)
+{
+	dev_info(&pdev->dev, "putting into D3cold...\n");
+
+	pci_save_state(pdev);
+	if (pci_is_enabled(pdev))
+		pci_disable_device(pdev);
+	pci_set_power_state(pdev, PCI_D3cold);
+}
+
+static int mwifiex_pcie_set_power_d0(struct pci_dev *pdev)
+{
+	int ret;
+
+	dev_info(&pdev->dev, "putting into D0...\n");
+
+	pci_set_power_state(pdev, PCI_D0);
+	ret = pci_enable_device(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "pci_enable_device failed\n");
+		return ret;
+	}
+	pci_restore_state(pdev);
+
+	return 0;
+}
+
+int mwifiex_pcie_reset_d3cold_quirk(struct pci_dev *pdev)
+{
+	struct pci_dev *parent_pdev = pci_upstream_bridge(pdev);
+	int ret;
+
+	/* Power-cycle (put into D3cold then D0) */
+	dev_info(&pdev->dev, "Using reset_d3cold quirk to perform FW reset\n");
+
+	/* We need to perform power-cycle also for bridge of wifi because
+	 * on some devices (e.g. Surface Book 1), the OS for some reasons
+	 * can't know the real power state of the bridge.
+	 * When tried to power-cycle only wifi, the reset failed with the
+	 * following dmesg log:
+	 * "Cannot transition to power state D0 for parent in D3hot".
+	 */
+	mwifiex_pcie_set_power_d3cold(pdev);
+	mwifiex_pcie_set_power_d3cold(parent_pdev);
+
+	ret = mwifiex_pcie_set_power_d0(parent_pdev);
+	if (ret)
+		return ret;
+	ret = mwifiex_pcie_set_power_d0(pdev);
+	if (ret)
+		return ret;
+
+	return 0;
+}
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie_quirks.h b/drivers/net/wireless/marvell/mwifiex/pcie_quirks.h
new file mode 100644
index 000000000000..8ec4176d698f
--- /dev/null
+++ b/drivers/net/wireless/marvell/mwifiex/pcie_quirks.h
@@ -0,0 +1,23 @@
+/*
+ * NXP Wireless LAN device driver: PCIE and platform specific quirks
+ *
+ * This software file (the "File") is distributed by NXP
+ * under the terms of the GNU General Public License Version 2, June 1991
+ * (the "License").  You may use, redistribute and/or modify this File in
+ * accordance with the terms and conditions of the License, a copy of which
+ * is available by writing to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA or on the
+ * worldwide web at http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt.
+ *
+ * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE
+ * ARE EXPRESSLY DISCLAIMED.  The License provides additional details about
+ * this warranty disclaimer.
+ */
+
+#include "pcie.h"
+
+#define QUIRK_FW_RST_D3COLD	BIT(0)
+
+void mwifiex_initialize_quirks(struct pcie_service_card *card);
+int mwifiex_pcie_reset_d3cold_quirk(struct pci_dev *pdev);
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
index 653f9e094256..4062e515697a 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
@@ -1325,8 +1325,8 @@ mwifiex_set_gen_ie_helper(struct mwifiex_private *priv, u8 *ie_data_ptr,
 			  u16 ie_len)
 {
 	struct ieee_types_vendor_header *pvendor_ie;
-	const u8 wpa_oui[] = { 0x00, 0x50, 0xf2, 0x01 };
-	const u8 wps_oui[] = { 0x00, 0x50, 0xf2, 0x04 };
+	static const u8 wpa_oui[] = { 0x00, 0x50, 0xf2, 0x01 };
+	static const u8 wps_oui[] = { 0x00, 0x50, 0xf2, 0x04 };
 	u16 unparsed_len = ie_len, cur_ie_len;
 
 	/* If the passed length is zero, reset the buffer */
diff --git a/drivers/net/wireless/marvell/mwifiex/usb.h b/drivers/net/wireless/marvell/mwifiex/usb.h
index d822ec15b7e6..61a96b7fbf21 100644
--- a/drivers/net/wireless/marvell/mwifiex/usb.h
+++ b/drivers/net/wireless/marvell/mwifiex/usb.h
@@ -134,7 +134,7 @@ struct fw_sync_header {
 struct fw_data {
 	struct fw_header fw_hdr;
 	__le32 seq_num;
-	u8 data[1];
+	u8 data[];
 } __packed;
 
 #endif /*_MWIFIEX_USB_H */
diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index e14b9fc2c67a..42e03a701ae1 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -129,10 +129,8 @@ static int wilc_sdio_probe(struct sdio_func *func,
 
 	ret = wilc_cfg80211_init(&wilc, &func->dev, WILC_HIF_SDIO,
 				 &wilc_hif_sdio);
-	if (ret) {
-		kfree(sdio_priv);
-		return ret;
-	}
+	if (ret)
+		goto free;
 
 	if (IS_ENABLED(CONFIG_WILC1000_HW_OOB_INTR)) {
 		struct device_node *np = func->card->dev.of_node;
@@ -148,24 +146,29 @@ static int wilc_sdio_probe(struct sdio_func *func,
 	wilc->bus_data = sdio_priv;
 	wilc->dev = &func->dev;
 
-	wilc->rtc_clk = devm_clk_get(&func->card->dev, "rtc");
-	if (PTR_ERR_OR_ZERO(wilc->rtc_clk) == -EPROBE_DEFER) {
-		kfree(sdio_priv);
-		return -EPROBE_DEFER;
-	} else if (!IS_ERR(wilc->rtc_clk))
-		clk_prepare_enable(wilc->rtc_clk);
+	wilc->rtc_clk = devm_clk_get_optional(&func->card->dev, "rtc");
+	if (IS_ERR(wilc->rtc_clk)) {
+		ret = PTR_ERR(wilc->rtc_clk);
+		goto dispose_irq;
+	}
+	clk_prepare_enable(wilc->rtc_clk);
 
 	dev_info(&func->dev, "Driver Initializing success\n");
 	return 0;
+
+dispose_irq:
+	irq_dispose_mapping(wilc->dev_irq_num);
+	wilc_netdev_cleanup(wilc);
+free:
+	kfree(sdio_priv);
+	return ret;
 }
 
 static void wilc_sdio_remove(struct sdio_func *func)
 {
 	struct wilc *wilc = sdio_get_drvdata(func);
 
-	if (!IS_ERR(wilc->rtc_clk))
-		clk_disable_unprepare(wilc->rtc_clk);
-
+	clk_disable_unprepare(wilc->rtc_clk);
 	wilc_netdev_cleanup(wilc);
 }
 
diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c
index 8e9aaf03a6fa..dd481dc0b5ce 100644
--- a/drivers/net/wireless/microchip/wilc1000/spi.c
+++ b/drivers/net/wireless/microchip/wilc1000/spi.c
@@ -39,6 +39,7 @@ MODULE_PARM_DESC(enable_crc16,
 #define WILC_SPI_RSP_HDR_EXTRA_DATA	8
 
 struct wilc_spi {
+	bool isinit;		/* true if SPI protocol has been configured */
 	bool probing_crc;	/* true if we're probing chip's CRC config */
 	bool crc7_enabled;	/* true if crc7 is currently enabled */
 	bool crc16_enabled;	/* true if crc16 is currently enabled */
@@ -154,34 +155,37 @@ static int wilc_bus_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	ret = wilc_cfg80211_init(&wilc, &spi->dev, WILC_HIF_SPI, &wilc_hif_spi);
-	if (ret) {
-		kfree(spi_priv);
-		return ret;
-	}
+	if (ret)
+		goto free;
 
 	spi_set_drvdata(spi, wilc);
 	wilc->dev = &spi->dev;
 	wilc->bus_data = spi_priv;
 	wilc->dev_irq_num = spi->irq;
 
-	wilc->rtc_clk = devm_clk_get(&spi->dev, "rtc");
-	if (PTR_ERR_OR_ZERO(wilc->rtc_clk) == -EPROBE_DEFER) {
-		kfree(spi_priv);
-		return -EPROBE_DEFER;
-	} else if (!IS_ERR(wilc->rtc_clk))
-		clk_prepare_enable(wilc->rtc_clk);
+	wilc->rtc_clk = devm_clk_get_optional(&spi->dev, "rtc");
+	if (IS_ERR(wilc->rtc_clk)) {
+		ret = PTR_ERR(wilc->rtc_clk);
+		goto netdev_cleanup;
+	}
+	clk_prepare_enable(wilc->rtc_clk);
 
 	return 0;
+
+netdev_cleanup:
+	wilc_netdev_cleanup(wilc);
+free:
+	kfree(spi_priv);
+	return ret;
 }
 
 static int wilc_bus_remove(struct spi_device *spi)
 {
 	struct wilc *wilc = spi_get_drvdata(spi);
 
-	if (!IS_ERR(wilc->rtc_clk))
-		clk_disable_unprepare(wilc->rtc_clk);
-
+	clk_disable_unprepare(wilc->rtc_clk);
 	wilc_netdev_cleanup(wilc);
+
 	return 0;
 }
 
@@ -905,15 +909,15 @@ static int wilc_spi_init(struct wilc *wilc, bool resume)
 	struct wilc_spi *spi_priv = wilc->bus_data;
 	u32 reg;
 	u32 chipid;
-	static int isinit;
 	int ret, i;
 
-	if (isinit) {
+	if (spi_priv->isinit) {
+		/* Confirm we can read chipid register without error: */
 		ret = wilc_spi_read_reg(wilc, WILC_CHIPID, &chipid);
-		if (ret)
-			dev_err(&spi->dev, "Fail cmd read chip id...\n");
+		if (ret == 0)
+			return 0;
 
-		return ret;
+		dev_err(&spi->dev, "Fail cmd read chip id...\n");
 	}
 
 	/*
@@ -971,7 +975,7 @@ static int wilc_spi_init(struct wilc *wilc, bool resume)
 	spi_priv->probing_crc = false;
 
 	/*
-	 * make sure can read back chip id correctly
+	 * make sure can read chip id without protocol error
 	 */
 	ret = wilc_spi_read_reg(wilc, WILC_CHIPID, &chipid);
 	if (ret) {
@@ -979,7 +983,7 @@ static int wilc_spi_init(struct wilc *wilc, bool resume)
 		return ret;
 	}
 
-	isinit = 1;
+	spi_priv->isinit = true;
 
 	return 0;
 }
diff --git a/drivers/net/wireless/microchip/wilc1000/wlan.c b/drivers/net/wireless/microchip/wilc1000/wlan.c
index 2030fc7f53ca..200a103a0a85 100644
--- a/drivers/net/wireless/microchip/wilc1000/wlan.c
+++ b/drivers/net/wireless/microchip/wilc1000/wlan.c
@@ -1127,27 +1127,22 @@ int wilc_wlan_start(struct wilc *wilc)
 	}
 	acquire_bus(wilc, WILC_BUS_ACQUIRE_ONLY);
 	ret = wilc->hif_func->hif_write_reg(wilc, WILC_VMM_CORE_CFG, reg);
-	if (ret) {
-		release_bus(wilc, WILC_BUS_RELEASE_ONLY);
-		return ret;
-	}
+	if (ret)
+		goto release;
+
 	reg = 0;
 	if (wilc->io_type == WILC_HIF_SDIO && wilc->dev_irq_num)
 		reg |= WILC_HAVE_SDIO_IRQ_GPIO;
 
 	ret = wilc->hif_func->hif_write_reg(wilc, WILC_GP_REG_1, reg);
-	if (ret) {
-		release_bus(wilc, WILC_BUS_RELEASE_ONLY);
-		return ret;
-	}
+	if (ret)
+		goto release;
 
 	wilc->hif_func->hif_sync_ext(wilc, NUM_INT_EXT);
 
 	ret = wilc->hif_func->hif_read_reg(wilc, WILC_CHIPID, &chipid);
-	if (ret) {
-		release_bus(wilc, WILC_BUS_RELEASE_ONLY);
-		return ret;
-	}
+	if (ret)
+		goto release;
 
 	wilc->hif_func->hif_read_reg(wilc, WILC_GLB_RESET_0, &reg);
 	if ((reg & BIT(10)) == BIT(10)) {
@@ -1159,8 +1154,9 @@ int wilc_wlan_start(struct wilc *wilc)
 	reg |= BIT(10);
 	ret = wilc->hif_func->hif_write_reg(wilc, WILC_GLB_RESET_0, reg);
 	wilc->hif_func->hif_read_reg(wilc, WILC_GLB_RESET_0, &reg);
-	release_bus(wilc, WILC_BUS_RELEASE_ONLY);
 
+release:
+	release_bus(wilc, WILC_BUS_RELEASE_ONLY);
 	return ret;
 }
 
@@ -1174,36 +1170,34 @@ int wilc_wlan_stop(struct wilc *wilc, struct wilc_vif *vif)
 	ret = wilc->hif_func->hif_read_reg(wilc, WILC_GP_REG_0, &reg);
 	if (ret) {
 		netdev_err(vif->ndev, "Error while reading reg\n");
-		release_bus(wilc, WILC_BUS_RELEASE_ALLOW_SLEEP);
-		return ret;
+		goto release;
 	}
 
 	ret = wilc->hif_func->hif_write_reg(wilc, WILC_GP_REG_0,
 					(reg | WILC_ABORT_REQ_BIT));
 	if (ret) {
 		netdev_err(vif->ndev, "Error while writing reg\n");
-		release_bus(wilc, WILC_BUS_RELEASE_ALLOW_SLEEP);
-		return ret;
+		goto release;
 	}
 
 	ret = wilc->hif_func->hif_read_reg(wilc, WILC_FW_HOST_COMM, &reg);
 	if (ret) {
 		netdev_err(vif->ndev, "Error while reading reg\n");
-		release_bus(wilc, WILC_BUS_RELEASE_ALLOW_SLEEP);
-		return ret;
+		goto release;
 	}
 	reg = BIT(0);
 
 	ret = wilc->hif_func->hif_write_reg(wilc, WILC_FW_HOST_COMM, reg);
 	if (ret) {
 		netdev_err(vif->ndev, "Error while writing reg\n");
-		release_bus(wilc, WILC_BUS_RELEASE_ALLOW_SLEEP);
-		return ret;
+		goto release;
 	}
 
+	ret = 0;
+release:
 	release_bus(wilc, WILC_BUS_RELEASE_ALLOW_SLEEP);
 
-	return 0;
+	return ret;
 }
 
 void wilc_wlan_cleanup(struct net_device *dev)
diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/pearl_pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pcie/pearl_pcie.c
index 0003df577cb3..840728ed57b2 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/pcie/pearl_pcie.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/pearl_pcie.c
@@ -295,9 +295,9 @@ static int pearl_skb2rbd_attach(struct qtnf_pcie_pearl_state *ps, u16 index)
 	priv->rx_skb[index] = skb;
 	rxbd = &ps->rx_bd_vbase[index];
 
-	paddr = pci_map_single(priv->pdev, skb->data,
-			       SKB_BUF_SIZE, PCI_DMA_FROMDEVICE);
-	if (pci_dma_mapping_error(priv->pdev, paddr)) {
+	paddr = dma_map_single(&priv->pdev->dev, skb->data, SKB_BUF_SIZE,
+			       DMA_FROM_DEVICE);
+	if (dma_mapping_error(&priv->pdev->dev, paddr)) {
 		pr_err("skb DMA mapping error: %pad\n", &paddr);
 		return -ENOMEM;
 	}
@@ -357,8 +357,8 @@ static void qtnf_pearl_free_xfer_buffers(struct qtnf_pcie_pearl_state *ps)
 			skb = priv->rx_skb[i];
 			paddr = QTN_HOST_ADDR(le32_to_cpu(rxbd->addr_h),
 					      le32_to_cpu(rxbd->addr));
-			pci_unmap_single(priv->pdev, paddr, SKB_BUF_SIZE,
-					 PCI_DMA_FROMDEVICE);
+			dma_unmap_single(&priv->pdev->dev, paddr,
+					 SKB_BUF_SIZE, DMA_FROM_DEVICE);
 			dev_kfree_skb_any(skb);
 			priv->rx_skb[i] = NULL;
 		}
@@ -371,8 +371,8 @@ static void qtnf_pearl_free_xfer_buffers(struct qtnf_pcie_pearl_state *ps)
 			skb = priv->tx_skb[i];
 			paddr = QTN_HOST_ADDR(le32_to_cpu(txbd->addr_h),
 					      le32_to_cpu(txbd->addr));
-			pci_unmap_single(priv->pdev, paddr, skb->len,
-					 PCI_DMA_TODEVICE);
+			dma_unmap_single(&priv->pdev->dev, paddr, skb->len,
+					 DMA_TO_DEVICE);
 			dev_kfree_skb_any(skb);
 			priv->tx_skb[i] = NULL;
 		}
@@ -485,8 +485,8 @@ static void qtnf_pearl_data_tx_reclaim(struct qtnf_pcie_pearl_state *ps)
 			txbd = &ps->tx_bd_vbase[i];
 			paddr = QTN_HOST_ADDR(le32_to_cpu(txbd->addr_h),
 					      le32_to_cpu(txbd->addr));
-			pci_unmap_single(priv->pdev, paddr, skb->len,
-					 PCI_DMA_TODEVICE);
+			dma_unmap_single(&priv->pdev->dev, paddr, skb->len,
+					 DMA_TO_DEVICE);
 
 			if (skb->dev) {
 				dev_sw_netstats_tx_add(skb->dev, 1, skb->len);
@@ -559,9 +559,9 @@ static int qtnf_pcie_skb_send(struct qtnf_bus *bus, struct sk_buff *skb)
 	priv->tx_skb[i] = skb;
 	len = skb->len;
 
-	skb_paddr = pci_map_single(priv->pdev, skb->data,
-				   skb->len, PCI_DMA_TODEVICE);
-	if (pci_dma_mapping_error(priv->pdev, skb_paddr)) {
+	skb_paddr = dma_map_single(&priv->pdev->dev, skb->data, skb->len,
+				   DMA_TO_DEVICE);
+	if (dma_mapping_error(&priv->pdev->dev, skb_paddr)) {
 		pr_err("skb DMA mapping error: %pad\n", &skb_paddr);
 		ret = -ENOMEM;
 		goto tx_done;
@@ -748,8 +748,8 @@ static int qtnf_pcie_pearl_rx_poll(struct napi_struct *napi, int budget)
 		if (skb) {
 			skb_paddr = QTN_HOST_ADDR(le32_to_cpu(rxbd->addr_h),
 						  le32_to_cpu(rxbd->addr));
-			pci_unmap_single(priv->pdev, skb_paddr, SKB_BUF_SIZE,
-					 PCI_DMA_FROMDEVICE);
+			dma_unmap_single(&priv->pdev->dev, skb_paddr,
+					 SKB_BUF_SIZE, DMA_FROM_DEVICE);
 		}
 
 		if (consume) {
diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie.c
index 24f1be8ddcef..9534e1b33780 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie.c
@@ -255,9 +255,9 @@ topaz_skb2rbd_attach(struct qtnf_pcie_topaz_state *ts, u16 index, u32 wrap)
 
 	ts->base.rx_skb[index] = skb;
 
-	paddr = pci_map_single(ts->base.pdev, skb->data,
-			       SKB_BUF_SIZE, PCI_DMA_FROMDEVICE);
-	if (pci_dma_mapping_error(ts->base.pdev, paddr)) {
+	paddr = dma_map_single(&ts->base.pdev->dev, skb->data, SKB_BUF_SIZE,
+			       DMA_FROM_DEVICE);
+	if (dma_mapping_error(&ts->base.pdev->dev, paddr)) {
 		pr_err("skb mapping error: %pad\n", &paddr);
 		return -ENOMEM;
 	}
@@ -306,8 +306,8 @@ static void qtnf_topaz_free_xfer_buffers(struct qtnf_pcie_topaz_state *ts)
 			rxbd = &ts->rx_bd_vbase[i];
 			skb = priv->rx_skb[i];
 			paddr = QTN_HOST_ADDR(0x0, le32_to_cpu(rxbd->addr));
-			pci_unmap_single(priv->pdev, paddr, SKB_BUF_SIZE,
-					 PCI_DMA_FROMDEVICE);
+			dma_unmap_single(&priv->pdev->dev, paddr,
+					 SKB_BUF_SIZE, DMA_FROM_DEVICE);
 			dev_kfree_skb_any(skb);
 			priv->rx_skb[i] = NULL;
 			rxbd->addr = 0;
@@ -321,8 +321,8 @@ static void qtnf_topaz_free_xfer_buffers(struct qtnf_pcie_topaz_state *ts)
 			txbd = &ts->tx_bd_vbase[i];
 			skb = priv->tx_skb[i];
 			paddr = QTN_HOST_ADDR(0x0, le32_to_cpu(txbd->addr));
-			pci_unmap_single(priv->pdev, paddr, SKB_BUF_SIZE,
-					 PCI_DMA_TODEVICE);
+			dma_unmap_single(&priv->pdev->dev, paddr,
+					 SKB_BUF_SIZE, DMA_TO_DEVICE);
 			dev_kfree_skb_any(skb);
 			priv->tx_skb[i] = NULL;
 			txbd->addr = 0;
@@ -414,8 +414,8 @@ static void qtnf_topaz_data_tx_reclaim(struct qtnf_pcie_topaz_state *ts)
 		if (likely(skb)) {
 			txbd = &ts->tx_bd_vbase[i];
 			paddr = QTN_HOST_ADDR(0x0, le32_to_cpu(txbd->addr));
-			pci_unmap_single(priv->pdev, paddr, skb->len,
-					 PCI_DMA_TODEVICE);
+			dma_unmap_single(&priv->pdev->dev, paddr, skb->len,
+					 DMA_TO_DEVICE);
 
 			if (skb->dev) {
 				dev_sw_netstats_tx_add(skb->dev, 1, skb->len);
@@ -522,9 +522,9 @@ static int qtnf_pcie_data_tx(struct qtnf_bus *bus, struct sk_buff *skb,
 	priv->tx_skb[i] = skb;
 	len = skb->len;
 
-	skb_paddr = pci_map_single(priv->pdev, skb->data,
-				   skb->len, PCI_DMA_TODEVICE);
-	if (pci_dma_mapping_error(priv->pdev, skb_paddr)) {
+	skb_paddr = dma_map_single(&priv->pdev->dev, skb->data, skb->len,
+				   DMA_TO_DEVICE);
+	if (dma_mapping_error(&priv->pdev->dev, skb_paddr)) {
 		ret = -ENOMEM;
 		goto tx_done;
 	}
@@ -653,8 +653,8 @@ static int qtnf_topaz_rx_poll(struct napi_struct *napi, int budget)
 
 		if (skb) {
 			skb_paddr = QTN_HOST_ADDR(0x0, le32_to_cpu(rxbd->addr));
-			pci_unmap_single(priv->pdev, skb_paddr, SKB_BUF_SIZE,
-					 PCI_DMA_FROMDEVICE);
+			dma_unmap_single(&priv->pdev->dev, skb_paddr,
+					 SKB_BUF_SIZE, DMA_FROM_DEVICE);
 		}
 
 		if (consume) {
diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index 590bd974d94f..0f5009c47cd0 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -982,7 +982,9 @@ AP to AP	1	1	dest AP		src AP		dest	source
 	if (local->net_type == ADHOC) {
 		writeb(0, &ptx->mac.frame_ctl_2);
 		memcpy_toio(ptx->mac.addr_1, ((struct ethhdr *)data)->h_dest,
-			    2 * ADDRLEN);
+			    ADDRLEN);
+		memcpy_toio(ptx->mac.addr_2, ((struct ethhdr *)data)->h_source,
+			    ADDRLEN);
 		memcpy_toio(ptx->mac.addr_3, local->bss_id, ADDRLEN);
 	} else { /* infrastructure */
 
@@ -2424,9 +2426,7 @@ static void rx_authenticate(ray_dev_t *local, struct rcs __iomem *prcs,
 	copy_from_rx_buff(local, buff, pkt_addr, rx_len & 0xff);
 	/* if we are trying to get authenticated */
 	if (local->sparm.b4.a_network_type == ADHOC) {
-		pr_debug("ray_cs rx_auth var= %02x %02x %02x %02x %02x %02x\n",
-		      msg->var[0], msg->var[1], msg->var[2], msg->var[3],
-		      msg->var[4], msg->var[5]);
+		pr_debug("ray_cs rx_auth var= %6ph\n", msg->var);
 		if (msg->var[2] == 1) {
 			pr_debug("ray_cs Sending authentication response.\n");
 			if (!build_auth_frame
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
index 01735776345a..7ddce3c3f0c4 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
@@ -1378,6 +1378,8 @@ struct rtl8xxxu_priv {
 	u8 no_pape:1;
 	u8 int_buf[USB_INTR_CONTENT_LENGTH];
 	u8 rssi_level;
+	DECLARE_BITMAP(tx_aggr_started, IEEE80211_NUM_TIDS);
+	DECLARE_BITMAP(tid_tx_operational, IEEE80211_NUM_TIDS);
 	/*
 	 * Only one virtual interface permitted because only STA mode
 	 * is supported and no iface_combinations are provided.
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
index ac1061caacd6..774341b0005a 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
@@ -1670,7 +1670,7 @@ static int rtl8xxxu_identify_chip(struct rtl8xxxu_priv *priv)
 			priv->rf_paths = 2;
 			priv->rx_paths = 2;
 			priv->tx_paths = 2;
-			priv->usb_interrupts = 1;
+			priv->usb_interrupts = 0;
 			priv->rtl_chip = RTL8192C;
 		}
 		priv->has_wifi = 1;
@@ -1680,7 +1680,7 @@ static int rtl8xxxu_identify_chip(struct rtl8xxxu_priv *priv)
 		priv->rx_paths = 1;
 		priv->tx_paths = 1;
 		priv->rtl_chip = RTL8188C;
-		priv->usb_interrupts = 1;
+		priv->usb_interrupts = 0;
 		priv->has_wifi = 1;
 	}
 
@@ -4805,6 +4805,8 @@ rtl8xxxu_fill_txdesc_v1(struct ieee80211_hw *hw, struct ieee80211_hdr *hdr,
 	struct ieee80211_rate *tx_rate = ieee80211_get_tx_rate(hw, tx_info);
 	struct rtl8xxxu_priv *priv = hw->priv;
 	struct device *dev = &priv->udev->dev;
+	u8 *qc = ieee80211_get_qos_ctl(hdr);
+	u8 tid = qc[0] & IEEE80211_QOS_CTL_TID_MASK;
 	u32 rate;
 	u16 rate_flags = tx_info->control.rates[0].flags;
 	u16 seq_number;
@@ -4828,7 +4830,7 @@ rtl8xxxu_fill_txdesc_v1(struct ieee80211_hw *hw, struct ieee80211_hdr *hdr,
 
 	tx_desc->txdw3 = cpu_to_le32((u32)seq_number << TXDESC32_SEQ_SHIFT);
 
-	if (ampdu_enable)
+	if (ampdu_enable && test_bit(tid, priv->tid_tx_operational))
 		tx_desc->txdw1 |= cpu_to_le32(TXDESC32_AGG_ENABLE);
 	else
 		tx_desc->txdw1 |= cpu_to_le32(TXDESC32_AGG_BREAK);
@@ -4876,6 +4878,8 @@ rtl8xxxu_fill_txdesc_v2(struct ieee80211_hw *hw, struct ieee80211_hdr *hdr,
 	struct rtl8xxxu_priv *priv = hw->priv;
 	struct device *dev = &priv->udev->dev;
 	struct rtl8xxxu_txdesc40 *tx_desc40;
+	u8 *qc = ieee80211_get_qos_ctl(hdr);
+	u8 tid = qc[0] & IEEE80211_QOS_CTL_TID_MASK;
 	u32 rate;
 	u16 rate_flags = tx_info->control.rates[0].flags;
 	u16 seq_number;
@@ -4902,7 +4906,7 @@ rtl8xxxu_fill_txdesc_v2(struct ieee80211_hw *hw, struct ieee80211_hdr *hdr,
 
 	tx_desc40->txdw9 = cpu_to_le32((u32)seq_number << TXDESC40_SEQ_SHIFT);
 
-	if (ampdu_enable)
+	if (ampdu_enable && test_bit(tid, priv->tid_tx_operational))
 		tx_desc40->txdw2 |= cpu_to_le32(TXDESC40_AGG_ENABLE);
 	else
 		tx_desc40->txdw2 |= cpu_to_le32(TXDESC40_AGG_BREAK);
@@ -5015,12 +5019,19 @@ static void rtl8xxxu_tx(struct ieee80211_hw *hw,
 	if (ieee80211_is_data_qos(hdr->frame_control) && sta) {
 		if (sta->ht_cap.ht_supported) {
 			u32 ampdu, val32;
+			u8 *qc = ieee80211_get_qos_ctl(hdr);
+			u8 tid = qc[0] & IEEE80211_QOS_CTL_TID_MASK;
 
 			ampdu = (u32)sta->ht_cap.ampdu_density;
 			val32 = ampdu << TXDESC_AMPDU_DENSITY_SHIFT;
 			tx_desc->txdw2 |= cpu_to_le32(val32);
 
 			ampdu_enable = true;
+
+			if (!test_bit(tid, priv->tx_aggr_started) &&
+			    !(skb->protocol == cpu_to_be16(ETH_P_PAE)))
+				if (!ieee80211_start_tx_ba_session(sta, tid, 0))
+					set_bit(tid, priv->tx_aggr_started);
 		}
 	}
 
@@ -6096,6 +6107,7 @@ rtl8xxxu_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct device *dev = &priv->udev->dev;
 	u8 ampdu_factor, ampdu_density;
 	struct ieee80211_sta *sta = params->sta;
+	u16 tid = params->tid;
 	enum ieee80211_ampdu_mlme_action action = params->action;
 
 	switch (action) {
@@ -6108,17 +6120,20 @@ rtl8xxxu_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		dev_dbg(dev,
 			"Changed HT: ampdu_factor %02x, ampdu_density %02x\n",
 			ampdu_factor, ampdu_density);
-		break;
+		return IEEE80211_AMPDU_TX_START_IMMEDIATE;
+	case IEEE80211_AMPDU_TX_STOP_CONT:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
-		dev_dbg(dev, "%s: IEEE80211_AMPDU_TX_STOP_FLUSH\n", __func__);
-		rtl8xxxu_set_ampdu_factor(priv, 0);
-		rtl8xxxu_set_ampdu_min_space(priv, 0);
-		break;
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
-		dev_dbg(dev, "%s: IEEE80211_AMPDU_TX_STOP_FLUSH_CONT\n",
-			 __func__);
+		dev_dbg(dev, "%s: IEEE80211_AMPDU_TX_STOP\n", __func__);
 		rtl8xxxu_set_ampdu_factor(priv, 0);
 		rtl8xxxu_set_ampdu_min_space(priv, 0);
+		clear_bit(tid, priv->tx_aggr_started);
+		clear_bit(tid, priv->tid_tx_operational);
+		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+		break;
+	case IEEE80211_AMPDU_TX_OPERATIONAL:
+		dev_dbg(dev, "%s: IEEE80211_AMPDU_TX_OPERATIONAL\n", __func__);
+		set_bit(tid, priv->tid_tx_operational);
 		break;
 	case IEEE80211_AMPDU_RX_START:
 		dev_dbg(dev, "%s: IEEE80211_AMPDU_RX_START\n", __func__);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
index 76dd881ef9bb..9b83c710c9b8 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
@@ -160,6 +160,15 @@ static u32 targetchnl_2g[TARGET_CHNL_NUM_2G] = {
 	25711, 25658, 25606, 25554, 25502, 25451, 25328
 };
 
+static const u8 channel_all[59] = {
+	1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
+	36, 38, 40, 42, 44, 46, 48, 50, 52, 54, 56, 58,
+	60, 62, 64, 100, 102, 104, 106, 108, 110, 112,
+	114, 116, 118, 120, 122, 124, 126, 128,	130,
+	132, 134, 136, 138, 140, 149, 151, 153, 155,
+	157, 159, 161, 163, 165
+};
+
 static u32 _rtl92d_phy_calculate_bit_shift(u32 bitmask)
 {
 	u32 i = ffs(bitmask);
@@ -681,7 +690,7 @@ static bool _rtl92d_phy_bb_config(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_phy *rtlphy = &(rtlpriv->phy);
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
-	bool rtstatus = true;
+	bool rtstatus;
 
 	rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE, "==>\n");
 	rtstatus = _rtl92d_phy_config_bb_with_headerfile(hw,
@@ -1354,15 +1363,7 @@ static void _rtl92d_phy_switch_rf_setting(struct ieee80211_hw *hw, u8 channel)
 
 u8 rtl92d_get_rightchnlplace_for_iqk(u8 chnl)
 {
-	u8 channel_all[59] = {
-		1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
-		36, 38, 40, 42, 44, 46, 48, 50, 52, 54, 56, 58,
-		60, 62, 64, 100, 102, 104, 106, 108, 110, 112,
-		114, 116, 118, 120, 122, 124, 126, 128,	130,
-		132, 134, 136, 138, 140, 149, 151, 153, 155,
-		157, 159, 161, 163, 165
-	};
-	u8 place = chnl;
+	u8 place;
 
 	if (chnl > 14) {
 		for (place = 14; place < sizeof(channel_all); place++) {
@@ -3220,37 +3221,28 @@ void rtl92d_phy_config_macphymode_info(struct ieee80211_hw *hw)
 u8 rtl92d_get_chnlgroup_fromarray(u8 chnl)
 {
 	u8 group;
-	u8 channel_info[59] = {
-		1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
-		36, 38, 40, 42, 44, 46, 48, 50, 52, 54, 56,
-		58, 60, 62, 64, 100, 102, 104, 106, 108,
-		110, 112, 114, 116, 118, 120, 122, 124,
-		126, 128, 130, 132, 134, 136, 138, 140,
-		149, 151, 153, 155, 157, 159, 161, 163,
-		165
-	};
 
-	if (channel_info[chnl] <= 3)
+	if (channel_all[chnl] <= 3)
 		group = 0;
-	else if (channel_info[chnl] <= 9)
+	else if (channel_all[chnl] <= 9)
 		group = 1;
-	else if (channel_info[chnl] <= 14)
+	else if (channel_all[chnl] <= 14)
 		group = 2;
-	else if (channel_info[chnl] <= 44)
+	else if (channel_all[chnl] <= 44)
 		group = 3;
-	else if (channel_info[chnl] <= 54)
+	else if (channel_all[chnl] <= 54)
 		group = 4;
-	else if (channel_info[chnl] <= 64)
+	else if (channel_all[chnl] <= 64)
 		group = 5;
-	else if (channel_info[chnl] <= 112)
+	else if (channel_all[chnl] <= 112)
 		group = 6;
-	else if (channel_info[chnl] <= 126)
+	else if (channel_all[chnl] <= 126)
 		group = 7;
-	else if (channel_info[chnl] <= 140)
+	else if (channel_all[chnl] <= 140)
 		group = 8;
-	else if (channel_info[chnl] <= 153)
+	else if (channel_all[chnl] <= 153)
 		group = 9;
-	else if (channel_info[chnl] <= 159)
+	else if (channel_all[chnl] <= 159)
 		group = 10;
 	else
 		group = 11;
diff --git a/drivers/net/wireless/realtek/rtw88/Makefile b/drivers/net/wireless/realtek/rtw88/Makefile
index c0e4b111c8b4..73d6807a8cdf 100644
--- a/drivers/net/wireless/realtek/rtw88/Makefile
+++ b/drivers/net/wireless/realtek/rtw88/Makefile
@@ -15,9 +15,9 @@ rtw88_core-y += main.o \
 	   ps.o \
 	   sec.o \
 	   bf.o \
-	   wow.o \
 	   regd.o
 
+rtw88_core-$(CONFIG_PM) += wow.o
 
 obj-$(CONFIG_RTW88_8822B)	+= rtw88_8822b.o
 rtw88_8822b-objs		:= rtw8822b.o rtw8822b_table.o
diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c
index 3bfa5ecc0053..e6399519584b 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.c
+++ b/drivers/net/wireless/realtek/rtw88/fw.c
@@ -819,7 +819,7 @@ static u16 rtw_get_rsvd_page_probe_req_size(struct rtw_dev *rtwdev,
 			continue;
 		if ((!ssid && !rsvd_pkt->ssid) ||
 		    rtw_ssid_equal(rsvd_pkt->ssid, ssid))
-			size = rsvd_pkt->skb->len;
+			size = rsvd_pkt->probe_req_size;
 	}
 
 	return size;
@@ -1047,6 +1047,8 @@ static struct sk_buff *rtw_get_rsvd_page_skb(struct ieee80211_hw *hw,
 							 ssid->ssid_len, 0);
 		else
 			skb_new = ieee80211_probereq_get(hw, vif->addr, NULL, 0, 0);
+		if (skb_new)
+			rsvd_pkt->probe_req_size = (u16)skb_new->len;
 		break;
 	case RSVD_NLO_INFO:
 		skb_new = rtw_nlo_info_get(hw);
@@ -1643,6 +1645,7 @@ int rtw_fw_dump_fifo(struct rtw_dev *rtwdev, u8 fifo_sel, u32 addr, u32 size,
 static void __rtw_fw_update_pkt(struct rtw_dev *rtwdev, u8 pkt_id, u16 size,
 				u8 location)
 {
+	struct rtw_chip_info *chip = rtwdev->chip;
 	u8 h2c_pkt[H2C_PKT_SIZE] = {0};
 	u16 total_size = H2C_PKT_HDR_SIZE + H2C_PKT_UPDATE_PKT_LEN;
 
@@ -1653,6 +1656,7 @@ static void __rtw_fw_update_pkt(struct rtw_dev *rtwdev, u8 pkt_id, u16 size,
 	UPDATE_PKT_SET_LOCATION(h2c_pkt, location);
 
 	/* include txdesc size */
+	size += chip->tx_pkt_desc_sz;
 	UPDATE_PKT_SET_SIZE(h2c_pkt, size);
 
 	rtw_fw_send_h2c_packet(rtwdev, h2c_pkt);
@@ -1662,7 +1666,7 @@ void rtw_fw_update_pkt_probe_req(struct rtw_dev *rtwdev,
 				 struct cfg80211_ssid *ssid)
 {
 	u8 loc;
-	u32 size;
+	u16 size;
 
 	loc = rtw_get_rsvd_page_probe_req_location(rtwdev, ssid);
 	if (!loc) {
diff --git a/drivers/net/wireless/realtek/rtw88/fw.h b/drivers/net/wireless/realtek/rtw88/fw.h
index a8a7162fbe64..64dcde35a021 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.h
+++ b/drivers/net/wireless/realtek/rtw88/fw.h
@@ -99,7 +99,7 @@ enum rtw_beacon_filter_offload_mode {
 	BCN_FILTER_OFFLOAD_MODE_2,
 	BCN_FILTER_OFFLOAD_MODE_3,
 
-	BCN_FILTER_OFFLOAD_MODE_DEFAULT = BCN_FILTER_OFFLOAD_MODE_1,
+	BCN_FILTER_OFFLOAD_MODE_DEFAULT = BCN_FILTER_OFFLOAD_MODE_0,
 };
 
 struct rtw_coex_info_req {
@@ -147,6 +147,7 @@ struct rtw_rsvd_page {
 	u8 page;
 	bool add_txdesc;
 	struct cfg80211_ssid *ssid;
+	u16 probe_req_size;
 };
 
 enum rtw_keep_alive_pkt_type {
diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index c6364837e83b..6bb55e663fc3 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -1338,6 +1338,8 @@ static void rtw_init_ht_cap(struct rtw_dev *rtwdev,
 
 	if (rtw_chip_has_rx_ldpc(rtwdev))
 		ht_cap->cap |= IEEE80211_HT_CAP_LDPC_CODING;
+	if (rtw_chip_has_tx_stbc(rtwdev))
+		ht_cap->cap |= IEEE80211_HT_CAP_TX_STBC;
 
 	if (efuse->hw_cap.bw & BIT(RTW_CHANNEL_WIDTH_40))
 		ht_cap->cap |= IEEE80211_HT_CAP_SUP_WIDTH_20_40 |
diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index e5af375b3dd0..56812127a053 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -1146,6 +1146,7 @@ struct rtw_chip_info {
 	u8 txgi_factor;
 	bool is_pwr_by_rate_dec;
 	bool rx_ldpc;
+	bool tx_stbc;
 	u8 max_power_index;
 
 	u16 fw_fifo_addr[RTW_FW_FIFO_MAX];
@@ -1959,6 +1960,11 @@ static inline bool rtw_chip_has_rx_ldpc(struct rtw_dev *rtwdev)
 	return rtwdev->chip->rx_ldpc;
 }
 
+static inline bool rtw_chip_has_tx_stbc(struct rtw_dev *rtwdev)
+{
+	return rtwdev->chip->tx_stbc;
+}
+
 static inline void rtw_release_macid(struct rtw_dev *rtwdev, u8 mac_id)
 {
 	clear_bit(mac_id, rtwdev->mac_id_map);
diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index e7d17ab8f113..a7a6ebfaa203 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -268,11 +268,6 @@ static int rtw_pci_init_rx_ring(struct rtw_dev *rtwdev,
 	int i, allocated;
 	int ret = 0;
 
-	if (len > TRX_BD_IDX_MASK) {
-		rtw_err(rtwdev, "len %d exceeds maximum RX entries\n", len);
-		return -EINVAL;
-	}
-
 	head = dma_alloc_coherent(&pdev->dev, ring_sz, &dma, GFP_KERNEL);
 	if (!head) {
 		rtw_err(rtwdev, "failed to allocate rx ring\n");
@@ -1359,6 +1354,25 @@ static void rtw_pci_clkreq_set(struct rtw_dev *rtwdev, bool enable)
 	rtw_dbi_write8(rtwdev, RTK_PCIE_LINK_CFG, value);
 }
 
+static void rtw_pci_clkreq_pad_low(struct rtw_dev *rtwdev, bool enable)
+{
+	u8 value;
+	int ret;
+
+	ret = rtw_dbi_read8(rtwdev, RTK_PCIE_LINK_CFG, &value);
+	if (ret) {
+		rtw_err(rtwdev, "failed to read CLKREQ_L1, ret=%d", ret);
+		return;
+	}
+
+	if (enable)
+		value &= ~BIT_CLKREQ_N_PAD;
+	else
+		value |= BIT_CLKREQ_N_PAD;
+
+	rtw_dbi_write8(rtwdev, RTK_PCIE_LINK_CFG, value);
+}
+
 static void rtw_pci_aspm_set(struct rtw_dev *rtwdev, bool enable)
 {
 	u8 value;
@@ -1500,11 +1514,25 @@ static void rtw_pci_phy_cfg(struct rtw_dev *rtwdev)
 
 static int __maybe_unused rtw_pci_suspend(struct device *dev)
 {
+	struct ieee80211_hw *hw = dev_get_drvdata(dev);
+	struct rtw_dev *rtwdev = hw->priv;
+	struct rtw_chip_info *chip = rtwdev->chip;
+	struct rtw_efuse *efuse = &rtwdev->efuse;
+
+	if (chip->id == RTW_CHIP_TYPE_8822C && efuse->rfe_option == 6)
+		rtw_pci_clkreq_pad_low(rtwdev, true);
 	return 0;
 }
 
 static int __maybe_unused rtw_pci_resume(struct device *dev)
 {
+	struct ieee80211_hw *hw = dev_get_drvdata(dev);
+	struct rtw_dev *rtwdev = hw->priv;
+	struct rtw_chip_info *chip = rtwdev->chip;
+	struct rtw_efuse *efuse = &rtwdev->efuse;
+
+	if (chip->id == RTW_CHIP_TYPE_8822C && efuse->rfe_option == 6)
+		rtw_pci_clkreq_pad_low(rtwdev, false);
 	return 0;
 }
 
@@ -1701,6 +1729,15 @@ static const struct dmi_system_id rtw88_pci_quirks[] = {
 		},
 		.driver_data = (void *)BIT(QUIRK_DIS_PCI_CAP_ASPM),
 	},
+	{
+		.callback = disable_pci_caps,
+		.ident = "HP HP Pavilion Laptop 14-ce0xxx",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Laptop 14-ce0xxx"),
+		},
+		.driver_data = (void *)BIT(QUIRK_DIS_PCI_CAP_ASPM),
+	},
 	{}
 };
 
diff --git a/drivers/net/wireless/realtek/rtw88/pci.h b/drivers/net/wireless/realtek/rtw88/pci.h
index 0ffae887527a..66f78eb7757c 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.h
+++ b/drivers/net/wireless/realtek/rtw88/pci.h
@@ -37,6 +37,7 @@
 #define RTK_PCIE_LINK_CFG	0x0719
 #define BIT_CLKREQ_SW_EN	BIT(4)
 #define BIT_L1_SW_EN		BIT(3)
+#define BIT_CLKREQ_N_PAD	BIT(0)
 #define RTK_PCIE_CLKDLY_CTRL	0x0725
 
 #define BIT_PCI_BCNQ_FLAG	BIT(4)
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
index 8bf3cd3a3678..f3ad079967a6 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
@@ -5288,6 +5288,7 @@ struct rtw_chip_info rtw8822c_hw_spec = {
 	.bfer_su_max_num = 2,
 	.bfer_mu_max_num = 1,
 	.rx_ldpc = true,
+	.tx_stbc = true,
 
 #ifdef CONFIG_PM
 	.wow_fw_name = "rtw88/rtw8822c_wow_fw.bin",
diff --git a/drivers/net/wireless/realtek/rtw88/tx.c b/drivers/net/wireless/realtek/rtw88/tx.c
index 0193708fc013..3a101aa139ed 100644
--- a/drivers/net/wireless/realtek/rtw88/tx.c
+++ b/drivers/net/wireless/realtek/rtw88/tx.c
@@ -162,7 +162,7 @@ void rtw_tx_report_purge_timer(struct timer_list *t)
 	if (skb_queue_len(&tx_report->queue) == 0)
 		return;
 
-	rtw_dbg(rtwdev, RTW_DBG_TX, "purge skb(s) not reported by firmware\n");
+	rtw_warn(rtwdev, "failed to get tx report from firmware\n");
 
 	spin_lock_irqsave(&tx_report->q_lock, flags);
 	skb_queue_purge(&tx_report->queue);
diff --git a/drivers/net/wireless/realtek/rtw88/wow.c b/drivers/net/wireless/realtek/rtw88/wow.c
index fc9544f4e5e4..89dc595094d5 100644
--- a/drivers/net/wireless/realtek/rtw88/wow.c
+++ b/drivers/net/wireless/realtek/rtw88/wow.c
@@ -12,26 +12,54 @@
 
 static void rtw_wow_show_wakeup_reason(struct rtw_dev *rtwdev)
 {
+	struct cfg80211_wowlan_nd_info nd_info;
+	struct cfg80211_wowlan_wakeup wakeup = {
+		.pattern_idx = -1,
+	};
 	u8 reason;
 
 	reason = rtw_read8(rtwdev, REG_WOWLAN_WAKE_REASON);
 
-	if (reason == RTW_WOW_RSN_RX_DEAUTH)
+	switch (reason) {
+	case RTW_WOW_RSN_RX_DEAUTH:
+		wakeup.disconnect = true;
 		rtw_dbg(rtwdev, RTW_DBG_WOW, "WOW: Rx deauth\n");
-	else if (reason == RTW_WOW_RSN_DISCONNECT)
+		break;
+	case RTW_WOW_RSN_DISCONNECT:
+		wakeup.disconnect = true;
 		rtw_dbg(rtwdev, RTW_DBG_WOW, "WOW: AP is off\n");
-	else if (reason == RTW_WOW_RSN_RX_MAGIC_PKT)
+		break;
+	case RTW_WOW_RSN_RX_MAGIC_PKT:
+		wakeup.magic_pkt = true;
 		rtw_dbg(rtwdev, RTW_DBG_WOW, "WOW: Rx magic packet\n");
-	else if (reason == RTW_WOW_RSN_RX_GTK_REKEY)
+		break;
+	case RTW_WOW_RSN_RX_GTK_REKEY:
+		wakeup.gtk_rekey_failure = true;
 		rtw_dbg(rtwdev, RTW_DBG_WOW, "WOW: Rx gtk rekey\n");
-	else if (reason == RTW_WOW_RSN_RX_PTK_REKEY)
-		rtw_dbg(rtwdev, RTW_DBG_WOW, "WOW: Rx ptk rekey\n");
-	else if (reason == RTW_WOW_RSN_RX_PATTERN_MATCH)
+		break;
+	case RTW_WOW_RSN_RX_PATTERN_MATCH:
+		/* Current firmware and driver don't report pattern index
+		 * Use pattern_idx to 0 defaultly.
+		 */
+		wakeup.pattern_idx = 0;
 		rtw_dbg(rtwdev, RTW_DBG_WOW, "WOW: Rx pattern match packet\n");
-	else if (reason == RTW_WOW_RSN_RX_NLO)
+		break;
+	case RTW_WOW_RSN_RX_NLO:
+		/* Current firmware and driver don't report ssid index.
+		 * Use 0 for n_matches based on its comment.
+		 */
+		nd_info.n_matches = 0;
+		wakeup.net_detect = &nd_info;
 		rtw_dbg(rtwdev, RTW_DBG_WOW, "Rx NLO\n");
-	else
+		break;
+	default:
 		rtw_warn(rtwdev, "Unknown wakeup reason %x\n", reason);
+		ieee80211_report_wowlan_wakeup(rtwdev->wow.wow_vif, NULL,
+					       GFP_KERNEL);
+		return;
+	}
+	ieee80211_report_wowlan_wakeup(rtwdev->wow.wow_vif, &wakeup,
+				       GFP_KERNEL);
 }
 
 static void rtw_wow_pattern_write_cam(struct rtw_dev *rtwdev, u8 addr,
@@ -283,15 +311,26 @@ static void rtw_wow_rx_dma_start(struct rtw_dev *rtwdev)
 
 static int rtw_wow_check_fw_status(struct rtw_dev *rtwdev, bool wow_enable)
 {
-	/* wait 100ms for wow firmware to finish work */
-	msleep(100);
+	int ret;
+	u8 check;
+	u32 check_dis;
 
 	if (wow_enable) {
-		if (rtw_read8(rtwdev, REG_WOWLAN_WAKE_REASON))
+		ret = read_poll_timeout(rtw_read8, check, !check, 1000,
+					100000, true, rtwdev,
+					REG_WOWLAN_WAKE_REASON);
+		if (ret)
 			goto wow_fail;
 	} else {
-		if (rtw_read32_mask(rtwdev, REG_FE1IMR, BIT_FS_RXDONE) ||
-		    rtw_read32_mask(rtwdev, REG_RXPKT_NUM, BIT_RW_RELEASE))
+		ret = read_poll_timeout(rtw_read32_mask, check_dis,
+					!check_dis, 1000, 100000, true, rtwdev,
+					REG_FE1IMR, BIT_FS_RXDONE);
+		if (ret)
+			goto wow_fail;
+		ret = read_poll_timeout(rtw_read32_mask, check_dis,
+					!check_dis, 1000, 100000, false, rtwdev,
+					REG_RXPKT_NUM, BIT_RW_RELEASE);
+		if (ret)
 			goto wow_fail;
 	}
 
@@ -432,37 +471,31 @@ static void rtw_wow_fw_media_status(struct rtw_dev *rtwdev, bool connect)
 	rtw_iterate_stas_atomic(rtwdev, rtw_wow_fw_media_status_iter, &data);
 }
 
-static void rtw_wow_config_pno_rsvd_page(struct rtw_dev *rtwdev,
-					 struct rtw_vif *rtwvif)
+static int rtw_wow_config_wow_fw_rsvd_page(struct rtw_dev *rtwdev)
 {
-	rtw_add_rsvd_page_pno(rtwdev, rtwvif);
-}
-
-static void rtw_wow_config_linked_rsvd_page(struct rtw_dev *rtwdev,
-					   struct rtw_vif *rtwvif)
-{
-	rtw_add_rsvd_page_sta(rtwdev, rtwvif);
-}
+	struct ieee80211_vif *wow_vif = rtwdev->wow.wow_vif;
+	struct rtw_vif *rtwvif = (struct rtw_vif *)wow_vif->drv_priv;
 
-static void rtw_wow_config_rsvd_page(struct rtw_dev *rtwdev,
-				     struct rtw_vif *rtwvif)
-{
 	rtw_remove_rsvd_page(rtwdev, rtwvif);
 
-	if (rtw_wow_mgd_linked(rtwdev)) {
-		rtw_wow_config_linked_rsvd_page(rtwdev, rtwvif);
-	} else if (test_bit(RTW_FLAG_WOWLAN, rtwdev->flags) &&
-		   rtw_wow_no_link(rtwdev)) {
-		rtw_wow_config_pno_rsvd_page(rtwdev, rtwvif);
-	}
+	if (rtw_wow_no_link(rtwdev))
+		rtw_add_rsvd_page_pno(rtwdev, rtwvif);
+	else
+		rtw_add_rsvd_page_sta(rtwdev, rtwvif);
+
+	return rtw_fw_download_rsvd_page(rtwdev);
 }
 
-static int rtw_wow_dl_fw_rsvd_page(struct rtw_dev *rtwdev)
+static int rtw_wow_config_normal_fw_rsvd_page(struct rtw_dev *rtwdev)
 {
 	struct ieee80211_vif *wow_vif = rtwdev->wow.wow_vif;
 	struct rtw_vif *rtwvif = (struct rtw_vif *)wow_vif->drv_priv;
 
-	rtw_wow_config_rsvd_page(rtwdev, rtwvif);
+	rtw_remove_rsvd_page(rtwdev, rtwvif);
+	rtw_add_rsvd_page_sta(rtwdev, rtwvif);
+
+	if (rtw_wow_no_link(rtwdev))
+		return 0;
 
 	return rtw_fw_download_rsvd_page(rtwdev);
 }
@@ -660,7 +693,7 @@ static int rtw_wow_enable(struct rtw_dev *rtwdev)
 
 	set_bit(RTW_FLAG_WOWLAN, rtwdev->flags);
 
-	ret = rtw_wow_dl_fw_rsvd_page(rtwdev);
+	ret = rtw_wow_config_wow_fw_rsvd_page(rtwdev);
 	if (ret) {
 		rtw_err(rtwdev, "failed to download wowlan rsvd page\n");
 		goto error;
@@ -733,7 +766,7 @@ static int rtw_wow_disable(struct rtw_dev *rtwdev)
 		goto out;
 	}
 
-	ret = rtw_wow_dl_fw_rsvd_page(rtwdev);
+	ret = rtw_wow_config_normal_fw_rsvd_page(rtwdev);
 	if (ret)
 		rtw_err(rtwdev, "failed to download normal rsvd page\n");
 
diff --git a/drivers/net/wireless/rsi/rsi_91x_debugfs.c b/drivers/net/wireless/rsi/rsi_91x_debugfs.c
index 24a417ea2ae7..bf22fd948276 100644
--- a/drivers/net/wireless/rsi/rsi_91x_debugfs.c
+++ b/drivers/net/wireless/rsi/rsi_91x_debugfs.c
@@ -117,7 +117,7 @@ static int rsi_stats_read(struct seq_file *seq, void *data)
 {
 	struct rsi_common *common = seq->private;
 
-	unsigned char fsm_state[][32] = {
+	static const unsigned char fsm_state[][32] = {
 		"FSM_FW_NOT_LOADED",
 		"FSM_CARD_NOT_READY",
 		"FSM_COMMON_DEV_PARAMS_SENT",
diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c
index 99b21a2c8386..f4a26f16f00f 100644
--- a/drivers/net/wireless/rsi/rsi_91x_hal.c
+++ b/drivers/net/wireless/rsi/rsi_91x_hal.c
@@ -1038,8 +1038,10 @@ static int rsi_load_9116_firmware(struct rsi_hw *adapter)
 	}
 
 	ta_firmware = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL);
-	if (!ta_firmware)
+	if (!ta_firmware) {
+		status = -ENOMEM;
 		goto fail_release_fw;
+	}
 	fw_p = ta_firmware;
 	instructions_sz = fw_entry->size;
 	rsi_dbg(INFO_ZONE, "FW Length = %d bytes\n", instructions_sz);
diff --git a/drivers/net/wireless/rsi/rsi_91x_usb.c b/drivers/net/wireless/rsi/rsi_91x_usb.c
index 3fbe2a3c1455..416976f09888 100644
--- a/drivers/net/wireless/rsi/rsi_91x_usb.c
+++ b/drivers/net/wireless/rsi/rsi_91x_usb.c
@@ -816,6 +816,7 @@ static int rsi_probe(struct usb_interface *pfunction,
 	} else {
 		rsi_dbg(ERR_ZONE, "%s: Unsupported RSI device id 0x%x\n",
 			__func__, id->idProduct);
+		status = -ENODEV;
 		goto err1;
 	}
 
diff --git a/drivers/net/wwan/Kconfig b/drivers/net/wwan/Kconfig
index de9384326bc8..77dbfc418bce 100644
--- a/drivers/net/wwan/Kconfig
+++ b/drivers/net/wwan/Kconfig
@@ -38,6 +38,18 @@ config MHI_WWAN_CTRL
 	  To compile this driver as a module, choose M here: the module will be
 	  called mhi_wwan_ctrl.
 
+config MHI_WWAN_MBIM
+        tristate "MHI WWAN MBIM network driver for QCOM-based PCIe modems"
+        depends on MHI_BUS
+        help
+          MHI WWAN MBIM is a WWAN network driver for QCOM-based PCIe modems.
+          It implements MBIM over MHI, for IP data aggregation and muxing.
+          A default wwan0 network interface is created for MBIM data session
+          ID 0. Additional links can be created via wwan rtnetlink type.
+
+          To compile this driver as a module, choose M here: the module will be
+          called mhi_wwan_mbim.
+
 config RPMSG_WWAN_CTRL
 	tristate "RPMSG WWAN control driver"
 	depends on RPMSG
diff --git a/drivers/net/wwan/Makefile b/drivers/net/wwan/Makefile
index d90ac33abaef..fe51feedac21 100644
--- a/drivers/net/wwan/Makefile
+++ b/drivers/net/wwan/Makefile
@@ -9,5 +9,6 @@ wwan-objs += wwan_core.o
 obj-$(CONFIG_WWAN_HWSIM) += wwan_hwsim.o
 
 obj-$(CONFIG_MHI_WWAN_CTRL) += mhi_wwan_ctrl.o
+obj-$(CONFIG_MHI_WWAN_MBIM) += mhi_wwan_mbim.o
 obj-$(CONFIG_RPMSG_WWAN_CTRL) += rpmsg_wwan_ctrl.o
 obj-$(CONFIG_IOSM) += iosm/
diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c
index 7f7d364d3a51..2fe88b8be348 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c
@@ -479,6 +479,7 @@ static struct pci_driver iosm_ipc_driver = {
 	},
 	.id_table = iosm_ipc_ids,
 };
+module_pci_driver(iosm_ipc_driver);
 
 int ipc_pcie_addr_map(struct iosm_pcie *ipc_pcie, unsigned char *data,
 		      size_t size, dma_addr_t *mapping, int direction)
@@ -560,21 +561,3 @@ void ipc_pcie_kfree_skb(struct iosm_pcie *ipc_pcie, struct sk_buff *skb)
 	IPC_CB(skb)->mapping = 0;
 	dev_kfree_skb(skb);
 }
-
-static int __init iosm_ipc_driver_init(void)
-{
-	if (pci_register_driver(&iosm_ipc_driver)) {
-		pr_err("registering of IOSM PCIe driver failed");
-		return -1;
-	}
-
-	return 0;
-}
-
-static void __exit iosm_ipc_driver_exit(void)
-{
-	pci_unregister_driver(&iosm_ipc_driver);
-}
-
-module_init(iosm_ipc_driver_init);
-module_exit(iosm_ipc_driver_exit);
diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol.c b/drivers/net/wwan/iosm/iosm_ipc_protocol.c
index 834d8b146a94..63fc7012f09f 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_protocol.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_protocol.c
@@ -239,9 +239,9 @@ struct iosm_protocol *ipc_protocol_init(struct iosm_imem *ipc_imem)
 	ipc_protocol->old_msg_tail = 0;
 
 	ipc_protocol->p_ap_shm =
-		pci_alloc_consistent(ipc_protocol->pcie->pci,
-				     sizeof(*ipc_protocol->p_ap_shm),
-				     &ipc_protocol->phy_ap_shm);
+		dma_alloc_coherent(&ipc_protocol->pcie->pci->dev,
+				   sizeof(*ipc_protocol->p_ap_shm),
+				   &ipc_protocol->phy_ap_shm, GFP_KERNEL);
 
 	if (!ipc_protocol->p_ap_shm) {
 		dev_err(ipc_protocol->dev, "pci shm alloc error");
@@ -275,8 +275,8 @@ struct iosm_protocol *ipc_protocol_init(struct iosm_imem *ipc_imem)
 
 void ipc_protocol_deinit(struct iosm_protocol *proto)
 {
-	pci_free_consistent(proto->pcie->pci, sizeof(*proto->p_ap_shm),
-			    proto->p_ap_shm, proto->phy_ap_shm);
+	dma_free_coherent(&proto->pcie->pci->dev, sizeof(*proto->p_ap_shm),
+			  proto->p_ap_shm, proto->phy_ap_shm);
 
 	ipc_pm_deinit(proto);
 	kfree(proto);
diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c
index 35d590743d3a..c6b032f95d2e 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c
@@ -74,9 +74,9 @@ static int ipc_protocol_msg_prepipe_open(struct iosm_protocol *ipc_protocol,
 		return -ENOMEM;
 
 	/* Allocate the transfer descriptors for the pipe. */
-	tdr = pci_alloc_consistent(ipc_protocol->pcie->pci,
-				   pipe->nr_of_entries * sizeof(*tdr),
-				   &pipe->phy_tdr_start);
+	tdr = dma_alloc_coherent(&ipc_protocol->pcie->pci->dev,
+				 pipe->nr_of_entries * sizeof(*tdr),
+				 &pipe->phy_tdr_start, GFP_ATOMIC);
 	if (!tdr) {
 		kfree(skbr);
 		dev_err(ipc_protocol->dev, "tdr alloc error");
@@ -492,10 +492,9 @@ void ipc_protocol_pipe_cleanup(struct iosm_protocol *ipc_protocol,
 
 	/* Free and reset the td and skbuf circular buffers. kfree is save! */
 	if (pipe->tdr_start) {
-		pci_free_consistent(ipc_protocol->pcie->pci,
-				    sizeof(*pipe->tdr_start) *
-					    pipe->nr_of_entries,
-				    pipe->tdr_start, pipe->phy_tdr_start);
+		dma_free_coherent(&ipc_protocol->pcie->pci->dev,
+				  sizeof(*pipe->tdr_start) * pipe->nr_of_entries,
+				  pipe->tdr_start, pipe->phy_tdr_start);
 
 		pipe->tdr_start = NULL;
 	}
diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c
new file mode 100644
index 000000000000..71bf9b4f769f
--- /dev/null
+++ b/drivers/net/wwan/mhi_wwan_mbim.c
@@ -0,0 +1,658 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* MHI MBIM Network driver - Network/MBIM over MHI bus
+ *
+ * Copyright (C) 2021 Linaro Ltd <loic.poulain@linaro.org>
+ *
+ * This driver copy some code from cdc_ncm, which is:
+ * Copyright (C) ST-Ericsson 2010-2012
+ * and cdc_mbim, which is:
+ * Copyright (c) 2012  Smith Micro Software, Inc.
+ * Copyright (c) 2012  Bjørn Mork <bjorn@mork.no>
+ *
+ */
+
+#include <linux/ethtool.h>
+#include <linux/if_arp.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/mhi.h>
+#include <linux/mii.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/u64_stats_sync.h>
+#include <linux/usb.h>
+#include <linux/usb/cdc.h>
+#include <linux/usb/usbnet.h>
+#include <linux/usb/cdc_ncm.h>
+#include <linux/wwan.h>
+
+/* 3500 allows to optimize skb allocation, the skbs will basically fit in
+ * one 4K page. Large MBIM packets will simply be split over several MHI
+ * transfers and chained by the MHI net layer (zerocopy).
+ */
+#define MHI_DEFAULT_MRU 3500
+
+#define MHI_MBIM_DEFAULT_MTU 1500
+#define MHI_MAX_BUF_SZ 0xffff
+
+#define MBIM_NDP16_SIGN_MASK 0x00ffffff
+
+#define MHI_MBIM_LINK_HASH_SIZE 8
+#define LINK_HASH(session) ((session) % MHI_MBIM_LINK_HASH_SIZE)
+
+struct mhi_mbim_link {
+	struct mhi_mbim_context *mbim;
+	struct net_device *ndev;
+	unsigned int session;
+
+	/* stats */
+	u64_stats_t rx_packets;
+	u64_stats_t rx_bytes;
+	u64_stats_t rx_errors;
+	u64_stats_t tx_packets;
+	u64_stats_t tx_bytes;
+	u64_stats_t tx_errors;
+	u64_stats_t tx_dropped;
+	struct u64_stats_sync tx_syncp;
+	struct u64_stats_sync rx_syncp;
+
+	struct hlist_node hlnode;
+};
+
+struct mhi_mbim_context {
+	struct mhi_device *mdev;
+	struct sk_buff *skbagg_head;
+	struct sk_buff *skbagg_tail;
+	unsigned int mru;
+	u32 rx_queue_sz;
+	u16 rx_seq;
+	u16 tx_seq;
+	struct delayed_work rx_refill;
+	spinlock_t tx_lock;
+	struct hlist_head link_list[MHI_MBIM_LINK_HASH_SIZE];
+};
+
+struct mbim_tx_hdr {
+	struct usb_cdc_ncm_nth16 nth16;
+	struct usb_cdc_ncm_ndp16 ndp16;
+	struct usb_cdc_ncm_dpe16 dpe16[2];
+} __packed;
+
+static struct mhi_mbim_link *mhi_mbim_get_link_rcu(struct mhi_mbim_context *mbim,
+						   unsigned int session)
+{
+	struct mhi_mbim_link *link;
+
+	hlist_for_each_entry_rcu(link, &mbim->link_list[LINK_HASH(session)], hlnode) {
+		if (link->session == session)
+			return link;
+	}
+
+	return NULL;
+}
+
+static struct sk_buff *mbim_tx_fixup(struct sk_buff *skb, unsigned int session,
+				     u16 tx_seq)
+{
+	unsigned int dgram_size = skb->len;
+	struct usb_cdc_ncm_nth16 *nth16;
+	struct usb_cdc_ncm_ndp16 *ndp16;
+	struct mbim_tx_hdr *mbim_hdr;
+
+	/* Only one NDP is sent, containing the IP packet (no aggregation) */
+
+	/* Ensure we have enough headroom for crafting MBIM header */
+	if (skb_cow_head(skb, sizeof(struct mbim_tx_hdr))) {
+		dev_kfree_skb_any(skb);
+		return NULL;
+	}
+
+	mbim_hdr = skb_push(skb, sizeof(struct mbim_tx_hdr));
+
+	/* Fill NTB header */
+	nth16 = &mbim_hdr->nth16;
+	nth16->dwSignature = cpu_to_le32(USB_CDC_NCM_NTH16_SIGN);
+	nth16->wHeaderLength = cpu_to_le16(sizeof(struct usb_cdc_ncm_nth16));
+	nth16->wSequence = cpu_to_le16(tx_seq);
+	nth16->wBlockLength = cpu_to_le16(skb->len);
+	nth16->wNdpIndex = cpu_to_le16(sizeof(struct usb_cdc_ncm_nth16));
+
+	/* Fill the unique NDP */
+	ndp16 = &mbim_hdr->ndp16;
+	ndp16->dwSignature = cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN | (session << 24));
+	ndp16->wLength = cpu_to_le16(sizeof(struct usb_cdc_ncm_ndp16)
+					+ sizeof(struct usb_cdc_ncm_dpe16) * 2);
+	ndp16->wNextNdpIndex = 0;
+
+	/* Datagram follows the mbim header */
+	ndp16->dpe16[0].wDatagramIndex = cpu_to_le16(sizeof(struct mbim_tx_hdr));
+	ndp16->dpe16[0].wDatagramLength = cpu_to_le16(dgram_size);
+
+	/* null termination */
+	ndp16->dpe16[1].wDatagramIndex = 0;
+	ndp16->dpe16[1].wDatagramLength = 0;
+
+	return skb;
+}
+
+static netdev_tx_t mhi_mbim_ndo_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct mhi_mbim_link *link = wwan_netdev_drvpriv(ndev);
+	struct mhi_mbim_context *mbim = link->mbim;
+	unsigned long flags;
+	int err = -ENOMEM;
+
+	/* Serialize MHI channel queuing and MBIM seq */
+	spin_lock_irqsave(&mbim->tx_lock, flags);
+
+	skb = mbim_tx_fixup(skb, link->session, mbim->tx_seq);
+	if (unlikely(!skb))
+		goto exit_unlock;
+
+	err = mhi_queue_skb(mbim->mdev, DMA_TO_DEVICE, skb, skb->len, MHI_EOT);
+
+	if (mhi_queue_is_full(mbim->mdev, DMA_TO_DEVICE))
+		netif_stop_queue(ndev);
+
+	if (!err)
+		mbim->tx_seq++;
+
+exit_unlock:
+	spin_unlock_irqrestore(&mbim->tx_lock, flags);
+
+	if (unlikely(err)) {
+		net_err_ratelimited("%s: Failed to queue TX buf (%d)\n",
+				    ndev->name, err);
+		dev_kfree_skb_any(skb);
+		goto exit_drop;
+	}
+
+	return NETDEV_TX_OK;
+
+exit_drop:
+	u64_stats_update_begin(&link->tx_syncp);
+	u64_stats_inc(&link->tx_dropped);
+	u64_stats_update_end(&link->tx_syncp);
+
+	return NETDEV_TX_OK;
+}
+
+static int mbim_rx_verify_nth16(struct mhi_mbim_context *mbim, struct sk_buff *skb)
+{
+	struct usb_cdc_ncm_nth16 *nth16;
+	int len;
+
+	if (skb->len < sizeof(struct usb_cdc_ncm_nth16) +
+			sizeof(struct usb_cdc_ncm_ndp16)) {
+		net_err_ratelimited("frame too short\n");
+		return -EINVAL;
+	}
+
+	nth16 = (struct usb_cdc_ncm_nth16 *)skb->data;
+
+	if (nth16->dwSignature != cpu_to_le32(USB_CDC_NCM_NTH16_SIGN)) {
+		net_err_ratelimited("invalid NTH16 signature <%#010x>\n",
+				    le32_to_cpu(nth16->dwSignature));
+		return -EINVAL;
+	}
+
+	/* No limit on the block length, except the size of the data pkt */
+	len = le16_to_cpu(nth16->wBlockLength);
+	if (len > skb->len) {
+		net_err_ratelimited("NTB does not fit into the skb %u/%u\n",
+				    len, skb->len);
+		return -EINVAL;
+	}
+
+	if (mbim->rx_seq + 1 != le16_to_cpu(nth16->wSequence) &&
+	    (mbim->rx_seq || le16_to_cpu(nth16->wSequence)) &&
+	    !(mbim->rx_seq == 0xffff && !le16_to_cpu(nth16->wSequence))) {
+		net_err_ratelimited("sequence number glitch prev=%d curr=%d\n",
+				    mbim->rx_seq, le16_to_cpu(nth16->wSequence));
+	}
+	mbim->rx_seq = le16_to_cpu(nth16->wSequence);
+
+	return le16_to_cpu(nth16->wNdpIndex);
+}
+
+static int mbim_rx_verify_ndp16(struct sk_buff *skb, struct usb_cdc_ncm_ndp16 *ndp16)
+{
+	int ret;
+
+	if (le16_to_cpu(ndp16->wLength) < USB_CDC_NCM_NDP16_LENGTH_MIN) {
+		net_err_ratelimited("invalid DPT16 length <%u>\n",
+				    le16_to_cpu(ndp16->wLength));
+		return -EINVAL;
+	}
+
+	ret = ((le16_to_cpu(ndp16->wLength) - sizeof(struct usb_cdc_ncm_ndp16))
+			/ sizeof(struct usb_cdc_ncm_dpe16));
+	ret--; /* Last entry is always a NULL terminator */
+
+	if (sizeof(struct usb_cdc_ncm_ndp16) +
+	     ret * sizeof(struct usb_cdc_ncm_dpe16) > skb->len) {
+		net_err_ratelimited("Invalid nframes = %d\n", ret);
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
+static void mhi_mbim_rx(struct mhi_mbim_context *mbim, struct sk_buff *skb)
+{
+	int ndpoffset;
+
+	/* Check NTB header and retrieve first NDP offset */
+	ndpoffset = mbim_rx_verify_nth16(mbim, skb);
+	if (ndpoffset < 0) {
+		net_err_ratelimited("mbim: Incorrect NTB header\n");
+		goto error;
+	}
+
+	/* Process each NDP */
+	while (1) {
+		struct usb_cdc_ncm_ndp16 ndp16;
+		struct usb_cdc_ncm_dpe16 dpe16;
+		struct mhi_mbim_link *link;
+		int nframes, n, dpeoffset;
+		unsigned int session;
+
+		if (skb_copy_bits(skb, ndpoffset, &ndp16, sizeof(ndp16))) {
+			net_err_ratelimited("mbim: Incorrect NDP offset (%u)\n",
+					    ndpoffset);
+			goto error;
+		}
+
+		/* Check NDP header and retrieve number of datagrams */
+		nframes = mbim_rx_verify_ndp16(skb, &ndp16);
+		if (nframes < 0) {
+			net_err_ratelimited("mbim: Incorrect NDP16\n");
+			goto error;
+		}
+
+		 /* Only IP data type supported, no DSS in MHI context */
+		if ((ndp16.dwSignature & cpu_to_le32(MBIM_NDP16_SIGN_MASK))
+				!= cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN)) {
+			net_err_ratelimited("mbim: Unsupported NDP type\n");
+			goto next_ndp;
+		}
+
+		session = (le32_to_cpu(ndp16.dwSignature) & ~MBIM_NDP16_SIGN_MASK) >> 24;
+
+		rcu_read_lock();
+
+		link = mhi_mbim_get_link_rcu(mbim, session);
+		if (!link) {
+			net_err_ratelimited("mbim: bad packet session (%u)\n", session);
+			goto unlock;
+		}
+
+		/* de-aggregate and deliver IP packets */
+		dpeoffset = ndpoffset + sizeof(struct usb_cdc_ncm_ndp16);
+		for (n = 0; n < nframes; n++, dpeoffset += sizeof(dpe16)) {
+			u16 dgram_offset, dgram_len;
+			struct sk_buff *skbn;
+
+			if (skb_copy_bits(skb, dpeoffset, &dpe16, sizeof(dpe16)))
+				break;
+
+			dgram_offset = le16_to_cpu(dpe16.wDatagramIndex);
+			dgram_len = le16_to_cpu(dpe16.wDatagramLength);
+
+			if (!dgram_offset || !dgram_len)
+				break; /* null terminator */
+
+			skbn = netdev_alloc_skb(link->ndev, dgram_len);
+			if (!skbn)
+				continue;
+
+			skb_put(skbn, dgram_len);
+			skb_copy_bits(skb, dgram_offset, skbn->data, dgram_len);
+
+			switch (skbn->data[0] & 0xf0) {
+			case 0x40:
+				skbn->protocol = htons(ETH_P_IP);
+				break;
+			case 0x60:
+				skbn->protocol = htons(ETH_P_IPV6);
+				break;
+			default:
+				net_err_ratelimited("%s: unknown protocol\n",
+						    link->ndev->name);
+				dev_kfree_skb_any(skbn);
+				u64_stats_update_begin(&link->rx_syncp);
+				u64_stats_inc(&link->rx_errors);
+				u64_stats_update_end(&link->rx_syncp);
+				continue;
+			}
+
+			u64_stats_update_begin(&link->rx_syncp);
+			u64_stats_inc(&link->rx_packets);
+			u64_stats_add(&link->rx_bytes, skbn->len);
+			u64_stats_update_end(&link->rx_syncp);
+
+			netif_rx(skbn);
+		}
+unlock:
+		rcu_read_unlock();
+next_ndp:
+		/* Other NDP to process? */
+		ndpoffset = (int)le16_to_cpu(ndp16.wNextNdpIndex);
+		if (!ndpoffset)
+			break;
+	}
+
+	/* free skb */
+	dev_consume_skb_any(skb);
+	return;
+error:
+	dev_kfree_skb_any(skb);
+}
+
+static struct sk_buff *mhi_net_skb_agg(struct mhi_mbim_context *mbim,
+				       struct sk_buff *skb)
+{
+	struct sk_buff *head = mbim->skbagg_head;
+	struct sk_buff *tail = mbim->skbagg_tail;
+
+	/* This is non-paged skb chaining using frag_list */
+	if (!head) {
+		mbim->skbagg_head = skb;
+		return skb;
+	}
+
+	if (!skb_shinfo(head)->frag_list)
+		skb_shinfo(head)->frag_list = skb;
+	else
+		tail->next = skb;
+
+	head->len += skb->len;
+	head->data_len += skb->len;
+	head->truesize += skb->truesize;
+
+	mbim->skbagg_tail = skb;
+
+	return mbim->skbagg_head;
+}
+
+static void mhi_net_rx_refill_work(struct work_struct *work)
+{
+	struct mhi_mbim_context *mbim = container_of(work, struct mhi_mbim_context,
+						     rx_refill.work);
+	struct mhi_device *mdev = mbim->mdev;
+	int err;
+
+	while (!mhi_queue_is_full(mdev, DMA_FROM_DEVICE)) {
+		struct sk_buff *skb = alloc_skb(MHI_DEFAULT_MRU, GFP_KERNEL);
+
+		if (unlikely(!skb))
+			break;
+
+		err = mhi_queue_skb(mdev, DMA_FROM_DEVICE, skb,
+				    MHI_DEFAULT_MRU, MHI_EOT);
+		if (unlikely(err)) {
+			kfree_skb(skb);
+			break;
+		}
+
+		/* Do not hog the CPU if rx buffers are consumed faster than
+		 * queued (unlikely).
+		 */
+		cond_resched();
+	}
+
+	/* If we're still starved of rx buffers, reschedule later */
+	if (mhi_get_free_desc_count(mdev, DMA_FROM_DEVICE) == mbim->rx_queue_sz)
+		schedule_delayed_work(&mbim->rx_refill, HZ / 2);
+}
+
+static void mhi_mbim_dl_callback(struct mhi_device *mhi_dev,
+				 struct mhi_result *mhi_res)
+{
+	struct mhi_mbim_context *mbim = dev_get_drvdata(&mhi_dev->dev);
+	struct sk_buff *skb = mhi_res->buf_addr;
+	int free_desc_count;
+
+	free_desc_count = mhi_get_free_desc_count(mhi_dev, DMA_FROM_DEVICE);
+
+	if (unlikely(mhi_res->transaction_status)) {
+		switch (mhi_res->transaction_status) {
+		case -EOVERFLOW:
+			/* Packet has been split over multiple transfers */
+			skb_put(skb, mhi_res->bytes_xferd);
+			mhi_net_skb_agg(mbim, skb);
+			break;
+		case -ENOTCONN:
+			/* MHI layer stopping/resetting the DL channel */
+			dev_kfree_skb_any(skb);
+			return;
+		default:
+			/* Unknown error, simply drop */
+			dev_kfree_skb_any(skb);
+		}
+	} else {
+		skb_put(skb, mhi_res->bytes_xferd);
+
+		if (mbim->skbagg_head) {
+			/* Aggregate the final fragment */
+			skb = mhi_net_skb_agg(mbim, skb);
+			mbim->skbagg_head = NULL;
+		}
+
+		mhi_mbim_rx(mbim, skb);
+	}
+
+	/* Refill if RX buffers queue becomes low */
+	if (free_desc_count >= mbim->rx_queue_sz / 2)
+		schedule_delayed_work(&mbim->rx_refill, 0);
+}
+
+static void mhi_mbim_ndo_get_stats64(struct net_device *ndev,
+				     struct rtnl_link_stats64 *stats)
+{
+	struct mhi_mbim_link *link = wwan_netdev_drvpriv(ndev);
+	unsigned int start;
+
+	do {
+		start = u64_stats_fetch_begin_irq(&link->rx_syncp);
+		stats->rx_packets = u64_stats_read(&link->rx_packets);
+		stats->rx_bytes = u64_stats_read(&link->rx_bytes);
+		stats->rx_errors = u64_stats_read(&link->rx_errors);
+	} while (u64_stats_fetch_retry_irq(&link->rx_syncp, start));
+
+	do {
+		start = u64_stats_fetch_begin_irq(&link->tx_syncp);
+		stats->tx_packets = u64_stats_read(&link->tx_packets);
+		stats->tx_bytes = u64_stats_read(&link->tx_bytes);
+		stats->tx_errors = u64_stats_read(&link->tx_errors);
+		stats->tx_dropped = u64_stats_read(&link->tx_dropped);
+	} while (u64_stats_fetch_retry_irq(&link->tx_syncp, start));
+}
+
+static void mhi_mbim_ul_callback(struct mhi_device *mhi_dev,
+				 struct mhi_result *mhi_res)
+{
+	struct mhi_mbim_context *mbim = dev_get_drvdata(&mhi_dev->dev);
+	struct sk_buff *skb = mhi_res->buf_addr;
+	struct net_device *ndev = skb->dev;
+	struct mhi_mbim_link *link = wwan_netdev_drvpriv(ndev);
+
+	/* Hardware has consumed the buffer, so free the skb (which is not
+	 * freed by the MHI stack) and perform accounting.
+	 */
+	dev_consume_skb_any(skb);
+
+	u64_stats_update_begin(&link->tx_syncp);
+	if (unlikely(mhi_res->transaction_status)) {
+		/* MHI layer stopping/resetting the UL channel */
+		if (mhi_res->transaction_status == -ENOTCONN) {
+			u64_stats_update_end(&link->tx_syncp);
+			return;
+		}
+
+		u64_stats_inc(&link->tx_errors);
+	} else {
+		u64_stats_inc(&link->tx_packets);
+		u64_stats_add(&link->tx_bytes, mhi_res->bytes_xferd);
+	}
+	u64_stats_update_end(&link->tx_syncp);
+
+	if (netif_queue_stopped(ndev) && !mhi_queue_is_full(mbim->mdev, DMA_TO_DEVICE))
+		netif_wake_queue(ndev);
+}
+
+static int mhi_mbim_ndo_open(struct net_device *ndev)
+{
+	struct mhi_mbim_link *link = wwan_netdev_drvpriv(ndev);
+
+	/* Feed the MHI rx buffer pool */
+	schedule_delayed_work(&link->mbim->rx_refill, 0);
+
+	/* Carrier is established via out-of-band channel (e.g. qmi) */
+	netif_carrier_on(ndev);
+
+	netif_start_queue(ndev);
+
+	return 0;
+}
+
+static int mhi_mbim_ndo_stop(struct net_device *ndev)
+{
+	netif_stop_queue(ndev);
+	netif_carrier_off(ndev);
+
+	return 0;
+}
+
+static const struct net_device_ops mhi_mbim_ndo = {
+	.ndo_open = mhi_mbim_ndo_open,
+	.ndo_stop = mhi_mbim_ndo_stop,
+	.ndo_start_xmit = mhi_mbim_ndo_xmit,
+	.ndo_get_stats64 = mhi_mbim_ndo_get_stats64,
+};
+
+static int mhi_mbim_newlink(void *ctxt, struct net_device *ndev, u32 if_id,
+			    struct netlink_ext_ack *extack)
+{
+	struct mhi_mbim_link *link = wwan_netdev_drvpriv(ndev);
+	struct mhi_mbim_context *mbim = ctxt;
+
+	link->session = if_id;
+	link->mbim = mbim;
+	link->ndev = ndev;
+	u64_stats_init(&link->rx_syncp);
+	u64_stats_init(&link->tx_syncp);
+
+	rcu_read_lock();
+	if (mhi_mbim_get_link_rcu(mbim, if_id)) {
+		rcu_read_unlock();
+		return -EEXIST;
+	}
+	rcu_read_unlock();
+
+	/* Already protected by RTNL lock */
+	hlist_add_head_rcu(&link->hlnode, &mbim->link_list[LINK_HASH(if_id)]);
+
+	return register_netdevice(ndev);
+}
+
+static void mhi_mbim_dellink(void *ctxt, struct net_device *ndev,
+			     struct list_head *head)
+{
+	struct mhi_mbim_link *link = wwan_netdev_drvpriv(ndev);
+
+	hlist_del_init_rcu(&link->hlnode);
+	synchronize_rcu();
+
+	unregister_netdevice_queue(ndev, head);
+}
+
+static void mhi_mbim_setup(struct net_device *ndev)
+{
+	ndev->header_ops = NULL;  /* No header */
+	ndev->type = ARPHRD_RAWIP;
+	ndev->needed_headroom = sizeof(struct mbim_tx_hdr);
+	ndev->hard_header_len = 0;
+	ndev->addr_len = 0;
+	ndev->flags = IFF_POINTOPOINT | IFF_NOARP;
+	ndev->netdev_ops = &mhi_mbim_ndo;
+	ndev->mtu = MHI_MBIM_DEFAULT_MTU;
+	ndev->min_mtu = ETH_MIN_MTU;
+	ndev->max_mtu = MHI_MAX_BUF_SZ - ndev->needed_headroom;
+	ndev->tx_queue_len = 1000;
+}
+
+static const struct wwan_ops mhi_mbim_wwan_ops = {
+	.priv_size = sizeof(struct mhi_mbim_link),
+	.setup = mhi_mbim_setup,
+	.newlink = mhi_mbim_newlink,
+	.dellink = mhi_mbim_dellink,
+};
+
+static int mhi_mbim_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id)
+{
+	struct mhi_controller *cntrl = mhi_dev->mhi_cntrl;
+	struct mhi_mbim_context *mbim;
+	int err;
+
+	mbim = devm_kzalloc(&mhi_dev->dev, sizeof(*mbim), GFP_KERNEL);
+	if (!mbim)
+		return -ENOMEM;
+
+	spin_lock_init(&mbim->tx_lock);
+	dev_set_drvdata(&mhi_dev->dev, mbim);
+	mbim->mdev = mhi_dev;
+	mbim->mru = mhi_dev->mhi_cntrl->mru ? mhi_dev->mhi_cntrl->mru : MHI_DEFAULT_MRU;
+
+	INIT_DELAYED_WORK(&mbim->rx_refill, mhi_net_rx_refill_work);
+
+	/* Start MHI channels */
+	err = mhi_prepare_for_transfer(mhi_dev);
+	if (err)
+		return err;
+
+	/* Number of transfer descriptors determines size of the queue */
+	mbim->rx_queue_sz = mhi_get_free_desc_count(mhi_dev, DMA_FROM_DEVICE);
+
+	/* Register wwan link ops with MHI controller representing WWAN instance */
+	return wwan_register_ops(&cntrl->mhi_dev->dev, &mhi_mbim_wwan_ops, mbim, 0);
+}
+
+static void mhi_mbim_remove(struct mhi_device *mhi_dev)
+{
+	struct mhi_mbim_context *mbim = dev_get_drvdata(&mhi_dev->dev);
+	struct mhi_controller *cntrl = mhi_dev->mhi_cntrl;
+
+	mhi_unprepare_from_transfer(mhi_dev);
+	cancel_delayed_work_sync(&mbim->rx_refill);
+	wwan_unregister_ops(&cntrl->mhi_dev->dev);
+	kfree_skb(mbim->skbagg_head);
+	dev_set_drvdata(&mhi_dev->dev, NULL);
+}
+
+static const struct mhi_device_id mhi_mbim_id_table[] = {
+	/* Hardware accelerated data PATH (to modem IPA), MBIM protocol */
+	{ .chan = "IP_HW0_MBIM", .driver_data = 0 },
+	{}
+};
+MODULE_DEVICE_TABLE(mhi, mhi_mbim_id_table);
+
+static struct mhi_driver mhi_mbim_driver = {
+	.probe = mhi_mbim_probe,
+	.remove = mhi_mbim_remove,
+	.dl_xfer_cb = mhi_mbim_dl_callback,
+	.ul_xfer_cb = mhi_mbim_ul_callback,
+	.id_table = mhi_mbim_id_table,
+	.driver = {
+		.name = "mhi_wwan_mbim",
+		.owner = THIS_MODULE,
+	},
+};
+
+module_mhi_driver(mhi_mbim_driver);
+
+MODULE_AUTHOR("Loic Poulain <loic.poulain@linaro.org>");
+MODULE_DESCRIPTION("Network/MBIM over MHI");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c
index 35ece98134c0..d293ab688044 100644
--- a/drivers/net/wwan/wwan_core.c
+++ b/drivers/net/wwan/wwan_core.c
@@ -359,8 +359,8 @@ struct wwan_port *wwan_create_port(struct device *parent,
 {
 	struct wwan_device *wwandev;
 	struct wwan_port *port;
-	int minor, err = -ENOMEM;
 	char namefmt[0x20];
+	int minor, err;
 
 	if (type > WWAN_PORT_MAX || !ops)
 		return ERR_PTR(-EINVAL);
@@ -374,11 +374,14 @@ struct wwan_port *wwan_create_port(struct device *parent,
 
 	/* A port is exposed as character device, get a minor */
 	minor = ida_alloc_range(&minors, 0, WWAN_MAX_MINORS - 1, GFP_KERNEL);
-	if (minor < 0)
+	if (minor < 0) {
+		err = minor;
 		goto error_wwandev_remove;
+	}
 
 	port = kzalloc(sizeof(*port), GFP_KERNEL);
 	if (!port) {
+		err = -ENOMEM;
 		ida_free(&minors, minor);
 		goto error_wwandev_remove;
 	}
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 44275908d61a..e31b98403f31 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -126,21 +126,17 @@ struct netfront_queue {
 
 	/*
 	 * {tx,rx}_skbs store outstanding skbuffs. Free tx_skb entries
-	 * are linked from tx_skb_freelist through skb_entry.link.
-	 *
-	 *  NB. Freelist index entries are always going to be less than
-	 *  PAGE_OFFSET, whereas pointers to skbs will always be equal or
-	 *  greater than PAGE_OFFSET: we use this property to distinguish
-	 *  them.
+	 * are linked from tx_skb_freelist through tx_link.
 	 */
-	union skb_entry {
-		struct sk_buff *skb;
-		unsigned long link;
-	} tx_skbs[NET_TX_RING_SIZE];
+	struct sk_buff *tx_skbs[NET_TX_RING_SIZE];
+	unsigned short tx_link[NET_TX_RING_SIZE];
+#define TX_LINK_NONE 0xffff
+#define TX_PENDING   0xfffe
 	grant_ref_t gref_tx_head;
 	grant_ref_t grant_tx_ref[NET_TX_RING_SIZE];
 	struct page *grant_tx_page[NET_TX_RING_SIZE];
 	unsigned tx_skb_freelist;
+	unsigned int tx_pend_queue;
 
 	spinlock_t   rx_lock ____cacheline_aligned_in_smp;
 	struct xen_netif_rx_front_ring rx;
@@ -173,6 +169,9 @@ struct netfront_info {
 	bool netback_has_xdp_headroom;
 	bool netfront_xdp_enabled;
 
+	/* Is device behaving sane? */
+	bool broken;
+
 	atomic_t rx_gso_checksum_fixup;
 };
 
@@ -181,33 +180,25 @@ struct netfront_rx_info {
 	struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1];
 };
 
-static void skb_entry_set_link(union skb_entry *list, unsigned short id)
-{
-	list->link = id;
-}
-
-static int skb_entry_is_link(const union skb_entry *list)
-{
-	BUILD_BUG_ON(sizeof(list->skb) != sizeof(list->link));
-	return (unsigned long)list->skb < PAGE_OFFSET;
-}
-
 /*
  * Access macros for acquiring freeing slots in tx_skbs[].
  */
 
-static void add_id_to_freelist(unsigned *head, union skb_entry *list,
-			       unsigned short id)
+static void add_id_to_list(unsigned *head, unsigned short *list,
+			   unsigned short id)
 {
-	skb_entry_set_link(&list[id], *head);
+	list[id] = *head;
 	*head = id;
 }
 
-static unsigned short get_id_from_freelist(unsigned *head,
-					   union skb_entry *list)
+static unsigned short get_id_from_list(unsigned *head, unsigned short *list)
 {
 	unsigned int id = *head;
-	*head = list[id].link;
+
+	if (id != TX_LINK_NONE) {
+		*head = list[id];
+		list[id] = TX_LINK_NONE;
+	}
 	return id;
 }
 
@@ -363,7 +354,7 @@ static int xennet_open(struct net_device *dev)
 	unsigned int i = 0;
 	struct netfront_queue *queue = NULL;
 
-	if (!np->queues)
+	if (!np->queues || np->broken)
 		return -ENODEV;
 
 	for (i = 0; i < num_queues; ++i) {
@@ -391,27 +382,47 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
 	unsigned short id;
 	struct sk_buff *skb;
 	bool more_to_do;
+	const struct device *dev = &queue->info->netdev->dev;
 
 	BUG_ON(!netif_carrier_ok(queue->info->netdev));
 
 	do {
 		prod = queue->tx.sring->rsp_prod;
+		if (RING_RESPONSE_PROD_OVERFLOW(&queue->tx, prod)) {
+			dev_alert(dev, "Illegal number of responses %u\n",
+				  prod - queue->tx.rsp_cons);
+			goto err;
+		}
 		rmb(); /* Ensure we see responses up to 'rp'. */
 
 		for (cons = queue->tx.rsp_cons; cons != prod; cons++) {
-			struct xen_netif_tx_response *txrsp;
+			struct xen_netif_tx_response txrsp;
 
-			txrsp = RING_GET_RESPONSE(&queue->tx, cons);
-			if (txrsp->status == XEN_NETIF_RSP_NULL)
+			RING_COPY_RESPONSE(&queue->tx, cons, &txrsp);
+			if (txrsp.status == XEN_NETIF_RSP_NULL)
 				continue;
 
-			id  = txrsp->id;
-			skb = queue->tx_skbs[id].skb;
+			id = txrsp.id;
+			if (id >= RING_SIZE(&queue->tx)) {
+				dev_alert(dev,
+					  "Response has incorrect id (%u)\n",
+					  id);
+				goto err;
+			}
+			if (queue->tx_link[id] != TX_PENDING) {
+				dev_alert(dev,
+					  "Response for inactive request\n");
+				goto err;
+			}
+
+			queue->tx_link[id] = TX_LINK_NONE;
+			skb = queue->tx_skbs[id];
+			queue->tx_skbs[id] = NULL;
 			if (unlikely(gnttab_query_foreign_access(
 				queue->grant_tx_ref[id]) != 0)) {
-				pr_alert("%s: warning -- grant still in use by backend domain\n",
-					 __func__);
-				BUG();
+				dev_alert(dev,
+					  "Grant still in use by backend domain\n");
+				goto err;
 			}
 			gnttab_end_foreign_access_ref(
 				queue->grant_tx_ref[id], GNTMAP_readonly);
@@ -419,7 +430,7 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
 				&queue->gref_tx_head, queue->grant_tx_ref[id]);
 			queue->grant_tx_ref[id] = GRANT_INVALID_REF;
 			queue->grant_tx_page[id] = NULL;
-			add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, id);
+			add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, id);
 			dev_kfree_skb_irq(skb);
 		}
 
@@ -429,13 +440,20 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
 	} while (more_to_do);
 
 	xennet_maybe_wake_tx(queue);
+
+	return;
+
+ err:
+	queue->info->broken = true;
+	dev_alert(dev, "Disabled for further use\n");
 }
 
 struct xennet_gnttab_make_txreq {
 	struct netfront_queue *queue;
 	struct sk_buff *skb;
 	struct page *page;
-	struct xen_netif_tx_request *tx; /* Last request */
+	struct xen_netif_tx_request *tx;      /* Last request on ring page */
+	struct xen_netif_tx_request tx_local; /* Last request local copy*/
 	unsigned int size;
 };
 
@@ -451,7 +469,7 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset,
 	struct netfront_queue *queue = info->queue;
 	struct sk_buff *skb = info->skb;
 
-	id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
+	id = get_id_from_list(&queue->tx_skb_freelist, queue->tx_link);
 	tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
 	ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
 	WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref));
@@ -459,34 +477,37 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset,
 	gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id,
 					gfn, GNTMAP_readonly);
 
-	queue->tx_skbs[id].skb = skb;
+	queue->tx_skbs[id] = skb;
 	queue->grant_tx_page[id] = page;
 	queue->grant_tx_ref[id] = ref;
 
-	tx->id = id;
-	tx->gref = ref;
-	tx->offset = offset;
-	tx->size = len;
-	tx->flags = 0;
+	info->tx_local.id = id;
+	info->tx_local.gref = ref;
+	info->tx_local.offset = offset;
+	info->tx_local.size = len;
+	info->tx_local.flags = 0;
+
+	*tx = info->tx_local;
+
+	/*
+	 * Put the request in the pending queue, it will be set to be pending
+	 * when the producer index is about to be raised.
+	 */
+	add_id_to_list(&queue->tx_pend_queue, queue->tx_link, id);
 
 	info->tx = tx;
-	info->size += tx->size;
+	info->size += info->tx_local.size;
 }
 
 static struct xen_netif_tx_request *xennet_make_first_txreq(
-	struct netfront_queue *queue, struct sk_buff *skb,
-	struct page *page, unsigned int offset, unsigned int len)
+	struct xennet_gnttab_make_txreq *info,
+	unsigned int offset, unsigned int len)
 {
-	struct xennet_gnttab_make_txreq info = {
-		.queue = queue,
-		.skb = skb,
-		.page = page,
-		.size = 0,
-	};
+	info->size = 0;
 
-	gnttab_for_one_grant(page, offset, len, xennet_tx_setup_grant, &info);
+	gnttab_for_one_grant(info->page, offset, len, xennet_tx_setup_grant, info);
 
-	return info.tx;
+	return info->tx;
 }
 
 static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset,
@@ -499,35 +520,27 @@ static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset,
 	xennet_tx_setup_grant(gfn, offset, len, data);
 }
 
-static struct xen_netif_tx_request *xennet_make_txreqs(
-	struct netfront_queue *queue, struct xen_netif_tx_request *tx,
-	struct sk_buff *skb, struct page *page,
+static void xennet_make_txreqs(
+	struct xennet_gnttab_make_txreq *info,
+	struct page *page,
 	unsigned int offset, unsigned int len)
 {
-	struct xennet_gnttab_make_txreq info = {
-		.queue = queue,
-		.skb = skb,
-		.tx = tx,
-	};
-
 	/* Skip unused frames from start of page */
 	page += offset >> PAGE_SHIFT;
 	offset &= ~PAGE_MASK;
 
 	while (len) {
-		info.page = page;
-		info.size = 0;
+		info->page = page;
+		info->size = 0;
 
 		gnttab_foreach_grant_in_range(page, offset, len,
 					      xennet_make_one_txreq,
-					      &info);
+					      info);
 
 		page++;
 		offset = 0;
-		len -= info.size;
+		len -= info->size;
 	}
-
-	return info.tx;
 }
 
 /*
@@ -574,19 +587,34 @@ static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
 	return queue_idx;
 }
 
+static void xennet_mark_tx_pending(struct netfront_queue *queue)
+{
+	unsigned int i;
+
+	while ((i = get_id_from_list(&queue->tx_pend_queue, queue->tx_link)) !=
+	       TX_LINK_NONE)
+		queue->tx_link[i] = TX_PENDING;
+}
+
 static int xennet_xdp_xmit_one(struct net_device *dev,
 			       struct netfront_queue *queue,
 			       struct xdp_frame *xdpf)
 {
 	struct netfront_info *np = netdev_priv(dev);
 	struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats);
+	struct xennet_gnttab_make_txreq info = {
+		.queue = queue,
+		.skb = NULL,
+		.page = virt_to_page(xdpf->data),
+	};
 	int notify;
 
-	xennet_make_first_txreq(queue, NULL,
-				virt_to_page(xdpf->data),
+	xennet_make_first_txreq(&info,
 				offset_in_page(xdpf->data),
 				xdpf->len);
 
+	xennet_mark_tx_pending(queue);
+
 	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify);
 	if (notify)
 		notify_remote_via_irq(queue->tx_irq);
@@ -611,6 +639,8 @@ static int xennet_xdp_xmit(struct net_device *dev, int n,
 	int nxmit = 0;
 	int i;
 
+	if (unlikely(np->broken))
+		return -ENODEV;
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 
@@ -638,7 +668,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 {
 	struct netfront_info *np = netdev_priv(dev);
 	struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats);
-	struct xen_netif_tx_request *tx, *first_tx;
+	struct xen_netif_tx_request *first_tx;
 	unsigned int i;
 	int notify;
 	int slots;
@@ -647,6 +677,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 	unsigned int len;
 	unsigned long flags;
 	struct netfront_queue *queue = NULL;
+	struct xennet_gnttab_make_txreq info = { };
 	unsigned int num_queues = dev->real_num_tx_queues;
 	u16 queue_index;
 	struct sk_buff *nskb;
@@ -654,6 +685,8 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 	/* Drop the packet if no queues are set up */
 	if (num_queues < 1)
 		goto drop;
+	if (unlikely(np->broken))
+		goto drop;
 	/* Determine which queue to transmit this SKB on */
 	queue_index = skb_get_queue_mapping(skb);
 	queue = &np->queues[queue_index];
@@ -704,21 +737,24 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 	}
 
 	/* First request for the linear area. */
-	first_tx = tx = xennet_make_first_txreq(queue, skb,
-						page, offset, len);
-	offset += tx->size;
+	info.queue = queue;
+	info.skb = skb;
+	info.page = page;
+	first_tx = xennet_make_first_txreq(&info, offset, len);
+	offset += info.tx_local.size;
 	if (offset == PAGE_SIZE) {
 		page++;
 		offset = 0;
 	}
-	len -= tx->size;
+	len -= info.tx_local.size;
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		/* local packet? */
-		tx->flags |= XEN_NETTXF_csum_blank | XEN_NETTXF_data_validated;
+		first_tx->flags |= XEN_NETTXF_csum_blank |
+				   XEN_NETTXF_data_validated;
 	else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
 		/* remote but checksummed. */
-		tx->flags |= XEN_NETTXF_data_validated;
+		first_tx->flags |= XEN_NETTXF_data_validated;
 
 	/* Optional extra info after the first request. */
 	if (skb_shinfo(skb)->gso_size) {
@@ -727,7 +763,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 		gso = (struct xen_netif_extra_info *)
 			RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
 
-		tx->flags |= XEN_NETTXF_extra_info;
+		first_tx->flags |= XEN_NETTXF_extra_info;
 
 		gso->u.gso.size = skb_shinfo(skb)->gso_size;
 		gso->u.gso.type = (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) ?
@@ -741,12 +777,12 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 	}
 
 	/* Requests for the rest of the linear area. */
-	tx = xennet_make_txreqs(queue, tx, skb, page, offset, len);
+	xennet_make_txreqs(&info, page, offset, len);
 
 	/* Requests for all the frags. */
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-		tx = xennet_make_txreqs(queue, tx, skb, skb_frag_page(frag),
+		xennet_make_txreqs(&info, skb_frag_page(frag),
 					skb_frag_off(frag),
 					skb_frag_size(frag));
 	}
@@ -757,6 +793,8 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 	/* timestamp packet in software */
 	skb_tx_timestamp(skb);
 
+	xennet_mark_tx_pending(queue);
+
 	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify);
 	if (notify)
 		notify_remote_via_irq(queue->tx_irq);
@@ -814,7 +852,7 @@ static int xennet_get_extras(struct netfront_queue *queue,
 			     RING_IDX rp)
 
 {
-	struct xen_netif_extra_info *extra;
+	struct xen_netif_extra_info extra;
 	struct device *dev = &queue->info->netdev->dev;
 	RING_IDX cons = queue->rx.rsp_cons;
 	int err = 0;
@@ -830,24 +868,22 @@ static int xennet_get_extras(struct netfront_queue *queue,
 			break;
 		}
 
-		extra = (struct xen_netif_extra_info *)
-			RING_GET_RESPONSE(&queue->rx, ++cons);
+		RING_COPY_RESPONSE(&queue->rx, ++cons, &extra);
 
-		if (unlikely(!extra->type ||
-			     extra->type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
+		if (unlikely(!extra.type ||
+			     extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
 			if (net_ratelimit())
 				dev_warn(dev, "Invalid extra type: %d\n",
-					extra->type);
+					 extra.type);
 			err = -EINVAL;
 		} else {
-			memcpy(&extras[extra->type - 1], extra,
-			       sizeof(*extra));
+			extras[extra.type - 1] = extra;
 		}
 
 		skb = xennet_get_rx_skb(queue, cons);
 		ref = xennet_get_rx_ref(queue, cons);
 		xennet_move_rx_slot(queue, skb, ref);
-	} while (extra->flags & XEN_NETIF_EXTRA_FLAG_MORE);
+	} while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);
 
 	queue->rx.rsp_cons = cons;
 	return err;
@@ -905,7 +941,7 @@ static int xennet_get_responses(struct netfront_queue *queue,
 				struct sk_buff_head *list,
 				bool *need_xdp_flush)
 {
-	struct xen_netif_rx_response *rx = &rinfo->rx;
+	struct xen_netif_rx_response *rx = &rinfo->rx, rx_local;
 	int max = XEN_NETIF_NR_SLOTS_MIN + (rx->status <= RX_COPY_THRESHOLD);
 	RING_IDX cons = queue->rx.rsp_cons;
 	struct sk_buff *skb = xennet_get_rx_skb(queue, cons);
@@ -989,7 +1025,8 @@ next:
 			break;
 		}
 
-		rx = RING_GET_RESPONSE(&queue->rx, cons + slots);
+		RING_COPY_RESPONSE(&queue->rx, cons + slots, &rx_local);
+		rx = &rx_local;
 		skb = xennet_get_rx_skb(queue, cons + slots);
 		ref = xennet_get_rx_ref(queue, cons + slots);
 		slots++;
@@ -1044,10 +1081,11 @@ static int xennet_fill_frags(struct netfront_queue *queue,
 	struct sk_buff *nskb;
 
 	while ((nskb = __skb_dequeue(list))) {
-		struct xen_netif_rx_response *rx =
-			RING_GET_RESPONSE(&queue->rx, ++cons);
+		struct xen_netif_rx_response rx;
 		skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
 
+		RING_COPY_RESPONSE(&queue->rx, ++cons, &rx);
+
 		if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) {
 			unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
 
@@ -1062,7 +1100,7 @@ static int xennet_fill_frags(struct netfront_queue *queue,
 
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 				skb_frag_page(nfrag),
-				rx->offset, rx->status, PAGE_SIZE);
+				rx.offset, rx.status, PAGE_SIZE);
 
 		skb_shinfo(nskb)->nr_frags = 0;
 		kfree_skb(nskb);
@@ -1156,12 +1194,19 @@ static int xennet_poll(struct napi_struct *napi, int budget)
 	skb_queue_head_init(&tmpq);
 
 	rp = queue->rx.sring->rsp_prod;
+	if (RING_RESPONSE_PROD_OVERFLOW(&queue->rx, rp)) {
+		dev_alert(&dev->dev, "Illegal number of responses %u\n",
+			  rp - queue->rx.rsp_cons);
+		queue->info->broken = true;
+		spin_unlock(&queue->rx_lock);
+		return 0;
+	}
 	rmb(); /* Ensure we see queued responses up to 'rp'. */
 
 	i = queue->rx.rsp_cons;
 	work_done = 0;
 	while ((i != rp) && (work_done < budget)) {
-		memcpy(rx, RING_GET_RESPONSE(&queue->rx, i), sizeof(*rx));
+		RING_COPY_RESPONSE(&queue->rx, i, rx);
 		memset(extras, 0, sizeof(rinfo.extras));
 
 		err = xennet_get_responses(queue, &rinfo, rp, &tmpq,
@@ -1286,17 +1331,18 @@ static void xennet_release_tx_bufs(struct netfront_queue *queue)
 
 	for (i = 0; i < NET_TX_RING_SIZE; i++) {
 		/* Skip over entries which are actually freelist references */
-		if (skb_entry_is_link(&queue->tx_skbs[i]))
+		if (!queue->tx_skbs[i])
 			continue;
 
-		skb = queue->tx_skbs[i].skb;
+		skb = queue->tx_skbs[i];
+		queue->tx_skbs[i] = NULL;
 		get_page(queue->grant_tx_page[i]);
 		gnttab_end_foreign_access(queue->grant_tx_ref[i],
 					  GNTMAP_readonly,
 					  (unsigned long)page_address(queue->grant_tx_page[i]));
 		queue->grant_tx_page[i] = NULL;
 		queue->grant_tx_ref[i] = GRANT_INVALID_REF;
-		add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, i);
+		add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, i);
 		dev_kfree_skb_irq(skb);
 	}
 }
@@ -1376,6 +1422,9 @@ static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id)
 	struct netfront_queue *queue = dev_id;
 	unsigned long flags;
 
+	if (queue->info->broken)
+		return IRQ_HANDLED;
+
 	spin_lock_irqsave(&queue->tx_lock, flags);
 	xennet_tx_buf_gc(queue);
 	spin_unlock_irqrestore(&queue->tx_lock, flags);
@@ -1388,6 +1437,9 @@ static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id)
 	struct netfront_queue *queue = dev_id;
 	struct net_device *dev = queue->info->netdev;
 
+	if (queue->info->broken)
+		return IRQ_HANDLED;
+
 	if (likely(netif_carrier_ok(dev) &&
 		   RING_HAS_UNCONSUMED_RESPONSES(&queue->rx)))
 		napi_schedule(&queue->napi);
@@ -1409,6 +1461,10 @@ static void xennet_poll_controller(struct net_device *dev)
 	struct netfront_info *info = netdev_priv(dev);
 	unsigned int num_queues = dev->real_num_tx_queues;
 	unsigned int i;
+
+	if (info->broken)
+		return;
+
 	for (i = 0; i < num_queues; ++i)
 		xennet_interrupt(0, &info->queues[i]);
 }
@@ -1480,6 +1536,11 @@ static int xennet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 
 static int xennet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
+	struct netfront_info *np = netdev_priv(dev);
+
+	if (np->broken)
+		return -ENODEV;
+
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return xennet_xdp_set(dev, xdp->prog, xdp->extack);
@@ -1853,13 +1914,15 @@ static int xennet_init_queue(struct netfront_queue *queue)
 	snprintf(queue->name, sizeof(queue->name), "vif%s-q%u",
 		 devid, queue->id);
 
-	/* Initialise tx_skbs as a free chain containing every entry. */
+	/* Initialise tx_skb_freelist as a free chain containing every entry. */
 	queue->tx_skb_freelist = 0;
+	queue->tx_pend_queue = TX_LINK_NONE;
 	for (i = 0; i < NET_TX_RING_SIZE; i++) {
-		skb_entry_set_link(&queue->tx_skbs[i], i+1);
+		queue->tx_link[i] = i + 1;
 		queue->grant_tx_ref[i] = GRANT_INVALID_REF;
 		queue->grant_tx_page[i] = NULL;
 	}
+	queue->tx_link[NET_TX_RING_SIZE - 1] = TX_LINK_NONE;
 
 	/* Clear out rx_skbs */
 	for (i = 0; i < NET_RX_RING_SIZE; i++) {
@@ -2128,6 +2191,9 @@ static int talk_to_netback(struct xenbus_device *dev,
 	if (info->queues)
 		xennet_destroy_queues(info);
 
+	/* For the case of a reconnect reset the "broken" indicator. */
+	info->broken = false;
+
 	err = xennet_create_queues(info, &num_queues);
 	if (err < 0) {
 		xenbus_dev_fatal(dev, err, "creating queues");